From 4a7bccb2cc85441a1b6a27f09c205b6a121f6a6b Mon Sep 17 00:00:00 2001
From: Aditi Kala <130339327+why-aditi@users.noreply.github.com>
Date: Tue, 18 Jun 2024 23:47:45 +0530
Subject: [PATCH 01/10] ACI IoT Network Traffic Dataset Analysis

---
 .../.idea/.gitignore                          |    3 +
 ...I IoT Network Traffic Dataset Analysis.iml |   12 +
 .../inspectionProfiles/profiles_settings.xml  |    6 +
 .../.idea/misc.xml                            |    4 +
 .../.idea/modules.xml                         |    8 +
 .../Images/Bar Graph.png                      |  Bin 0 -> 34427 bytes
 .../Images/Pie Chart.png                      |  Bin 0 -> 60217 bytes
 ..._Traffic_Dataset_Analysis-checkpoint.ipynb | 1977 +++++++++++++++++
 ...IoT_Network_Traffic_Dataset_Analysis.ipynb | 1977 +++++++++++++++++
 .../requirements.txt                          |    4 +
 10 files changed, 3991 insertions(+)
 create mode 100644 ACI IoT Network Traffic Dataset Analysis/.idea/.gitignore
 create mode 100644 ACI IoT Network Traffic Dataset Analysis/.idea/ACI IoT Network Traffic Dataset Analysis.iml
 create mode 100644 ACI IoT Network Traffic Dataset Analysis/.idea/inspectionProfiles/profiles_settings.xml
 create mode 100644 ACI IoT Network Traffic Dataset Analysis/.idea/misc.xml
 create mode 100644 ACI IoT Network Traffic Dataset Analysis/.idea/modules.xml
 create mode 100644 ACI IoT Network Traffic Dataset Analysis/Images/Bar Graph.png
 create mode 100644 ACI IoT Network Traffic Dataset Analysis/Images/Pie Chart.png
 create mode 100644 ACI IoT Network Traffic Dataset Analysis/Model/.ipynb_checkpoints/ACI_IoT_Network_Traffic_Dataset_Analysis-checkpoint.ipynb
 create mode 100644 ACI IoT Network Traffic Dataset Analysis/Model/ACI_IoT_Network_Traffic_Dataset_Analysis.ipynb
 create mode 100644 ACI IoT Network Traffic Dataset Analysis/requirements.txt

diff --git a/ACI IoT Network Traffic Dataset Analysis/.idea/.gitignore b/ACI IoT Network Traffic Dataset Analysis/.idea/.gitignore
new file mode 100644
index 000000000..26d33521a
--- /dev/null
+++ b/ACI IoT Network Traffic Dataset Analysis/.idea/.gitignore	
@@ -0,0 +1,3 @@
+# Default ignored files
+/shelf/
+/workspace.xml
diff --git a/ACI IoT Network Traffic Dataset Analysis/.idea/ACI IoT Network Traffic Dataset Analysis.iml b/ACI IoT Network Traffic Dataset Analysis/.idea/ACI IoT Network Traffic Dataset Analysis.iml
new file mode 100644
index 000000000..408235d99
--- /dev/null
+++ b/ACI IoT Network Traffic Dataset Analysis/.idea/ACI IoT Network Traffic Dataset Analysis.iml	
@@ -0,0 +1,12 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<module type="PYTHON_MODULE" version="4">
+  <component name="NewModuleRootManager">
+    <content url="file://$MODULE_DIR$" />
+    <orderEntry type="inheritedJdk" />
+    <orderEntry type="sourceFolder" forTests="false" />
+  </component>
+  <component name="PackageRequirementsSettings">
+    <option name="requirementsPath" value="D:\ML\ACI IoT Network Traffic Dataset Analysis\requirements.txt" />
+    <option name="versionSpecifier" value="Greater or equal (&gt;=x.y.z)" />
+  </component>
+</module>
\ No newline at end of file
diff --git a/ACI IoT Network Traffic Dataset Analysis/.idea/inspectionProfiles/profiles_settings.xml b/ACI IoT Network Traffic Dataset Analysis/.idea/inspectionProfiles/profiles_settings.xml
new file mode 100644
index 000000000..105ce2da2
--- /dev/null
+++ b/ACI IoT Network Traffic Dataset Analysis/.idea/inspectionProfiles/profiles_settings.xml	
@@ -0,0 +1,6 @@
+<component name="InspectionProjectProfileManager">
+  <settings>
+    <option name="USE_PROJECT_PROFILE" value="false" />
+    <version value="1.0" />
+  </settings>
+</component>
\ No newline at end of file
diff --git a/ACI IoT Network Traffic Dataset Analysis/.idea/misc.xml b/ACI IoT Network Traffic Dataset Analysis/.idea/misc.xml
new file mode 100644
index 000000000..a971a2c93
--- /dev/null
+++ b/ACI IoT Network Traffic Dataset Analysis/.idea/misc.xml	
@@ -0,0 +1,4 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.11" project-jdk-type="Python SDK" />
+</project>
\ No newline at end of file
diff --git a/ACI IoT Network Traffic Dataset Analysis/.idea/modules.xml b/ACI IoT Network Traffic Dataset Analysis/.idea/modules.xml
new file mode 100644
index 000000000..1983d66b9
--- /dev/null
+++ b/ACI IoT Network Traffic Dataset Analysis/.idea/modules.xml	
@@ -0,0 +1,8 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="ProjectModuleManager">
+    <modules>
+      <module fileurl="file://$PROJECT_DIR$/.idea/ACI IoT Network Traffic Dataset Analysis.iml" filepath="$PROJECT_DIR$/.idea/ACI IoT Network Traffic Dataset Analysis.iml" />
+    </modules>
+  </component>
+</project>
\ No newline at end of file
diff --git a/ACI IoT Network Traffic Dataset Analysis/Images/Bar Graph.png b/ACI IoT Network Traffic Dataset Analysis/Images/Bar Graph.png
new file mode 100644
index 0000000000000000000000000000000000000000..2d390c3bda9189f5f69d762fe41b35eacaeab052
GIT binary patch
literal 34427
zcmeFZcT|&YmoFSTA_yXgf)qP~2r5NEAczz}Ispk?q&Jl&y@?1)Q$gvy_by$qpd!5l
zf`BMeLY3Zg_KnZ`%sXdh*7^Q8=bJg}jB81Nggd#fviJU#eFdp1%hA!W(x6Z%x|{Mh
z)KMsMG8Br`lA02J(@(O+4G$y^>T=gn1#QQs;0JPZDJ3ZssyJ-_wlM|#yzid8jsptC
z=!pC$88+j5h(bMPxOqcL^P$1)(7rgO6=L&mdKr0c#$XGXAbCrbpw*WOY`+SX)U(bv
z1b6wR$wW9~<#{5*gDsN9uXoD6v|;W_`LHvx*1VyNJ7OmL@oW5&n*>K?)mq%;?kf)S
zS4ZY2wl=)#WzHzYycB>BfI=~_$!O)>miqI9&yjN_X05D#BzsT2myfuizI^P@_vp?^
z-o5Xh?Av?#s^iZP5p2W>8JmF;)6T;vRM(+Kc-~0*G3{?<J3{K655awJ?whcQ*y%a;
zL|t}Uwh-GGdtsXy?_BcZ!_&b7Vlzf^$L>E`nI9R^D$qO14#OeLj9ei+S-a3+_5C50
z{-0rzcKX$h#p#N#@cYij8Syu4KXAM;j4d?_DYxwYsC@Mo)7I*s{p?~3e`TXTm2P{2
zc)mg;kMqt7ZqPC_{xCb;-`5;n{~1=f)Gj%KEw?ho={bbdt@P=_eP3jg@L0!_?Vfa6
zCBjQ4dpGSGcAVSQCwsDAC?!e^`J;$y-b8b4eWytAo#pP;R*{k0-5E-$sijdvM3`#^
zTKL3lY6W^%d38$CY~iY%QRQ=QejX4T3zyFG*jTJ@kn*QoohfaXbtk4zQEKbm4-jAJ
z(Wq#b*y<M^v@t2HT~sJ@(QnvUja``?#Dz`c3KPBU%_4cVD+=^$WDEQ7{X`QDulBmN
z;X#F$+@sC)8{@H^2dA<19##4eM+3aPzC`g&572Jzkf7vQkmZMd%*?Cx@cuO=`qx6%
zQRUXSHm!W@uL08RxvB|{L2u%YC$`bHa%jBK?{fRK?vKxo9%BDp7<B0Dro4Ac6yMHP
zj&>o(tPXC_zF{_g#-Z(Ma|PZi*TTBZW|9~YJL0f7_PMXvM2=WVSm*TK?hF;1yApfV
z!OZb}L!0RI`K@2C4D(#(hj;Y`Xhnt`HOg2}K7NJrC(gMYK%wp^#Os9EnP;f2QgJ+d
zd*RJ@KZ_P@197(|tc=QgXXRCIq2b8W1In)jj^nGH-`81mrU;vSq|Mc@aV`_GCZnWX
zm_qT_F8IZ}5wbhAO1*bCn!R>6CMJ8atW)&SWNcgBW8-Tt=_R*2E|cEf-QGwzos@m3
zU6NR9-)%)oShglKoeaD7V{mM_TV?G$sn$^xDsBIzy#ezjqrzJk){TdqP4wu}KJ;cX
z<>@8ScT!eVy6jG-Ovk*|M^}G0bIR!woyH>M%-E>IixkjPUFkd4Ny@u00B_o)Q&+Qv
zmx-TR=Uo>Xsm#eq(_o!(ygVZ5RZDeBUEg`Yw6nB)`SOZbaTf`SOMh?G96fMt0d3ut
z79`mwHh)beQ~Rv$(iCxfseO`rsh5IP$ZE`Cx_l;4baHLPyTPU6a;{pc?6S?zia|Ru
zVvgm$?A3mguxF?M8a6XiX=2#7?F9F^D)Z$TL-*P8S2)s+vLH<wrZl|Q*6fb;I4uMu
z8Xjcd8u`EUDxC4*^jdGM-(FN4$zY}|TTT@1_ot*QDK=?#liT^`&|aQr#+eb?W`C<S
zMhO1;>gE?FYLeg~=RrPvbwS=PXVs3lgNd{d-D}T%e=WMVvO7C#BfCP+`X$%CISe;y
zZPt#rSu59x5{QxNvzTZ@MQSV8w?v-G26JlXw9Ow+`SUch)f3cUxf)+bVvkKY&0O6k
zAy=#R;r(1pZj^m@)*G6+^tRMQ5&Hy|-7Wr}skyH7r{<K7(|vp`YOCL#)lRIg#fdr*
zM9aw!pTBLyU%#FrWQ!NX<+7nrsvQTBjd}EA2-`#e*~*)xHnF;_1lg}*E^{`fUtaz;
zQNH&3MxtDy=^7<H$4tutyJLrxL?y97odK=5wK9!se??vk`)szjnPX{0W^ikH>L)LW
z#d}FHxbw9k7enj5ylA4NJrXK38KP*(QB1ObwjPJL+rtP6@q(H;QBI6@qj-KN=P}Ra
z&icIJ6q%<U`n#j=0(D2~J!i|hm7j+8JLae@Ab~DRE!Acs-lf8Qz7BVxYK(C{$$M+I
z(s??+(v9FX&P-MEd~igAm+_nD+R!c$=c?K$MIi@)uVIoJrZw!uKAs^I%I9^rqu=W6
z;2^w+#g+t>bnoP47y{&p<45+sL4Vy_cPJE>Sr#mQ_=o-){x9DYQRM5Cems0Z&tlNF
zGG3bx$zdoi{_GZF3xC7yNFI#Gz7Zdzw}+R9Tt;+yb1<pe$O}+5NB18-Uj$41w4028
z(Nk>kod5`4ZA5Aq=b#Ew<R#%E5aFl%yINlHSC*Kz$m;H+v{BnUIXTA5jsBB&!g0bq
z^yxla$g5EorT<Ds|IP>B%d8M~FC)VZ|DGKEN3NnpatHjo^Vn$b@qgQ8Ud%W8%r_8+
z+a!q|yoU9)k>_=~2tC;*u!W4vaOWfBZ-;S+=RNrKrM}_ji!-Yb0A<~An^T#IGqp=?
zrI$><+^%}?E6;YYqQa^-$6_9v=(U;64k1M=<;K2TY<bQQY|+jH?~r3xyR7>1rkW?$
zj)*zil$qzpZC}{C6DG$ER@(KAiNx6sY5H==s{?QD|AdSpQM$XcH3;i~lihgOl2gFQ
zhmPY~|FHYK_@MKkElj4_YBQ(z4Y}7;q-L!#riFE@F?HLEEvw_P_W0AU^cZJ_bgLeu
z!=CAJ9&*y&noJGLGi>m3hP00Nr<XXwZY*s2g-L88&f!}4!soMzx0l9ScP=`Nf1P|1
zxATurCd0@&*LHTO+NsoK*tL1sZ93ngrFuCRldb-tpnlV;W<18)V=$PR*9OV^$E6?l
z511#~CVKBy^%m$4O00h;6Z`H%w*6Y$!1aUjl~MAoxtjUyEf{UDnz`y}o6Zy&Bpyi0
z66aYA9yXe_C(IV=R@hiJ>~7{#9rBY6Vb!T~Td7@2d@*ubj7H%lpKf1+iViJ>&WfE$
ziaGW8%GHZ*d&_vrSbC?!qm}mIRQju0GVk$dbL@v;W?SOUT4f-I8#mrs*kw*{{w*)N
zWQXLBB>w{?*&3Of)}FmRJ`B_h?1p6)YMgZ}><;e_%H1U=y>W6AM&b7idFRD!B4_8t
zQQ`}D|I*%E?X4gc&%G%NA6XPSvH-=xde#oaWy_z<VU^Ca_<=}m154?^11mcOkEgOD
z8dFaFnT0f`((o{Dwt?)<w<libc|E@Ca*N<K(0?&{Wo~GYjB+#?i<F8e)L5kl9c3Qu
zQ39^ezH-Pp)||p3f%t*NaK>^YKx%DnNSyiPH3)?avk>QD>k`MT1<;rcp%F<;KDOKj
zGU9Hndb+}{)9)W2c7-~oi&P9>o!9x%?hh$=Q2U6y_?g_q;{)t3sttvmZ<!6+l!ml_
zmj9>wNs1&Fw3qB<G4vS45Yu7shdUDljQtu8x7KL$`M{FtH=Lec{MF(a>0|WceNci^
z(#Cd*Nm<idL+_nmg)+SKGf>1F<z<<C-9rqUe7!*Y{CR#aKA=TE;f&Ck%JDN0T2?Gc
z4Lw&P>DYw7zS^=Lsjr*oS5JH5G}GT{SM}>Kzwi|(39N^z%e7Z<CEh8w{C<XtwPmu@
z5_h-iMH`v5^+tPloZ{jj7aCksZK1T<*L3itY`^&0H<NfVm(`sIy%_Bc9&#*Rm6z6H
zsu3v`yrag(T>gw0``C1sUrPG6VC62vyyZ?8r;grY`sL}BnSpM9@-L_>Gez%gI+CO+
za0c!&a<5hPsb+dEPj=P^qn{q;vw7=7qE+oUHA!8nBDvG!PmA>{x*kB&mn=;+jW4$@
zbIFf5DTiOd8QQ}}T1t6bIpS5ruXY69eBg*FV^%nq;{J@YQHRN4>cZ_H9Ja0*q2m~6
z<?a83y0loj73n3X7-VVzTrB=4M8f}CarwVL&3~NwUKBR^u-Vsk1~Z*2X-kFZ-)T@P
zxx4-jUukdutL0T?SGuAuvSc9=bPkt~w<p@4O?a3BIsOZeR-Of{?tG-2gQox|-i3Oo
z(zasYBNUwUY?toJmrWRwQ5`5F^ycaYF`k}5!X=cblK4_BWiOV!)!8LgZ%&D1sMUA$
zl6S8SLx!^m(}4|c1G`1|!I*sPHP;e8y*C}ok~_;5g#(hr?Vr9r@U=VRR`eYtK!$oj
zQcXGeb-XQpx>?ZfTYrX9tQotQbJ^1i)t^3waYD)yzVn`X`dd{gvN<Jo*G+PDD+`3I
z`@Tk<*I{Ij*!e58RC7O<4^FVZ|AiL75=-rigaITQHM6^v8NYixaMV0*bP&>tZMju1
z67#XCvLQC#-rRTYx_Q>M*#nZ+q6t)pHUL4&0fk~=ymmHTUo^29{~BFy*e0=MqYF5!
zZt)B6E;bqkF{=zRSi4~%1nC^Dd@FWQ$0EC->R*#CpM#(%!U9s>nTR~6aR!eSz|0Gu
zaeHiJka#H792vB5j=eqq)dx^+SB_@(otoK-*m%gQ39I~^p34ycY7P6+ZXWXHi@C0v
zj}@Btd0O9>t#S4w0~c#2PSUwAPiGg~oVH5~3CWy07fmeeF$q4*M<{%E@#=<tNr~Hv
z6;WTEb8mk3GKs|v1Ir!OWC;FS;_1YNcl4EpUK<|{^I^wMZvFZa`83o(k==Xtkf#zI
zx%|WUp^Jpq@XGlLn}JJ-cHzAjvn5Z~jGX4Jb6;DfzV(oMaPPuC+flIc0JjgfU0b>Z
z73z*hnb%BzaY8-u>*e+va%q)wLpAO^vJcPSF5<%Pm2l|Y&uf;X*@BDpu<Qo34Lwa^
z87?w;QBbL8`!%cv)tePeavGSsJR4Vd36&R*W|onzZ8;_iZuQxW*Q-2>71AB=zwe8b
znf7+MRir13mR8jRQ|pc-UqHiO&)j;=Fe?;$**p}-bY=a!|4w;*8%$$-4iTw}T&k^c
z1+#@tw+QVF?1#J_cM(^J3gWU9<SU}bAhqvhUmwQ^xHId5s*kUxVgZuy(>=snW^Qor
zT%Cyf=`b@`VLPq3Tlf1To5A}+rC8zNjRU<~vBI{5_+3EX1Itt0o>gzB3mb-E2hOK1
zJ{T~4H6SwLVFL8VZ)OxF9qU*(Lz$*g60upDUVKdP5CUxb3iQRcVAgktXJH2S##f#N
zDFvZOs{PrpHtasAV;*mc>}Qt|Pu#2DFQ8~@d36BFrU3T)?++$CN6_S!gxdG-P?W9~
z5?({$wb57YWIYYFisK`l5LO`%ODR*bo_t;0=GweHWWypHH#HV2ESGQh16L+H-@zuI
zP-M@^GPY7{ocYJ@mf53)TyOCn;cnqt+6<*o`*-UtQp_I!f*KS5k0aH8NAdsX$A;;(
z5js)AGfzI^1Tag@7EcF&STdd+tgM7$QWtoZe3_?*D<1y-0pMwAqP_Bv%C%0Q`AlJB
zmjP?jw+mqjo_cXcsbq6ydJtjN+-Hgd>5g7Hg<mQJZU?(U=*_<o#OT~1MKu8Ef^$}f
z_iV%dy&W}`geE6LfQb8dUn(1*;ht9H^+H%>6L%{^AlVs}1e^UV7s|R-B*pR8t3W3`
z<oXU@%g$+J^mimn*QJi6%7sDASLHCVc`<}dq{6a0!?kEM<>`fz-#?q><X(pyx!5EM
zyo0#=YFU`%Za<+f-x_$8($k7jH{|XTYxX`y_=Vt8&r>Eg?f|fsu#&Xs;Hvo*rJH9^
z=jIH2!ybbA=bY8tmLNU|aMDyGQ@I=}@jXPC_Ck3vbVFHecC48efMB)rtd-)c3+2GJ
zZY^Cj`Plz8`m$$3oagF5g~!GN_g|6P+vS%?ScPpY;2jbh41iSyoX{)kIB5iUuBCJS
z`5|8If-(T?o9(<B8Mn&HjdF%<Z!Oa{)=Hd}ZAU&fm$*$9XUu#wi9#LjlP63-3ZFHw
z9dfHUL+||3I;cA!`27c&>hA7<=$UO=Q|3uxq}we(dOJ>6&YW#f)Y2+6m~Bub>?Mak
z`6M&Z3*WuyzBb2hyMaS^l)DXjRS$q@?fH$9=*0D)eIDTk*i%C{065wKhq*LGsl)za
z^K!|Seo2b=s}lmF$u@uJf<@hW3NnN(+9Py<hczfG6d(-O)nwjz6u8^EHx-Z^_fvAO
z7*K3#@*4pKvl>XVM0Z5sZK8FL{<-a#!9)e-ZC*^ySo?~QgA8#&w8lhGJLT@@=UU0v
zDF&@_^GmLsSuwx6R&!S-mt~UpVsr1JTn)c;1-`#F2`xT)+3aBeap4N!UW6cMd1wGE
zbgY2!^<{Q51XiY#(@U%ydFK~y9?ixOfz1<|cf<i$Hk^LllXx5%vUH+|MTb$mi6&YV
zk~=<e=pUudr%I!@fc(u76fGJC9B&`)H_oB8*nY4gpMPWRBb)uhGg6S0YM0n^)<gjJ
zi|qg~ESc)g+<M>(Q&z`vx+kkv57^2*p8M4WeGdv$K6U|8_qw{T?=C03_;NVE5<*4j
z);Q13z@MxT6aPj}`eW84jWgezaQgL*Mo?YOJUJP<@N#=1(OUv<oiI!Untn^$=__m=
z4+Ox$rsNfE%7fKgUzSutf^3VOEx_ZPUj5ok|0)T+64o^Hi(<dU$MgE{d)+JRPKH@h
zkeMF6YcNvG_3y4tY|`aF6aRKx?!OeN^nYL4i)Etihb1)wl+rVU9qWz7U-k5ROPfg#
zo_Y->(GKV<ow?rm26gy)C>1A}_nzi{@_>1dciBD;EJ*vq{AOS~XMlsMfZAfqYwtCx
z0?ap0$+VYZ$|mvsQlKfFU#djPHZl@qMZ8cJJ%<n0{3{sYp?=T16@96*&oA4p@?z&@
z@}<qVBjU(3`z#kFds!4*B7<7^XBdRXf#;_cFBwcHpCg5xb(~@Ez0f3;H-*RmS6DOi
zXg)F61O7ga&vT&$g(~rTSora9LZ=*ONWyXEZt^a+ZUm2`(qdaLDRI4-%81Q_@XkSd
zyTT@V2a2odYk#iUSbj5_1kr4u<Q)R)pV?MQIs9n&@F#?YM&P`)*;^>SECY`{kY7gR
zLb&7$B^pXS$4(hxoBpD|#!CKdtf12OoZNyE80Bxk>`8hv@oJsNm-Yb=I4Um9ld&&N
zBx4`)=kg-4PBCvGGFrhtDutkkhwwi8LPg^9!&|Y!e4>Begy}|XZ5h{tu&+MLvS!Gi
z`8by9{Iw;}oA|V^KEROc!hok}Psd)le`lFC`x7t@clSs$cnhJ+=oM1fnX$jK^lK{k
zMb<$E(Tx{%N=Zd7hC)k~=~z>Kd-yX1xJ{lKpkh+^<YmmzZhxp}boIaqAu@zFb%&(z
z7hjyjh0kmBL9iBp$CN)DGW;&h=q*sD^=&_a881bMJ&02?U5fl6p?ee&ilXxj1)1Oo
z*Glob17iJZa_pui&7tK9;_k9?f2PpSqVzDs`;Tg9fjTubGS%qn&o4;*5a=Wh!sG7x
z*b9}E{JoEz#5D+S2Ww*nIM0g5bZmIw<)*@*3h%$ze9Q!r=D&JZBqKI#FFu8&-Qu-5
zb=Lc9+|}-GdZs_DI*I}ZpUlAZ7c-lnML48yUi=-c8fRO!EBBJ19JqjgUI!(|2r`+8
zl}XKwRGhVKYeX2wzIsphJwEw@J|0_UVf>VZKXkP~$a~jA?DzXa`5=#I72lDmS;bq=
zLS93jvg|sQYuHe4TiPmI(ahoAAAVdqMV#0*4^@JbA?xpd4~RFyXM^2f0&M3~gB``e
zGX6{m?<~{ZnPE7NbpU;ygvRX51j13Ou76wfET_}@BPtsi34F~|ioW#W@d0)M`woa4
zz$&-Ki{Zj7zr862xYH`?JY&J4?-&unDJdb^Wb^*X!M-X7bHjb3fCVe6ou)yvZS@en
z5&n1l?oaC_?=dz6^i0Po@eT0qk3k3;?qc(`OE#c=RD#&GQK6J<N&|9?xq00E$FpyK
zhQd}6@V-!L-o9${=r6Q>?dkV_TlWyk_Xo4^&$Tx{JNmQxh#wFUgWlezSDsuV(IkGa
z-<n&((O76gt&=GYYEo<N1vALjrm&B8sRcu>OTOwQ?>dzG_bwA6af(?Xi_~g>w7LcS
z0Bij$aO@$WU)VzyfxhTo1z5M~NMgEw`wv2Y0mWd9kTpbs-deH?n^>Sdo}qm#ZWuPm
zeY(&AxLMlq*80&eJRL;dmDjLwH>dC2QU)Nq3~aB8+e7ZZ!ju=RQ6JHAg-qO&ny$GO
z&;;`AH3;5zUteE*H}TzCf@u0me_V$mN3zJG^91JrzjlG1;~18(Zk;%3ZN-Idnw|+&
zd;1-TnM%`^C|9l%xhCq~vd&OnRlCg3b-r4-U1TIxMuqGLpY0d9MsME-9jZ$$2z7*D
zFayfsil&?ROS1+<rq;EuV`h)P4B}K}`!DbLy0tu@L!28aSo+NqJrB<++0)#6^yA6s
z-Zn&gwO|CkL;X?ll)wH;i*kO~cmBF%^%@Z1Qu(f?9(2L1+XE)g?9F{Rf{?O*uzu^T
zN;=Ih{_JK<Rf;#lHEfFfJ6QiOZb_!VkEA<Or4pje1-J5gAci)#H;LCjY-u{GG?L^i
z3m7*&vIrZ9yXxR^PO6uQ!LwJ;zvnNYzZ}`fB?{%)lhA#V(v8$R4eDW?^GUeT*Z<I3
z(w^!;m|;xleeT!Tr)xip*>+HHAdGk{DIuWWg|On*m3Fh9$M+H){%^$3ao3_dBgCa%
zdc})^vuDb_Hz$&cr%dlVLiGZQS!424WB0SK-}ngR@DE-TEvw+C1lRGShCBit#GlE5
z9E<7ufckPsEJ(Wkc$0YZZxRi;QDi@eDlVI@LU6<aE0d}{(EY?~x-Y-Z?ky6lI6W48
zT_!P4(IA&xFcd8Uq~r`L#Y2T%NXGM9H>P%gPAc)nG;c$;T1&*`Y8OsYFJTU7PO1)|
zV*EN9yuIDmM*}@&e3M|AI0MGmQ?nqV7`#Kb9LPA#{B`axa$KKjFGr_e_hqfp&a4AG
z)!A3B8BKgkMqdV5WYC9%EG1t)z3J(fOP^}%O{6sI247De^>g)9ewKi&4YXUos-&QH
zBTDH|7DTbI_lEaBFiWKHD>QIIsO0a={6%q@zdNv;nleq~4<_zveY}}m6>|nu_Lt{0
zY(_lSRyKBklZ%nuU27n2Q~-k>i$+#33Pqs@gH<wJP=oI;Hn9bsZ58(DK+SypbbGnd
z($b%`*%&o#gf7}y9n^jIn66IQCt<HPgsS0l<DaX9C;T_7{{L#348+>xP)((fO@9Ys
zvB<q$oFZgD{0)fSL$mtR0Njf}T-SxNH{Wrpt1m@nzb+_~AnI%^O$-K|O|VE;h+Ir`
zm@UWQN4$ybv-;rdxT)3P<vC~;YikoGzFGw8=MDE=p?lxaxdwIBk=$xc2Sg{i+(Cm(
z6}SHNmjsoR)Pgg5JNEfSox=`9QN)#EhFD_|mDUSLO~@_E@uCBhovF5CpCY`rn*#RF
zf}bU9H3q4^IjGm+tL>MU=Y$<6Rp%$yCOc0;HlF)d<#p@l#}He5nI+=gsR4hB&G!25
z&VyzrWuFzb#fu@<so8%@)i$4>pYA+3K>Q=~rum-;N}F`8*R6KU4x7nM^@Ir1|3A~{
z&0qgNQ4$2nLSS-sJs^z<JB;5N;fEYj!Dm?i4XL2K^KYR{&wT?nbJq>3Ev<4Z%ydVx
zzY|zK<Qf#sAb73H6+QT+K#bnh*|QfMzSUb35|nWKHE!bl<errwjcP?2D1aIR$ue{=
zZ3q8Zv6&)&?;R-guIVO$KEI0vk=+u?w50=YCas~Ay+lfqa?o?f-@G;E*S}D}B{a)G
z0cU^(X?KqUK7CoqzvCu7J;k4D^picsnIlON57Xy4-6oSO=IggMD<Jf4eDVUVf7>Z3
z6d|rNC`nJ%w#^-(p!Fi|xPWdQts?S?04P3UX#TklqSwAX$N}bwC#!qWC)}InmH@h(
z?Bz!y%&44hS7I<T58cU?zw#<CL!%FG!J8%nuMJao(CBSm={pBi#9(qXKWnTDRZ2$k
z?4|zk;N4Lt=jJR2gOa;9b5)c5Y|DGKbU6O7A$#v5PX$X|b@n<1DbzBiht4XOf!FAU
zd!N-mapkrb4c$}~_i=bEH11*z&A+}bR_=w#NecCv#h34thu+*dnqtz_uDaQ<Yna_^
zf%h{AG<mT27nOAYwC|*B5*3M!H0{X|yP8>#xjK%RW`3S(T!pQ!;i8HT8P5+~h7#Mn
zM<8Jb8?5?2bL8F?UCX~pS}v6SuahPa_woGqv;K*N*wb)jf|-I6@~6SRQ@WqOwj&X#
zx1CpdwFehQ-+4w$<dY_~d01KPLIRnNUxQUK09)RgMem;P%2aoA1=tuMNqQ2ty;ld!
zC74Gav)O%G_a?_`6@fp3BRosHFaaTiULB)_d$#%dILeXx$!+XC&+~lX$3bxoA*2|H
z1#gZY2_OEGP~=6}2!V%R_wIp7)Z3_k*e(BSI9&ekBP0I*bN~D&j7>DyJP`Mp^Wx{T
zx=<h^#Q18{ety`a3a1$RQswA#^{Pq`8&Zs*<sA_1Od$<{tLQW0BLt@Q8REZ!^3*z4
zD?fO(U<FD?{AeJj-D!oFMLC#U{A}e2$Lt2~Q^d)9U}(K=K@hY7jjl7H{9kS11;8~}
zV1jMGzxC~ma?0+OFnWt(yY{dMTpaEdvlW8~rkjDp_#{+-p8P9-V*?;7-8X){5`TN|
z^XXSN+*`r+WeMo8T;FA=S7LMWBw}tI0=8iFyFb0G+-n3;wq2b#Mt{l!Zndx0)d7Ll
zmqkyQ|4q)zUzZ-H@VP_=q3T!sz0Sh)XTG_G_4tCSan_NFJ0EBepRdiQ@Z-*~QwM=*
zv;)6u1rVrj4_x_<k{kzIUwlaUN+V!CF+{y=7(twQx@8s-%=`x5!lr=PFh7nYF2hQj
zfiAK`G-t>`6a%f4;5s4s4>CFo?YqzP%%pqdXVvh3tJ?O^^XXR1xb1Y1>RvX2OgrqW
zE$Wrz{Z@*K{VuTcE4a;^Y?9*)T%z@mOeEa+MaO{_{X|XvM0R=NYqSYe{-q6l|7;}M
zlT?2;N&Eh(Nf&i}=_s?7_*gwv(s9O#^<Y}=Or!!#Rz6$w?!ff17rpJ_God$!_}RqH
z@DA0utW7HZD|OXa$oE=VtMK4MR@r}W>RLwrBna>-1j=Ex(AOZ)bF=#HXGU+1Z4mwI
zo6v-dIy<zV=U(^hfF<-#&S0SsKBAf`OE+(!g4lCQDi(aLNRItU53l$Q=W@x(kxT;m
z`?`l$=S8gX_riwVMO;cG6%^w3gNO?i$r?leUc|(I0b7Wn30wXJFx)u3TC#+AqNI0y
z;e`&QMgjR_CjFH`3Gn5&5xkS*efxeA$O+Eh?l%vB>B$C2k@`BomChfSwI4cpv!9(v
za4%q??<w)c`rQKp!ns|1?e;`lyk~=+Q!l2TMvAz*;~7B0Ck}XrbF=;VKYa>)>^-Q~
zz^?vtvbO<z$)tuQDh*hqCIY%<nbrp=r?0>c-34o{wqx4HOOz8{E{tO~m%7ZNvx$=S
zh!J=LLPG_%AaCb;Zmrgn8wb!Z=Yfx*50)cHQzzv@%MkH*yfxMwoJpC8<*)vRaX4aI
zW5aeObKS9QTq!Q&g0TjI4miwuO0pl1jetkn<Cyj`$``9YrN{gKV@AjSgi!Z?-o5!>
z^rp@su9TBu`Fd4d;NQ3A)ygXZr|1pc{TYOzk2l&GzD_&bS+?oEZ-A@3+J^L9_~hAU
zaVqR_xc~bcvKpr%n8f7{&>p+e0m`X4Xf`Fl)!`w)TZ2R2sLbUj62XBOC<iwFcJw9F
zlza+}f71FZrmhrD4<4JqT&bKM)SG}N5Y&{l^p2_@NtFP&a}bpWv7{n6rv}(F1hNR5
zw;cm)b;q&i@xeWB+ahJ7PwhK*VS9$VQ0Y!RGJ0#4ghB&ApWP$sz-e6!NedfzfIUyQ
z(ypGb7i5E-gOg+0xmvBD<f(r5C)rv(#wji>u#{oeS*q0Rsy{M*rLd_=pL2eow$Zhf
zEp{3UAFMCk$Y(PjEXZp~XtV%V;O_R43dndb#kXckA@wX-<PK1<=zTxC0<q;;#r8C)
zWo5B;)#u#y>>udej-=%aH8YHLCys=hAc8P3@&kxliHg(XURiG*kjBEUi+6z}TT9_1
zeu+DpbjuIP$zNXa+auLz#T}FDOuXzR=eqVy2-)8=SfZQ|n!jg<JRm<Em=ON!muo%0
zh)5F!DBN0QlMU9?478t;mG)77Z|Dvb*C(7$JJe=9{JnOZ4jx9o?LELx>}|GxemOn<
zuFLPL=3iRmp1~`se7PEYpPhf&cW5O1NUmxEc164~N_)Xvc-F8`<MJPqDfeVWwHjtF
z{G@_(6%@W6p<h5x|Jj}i_N%aKi%%ji=!=Td#KvB_6e>#K9t7WNDqsJxD}}E9OEDtw
z5a<w#Jit#bS1SMdWh|8t*@K%cG^^mN2Yb<7M6e(sqg;RP57UA)Vf^iY5ZWVT{#T~%
zx89eGo5;5ySEXumKgl}uv{o4O@`l4;jXi@WMfK~IJ=cNKCq?_yen>)Y%jXTC2=BjZ
zU$+ufZa*>%{HLAw_HVf|W{MzE5}2Fc6M)$3yeWi5D9A3<E?jp9D?T;#*g-!x3T>@<
z*Ik4DIOkzkbGD0j9_a&R)p^)PIniS=2!Z4UwToXY6g|LKU-X$((89<(!8HRZk2n~(
zq?3$5C-nw+iFj#t=Dmqa6Zfst9(&IN>adpFUhtP}9zWPN3$l$Z2=JAC`MU1m3y{=S
zXZsyTzwJUd62dH-c|@rdaWklbGB#dTa1o$w%bQgKZ_(8_r#_ukNH~K?mlU9~rxkY`
zvVmBjgUw8K0rYK5nGi=s^+o8sN#h%Oc3I?Q3I1`bT*wY$<qMVAwBWoCuyoC~E$%A9
z81@6($<7|I-2u34@P0G9El%HMrQro@4*j(SA1L<hoO{&dT+g1okQlOH?+I4AJkVdj
z?rJ$-7R9Z0LX?yk&^C)mTwu<Mj0e47uY(InWn0)06|jTN9G{1~k9rP*9hQEaPrtec
ziF<%vgF?|#3<c>T-|qSAd#>~%6h8uQXL>YL5U;x{I;qI(K+}p7s2Hn|jo0f8aauby
z#jcN%k_w7N8wh2?4_f#tz}+S`{@TQYbC)gtCn!6cC~Zi=h$R;>JJ^qWByq7!s{?g=
ze5-c3OHo2W=A@wg)W=g`;!jpN2wb?Y%N1tByI;_|8$i2k-~V{j{H|cz-O;81j@pPT
zp29t<y+WhV8M6`*33BA;FOj?~vmd<EWi`PO=qV`EO%A@v$@!X=3pLNqkr5-hw21S>
z-FC#%ZarLE6~ZpoXIHnP1-8crj^v9P1otgi8<h|`I^5RgW~DBgQqO=7&x^mOuB6C}
zdUA6U-pVz61KMO(+g`Mh9K9VI)>h2n7RC+>7imS(1#uxyB~d~`=@3z$`pslQx>P<)
zQX7D6VJMbj?fGXW`Hs&9gerk`03nDff#lgzx;-V~sIU}jr)=`^SuvE<8y2~;`t)Km
z0`m`{M0bkY@&MFbgSe%ChFo^?5DJj)IYQTn3K^puJ#+guqAR*p^nssb7UbJiwweMu
zgj~t|ZS@`_;<YVOePHq$51R}-33JsZ(o6s%EyuBkAm-eR941FR-G+uM3B4<t(IhnF
zd64+#YL}ErNh#14?%YmWuvIGRJ-4v1!1E!NI>XX*56|=3*$lYE#W2T)Sf(qYhGRFs
z<-Q#P1VA{6qd}W2ts{*@&{}~QAvqnRMV)exe8b^BbJ2?0hH~>fm`L%V;;Xlj0@O3c
z$Ior^*mN9=+h=;g@F-YNhr|_6J!kj10ZjyqpF>qnxH>2xJvKpiPYQL`xXix?|Kefx
zfL56ag9)L5fm^5eV><h8+=2KN1UAOA2*rG((r$?Hv#e?vm2MNl`@sbzz;*W?jHMC%
zu#FBSdammH_`+LwYZ)3HiFUwY>z^3NUigV9N0VY*h9&-q^3JP=ATNbgoZ22i+Q-g5
zr|WwU7V?+!&UuVrhj@4gIBx|T@Ph)+`0#`%V=T{rk-{l4@o7Elm0?jZk}$$@fL{~@
zL1P3j-hXCtDcd2leXbm5z-Fs&4Sv?3)G!Ir`_Pnf7BE`51@B@D7%d~Sp!=j!<avCV
z#Wdc14BlyS_Bq^srD}!r@;uVI!3dGi;KwUNub_%Ej1acmk=_UeJ+F;lK@g}U@WI48
zz%>RzMm~%59oXJncLx?pYInE>Qb$UDKa*81C>_y32iQe#=rRUDm3#)85EI^mNo8Vo
zpy`<rs>=Ynp$;L|{5IvBdl9F&!d*hasQf;F#o$OCRx#cO49KUz^BHad3;74ASz)VO
z{Ch@&(nl_CzYv$c4;nZ(Mi4j^d-8NH7lQ_H29j=KKj>qO5MOS_-D}$CWn+AhH4)PG
zav=?E)=$UD<iIn~O&M_o8nL$VNTbH77|?etpxuBoP$|>8Xjoh7%`nnx=|xunQsfWF
z_P=dEMJG!KZcbo)^T0AAr;Bp~57o8x2XIRd>|4wUH)>%y27$cLF7`H?iD4b~z_w^^
z1I9QtR09-=Ls0ooh?3k^L!)uuAljdW9-u%AUg1bT<!W!F3IRhC*b-v1G_#)@nu|FR
zm~3V2vWIf4ZINWgXALm(>!7M=L-f{>fPEC?5zf!&bybw;WJ8ZlS#~1qGgF;_Ts63w
zCA=}`+!flzwin)A9<MU#e&mp7Gq!#elY=dJX9=|GQZ^|*(~-AT2Up9xqXZnnkF9W*
z<u&Saxe9@tLRK$Ni*0LF+UY~zWd+!SzU;qdDddYdOP{mfA?8g^!>Wq?T{m^URzwKL
zKhU{$Lh-Y5)@im$iAb6Da+~mAkJI*>2{h|q8oCXF)sA?uQs#AE$ccq24XQDw+#DIM
z@1WdWaGXM9*-Q&A^W}kFcTL{QUlS!qM%u+@%U;Y6nuLjOCr9dO&d}&SE-1~mrB`#8
zUaG{zVQ~6NFS>(SQ%qj43ndn$GtD>Mi&skDn8yCP?$GZP*13F(+4u!mXnO`ps^={>
z&)E9JwS4=?T%L~f4t4Kp9=Sb#RV`M_HXm{F?$;vJhkffdcL28AAX5fsP`>}hg#PS4
zCD+a#zTP`L&*n}2NaV#vPi%nuZzE&^6zC<kMNr*q6&^y!@Mz%XN}^v{|NV0o+<w@3
z(x-9zM9#)L00UyU?e_*Dg*|L2$PZi{V@N!Ep2sm22OY65sP2YWHf>=)*p&?<&9Zh7
z9}``kIqmj7>=;p2WQ+$YL?R5s{JA%&LrK*)zNtgC*HzU=ff=_lKh>N2ii$+DB?Vxx
z*9&bq%#wS#iW8Zp(CY)3wnx)Gtmy=l#pfENooB=_NA4n`0leXvOmWD=<)|bl?Vq?}
zJsOw8kUOWbnd6Y%o-gr^CN0Z9+s~13@3D_hf(Eri%T2mBIkInIW~_mG&7iW;gke$7
zPfEVyw&`v;S37B+yXIAGX#Q?XGtoT$sX$SR=<&_3)+^+_r5!@Tc|8xHKh}-w2Jax3
zd6TOadld8vb&i<Rq!8Sa+G`0<AR~Mjk+WJO>>^%<!hxiu^Cc{8#ajDS#lsf7dYxR>
z7e+aHw6?g($$JvS5r-T&arkN*qsDHMbX~V%U4|?bdF98GlZ-$;1y`K%P!3a1E{!3J
zt98v^V!q1K7Oj4q4OTEBOfxzWdTw5WJy5>`u9)9t4(a4P6tK(MR~;*$SF~x(q@|;F
z=Ic~{_Pk3koy9;&dS=a(t8v=0WiRa!Fn>1GLpSQ7&uy9~1|F{AQYI7zdbeBd1`6YY
z<J4oUN{k6kQp;8L{YA+*t8l<J?U_{PY%%BNK8HTfym``kbSZiUy}7jtj=$eihk*lI
z5v6T}RXu)gGNwDmt^HjT4x-_WlArV5sTwNcz1?F@v&>3C2z$1}k&Pt@ka?JxV-V1_
zi<nAa-H9<GT+(a`UJ9Qu^U~~=#=DG8A*~e~NN)Y_p<<a6Iw$x`ePRWQVimo6jTFNl
zyCjsPMkS&gvS$a#=&yCmn^bFOi|1yO7S?a(RN4!fq7&`)9a>(Vd+}P_y~5kjSVjP4
zd0dDgsV#IoHCrP!bOHqQ6!D-N5O?c-6QLTD(cO*2U%Wn-^&)*KXQ@CoCzzbDJ)Mhe
zTeh17n*^x&0&=+Zt2<h4LGD_(x-?qHQUAC-%nyZF3rCh|VnHEs^}i{@s1e}v_Q}DM
z+vUT#JZG|ENItPM(`vkvpHOi)*SoLlY9X+j4aB=pSp`9bByiDVec?S^Vs@~|STvBw
zEZgA>4^u{{&v?>^>qLCLlH-s#AuIKgm9bF^!cO9_8^A7Zm*bCC)7yblhJ&1eg1jdh
z>0|7(tV|Q5*al?vi-L>@60+;TK43ueHQuY2$3jl3ywTvbV_|Q5qIW}0l?clGmp3Z(
zM+CU;BdgkzjoGr#nVB)}qRC@J`v@^Gv#kj?Lgtv6^;6`p>mlQ{YA0OI-HL0gBAnCr
z`2C^SqMeZzja3WOh*0%>!px3|Y=?QYi}yiKW)aB3h{_^PA(UmdgTnZdz9Qpy+t=ui
zUV3jB$cBR|ddjfaRDAK%$zip<1^_3*h!kDLSBh^m8fbLt>EK1)6i(J(*>v~e&KkR@
zb30Ur1g(-d9(+1JUF*^_+A#K9vDN`CC*<PD;l4ung~7>?@Hk~4{rTQm8cBCvNsXVd
z?SJ4n*L%<lj9EM7C1E|gstams%}_a?Iinmmxz%I5pXQyDR{Zghq{lv>mgQc1A=5Yk
zGXGh`BsVB?G=>~25-+;}{V5YGmvYLkN0F*wPgBRru6gELrAplxDpj{kQXKFD5$JB2
zX?|0WGX97k33t&Y?PP6#L(A;Z$Gli|)$FVstHhX(sgz8LI<_35VOEoYr?nmL(@s<X
zxJXb&>i=g?&#>p$mM3>+Ag2v<552@kDbR_8eCN(DEmD`UPuJwRl72d>Y3uTe9@1u?
zFkG<4BOJo>jrRxy))86VK2|W!WGc1;uZ;Jj+lOnuSJ!jNuR849lT2$%@R)hjWRO`f
zGbpjC%Awy>*j?4pH}93wSWvX3b9w~G#b89js)xH_b@DeDxV9>qZsh7r?iNP!E)QtG
zRX8fO`HeSMhQycQk<47WS3&u;3elZW&zG#XyUMk5O-388g7Iu;hc~;$kT<Im_~)&q
zH~QB5wJkN6SYbJavS=to+FWx@4pWs88u-3;N9Z%#bEUW|o%;u}b8=2eP8#URjQA5}
zC)9W^p0Zyxz+eLWpNDXaWZu#G{4|5*5G_SOlZ1_zC@vWl8LT~JpW^3=FE}9$z%8B_
zqWR|L7Uqo-b2AGdZp7^jTRg2v61?iGgg&0{=}kV>5|esU-#$Uau)l2f^%M7lpl=!%
zWtnX;zJmFT3>F_~n03`n@7vriX^m7nb}Jx9)7BHp!PTwTG?#J&KzGyMxn1XtDN~5-
zFDC@vvmLsmURa8BkPN}D+|>)v#=KWzUc_|Fg2{PlmgmGnkOcbQ`jUCBJa^1o%bvVk
z;OEP8H+wBzVhbA~%S(aO$Ay(V{ds;V5I$ae@4j0*;XbMd!wLu#-Ec<F^;cy5b!h}|
z)wJc~>v^<-ln%93&S3!KS4(OSO3mNz%#r31$iv;Q>4S~un<krSCzv7|VG+cE*@%ON
zvj(lR7*0FB;<TS~&yI}7C-=lggi5sqIArF$1;nv3kzzWjc~Otf51jmFj@#vquX(V!
zCwLd5c7>CDb10)p&4696Obr$Nf^;_1lOjE)^^QrQy^L2Xzdd;BO^I|75I4czyuOxM
zy1;>HHfRh*8k;jz66ZvmC`dIa-oVKi!^U(Zz6;`3Z%?|9dVm?<yuK`+=k`-SKkSJj
z^Y(;#x2JxERz+46Pmz9NAyS?0s~9qkd9|Uz`rS?I`E4qEVcV;y3P$!!cLP8-mq@?&
zUutsFYALXiIYvRHc~Mfe`Ib~aROiFmJ*v&OaeYk!)CY$%X#^3s4R{F)HyY&FH9bG}
z{w~zW45gxU^z2>HTI1y7s|NhYSo9_NUc!n50qlVdfn^VTChK9@H*CNwL?~9BRJwDN
zu!mW$9-1@3-n^MRn5EBa#WHm{KT=@1ijIV({G{M*)g$<uRZ-V;(7q8@g;b_?d9;|v
z6>>OycydFbnZi)9L@H8#xU7~Yi)JHD%UHJUG=JzWCg3fc1|uNZp7T2IY6L#>>T{ku
zsT;_F2nm^3%eFLiz2aY|*beN9Pz#}+vtKrp`3Yi}o;d}TxFPTlA4h}+?kyDt_|iCL
zTkQa6I6beCj(NP1r(kLehihmXYWwnA-5yhZ*f7bO+vKAV*vEuoF58dk#ynEjP=EQc
zfaZq+b4H5Os^&vGus<ztazsmpDKtp@dZ|$xjsarDb2C=UN@};GTzY;QoCzZMMShGE
z&N1(<`GsPT95$V}^~{?l&c<8f{d0P)O?`UYgYm{^;~k%~$az4!IU}+k8w@eE%vG6~
z8w#&3#LGJ?h>PpX%nHUU%^znb?F-h4X)egV?iO}Gq_t|{s^+L-d~=b))8Xz#;AA%H
zl$>-l*Rj0DQ})T{F5bT(fTD;IjjJBWl8+x(&TdS5n$D_#y^3~Nbv%w#Odba^#w&OQ
zd}d60Ejn{ZXtEG@u7SLaLl$(6&tq(yYJ+i;P|ZzcZmC~C?-04BPIfnkD=*znvsMjK
zxa)lQ)a7KhXg@(6C$39W16@jlc}~J3?#WDaQm}5e0~l4+`0t&~5lJ!f$ti?P-Bo#f
zLeL&Vg3@;plEVg&I9<TpI8UCed0!`<Qpn;mj^S-}Q@IuiZ!bm1max31eeOa`)JKdb
zeUw=%r<L3jJPVKDnbG-Io0VO9CUtAfg8N4_j*u2qH*+tr5RTu?;0g+U!h_0fV^R#X
zW7XGoI#7NrH!CWHQcsio%2#uid{i3gfMV47pbD<cGNufCDX1?iQZjUBa^lml+KXU@
z*`hg;)17jnAi(MKuQ;wFKBOkn?1%X<mC$VHdivgwqmx=s2`3F>R%4;O(~~dOW1CUB
zcE2b3-`sQPbj3-Bu;n)l1Gg}80iO{YnbKGN`c8|&&aJG7Gdw+MkNs(^tm>vA3^Z5f
z@>JP5=3FoM6+}ZuA?A1QLJtaOQASfh!CKrEVi3};YO6D^FPc4|k<7zfte9?{-&P!~
zl2K2^Y}4y}S4HQlm0rf-re3Qn$>_+m1YJ|Qj_>W9taM-FNRobid};i0Q-o1pTk{Hk
zDFcJNNHo#YVWMqCtp^$iFXKyg-y&`7-y3-@kv<srrQ*0<n3`>rgD;BKHc<7!C|*$y
zzvyy3`NM*jmXUJ&w(2_8k<SYbK)9BQX)(<BVs-Dla@J8F(&HOaUtecJQ;6UeA-B*&
zBH<dCkfUsTHsj8Tt2jSAzd^G06X@<A0q-=IrI!X)JYz;eL%QPxnMt~8t>az91t+i$
zxtgzzcU0U>{q$TUe}zW$guP|ky%OW^?LucufuoUlm4E-|M~OnEd3R>}YOo+}A8Ezd
zLILd^r8&kk)EX<&4y$XFejkpiH&@<y-L}z>Vpr6avlKdz@Q6p*p-3oDdwJNjVCCb~
zrt3^`Gafn5N9K(Gho>xCu06+$;$2z|nb|X~^9a;N?=-EGU6;lURF&s@(GHqUt-a>D
zP41!tjb)h$ZeONHCzqb`nfDhNuX@7)Pf;^PuIzzE&<k3EwC)eXAxY1wnp50JHfwUu
z+{{sxI~(r-<pg4?vR9<YVNS!MKOe|$(9-u&r9!Wq*DTWcU<JqCsPJ<=3sH1N&%&8N
z3tKP7x2fP&Bk#=G;*Q$tOovM!_`OM6O?lGX(NLWYBc$!9M3<=DTX`Ei(2^|7T#{31
zFY*8>c+Gc@oLMPlHzy}k<$5F=A-ZgJBU_^zG*NeG3iYh9>!+b!hNGhPQxK#JlYHt`
zFt33uxQp0rT*5U~8Q3yqy?~;c1uC!Q&CzVXoQiYQscdQ%FLPdG6P5{a>4$5t4|md8
zAx2h4AJ&6NQx9_F4O?7wauBQSW^6#iXOJ-_n4ic2wUGGKab7d)NPO_w>_s;#AA5w&
zg{;-gR_s>z_;C&?msMI$acIbXIxeAWg`mn8k{3`$ijt)Kcwu#8=-xZJT~SBco`*SL
zM4~bb7jjxf*ha&B==njYJ0$TY_4#1#>PuH-q5l-@SBM;HG4j*V<_*h<`6<sr_wUHz
z79Rq8lc|vgIuMta{i4CgwnUomW<fzh@dZxtc|ZASIc?1n@L+8#lf+s|1rBVnKc&pd
z$pkwXCq3$bk|ED~z!i6r8QW7=1qX6@@e_eG^r+FIpk7-=`erMGLc67<j*LCiGE%)K
zLw1^nF-zDNpTGGmXCc$i&3BgrtHecac75x(M@atNRMaPt&-=}m&qut5qb~{#V`s=W
z^f2jSXYFrExQKVWBxz+)R!Z)Q`wk6vr=G|6TI?@j?8>|@8rkNucqdxkK>l)Y2KNW-
zIZecD)PCr|b2|U`aJ1R?bI(8NW>00raJ;C^c0Jhq_2q@a6Dl$Oc~#$dL=TVWWq1{I
zsjcrgUC=zD>2y$&_xKy2rVb&jpC0ge2GZ!M-k6`cS6}ngKBC)?^X*yIRLbwF>c-vM
z6|~p4%p-1%5VxI5x(Oe6gqWo*n{Fp|WdKb)t)X>k|GcG=z8YOreg*!^QvoZliaz?x
zEB#UFmPdIcSP6w`U3zyq&1C{Uyc901`UcBtDLcp*d#75NPW4N5K{nV!6i<mMcJ_Hs
z#pG6_0A7bxHfx?=h_NpCJ+BsW*hcTo$DE8V1ngB6BwATd)iV=(vxaiA^C8vh{Qzgm
zs+*)}J5Ok=>n5s?xve;(BnV$ny$XD8bEaDGa5GQsLm=4-G$yf59|Y^JIOQ0BI|#L1
zQdJ|5UmsAk7K%;#yR&@agUK=|$u+-S`1Yu~uDdk-(f&-<I6_Y#<y&B9cFOJ4lP~66
zeQ&jH;Z;O)C5JnHJSEfMR)mPUKOgYYm=riF$6!h;ei!7MGx(+XErZAh_HRZX-`Fd#
zNT%>;CFWgED|FCsCPH|#6wqpZQuk$W%ITp_l8&sq$KGLH1s<JY6y0?++V`;2W6i)(
z@R=-r&(&g9ZB7F1jfr-Unps;j@M2FsgU|w|U!86j@yDk|6kZ*GHRy5&h!66TrABCN
z9c4Gjmtf2~>_hXDhdOujYBeQ*bd6f+Je1p;`p46@)oN7oB%wW3J<!=m>YFUw`t0as
zj}PP&C`Sn<a$~2bGXd6lZ5Uv*aM7^^ThWwnm}=>rJT=FZZO=1TYur<%pEF^5<;JNY
zAVYCjrjezbf(b=ULbAfn#MQB-J*z{<Q$*9ZNlnQ$0vIG}w?j!zty9zLq18()=U9;=
z)OVudy4MK-8j85P63x{|1ANeL&^!<F)yVjcr>ULSqWk2IbktM5zhUU~lP1DiNVWI2
zyuP}|B^ED59Ho_(pj-MKC)UP8G8>nv$OXUTP;P=mgcD=At!;G@(^x0)gR`PVNn~iO
zMGF|IEdQjoJW>@$tjLA)%|}=_!z4DdM6@u13ka(csZ*wTB!F*e1Zl#30TEEs8<J{N
z55@<bNM}kn>7><FHJj{Hx*Nh{#WIO!mEDbuAAoiXi+21$9Fj2}1oyw`sfY?j<<LbA
zfQ@O=malHD$?5w1S$*9VQS!GD<vk90rz6X2O>-C+R5R{UQ`aKx{T4d5Joy}GcV|y>
zvZ4>BLNSFAl9)LRHb+z@o9T3K;5u=4p13VEfV%qXMeGZUn~h(Ol1?SiL@PUn_8#oc
z^5tL+i5GWwE_31I3rvlml&S8OLL?%U^oXYQ=nkuW1o?CN`b?9mspSx?rUkVk>K1l8
zEE0#M-3rqc@*VThXliN(qtEOim#l|e<0VbY&ZWvl+l<EKl;=n4CkKx<)tx6=BuNd}
z$E>C_yviU&D6pg5cgqY1E*qa~ZMq(><h1T2sTLI+rLRG#E};+%&d2yOQGe#S{ba_H
zH6Y5AZi2tVikT)y{`I9KT9PORs7Vca%Cv@>FHw>D!AJ<}Qd2)EsMK>Pl@&ngY7#<Z
zmOL~ja;Gxfw|_UEMbs9~S;cfgE<1%-*@@drZPHv^z%=yZ7(=AsifaBnf<hM(bVD;J
zvPg2CJ>wEOl6rL!Ul<$5aokAb$fGqK!UK#|T#hkwm($8T290LtN!LF)QP!gm#;n?d
zF`EfpJ?C2!Z{?FES^I}#{G)!odvGRBqqnHjwOcx*ug8Wxq{QmI!ctKLv1h!)k%Z!y
z5Z{@|xxg=zs^fQz4;B<7=fsW3F`)*4@Hqsh-hG*TX|+)fu#V?GAk=m1v1e`h1tf$=
zJWu({ZF7B+GK|vAw9auQRYc91j_y95Ip>qUHrK0d$POtTz|mU!0|rvkm<r~SZ$-w)
zib!+jDL+#!i|+m2qdgRNim4nZo9u?@gAAX<O|jfRuTKbW(;+fl;r^s^q}e^4>Q-s$
zSm|V`G4XV}oI}Y~#2Ch;2Hy;Gi`X>h&B(=!cEw2#ri^S7H{!Wg><1K?siYt<62C$D
zShwD(!Jsu$b)V@?#1+JUDNrXX15L1ANr*(yTb-TrW?g*_bpok!TK>46RrqOM8iuU<
z3M3!5Bk_kn2aCSXjC&9q7R6E_EVo|Cds@GoL6G}}!o2ZLjr6Lj^90Sb`ho>={)tgJ
z=`ETHIMOoI;Jm<P3X9%8a6mYGsa5?LY324v&D*rn;w`U(R`I1_V2PrxEO$t|a+>=a
zp(?J(+;l3|loAvYgrTsw$(@%*UzS0^&7)GBLsVwJDYS~wOowJlgNI5YnLTJUAwXT~
zbsi6`$&xxgsq1lRN`#J+4>JRGywOg`rFN&5f~5$%p3mAn4Pc{7IGx;-0<B4TENYsE
z71!4YdaC=bOk59?otTFv<F&P@w!(30b1(V~XRn^yGJOvYJ<>2SJgF12dx%hC)bi=3
zxx_c3V?L(u@g*jw23o29CRT<|w}`_aw-0A3J=&Q0RCP~D6^%}GikHi$W$??_iC=44
z9mX?i%E@<AV2t#nczYSY9HXWd94ZkoT^ox$v8ht_g)2PsIg7YqqPBIefkUeh(jowD
z-G1@TcuS<OrXM+SjomV8hN&Oy{rUDI^?5bhoRdG}XY_PR4t<}%TAu@Pw^`VE<~E!t
z`O~AO&qPW5u&c`S0qF5*tT(9XJAre1gI%fu`+U9R0Qb^becwPKXf#gq!$TLK$I5VC
zfBG8B;ph<uxK7{@STm3l=75@>-!AWaYXIl+6_R*?{-{$z#>O7<O<wrM4mM}Hs81DF
zy;^;k9(2<}l5Fp%_s-)UtswgRh(Fd_AJ=m?bp((j=d6C>oNfEHrDu}fAY0kOK?zF}
z{Utpa{ZK0-hpy_>XF9dcg7oYOMQZ)ws$H{9y|m$z-Jd}&-btPw2L}P0?NAYN7*|iW
zhArefuaVBG>vL0^)xBD}17N_}YZsq>2dxdDI$6~xS`)^9gW&&g#28fgRcK$*1raz^
zy#Lf^ku%}uFRc<p{W7m=@D!z$Sup2oV5Sjw=bB}ms(AY~m#|M$<H=bKQOfEuIpgGy
z)%u!Vnk8I#`8#Dw0HKQtk0nKLn||W1W~ZSdl%@*WwYqB%YPEW}pJ|8)&Poxz(wC=7
z3)ZqS$|kQ_I4bBcVkHCye6WQJ?0uEVYLfdBUE|F$D%v|JrK8jXXZ5T_l+X3L*;_4Z
zDv}b!qcNNIJf_-{w=>Gd=<70_*gHoQqUG39r%MXtMjgTn)?`h?r%I7wn&3VplZ}gs
z$w(*9F54Xmn9eKF7qZGff1ZZI&MU_@{k)0N>961H(Q^#6=ma&l!YC4r>IT+jUpw_2
z%7QA8^LRSwbVbrSQ|07z!!?qBKi4-g2w|fzeo31B>)5;BqvHX56Cgq=m%$mZiMjHF
zbRyrrdmmDYR+E`fePauwI*jJCX^ic##00owFj_^@OFhijG$V~D@~_7fWRzKO@Y40h
z4fJ0!8ud&ojJcGQv&K`;M9?sLCkWEhE^|j;i5B7svLESKaWL^cYNG>kPjP#DUzgq0
zh@rZ&q^=dg^WAwdsH^E1ChoGRx`p}<pD4ejY?95McK0`DxMlRu&C=}V`f!(2Cbt`C
z;WY9^nY50a;3}Ge`a=ad!(x9As5qZr6?J|Z24Q+)OK?s5WIUFYujBcx<a^&Avub_9
zzPV>LOF-JCd2id_qNdI&Eg$jPO1Dits~@nGFB^MFa2T5Ry!mp@=NU!U^9Us2k6JmB
z2aJ{$Cm(n&n^j($6}74E`yQBW_sIF4k1Qpblyz2qHs_z7s0~|Q0pWhx!3*p;-L6AV
z7#?XTF}G4_8T0fu>?7fw)1{CeU%R(nV|nko)PjJz!4aat7d=aGRZ(FsYh(%ug?}{{
zUu&w9kKY8BYWsXIl>Cj9rT$Is=QZC-{(N@%QUS{+?3HF#+Rk#Vffv~n+9FI0s<AhB
z0(;WQBOG*3+nb5VUZ(VEy}op!@XZgJ#20SJ;dS4Z2TIKc!RkG;ln4zm$axo~V@d-P
zzfX%vI|JABKRSE!aH#h;{{KB=Nh3u_M&zVLgX&lhMWYUilx4;;))r!r3Y9IR^`w-9
zO38%53^R5`);c+|?-PkuvPIeV-~IBre&6r^-~Q>ks;e>Y<$m4E^ZB@E7qr_~H!YNW
zTlFlEs>>WtDJs=C-H>m6RQD~64c(|2HU*$i+N*aWRL?m~K>lILKeXTYntj7+$|YG3
z_%4ZQ_P|X-RK`poSH+b)pDn3}>F3AgqX_efMz)D&Gx59$-;VNSXs{QWC<Oi+trL_u
zo)$KL{HDCSiF`nei(JsekIw=4=t$+gpkrEGe0+EO!uZuewL@9Xr3<rv+}!jf%X%O*
z#@m0ky92bpL7_LGQ`6i3VvCpFX;jC4^lvps8gUxft$aYfV4!0+>QK5r;ArcjM*Pp$
zli=iVnJj+?UBgdV?NgT^Y>ohE%&|Y7_NWeA$^FMNw4;7*ODbwdxL|}1991h8=5wgG
zr>MKG7j^)RX#}j#)7mjz`MxE;ZY1)-uRB*r`K*^Q{Ru>XuJEN&sDS0@x?T5L_ZbX)
zdZ($IJwZ%#xuN}N7f=v#LwW~C&w`2|=*btv%SGDF;HZ-kBG{ALEsq~;?wB-YX^s|w
zRm)k4?A7U2ZX?<BTOSyf&v&yoBz3Txy}a%Ii6RBiJi~zib$F|sK$%*exQ{t&JX24s
zdOwld^7J){%Gnw%cIRIRpvn3}cO9iuEi<9t*uXFBsM%0+`B2Y-Bm_!Ye=n~XN1Jz6
z>Na(Gd*k{LndI{drtOQ}Ah+AyRcv6KmnYMZWm9%od#3d6O%Fj1s3;Be(mmBaI~oAd
z&ETQ*tVw~b<{}F?-b>SjTB)Jp^D82h1f4La_a2@|?-RTz9f(|__F8JanLD4vZ@0{_
zQQLgj=;uHQ(ALf;cxHi3_3r6PdVKGVvkCRi9?7J<0>t<InABgho+5X+70Z26le*0?
z2hixQc~<wO0_bh;_`f$NJ&9_uK;3x1Fs&W5orCt$lrKq-_YT%&{J58TGNmPu@|n{%
z>6JIAsTjt-`n(GVcjlXMf1u0;k|GUU?^(CRJv{dc<$<wH(#PJcV7*<}nXd-~OvjlT
zSx#AvudJ4(pMJC>W1ZGe%m}xY_&NE#3AFu6(Gtw3e0_ZS*}!;yKpDvJzs~2l9eK7-
zH+ci2BOq*$owh*pgZ^`nd=i2lqr`CQGqC>u4LRsO3!6tNJs)C8+@KB6Hkqzq=<$x<
z>Vr$(D9U3qx1BdB@NO$?pHP%`jM;OR<;R<rS(0lPYh@e<Mp&|%*T52sQF}x9)mX2@
znhN(cMg^#Z`n52r*beiZlLs^99uSX!$vmRa)p|gfB_SS(3DREzI<(yc-dyfr`=9_G
z?{Kuw`;M4UvF51Vki^Xcf7`pAOGyUIIM@2IgC^ffY}|ssWw^Dg2TTG1UqDGS#;?{D
zT4*DGM3NZPW07&AhF%}LZ2g~!mc!iC$WYe(y>pKANvw2#!50&8gDl!D!-R&j<+X<=
zFL)co-{TIiaU%{mrxhA)lzj+($KY&o@>h-?Z!zA*abrXgyCd3Qh$9nIOn=aGk5d^v
z+nbKtSn!{6ONnPp`-SR1Zf*sW$J2jdkTCM0t&rOE9ftaoe1IRjvB+`4FRXfB)fBeq
z?+Q38`b4G@`v%$;%9<mdLGf!9=`$G`99KrJ!0WeCx(|zz)8+0ruu`4UEmMpc5nFdU
zkUvoJbHIpvXHB1y5IvVfm&9uff><coSV8pa*k}s@R~)Vqsb1n6pkbS48cAxtpx>6>
z&QSuY$n*$Qe?t`@=GZruwzfRZqb<;OdmOKvxOx#nL+PKaqfIb27Y~&=e~@qEbSz*k
z71KGSrjR}zYL_Gtcuf8#Il&?FlFD_5aHDsQXDPDs9A4Idzv<qNe&ZG`IZNC+H>bhN
zSzesf6LfLK>TVlxx199SinffWtEY3@*crtacV<tZ*5fS@zV(cr1E2W4sVzFMgDC@x
zpB+`M+J%pxp|Zvfs#G38L=B`x18=%wzwZ#ijz<-1Yl|3&7tJIM+JDT9(r4}GR2^Vq
z45A^ZbTS&>+F*()Y>r_HXPDiIdw*V&#JX$$gM3ZSnWUwe@BNG@Gq7v?G_7@W%xWeZ
zd;T>=iX8dPGk;gCvE%Cy?^DMT&jol)$nt-b_X&78om0!w1YTp}h3DJGki;=Lm9Q~g
zW3T^@rXM>LRX%HQ8cx#tom(%pb+#1PWPBGK=z4tQbWpk1&#)gUp00*``+$Gi%S0wk
zUN6=0KY|Qwrh7J%_ul~7bCBp^xr0*a9$>14F(v5jrwH~c;p#b>*Nrk<ql%(S&u(tj
zHyf1@JHzU*ZJDIXJ~s6{<|KXF%kbw;0kYOrm_kSW3Z#fT;Begc%-H{+lQSU)QgZAY
zdygAgM>#-5>Rk_*XVvwDL$du$WXvLeXIzcdi_Vl-C*-K!C}(40Sh=x2`QNy-Di1h8
zLvK|?T7K2i+}ctQPBf^kv9Ua<pE7}{;I{xttFI(^=rNv7-YNMBILH(COAvL;WayAU
z-Lsy}L0RczgFrPN`H=tg6H-ok4kO6FuO#;zw~hg2TDL$R(U4MUc}gv0O0y-C9B1ql
zJD1f=4iKg&k*{+hF@E(gz;l26ccQkn`oc@+8`F8l;*%F!dd+<9wp~eyjyGP09DZ)n
zq_WFDIV|n+Md_>~tP!F}6NB+nH~dOiv9QXe^?k)B-@FbzGQCA85{5<Wp_(3q#vFa{
z&^hSc@><B<rX|mt@M&&>B;_>4NzmX8g<d-=22B?H`>w>GMpOQjr6CZK0*~Tw^=WNF
z)Sa1sh)2Z-U4Lr*JjLNm(ObS`*&rt)i958)#{Y6Gja7^rlv4EdQO;)h9}Vzt|5a}~
zIL#WWJ}{$`p2K!cRF}8%x|04U=d}}oc8e4E0us=)>>ut~!ZOnD{Y<P$ZT4c;7HyVP
z;Rqu4@$Elv2vasiP?l^-=QAX1oc2<~43&5^BQlPv<xFj}iha}0XrB=E)&+vvoo8GY
zRbb-cA@f<=Uu0=9%9Dfgr-~4-KXv;p`~Y#AE%AJDbAVOiJotuAb?<&XX=`stmrExG
zzgz<4Q%~z$M5JiH<zp$+W!nu;45szMND<umm+EQ)T;Y_R0yWiECL4+_La#q~14C~q
zzALrz%Gq+Os@qd+?w;T&@7^0FVBK`MW)&{wCWgcCINiMGYg37n@ozXM$n54pvXX;d
zZ*fJ-yP9BjGhNN4z_s$q9UoIINTmvFw>%VEG;d8X_)2&6`j?cU%Z?XjR#2dsLZA)U
z>9KWXdiE0^TQQ8}+Y|)_V|FFb?(3$AX>fAS5f^Qf_m2;%#w#!t`GBolC`hHVTa5$&
z(pF^Semk{9kZ}GYWI0)T*|=~J00w@)$aPHGd5hE(-_>XFXT86Z^D&&Vkmc37M9=mY
zO;Y%P+$g`##T-wm8eY?Bg8;Uk5KS}ET%|YVs900W#rV4{hNRht?~Wp;Lcy1J`KSMW
z>nO8ChXM)Etyv3C=yp)>Vyatw#n)79Fi`}h*ISE7MHZIvfbAzkQ1YZ46tmJ=u$Ie;
z4`wNb6AMxV`%BvzO07O?S+V5eTUH$;ayp7SJWd`rZ>1<5GRtt=m6D>WsCD#>NJ7g+
zX>p5*{ij5Ze|<e~max=TmD=*G-LPF#)Jf&QR}x$m-IT$B_j}B<EN-f6`3)i`o$|kN
zv};FORW;8`UmK59Gf5C^uR6TAS9wqJ{mbSbp|u(6uIY1Bc2lv=hEzk5NV3XCrsaT`
z<y`TVt=00S5B<+jT@2OBef@pfYqk(i9j@23{BUGi*W2#py@9gCF8B5AubL;cKekdn
zSy|^>X$UHWEu2flKMW+QY9}TMdml$<?8F+m2g8&upcQgKD;igl<B;p;`A)bDEh&i>
z!<k)JGh95x%LDJjdni<f|Eq=r(C3)`WXv`>_}AHU+TS9-X|+Xca0-?+zi@2?{<h%M
z&0b_haCmw4xjdBrh_*7*%YlIwvO1XctXZ6S{deL32&(Ks(3z~}jsWAkoQmy0mWV{t
z7hu5G1$H*oK<gLC{|M&G<R6E;@ASC9<gftgBcmg?zJhk<2$&*YoI3dqpnE<rNB!mX
z*2cld?OoM_ZF`L_NB%XGnWx%$>G!G*9q{U-{Vj`6x9@$3kk-9r5VtykG5oplMW_3d
zJB>rYWcuC@Mfma*U$3`17@-i+RuMm^V>j1rJ_FF6LeRf;ycmH?vGn2<NR$@5a=(5`
zd<>a;HyAG6KuVP6k{B%?b)b1F9T5_CT30P6Kr!c&-@cHy8yO{$=k)`j`tjMHfE4!0
zuwq5@)*_=sK#xu_f2fNyU-GOGe5mCnpdr4rvM+;R-+cNvR4wCEO`shFCzIOksYl2n
zk$N<Nj$o1?Ec^K3DE$Kn2VPy~fv*1hJh+0SLRV?O;6{txmP_u(2#?lpGo9gs=GOrk
z5&y6N^UTnP7g_o+A)SKj=fJjNg*-WP3Y@qsc`$n*5TLKPqAy!=JG5I8K0<=mGpj#V
zA%J-E(~Jt34*rPDLpD|<=|E5gUw*H#Sk&0!z!{KQA>ZQ6d;l6o0-L^i4t7suwg2e@
z8z*$W1aza5LMJ4^=HmO~H{l4*8(XqCdC29qv`Sy(A6f^%apXB#M;c2BCA^H;?b4Gt
zG~afM3t;5LlclS2b~zoBcJ%DZXBYT<=-4}hv_N;4jbxlo!3g37qBsd~pSLboE8Uy1
z6)F%B^wu4GG!VK;?>A(glS~Hw1Yy@;nH{XU`2gd=#nLbk%ymKs)OXdUvy9D~uQ7d!
ztrcCNR-V>o;KPf1kWqF2d{S6B{yGHiiSa8ind*SsS^vQT;W=GQT!8qnj=a+@eS{!#
zZTc91K1)Xmz<)3^DbU#(Xmj>E!X>_Yup>Ba8Sc(_;{>#B=!mflv$dH(o2XGhg^gdh
zvb2_X=sjqT7DvT<zE%so+rOTH-<o2<O11RbX;^P&b|E`tDXXP1Rv`pT9b2PijvX`S
zAM{eY8RP9O`>yI?R`l~N2mXlM>qp4xd&{1Qjrg3x!&^S`2r~WM_tUckWS_si(48G^
z4Yv0S)e69Oit;gT-5z)kcYDN|@)@Ugyh~fB1wC0*CS0n&p%}8iBW*gxDm?apf(PLS
z;VOH5X{vDg*;pQnW^iQOo;pAq|A$@mER0f(+F;EY1=hm;`t|$V$YHxbN{VWHbXn2l
z7(Fgf<r16+LpgJ++g8`;I++ycJunzg@(Pdhq8uj|WWCncKO${m=<4K$EZ||K+pX(`
z7gWZJEJKCrm-#W6z9!cq@pyZ=RkK6sMG!r-OSbfq6FtA_13*sbnz7c_zxPXX*G9{j
zd4cxzBiz!CESLTFqDiFzV4i(;mwVsFh$bE2w)Jf7>f~(D<4rbK?Fov~BgB?8%vJk<
z?_n4~b-%xY8Q`IZ@8{<OJAslE2?>zj(j;)(Chu=(K12uEd+6V0{i-GW9D@Y8(lGbB
zN1tV-(S%410ieAMBDjrVxp{PuNwH4HL!euA*++z(aotVI-><c(oua^+Ck2x%Qt!4j
zKM=dT-&pAi(Fqc=&`?fXt~%H+^fN#fJ0btR1u!iqA(JjE9eXXhMC-(%PUSIK5vBZi
z^|RykI`jHDds-(cd|NjGdRJ`E6F`;zKEeQm>m_&Md1LFDnEJGFcC)9GXoLQ=V;I+S
zqp2nT&p$N2qx~=1v`058JpwxX<=cxa9ZXug{ns9Y%~Oe6n5wEy)*z(q)Tc`hD5QCD
zyGrMr-2^=741?D9_>L+;>|0vf{fbj3s~#GINOQ~Lv3<X;jY>wk?~I1#><f4M9Qi<%
zzy}e}7R`*VYeq9IiEd|4Z3{^x*=5XFZ2a?{K;(&xA68)0P8WW9u#;P-sFxKUSJ7I7
zC&k6ZTV9(S2%#UgQM<?<O7|$L0HS+vAJs<v^c+gd@{ClzDQ76%`C_U}vV*1z>{+sR
z$`Dm5)p=7MdxvSBj8CGCn5YO{lURoFRMOBv@OF08w!JQXJ#R6+;+VHxUktlKG<wqJ
z7C2Gaxwx2joJ>(S4>STR+y77P>6eO3cPy$gTBhXAeRAZXohLZ69z@Sj5IlwS#PkW%
zp`6Hq2=Li2S8KDwTb^dk^%9w-qe<n4xf*?80&c=>9BQoz9VWOxlM6}C+unI)n*8_X
zM<uW!_XQu6#m5KRy+_zS=W19a5~KgzQq}uupAG$Am+J?q3#uVyT6B2=o=$N{z8bU+
zjeAI1r1YZp`0)s_)>%sGUHT;iP%!usg1q73Afqa6zt`Mv^SWPqQsYjEOhbXODE0KV
zwhflRZUL#>nU|l1%j13&XAtpo!Goje(_w?Xs%zEDb-w-{?U5?Jnf7e6oBhBu9#N81
zm^o)qqiQJ}<vg^=nt#QUBzdG2K6>^bFy}aX#9rE|{qz(Xes?MS@#;W7)yLK?uK|QD
zL(b_~GX2DL?FVDdJy)b8u&Dh91gTyh=%+X!JuK^{MtOglnd8KlbKC?4+}6dAsHA2<
za~X3B8Eq0WTuW}zTUyyKh<CM*tkdsz!ON<1e>lZW_jUSW&8B~9)35X`c}DssDAniv
z-QW@Px0&@|snk}v=Vg>f#;h0|llACz`r${l5#9EXPc%A!>o}J$Eb>?4?7`aOsSWEo
zO0z)*{cJUJ+hJ>dy)PhDdY8c+ChapTGkwte&Y&7=SM8&@%d;R1+INsV!bNB13-*m_
zq~<Kz3$i0)GYls7r%S)91vC<-)hxwuZpF@^#(nxB1ZITQr=K%pt=QYTpB_l2=qPL5
z@IRNJ>zC>)sde|zs~%`Nfe^djP`&`vL4h^p5!3<St)|U3Z=S<Qy-fRzJ6q@VUv_Zh
zo`7axv&y%B0X$S9nPSYwlSmfqEyvYp`D0hYp$~oN1n5Q&`Ty+Jom=ZoVx^KM9j%3}
z1TLjG_}ZK9=+GL!BD!nLs|uV@@#wgagb;D$1neVtcC?#mD3B;Di4>+w`lJ-mZ`Zmg
zq!X_|u$yIlM_o&iSrGt<Ln+fkxhj)vFrD*M4m8CtY$uBvIQ0*L%A}jDU5{D6@PBrH
zKNwAC4@EX0$bFiX*rKAN>YM8mpb<YJrAE`Ny)W)9i)7<+PnR|z{aoLWFPN(4XG;z?
zi<v8}yR+wn_4iY5!U0dmdOfAgWbrjqofh@$z9pQ!7Yr4NzB12p87+0V%Be)->Plk3
z7b!&%1b*Y?RZBaWKt@R!9o`RA<K~Wlz3BiQm>6b=e>3@+UPuM02p~S!Ub)r}U8LW|
zYt-HAHVPO1mfdzUJS3%v8lS}(ECA2-ctNMpc=!Vu^RQhU$Bd#1<e1{WYvhH!jY}>+
zjL^Xf3>fp}7T8>{*mk=9Wa)5jZAcG?F6<F{zW$z>_MW6s;q$w8sAzcb@_7P|qDxO;
zG&CE6>f%<FoE>|gH7j_pj+e;{{s`)NI<g`lm3vvx(U<&Nbm4q(=l1(%&@UqZ#Q(k%
zwYd!Xh*Qv#SwZ)_;$<Kj)_(q`DR>Od`_zZGU7$1LZ4nz5gty%;X$_0(8etFx>-!SF
zqRcm|yn4T&03*bPWh(7*fd|!5nYR^q&O%?|g+3pchkAbI9Er4@Eo19_+5Y3FySjZF
z_d;*Jq~ggHZ7{wSU2LJeG{5efU-DJ$MfZC7QXAz*0^j2F<_Y-JUE$Mk<RDB$Xy;z(
zQ!N1uugb7A21I|-rNg)?wPVx8EA&imkgr$Z3!R=zZ^}T81Z1Hr8MLDowJ`&JQ4vF`
z=MTOe%$Lf*<4INfKws9&`%?cK+!nKCZC<-`QyYIS%#Qm&=NZglJ~SbLwr5TN#mb*_
znOh)@S%FLIr;CsvuquTZL_LlOkHDAQeq^kfjer%q^Up&vHb0kvxSTpMQ5U5|MEaei
z&$Z9;BfTJZo0PDp`q>`*5^c8Ymq#Hn2U%h7?LmfwufgH<w_;^~$MGu9*?mrCHU(%G
zD2el)3?A}mf7(+T`~h0Rp)ocp1s<j6g&YFv^^uFt&ehrzG+7Vx^$<$Z2M*+(aCz`!
zoc09eZ?x7=Kk~?CG1q~z2`CYQZ`?D;s~NW3dpO)i$VJL=^?%cY?X`$(wa$BJl(AsD
z)lgxLg{vwpzxv^eIT!?#RJIm)+4^FhxBmQ?KLr`Uk3-+I+`RUU*J<>SJs_h!Ceif!
zF8yEdbhg6t*_RL&sj6&|EOk=LBOuSZ=8x<mkGWf^&(lAr3|)<L$G1@F6;#7rYJa>0
zb8us!)qgH#g=Mf1@^UFk)<bvdI9UgD!<aHu(AM16So)U>44*C<XnhCM?)3B{^;|T+
zzrrnIdPc{qBfoIh&a|f|kjQEUi9L0{%L2f>#R>i`hYhM(xD9HLx!9dJL8D68cBbrl
zfb0r6ec9a^_&0;>2Q{0>J%@c9%Rrlb;n!Q4U?oE~Cy09o6FLo!#GkF&2<nsghC?|J
z*~STv@2VEkP6KlM%)EK$PV#XkV+fgwS_L%A?f6X)b`Xm0hdpu7Q4=<y<b95*`3NgR
zMzh(*n6*H*?m!RszE5en)SUxAuU$X`(^0Jl2uk@u>yZ}l8nQx@2V&yqQXBumja<3z
zidkR-uQ@+B#wIa5W5IyhK=|=W$FtfBQR(u+Q`6M%i~qr)=H#0?HtmX3Vnz#1`fp}9
z0n^oh+&HV1X?fsdFU8MD)~@EVsG+TSy;UWdB{`JA%RA+K+|Nv2q$1T!Ohh@4T4^u~
z7Z!MogE`7SlD5<;+rfG|DKb%77j|gw)6%C%nDkh0U=WiyADCaX<6n_X<+~w(k0A4B
zRmPG5#KuHaEXqj~S2mM{7@2Iz&AF+Rn??!CV7O@jq$J%KqFzbOtCm7kAY~om>3)ch
zX3Z<|?Y~LmaZhe`8P&M9GjFBhl%JT}@2?qdK6rIovGCb4QH3iwGLB^_L7;u-?%5(<
z21+Mg4(VI^kHS6<N1Jht!LYK`nl|_Qia&D(%Rc^xI8=G-E)|~z<KqZeWq&u6N92%1
z&1#3~yu#dUijIk_0O7{XAq~Dg(^V9QD|jB$IR{g;Ii~5%!no|NM~}J*igB7XQfH2s
z9=8q^M*b1~QrH;FD)EdUGg<QU)1#weG_0a(Ku-=~@>W)afQoKk6Q`gX5$s~CwA9FP
zY7Tw1?#}=a0Mn-*WNhG|iijilyUTvxB&c|e2@1&p?=mM@nEnqX!w*e6y1-ICYNo@p
z%XyuM8cEg;;Qn)O6c*7u&l)xN`G&_jWO#WGb{w1P=X5y(+_-o9;6g?oQ{r#xHrooa
zERDuHVvY9~gRBTfnC9Z#4M~j}1Z{!{{vS1?EYL3)9y>;LXTUX!&MxC@XGE-~FGIqL
zIvsAFCRp`0^P-mcpENZx-^LAh?Es_rC&%C}9@mxCZtq_Ll+ND@=m%yRr^UI8f-O&_
z5wmCp9d$ISCi`EoD`Mj=NO2!z)G<Igp>#4v6pPZ}s2c!Dz{UN@b^IvoJ?&NCy^BxP
zf>SSXEz^@mSf8yY3abnAy>U`OXxfKJ%|QimdP@ipvQ5xP%&Oi=9$bLCWiNr^b?!pF
z6G9C=CSq7;bx35J7i*16&;ZN%w%gdJ$_uULI<p2scq#EFtCO^dBeDX==@`(P-m618
zpgcjDb+N~iBz9PylhgVONoup;ZBe4&aB5zxVMZMw!Wo&YjuXv4%57F7`HT<Xtjg-%
zYw;bw8rg%1^bBlkdAK=^LGHuwwX5(IaRB(h2;A(gv3)6=uPaqJFeJDz+%5A@&J}PD
z8rbH02QUgva=AfB{M7;3jmsPXiz>C4bdkkq3KrMxsr!y}Vqi^wTyFEL0#+B=gYm88
zk}GVswO7Ni-x6;e;S=g2kJLMj0Dlpglb7bebWvxwYYagUTq~h48nVZs19GzfR{a>#
zm=CsVEW{WnGz{e+PoNi0S(Ge<kNuN5G=?G_&H*DY!6r(kMZ8`B-T0t&Ed}jOGN7?2
z)Owdtu-E|!ijH>ouD~cki!*g&7*v#W#M(H$K08wy`}UNMfflk#gKG>U!%DCmz?mNc
zJ)79lrMV#+03NQB`VpVWP{ZM{>iwD9F=kV<DUNiA^&O|R9)UMUKk-3WI<2C})a9DG
zP%n@lC39+zS8r#=Yhm7YgOlp}`1vaJ2Gsjx?j|M?hv2;@W7N=B4jiKz+5+_uW2oJ8
z#TW-nlC4Q=05xlJY&H?BMSN@q^vt0YQ+Ng<aD){ult~_*m<~aK{T8p`vO9oF9h-!t
zC%4e&!<@F$&BnjJu2FF+&IkJS(;*d1N?b}@(841<oMW77JW;TZX`Do<7=#GD(!N8B
zf5Y)3wx2nGb_>c;k>1!1BZ#EL+{;`XRzVwFxJhQ@^5Eo!$@b#hE9lGx8powNB49bF
zk9Is!cZ)do-y9rN!)S1RB=am+82h#xcHc@7*h*B6BbQGQ^tj6*W<X)_V)r@LHbLuq
zp|B4nWFlfG4$D5rw#UG0koOT*J1BT0X#2!xtv?GJi~>V3H{tYM6>#^5aN%$&e^dya
zump4WBmRlwvt&$pBfJ2Ig4tqiV9IYWNt`Hv2Bv}5$`Ivf82ohlia^S=5p9}aoV=@B
zRep~MA9kG0uLhxKHK4}n2&aNpWtN@FxWel~Mht`$+Wf+`62Gp79u&uGc07$^x}vA5
zsp(KVoYJQuGk$5C*8@_7kXL;fB*nAPbDK}603Ja9IyKow^9auMjsHh)u&+(jgbY*w
z=y=x8{B0NN9~JS~1d$LB6DW9#P2#V#G1V}ptE;CW<~ab*8B87~p;d`?wGP9XoDUU~
zn;^bz)|QJ!QV=$Bt^R}sGOh#hMRl_XW{--5iwnDpzD2`E8<_GS*vYT&b_LhGvO&6b
z$%cW?A(=pUHBy8nt_lz<5A8)gQ%IP())T%U;8hT5Qnz_EoNHzrPHGpnaA$P9?17j+
z0vlr|ZWcbsC17%?vrEv^oLs{IGD7cB$p6=+ax9psm<MZv8|}K+FK9J-pzfV(CO-SQ
zwkUj`EgLb#5mi{dcAIkjeyG-8P$UVqZPW)(^*(X&sZ!{IPC>aGC}AiqzQ!XRPwtSi
zpxPiC)M5Y~#F&@O*UbP<WF%6jCz~KmIwdG5m97t45f|o&yh>R0d<$NVe2KoN9M@RA
zWz%^iwJ(t<h9P<<TtaW8y|m5b0Y%gJBv4p(uk2KV(&{i(h~fQ%Ca3p{z#JrINMkW`
zoAG!sz)jyR$Kz|nmEqDEe^OKgH2TWf<@rZ|ZiTqiMo2Hw(rnoD@ZHM+0igh})=%a2
zLSv{=7}0!J;X&BbA88+9hpVW%?v=vJia*No8m_|QQJy?tM{^g)q73ZJF*0oiB2J0r
z9CG?^qDC&=<~Z&LdBhZ~TtzUU5JEUHHHf=Yz|@VZhI3nQp@d=Q`yl@P8n8oz?NVqr
zIEPR>ZBdU$AG+-*>IOqlTX+wGmVaS|g4uRJ9U<Nsp#<0)?ar4z3;D)y;C&x}8f182
zIVr0~*aG{6!fSIzoroY-apU@MM%(aC>D46=-A0gBUNM7?1LgpWc5{vF2{i28t+g@5
z{Ve>S2GG<~ZqmfJLr4Nu&@*{h!=oT*ahB}443NM7b>2}DyRuU_)=S??REQu(!K%^L
zh|uqt<y36nvWhZn_{^t#0+Dnk_&YC)b@=0?PcA}!5)vB+`k`$~mnx)Gu|vCIJ%n<$
z!lh5RR}jEM+sa`KA!{vw)=7`fl*1n(^#2enYxW(5!()X<B!sXNJ{Us`ns5ohPCBvr
ztWQX^g*+W~)$1Pt_Rr-utO*U+y&-)kzNUo)k#TefT;mo=+cTI@G>C;2R;UDE?7vX;
z&jXuP@BJF}M*z$^mSod~gh+E`5WDz@V)oxAzdPl^nD<ixMtWm9uta!CC&m$Q4UaW;
zBqwKm$wa=w(*nxYD_QuJ+fyp8WOxJNgM2Ze20)qk02%q&&&_&s#2hO{#Y~ZGcqbfy
z);j{7gWrMNN(i9|ma5_q76;ol2Y$Oh1rKr{gDPuZBW1yGof__xm0tut&<F6Yc%$_t
z$Sw2Yut*yoYgq?rj8FqwP^BL<k&Qq?qEyd76-z~OG9^5&z{-aK*FXylh7m&ein-Ur
z7NKH|uL6eLK{`>2G*JrIM!=c5o6jNQ5N#2{NS&=)v(`&!f(km~m{ClIA_IRonMxwg
z0DL}JdI))@RqVZ_Ol9#zE|5N=Pp|dR3nw_?FzquC5|Kc(JZ?}zZxZpSN&#KsoQM{?
z+N2$opNGjt>Gs>|1)4@=>(vJ?*w|zg!etVD3{RVCy;~{t9YXF7LNruY7X*pH7b?w@
zY{Y}6k4*1c?EM~TC*;1Ap*iKAy5$RZU49-Nd>s6WV9<8YCopv7q7_<*UWF=8zLdon
zgN?&1{(_a%OtN*sAi9^QL{tF{jR+d3NzErT?c?vUG7^x+w2w^Mp_hGpDL{YaKw6_n
zDC2=0@!=V21-a9vIF<As(g|u~m6go~>uiiUwi3t<ha7uB_wBrA3=)-GNPK3M<BT~6
zjvHd+DJafGVZG%)X^R<srjQAZM5yqx0n*Tg6k({D;%TocD}r4|$+PD{TsY6^RnS#L
zi>o_i@0LQq&YKugoc0%N8UlH5sfFv!weko*r66LFzyMplv55diP=eRLr3ND5@IVHU
zy9L786XW{wJq4z%t2DpU!HuSUru(nGP($dGE80{r<!*F-nx$mnE5aTS#l^XrOsdcn
z_{<W6-Ue*I2>-+6+pQ|FgYWl0R3uvIJ^w#q-T&S84gU-J_5ZLmn-Bxka<soX$@U5F
z|Hsf~0n7h?yX5m;LA#v`hdN@*Sv38h_2TFQ8ES**n1luG?^g~#&>bQ%1f;3bBa08M
z7LZ>~#WLv{iU2E1i|vQtTIR!DpI?IWqW(<r!1j4afRamx=0F{|ayQ_$n*W939&AS5
z+a-#T7gj#ffdcEpP?JR4t3y>z&p#cR=%KD%58!slP4ZCt7tL)E*v%WdhzJ&I5?l|M
zXEl^hH~}6M{v;7`GCmauPw3k>FOMShD5M`%Xt01rwbU$U{gqE#*@A$>Fm2KHH5RK3
zb_gvz1H=;?)3qR=b6cV%%xU{{y@$;MUaRE&qkNwLT?2-CwP;v@?kpE*(--Rg{Lc;|
zN@)2$DDV_0cF>hAx4~7y@HlYfib_^V%hh#ArtG^4Q~bHILdYRT@7rKCi0m2);o6`B
z3GHE;@MfR|WoUzqaaJ8#9<H(`1a!qqLC|36$gtfF38sJ5S2%+U;T1cckSMAA*Pr0<
zMDsiSJ!8<$H4cUq>O0`6#9VJb1^^OjSrkH5)d|t{G+Ld5qW83?bJ$UK6@xCAes!|~
zumZB-#B1@wpGxh*qjB;R-?C0bINuA?;^8|Q4gXBxF>z?RVOYh6<c4L?R%V7RFLk6_
zDt$nToR&Fjw)iKYO>HbyPwda~Toq4J9PIY`0MxFWo`YJebFEU3$fDO>ABrKg<aM3#
z0;C+x&KULuni3dREeR>6-RW=6_aFm#4-wN1(S<@`%(KFr`&4-~d344$=fqn?V1)`8
zC&-#rxx@^@wE#MK_pbC|tR3Gp5e`L37Z3P=y@`))_G~l=c?k<~;8J-5q|%0MwJk9S
z9`j8SXn|AU3Ghl5qIU4OMZb&uIB?3kU?Mq0UCg6>$%6hQU|wza!UK&Kv`@xk#QJsl
zZJ*$2ANE_OI*`M!AbQfnHFXhm$!-9VU8umVn)wya+jC*~y_mZMygBc4;^AZ9*PjRf
k+Jt^*{2wrQ=A*^^m#EG2`<&gn(cc_4I{G*7fa{h257%2FrvLx|

literal 0
HcmV?d00001

diff --git a/ACI IoT Network Traffic Dataset Analysis/Images/Pie Chart.png b/ACI IoT Network Traffic Dataset Analysis/Images/Pie Chart.png
new file mode 100644
index 0000000000000000000000000000000000000000..86449d3576ebdcd37e6f1d156ff4a485f0a3b5c0
GIT binary patch
literal 60217
zcmeFYXH-*L)Gizq8yw&$B7y>XRFE!Rx)qe(dl8WiK}td|7EnPzq<4^BLrowMP!W(8
zIsrmak(Lk;Lg?kL?K$`T?)U%xycvUG68GM7&GyV^&b9JZTT_LRo`W6+gE2mOcwZL=
zI}Y9-C7n6}z6oq{)Cd0@@zhnh3oFN8S_B{H?C)sYfx#-H8TPD?gU_d*Jv8xz!OnU?
ze@CY5xP4$S68_QsJNiDBOOwYR57VaFS9?v^Dk~%VCnG1Hcw>5NY2%ZAC?k}+tDvC1
z{?Zp^Z5{pG2Io(sZCL71^>lFa>2D{Fp(}lwmpwDmS2ho)e=IGj9|UYL7!lE~`^6PO
z`+n3TKs0#WW*96pldk`mlaroxQ$V20@#w$bJD7~uI%8yRbmQ^Jlz+d1nI<G9T{u3v
z`@cWld~x@`w{)TZy*Wky-*fdZ-=Kp@$Q*9>2LJM?cQI&YQrdeqZ#bK1736-fq@}b!
zgd`EJCz^j;o@^i%yYmYQ4zU`UXTN$yH(y)7J(o&}NpPLSBJkwZAw8`z%^7`Kh7`B=
z$aJtGx`3}S5lAtW1>!$(Nx~;?@#Yp{LqkK0Y}%t_H%4t}d(_^NtgKHN_5QlLx@jTq
z2YcJ-K_7{^dBcm*iaUkWz{a^0=k?`=6%zO1)@y|-A(nH=D^y15iN|uO6wOn_A*&Wj
zM^6tTNVwa%+GR|PIO%KC_RhUYi&i8P%nejEJql#s&iUPUk6Gr*V3$bqp3$49%K41!
zV)q%?guO`oo4^UGs;Vvqay*}Wet$mcE&C}+!tsM=i5Afxj%q%@8kQPcm$WU;X9kZP
z?5?0ra{1go+zdV}z-^3oaTO(RW4j3!Mo8K&@m#=K2e0Ns2W6M0%_)C$1J#M1o>^gC
zdw#wnV8SH$aNB{jVhe+XBt&KX4ePscDR^&H^PAUVULq;Of4QGoX)lXAcu!|>aZz?Q
zP7h6g;^m7MX=e;+MRj$f+ZWEB{W-A__x=0h(6F%aVt29W9JDKO+^PKpBgZuqq2zFX
zB^W)}xD}unpO7%_v>C~*WXYTM>;+!wFaURWu!}bHK6><MS|%^m-Ja6jtD@&4atsEm
z@dDuxqD+2sHL9=qfF@FA)jV}ttymwU{Nq<gECN_V?zw@!e%ua?T;RWgBgok0*DP1}
zD&hlK?x*xhVv73>>>_JFzdY%TPm{qH7QcD(rdbh_FFC5-XNwojY5eEv)%2U<e0&{T
zWl!_RQV?SY@UHfWe$NuP1?J<&e<qPcSJFUU1WRKQYPj^}{N^r&J-&O!Jb0g$a?|<+
zm6q(O@le|R=Y9XSjbzyGwJs5(-3?0mWyjG9YrkCzhSJ}o7s|rILZe`&4`>rT;{imQ
zri=(-Y~e@_eQazjV$3#CrZ<P=>_hF5ru0*q!|Zna9zV_!55#m1YAI1JHPc4STnpBA
z$BGRECJ_V+bTt)K%}%k;NR`3l6Gj7;4U8;iUpZ$6AJkJuTw1~ycYq|XDc^Y+X{xDK
zs#FixWXd-CnD=yG`lg$gR}Iy&oP%O-NxiO?ut2a1-Y3(>))X9^sQovsBDUF!>ANsb
zzo=3(q)~~L4J)=R#Zg=e<Gz#K{@nr5Q2O!n^0sH_IBqPB;XUXoD=X=lnT?{k6w)^7
zKp>OO-?;+I(kU@rf%^{zYrs4P9`P2HmUbt9ad~l>WnzD|og2S;<k*Q@fi15j?82+-
zU1f&F08FqC-wN1z##?tm(kV_s7pKDI`}K6YdWF|aq_pgvSsfM5+CjaK&eRF?(-%C{
zT7})EYT4zwne}e*-djgTIK3w-4SpNUf+Qi-5-iED)V1VSUx^P;z<+x+O;JRxUY`!>
z_N@Q?g@N`fR;ySeRZ4S|I^o$XGoLgMk4pXB)(AJ~RS*`&%QPu$PI_m`bM-Q*u;%CG
z$qc6SEa<X4PF8C0UYXJiact6R+pui8$0YOhbWS%}yOqw(Zar<=*mkPX7oRU^fZD}3
z;q7*4LYRq<p1leL->6{buYa+WClglEy{G!wtOByd@wZyIipEZI2YjdNpWAo6`^ggL
zXCSvfs=g_yBw#m`;VY!>dQ_9z_!rd_u{>e2zq@%zrio6!BqgCfzsjB4$6aT+6tqtx
z$dXH|(|*%dkQ+FcB<;S&{F9ts@2S}2kp6%`o^xIelXw}P3dOl3n>5%CfTj@!k;d<h
zyaigB%a=|9oaPLVirPrM2!r{5F>}M&hS_i1_oUd$5uFC}BZI%bIfGu?<@Wi0WZtt_
z9#~s5JtoFljwlxGh8GQ<n&w1~TH`B?EPY#%QsV91Wu0++dTE|=2-2_K-d>DF^WjXi
z5^|?kVKa@gwGUvIY89~BiXLBDiLS@Z+bK@VYsQ~u;kh-hxc9pSt+!ZOjbCdp7d|8n
zm$<gGZ_F{DK0Q{9dHnfk!QmGMkx@;Wax@nuO*&}Lhq$`i)z!6s^3t;qC4PRV64a!8
zGmDmdzabGbTc2p@SEM8;*q!;|!_OfD6oof4;O9^qC=tsmec3OS#Ki}Z{J;&q_}z~H
zt%{ue7;%=UW(0ZUKyIaRuqaS5v)Q5nc>th;$bI3$g2;^<&vts{sqd67U;dOC8#^;3
zw=0|4Yf<&|Ek$2dUEM26Vf$BX5Qa!m+MMv*|MBC;0e8^W=Zs35dtraATKW741vXs4
zZCVDqxRg?T3=GRmXZN-XGJ~*G8oVO_X8=&KW_Y(;b(joS<e2m9-ra=)mc(zcvRb59
zFpgiwB?j+Oq~|99Q1>GFHPUXmmmGi?`Y}Y@b%U}Enb~oYUFQ_cVZB@88-)^NUaL3-
z3gY5BE+VTPwvfF?-^`9wnp|w!`mTxuOwhEuEJrNjo?Gp45Ec)2SF;OuX`QC*fP&##
z@PU2SK{?xiUDm766az1-bta5!(z-Kk@{>}E@(sEjB&qW$G2V9c<Ylqc0T(y@>}@~A
z-6ipKP)_js-QC^IaJ#Q2mX;ZF_;lyq@(gwvpYP94I+2EoG+mL5QaOA*-z2C>!3Wy~
zgVH$+J?l%wn*$(MUUMRoPB2|^C@G6iOe8N=_l`(U2h7NqvvV3<v}4J95OLm>rf_q!
zhu}8yyYxwZLh9yzGpHi2BkU4-!QKhmm#6_fo|4mKe(u2a7+Da1>Z>RQyV&#Ms<efi
z=qZxFvs8<y5>+o>-5p=DlaWL~ImKOpaOxz4Q~l!BtqIu^)5%32>_|TWU-(h#ZkIn6
zw71$W$I6icdulHwv^ZE0jWg<aC19tz6g4tWw6MdqMRCf(seVb0nPD<bdF2)j<Nm41
zH1a{y3Gk?PQLCBhmjx*YX%_v}_FDGXC1(^ae`rXbI4OAbYKw_k-zDk6WK5$$DAvxD
z6qU5tZnytPJbj$*1y3KRj7M(u+>_yT8*$08G$UJkEBk6YOARjnB~jk)-St7OL(^WA
zRCmftyYWijbVHOSWujX)$j+3SFc?iJHJJ&>bfV|?4&6=`LlKOu0%wQj?EC0m^W2_@
z|6M6tVp!(!Wom0{%eAR_uD4`oD&_AH^+f5xq8^D&JuL+THykaYdI;F&e}g!&&OL{P
zC+Y8U9y`xt;!nCuZR}t0il6PG<Fw1w9nNQvd%~4dK76ilXhUW=lr-`|yt}ZjEz7Cw
zOFMV)1X8Mm-meEfYRCAE1n0Rtbw>Os{@s1?oRb<ijag5nMCV&J1=O>s!r9L)mr`)S
z-3ux#TLxukOfJst+Kli@I3G`e^}RwHNV6!X_E(!lZIn3MSv+KUnDS}zrZY>*_r5*z
zVOHwC<P~egw2>z$H+_4TlHU&p9Cpjb8>AAGVqVj>Ie;oP_y2H*9+$AkNfoyK-EWGo
zM#~S3c|BPi$iv%RwY&PdcrgMYNnae!&RBb$Whv>5l^OhrweqrSJrN$?9IZ@Do*w~(
z*1q6-vsSB=b)t0?;W+iyob%ppVK?@`v%AKDg|2CbR6=~mFLAZ2`;8(?X$s%a@T7X*
zQ<oJ<iPVs!{*OH8Cd6(?q`Gt`iQZG%UmvtW#A5@}H5TlY&!tR;_q>s3dAIx~dEE7`
z2TMXSAJ%ND`;=OB<r`o1md3ET-KSHV#Oi9LWAkaAQPuvQK|xL8l+i{^51~pyj%uGY
z@0$NSwE}}(DPv!)zfQGJ&2+9lR>iL4C?&e{yM>ve1FSG~{13gfebIDyu-S~S(X8%r
z)TpYirr>(Ig&UQJ*YAse>?#zl1E?`SE_Cmj_|FbH3%mJW{5+>b<*HL8NySNskq;j}
zxEMIvXAn>GrhTWg7irr1NYNK-pr*XH>rx8#PExWT%-7Jot=~##Zr5&79h8>LWNOrH
z8fy17lieM2U7TY;T}G08PS~<>6e%s911o{-Gl<w6v*)&dH5JBq5zV3FpxmKwxJSir
zcB(%r*Cn8;PdBL-+P;t$Cm~b@f0pEPrgA>-*-12;DsNm<wSQ_oygoCiDc5tlQ=@Qe
zvwhOzSD|lXy6<6X|I4}gdBB2@8JN>d-cRkPy5?59on3<34)KkIVy+hT*u&jZqs@l_
zfL><7|2}sV#&Nt_=GAGHw#bX~>h~nCp3<m$GIB|RoSR%xz{7J{)EU1|wmKXbt+at~
zg;ZQpt~-xUKOFb@On1jl?-i(o58N78!&t_z@$ksDBOj=%zoU-ks6>w_Y);I$z@Ox+
zr2btHZXzx!B&5;K>753^w6Fb=bg!+N9Cf0*jVnhv(j$NAfSP$Ylq71Cmi3L!PkPd8
zP%0W%(oMD>nQ8d-LCp)0NxA3A+Ymf)`)&PrjcKs^g%|4`d&i%q6x>8{v6GS&Ju(%v
zODRZoYZ_zMu=nG6N+O^#6`b2q*{6>il^XwW$q;?|?e7A6<*O;}#`PYvQiD<C8H7}(
z+sKG`w0n;vVRRX-zGeGGM;y_Vzq!v>koHr(R+_w(yqWHs0g8Ai6(J8I7{5vW86h%)
z+njP%x`)@d5Eq&TsYkYXu|*M8(ldy5&Cqkr=UnObAA8j^S1aj!E9LRXo*-_0Kn=e+
z_HI<dD%1LfDm4&GE^kO%Y2Mz!-<tW$UXP3F3xc)qo*mi7^BC;0mJhiM)2*G|48L;a
z$^q!)4*ONODZ$J2^LyLd+Z)|ITo6B*;0GxcdkDHZn)lLZ|8@X%6|`%cDD(P(44p;L
zO06?ry4A;h?%c0{rtRv;7ACoFC5OJt^9R$(HgkryfVtr3gFp{);J;ko&dtre!pzLP
znd$TM?E#HUAXZEH?<^MVr^_PNUWbM4Fv~7nK3p2B#`vn|<j*5lTiJFS5ahWDl&-e+
z_vYCIvow_Wty`nh1zOyPv093Yo7({!?^Ng9%Nv$u&0OucdgYg+a`W=GMR4o7e^>#Q
ziCyd$YQFY5)n|^3icG;<)H=m0-Mrc7i_Z*LdrL7C>um|(w7`0~H(62-ZmoU0x{tzb
zq$uR*YM`=LL4?cV0M(j8@>{sKvT7biN>5d!_aHYBnh-rn?j0L|qUiu!2bVJgG_Kbv
zK+_;-dzNkf5>;Gxwnut;J^F&^7hhDevmBKxRo=Hsfwbv1Uen=AF{^c&4S)~(SCAB3
z6%Qr@Hz(&WktZ846c<<T>8`MC#brRX@x3v=@VP+be7g6J9%zkcJm>L<po|72g%sdA
zXTO{qtLYJx0Gz7r-7T5hwbvXTQRh_P`d?4)aL`@Km(K-q5PCrk{-4)v?Nk50$vO&(
z^uI5FU;n=TXEMMKW$mBW|GV-3igB_||Mm%7+ucV)X4U34@9*!&8+ap;=t1y#^bE^5
zYl3f_(NDvmw<_Ctb2hDIHO2PJMqJ_u>tr)HYWnn^ykc`Bt2A|WrFMIve8JTu)hzz|
z?Zmq;j|#w#&==JuN9P}qgPuK5s;IJGc2gA5j=A#O>EfA>3*R0;Fba70wzO_#=t?*}
zV^uJ;fIhL-uU{b-hp6)GbqNX*@*8#Y=Hm4yy4wfBvG>_SZ8g6evHq3v{#h3cRU~fx
z#OuCo$d=I?hhwe9SPT6(vNflT<`<rY9zQwW3&mB+NhpL&Pq7?LsSuI$_T0kAoGRT)
zviexlC>HM@xFN31lBnjy#$K%1AD?YKEA(Z1H1Fp~k?X53_fDM!@!D4dEvBzK=}d6R
zAVV!r&QC*{XwJinp5f_5%?=kR|J*~<|DA58{>rZ=LZ1*GedLI+KM$nGtv~nO&-<0I
z$9f8WV4U0iMa=&Mhd?#_399Y}&C$v|B3gH4%Mic6O!<fPVF-x*5QSG@_7b9ur+X0*
zORW(r`*h;P1JhKU!jB#(g=0OTCcKsQF1aVX9Lf$(m+>nh9rCsetvCJx(y|WzNPBb5
zmd*K*YR38Nsb)<H`T^bi{1}yf-B#t$!pzf5ET+!S3Zyv3Buy=d4@PsqZMP?(9D2;$
zA<R$M%e~Yy{l3KaQ9Zu!bJ`P(0=<isi+*94w_{1nBtP6DN3zt@OiCM=<P-b~xGU>O
zoNuG)hYu^SUQlEC-7Z!|P;?$|9zR}}rt|tL*6_sZxe*1a0WN4ViF^mC<@bGKr{*%B
z(cs9_#oln@1fvW;b!$l{%lhm6Fo*kz=-|-TE&R(WVJF6*rF|NKMu3IKEHkH*WtZq)
zI#)~hTcE?oT<9X-jp_J4YafxV(<)_J<}AQrAIM!S1h>FWK(Nv9X=T&d#OXN;{XspC
zp7_~n18q{J%Jcjy|6J4FrM>C@9Qf1gVWu(7b-I%aD05rwK7gIuLS>pFUU%<^JN41M
zv=cv@CF3|PJH+njaJS{9Ups%fL7@T&&X9x<ND+=W|A3SxDYe+d{KW!WN7W92T9uHw
z-q{a3wQjSo!d|bx9c)r~a_)S0c_&y@4?DCfvu^@O=gx314a<c5A^|ad?KZC`pH4B-
z_bE==c>N0T;gr60hjaWD@hZ5(K^Rh9$Wj+s$s?pO7|n_?Ay>_=$^;7?Equ=IdaK6M
zj8po?opxqT?ak4L{!o-_Kti%wMK8t(jwa0m6--ydYmWNUeJWqb>{D$|>3jC@ZtMOC
zngJ-09|jHh{;9($?l<udvde5y*Cg_06UVN?NV?IZ4>`pPaZ%h8cUojIF<pNtfv4Y&
zg^<|+-Tm$J7};~Zwee{n=7vFiE8L&%_PvEs9`*LWRG*DVOkn)q9X)!A5g3(293<WC
z>S|e>Hp|>~a@X+=)lT6`3z)yIi~bvNh3$7S>9s}}2O<cL+ctNhho2u{P^As;ozqCl
zEN$)BMl)oIlGra6iEolh#g&myHlKopD?{1Q_mnl>SHgXjhxbw%nn%qNDR3g?oH)yN
z)>Nge=Tm!oKM&()S$~|R@Ep24*QZfY!y-OgWG?Sk!}-KI+{USp{89sl_nH?5?$}c%
zO?JJa!OCDTiEGfBV=H)av{y8yvqa{31xgAhkVhm`CW#MjIkTrMcBGGsNwR}v%Z8GT
zLrC23*}#BAWM<P;vgu!0w(j-0$NbQq`8=upVLz^@Yk;|Zp%y4xA<Fi8mPJ#U^>?^?
z#<Obn#E8fHK0F9LvDh7x?$!T%a#%pP6A6r_od~%-^2PKDfxD!7eR&<R<7k4FcTqo@
z#bFos;|hq|#pja<pXR!7>_>2Yi0mC;xzU`p@X4L0njfYzEAKdqN4T)Tkfkavxd)ZO
z(&;#F`&xPiG^E}VKTz)zSLJ0sf{Ficaws1^Vi&qLBRL_U?VBbx$*}`m)es8V?D2$U
zW>ZS$N6evlLFh#)xQwJcT=PqfX(?Z4|7UUnK%9zLXtA{Nx``Qep&;rez`6KwVc1Y6
z0JHVzV_5Q~{Oh2;4{<<oIrZyYJh{w~ypGQ#$C)jG^*G!DML^aQg~zVF&mf&;v2Fmu
z3z?vc@z>`Q7HCDzwEog-@pU*5vi_RdA!-FoE4gH4ny%J}C<w{IKjTJxsk%U)Kyzuo
z5rgh8kRP>Rlz#U62gtM1m-<!q&zg=2gXjJQX%0`VRy4E8FYWIY7?|bdrt70i3e=3^
z=(7Y@n%$Gb)B+=gBt!!BE4qR#Gx8IIO>#`g9xf+gDH->6+ZNld`Z=#Gi=u&2ePU;T
z|B>OqQJ4r_+RxsS+5o-hl%ux?F~PkT>{Zw9;A~vMs4dGD!pWiWIMzi!(rZ?Lm2Psd
zzP)!#<Awz8elwMIH}Dw-6FLUee*D_5tZO8e#mK>~RR!k2cLL!;d3RGD{_F(>Tq5BH
z#Sw?lqmIE?rP4kT0Wq*HQ!eo@zcW})IB<{L1SaXZ1U=^B+vEp+egpLOLU)m(Cqh*1
z5`Q&BuM|wJmVrB9S-#MU_O45!?)UE3sb=EGZbV1F`Wtp2eDhPD=f-lWSrn;cYs4DD
zi9UHK%Hu5b%M<fUN46Hp26L;xoLM|SK0n9qedogN{I-OuHe|Pa$Zn<;U&Nv<GqHwl
zdl?H8Ct*uz$e1hGA8)3x&ko`AOn+7Ux$-S^<>ky?6tn$x8S>wDtnox)*kdDvGg~$>
zda)oj4Eerm_TPs>v1pnkL$0QMGE%F#B{PkL!4S5_^HSK|ts}BoMsh@u1rD+x5VJxb
z_KFPKOp6d+ZFej^{R>8O(Qm#r89Z>C79LT>30Bw^4IY+K?-8x#b`Vp@7G#<SYAWR@
zjAZsKOD&Oe;+`~Dze<dY4?y`87>E~#w*1nEgy3e&;@ac~!08SSr^{NrR^A@->a2+R
z69l(F5Zo58Q7n1L9Ej6b64JtO!ail7K?Epxksd?k1uPfF!3I4{IlN23Z*_i{W7q$q
z`0NE(Ume}?I<NjClZdYVz#)FYQ7Hd8Ag1EL)0CE3+TLVVuCbj5$t@knFby|raumjf
ziE#q(k>CQM(D$`WRiH1>N^qnbu_t{AmXgx4)3(@Lz+^~3o`F_ZF%O(~o5eQ&eDt<$
zZJWADj)%zLyCYde^bAaWh}WAVO3dWE_gOFqfgOCHC(`wpWajuQS{24ShC*^leytBk
z%>|4j&v8%w1hX}yFN?1JTt5p-B6)I=JnMPT#RzkN<EJqZ%X02nAMd{W6JyqYM6b55
zots>370dfoX>uAS;hjDnMt)lzM#`FcCk&#Mv7Ihd@YPXRq{*YG^=+l$Lqf^v(~uwW
zLj8w0(R-U(#<@Q|qJf8CLrRccN)v*4aW%~~zwgzm?He#}nm=I%u99oE;!p~F8O5n!
zFi5b2vi<h{6Ot%QLaLSZP~qS})3Kiyt<%BAm1EPDIaK`d83>sgI^jgGRbYF9`#vkz
zSqBJu5D`V~u)a~jU1g5yL#Zp-XS6?*VOY?VW3UuyaqP2+8iedYeNjqnl-2SvSjf&j
z0KAcR9Glk1;s;dNR6`xn^<_~VEC?fv0btQJ*T_}jh~<)CQuDN+K@rjUkA&AiLPf##
zo;byZyPXzp7m4$c?+DfpqMdCV3qg*XrewIs_>q>Z0Y4juA_vK=7k%Wh*4lQiRp$FC
z*`^V&D&x3vZ@FMc0l->nq;ekG<K#7>12O8hT*_>KFk_*5;D2{Yd65#E%NPAnG1_&+
zGCGpQ%OVj0E$hBw^Ezp$R(3X2sfNGo6BKhuP5>GbHF;L5BHY)?4qK#<Jwkal=h%Lt
zSz%durZI+DdX{_lxO-LqB#{NAH)CGo!<{w1#hHlQ0dwL6;?D7lG&p9(<v7ftLv_M(
za(nFV<XV3KYdmG|Ap+>}5+okSUDDCT;g($Am2u_Cg~atrVN%i)NQ+HCCeru5teB=i
z*a(BwssIVJj+MlG+>J;D)lO5}R7Csr=H<;uos!GS(J&Z)S&!hrqRl~H!=Q7s&Uuj8
zkkYign-(0w`4WqY9cJ)Ugvd4TvZ=-G*fJRGeW$$QzVnwS7MoM%vx!w1LZEhVf_N%q
zF5yuV;l5Gkm;`h48SqK(SDZA2!Sr{KI>nlP2i`&xb-T_pz^HQ&aF9Oq^6u|dtWS;U
z>V&zDC?!sps2sC0@W~<oPZic&X)w0O?G>~gphqCj6+=oO@@|>=tq3}jVp&6*s|X=q
zsuC9?Gn&WfVIe)8I7Nj$ikQXfhT!aZ!nDT)fXt3pZ_tHc-;1F<jAl-xIGM*D(`{Q^
z7<Dl_0;{OyPRt{}nhzRGqwQG$uc03R0S(T0;=sjrRo{y)Hofk?U6Qf^r7w<g1l_+1
z9`>+9VAvO>LGVF705l{R@>@fv9#0_R<vK0$1LkMY)icSWRwA1zZ~^eR*^M2<;j32c
zO2h-!%|HnJ|Llp6vTpMYn6;~UPFF^@&3+rIl)WL_3mItz$9{1=*v9@w!y5zxSPzJy
zrA9{aTmn<#hxt+EnVGe?h1rprUml{z*<lrdfP*7CBboszZvufHk`N9oifmiL<YKfw
z&=0!gtU9Gj-OKUESF^%klEfsvkK$Gt`73OB<4gdY-a_y$)d*iCr{=lw!>97a707Y#
zj3gQn*}%PpChqk{geE1UUUf^p=FBtTT*RNrZ^hM6_5mWVn&(tiWPXc*Wuf#q&K^>=
z_t(qb!x~k>yUdb*;Uy&D1y~N6*CtP5<CJ4dCc1yU=0AV|*CSnie$bG$>6W-|%SMEj
za~fI>4>>4t>XvEe<l~DPgyS+IC0bA4g2jwh&Zg3Pk<@}0dL>OD6i$(YA`Sl~I?r1x
zQPtBm$C2Si#|ZIs<|v4Qaj5B1no7#{J~X!nv7aRaML=`vPVV})friuIhw+6Zc^z+r
znJrj{Q~L~+Y-J_f-`s32Xw@1B%5wmO$E+xo9ny)#`PTyBbKA_>CG=Lh^A%zsX0-iR
z_UbJOI3*)nE)-<-If(VYt2(;4@0nY_GOA2H_dj3)L*h3hq!&L*+wnIKx&B!Spa~&+
z=N5Zr@+6hUl&K>&GjtY&(As>!5bczopz*%5TCSY}wV<;0nFF|Y7?To8Xydw`CsY-g
z@FQVBG@QX&;uP#LA&E1lH^4W=uz+n8vK|w#UX6K4@P{c`%T6tHWWv?L$2n7!jdaL*
zz8&?~Wy$eMlJ<dUXvO*9Aj0h~iOtDQ$<tkHt~s-d{{tK_q$Rx4j4diXyF+adDmoIj
zpoW=d@I^nevJlypNB4`>|03)+i8`?kRau>ceOl&2?0V6*WOg3Uoq$+_2J4+GAqg!j
ziA~LFJG5Z*^Y;_Aeg*bjqhF81w1XQJo0qo(Vw4Z-20%XF)&m`4mhErfJP}l^UE`CB
zg<|rKjd+JlD0h&P3*1JFQzGYOK3@R}`T+$cf-^i8W7TrESH@1Df35k`9KM&(Gp|F@
z+_1dQe$lIEONJjo-2|t5G#J4$=E@q4cfQLzjv1k!lU~`13|>?ShEk!y9&{HLdvofn
ziPcQP;NsKJ#U&D29Km5VVUk-;Ga+&Ava(V{kdjLo>~F_3jg9q{jX^W32QV?qq*I`4
za8?gK^u#Tj@>s=u$|I7AyW~4;B>pIDC=yUxul`hV&>N#6CnkYlazIw8R(UNlCpy{f
znD2{s7O<W^wsdCc;nTJN+=Me0a#5h?2+Mge4bg{uZa5GznEw8m0iM4AFCx-s;Ce6a
z0->v@(ncjeYWPmSFDN;WH+zWhOAh^Q^4C;P0i<x~hU{}OHC$?O;B6wms7ODO-!^e}
zA$(M7{KDWcvO+;v>#ZeRK~tDb@BI-N!v2nK`GMQgU$d-##2Q1ZJg@%HXN)<~@!sbX
z#4%Gp$NchzKFic`WEH227P*F<W70DNEVb}r#0RR^=h4MZAz?twfQHbL*NX3c$$fE+
zSY+wpo>IOvVPK-;j($mzxjw_n=+<L*6V%Y!YuByjn-%YkJ$Mxg;!27x6qZsm9`?#$
zg!MYPm}@_d?To8j;oFi%ZMPbK2n~nQZHu<C-)W1T{DRexqzjOws_wSyiHFa8%kF*Q
z7hsTHASvE6xG*w~)Q&|KHIrg8B3zGy>5EBI(QP2iBKeOj4oFsR_Xl;}Yo(4FUpP(D
zG7HH&D`g+vpCaDT!1o531YT7Gbr#&0Y*<LOOf6r3p$kQ`|JgfNLU?!!Bvg#{o`sIg
zqN>v^#HHP8;T&G?JCEISJvn^3&<8iIxit!{w`_RvkGS)YxVXKw01L@&{<01;8@Y!0
z-U(K$>%tA+qc2=e4llmnd%3)f9{6)pE&BuPLS%BMfIEbPqb!gk*_%H86S({Ns%Zvp
z0!eBUsaHev{?3{8T+RGSsjqtWPWE+W)HzsIP?98r2)DFa9{djyg|#(@ACWlSG@yIk
z!m}()X|)WldeN={VgCewR^jGPpY7Qy&OM9AI@mVvjK?6wNK;ER8LZvjrFxtqq%9+8
zA#Uf)dpFds=BMh*d*=V5k+Lvzq>Nu@HXJ6C-&a43jsgb*3N<$)tw=k<4H&6wFc?wX
z_CXl@@agltpk@eM!obuaONY7}pjuCcv+m0dBl-3BTCBgyRj+@?#-Me)6}wFe?UnyN
z5AW^C6X8>glgx#|X!Bj$e15;lc_6f5jG#Taor7L%J~TM+o*r{@KBkyd#A`SbXuM^(
z{0~lkiO%fD$_x4rG&q6O%nR%u?>;!<xE}423p{x5pBr?24tYwOX&y>jeTKv2gE4gl
zOzv{a7t!qq+D6}uYiKh$74W3xBp1j8?GVaP90h%kfO`Qr_ua6K4%RXeX?{{dA^#p$
z$H}|ZnIjtG`t^>ht*?H!aS0WI0B|aCm}k@mAo@@=IB0d>3O}Ey2ZEXol%+_`gRgH@
z{nvHOhBX`BR?~J$v+36el;9CAVbg5XiA#<GE_}D#%BGeNa-ekLw$oy%uI~V?EL7M?
z3?Sf?ulqiT%EvP$h)8@vI-zJ<o{}4z&*^C=!2t%U(ca3mt+Qm&bT;~>5F>Fb1MkqQ
zGyzQ5MWK<$S3M=cFc0#>4j3(E^?y?p9`Z&B4(vn<3n|R<`Pz&Vuhz1y?gm8e*GGTc
zyMnIXZ45#!uel5jS)LqcDz4+VOa%l?=RX3*eI1Sxz9_BMB|QrTXQ4BQY>v<`X}W>?
zUyjBn>X-W_X3P!0&^e4RP*W<HV$T+5BiC|c`NrAcat*yR)CEJMFuV29cBJ-oLI3)x
zrR`KmWu@&ruKk(FWH7pdF!IlMX35?5Iv4LX!A_y-bk%wjcn`aKN$1HWd%0RR3Abd+
z1D-ppO%I7<fwog(lYhsdwk?!LnTnS(_Y$Js+R9!4V_MsDaWYpKsA`jc%t#N+sL)BK
zIsPn(h)dUfDrY9px#?iHsb)~MavH7Ye?-l2u~p>B(AZ!b5^43e;65QN(eY9HXY{d_
zSx;xLQ8GPK;Y?Wpn3J{@uiv#eJdpPd+`}D%-L?SnRiUDBxToc6o?%l$icj>BtnTUH
zzqR%caqP4J3vH<&hBO1Wzu18KWKmdRR$o)RkJpNT<Npz3TZp$DgwSa}1uJ&%aNn*7
z7~{4D7!+5ucW?c)>DgLxZ}qmYk&~oi15+qOt+9d$7rEMbt%)oZrN4%<)_j2e^|QWM
zepz#}jsG~)yQ{kGr0+@c5G!eJ(=aRWE<j;GeH*m^ZrXVBGn74i{BOSI=>kTECVlgE
z89N3G{~Eu8@D?g{_XaKPq-(*(-bKCj%vCOm!PIA92RjpV`I~4%RWBpr^De!QqGeMb
zoKH@xfw1g+X(iOZQX&SH4?}{J9w8?%eBwG0_T5IQLnE>?S#swtUCPhB-dyb3twm42
zF<$M27E~}Ki};uxe7a05;tV#$F8ek-JQ<IyOrOLQUAt%GrLOIlie<Q*iXCwjr<tSb
zLF#7(`33}8>`q-O>$p(^BBP=N0>i?g#<P>_79Y-UJ{k#c8l%@d-N$~_O)qt1b-cze
z`^8J18-m3X85Y%&eAeK6m*-lj%9ti)ORO3}O*N4%u6s>cYRdhofvs|8p1nUZDf>oa
zvSShD^z`Dv=Myl83m_IP6yXUT5#9mNfYnJEq|N6zEDlRbmr1Ftxh<l(QfM34DdE=V
z=UY7?+ca-LnsChW&>iWr_}ygMzI^NHc+x*YG9b5zlnDpLV9Tb1ZRK!Hz9oSAZmvI+
zEry-5)>_E$*R%QEfG!hk+K7Oo?qGyVjE$l*uVM%gMSW}!72ungz^dC39|WYa-|z@>
z{iCv)LN&7<uByAXv$nEzG)E5k$8q5v)$y_GQR9e-Rlj@ej+Q-2OLyuUmM56L9(?&{
z-^S%5zN4feJtC2<lpq<XQhdv6URg%Uh@x9S>d%OPO5A>Gla$$EN(EH0{uTQ-#M`HZ
z)oTr|V~7O=9;^gT!>H#H)_nWSEQfwmCezq_K)sq;e3eV%&xX=!dxD?{u}r1~Zm|97
zm`ee2?|PoB{}R7Nn)o*)a{9}jBo_WDh@X)Olb%3nTrwJxuKEhqxn?kya$ItA{u4o9
zKOw|V+TFc4W8Xcm3{C4macKyy6v^B(<j3h1$=V@@-=4G(X`V(gGAJ3D7i_cIy9TpO
z{yZ9Ohr}6Q-%WoiS34sjLU?PFxRCNL8-SSIeAz(HOXe84n_rQp<sk!?aIwE*Kzcb`
zhz`Q2D+#GVysuCQz%$LsQMC!a@AG_**t@;n)#!oC9MWSr$>Zp{67V4JKB@HBioSz!
z?uYY-r3-adtaUFrW4hFEDPtr$)=P-Dl%WspIXZ55LRo4Uv2A(xs(1bJ1>`IFBXSsV
zPtUmb@{cx=D4824U|Hqc{N-}+oo7u6Zk-TM(!L0ilBA)jQ(qonj}Gs`aQ`+i!J^eg
zdPt?$1F5w>kHgJV_hena^@P7&%pHpNWIexDd-v+(#uCX_A*g3#Ij2<5tvcOwZM){M
zP6n&w_{w#uDbpi?bnv77+x$<ZTBBdhx#d5g3YvAmnvk6S-d>Jy6$Z;fZV?1R{H*gC
zr}z2;uFo$|?0B({&2sGPnF%eNFPC{~)M4>`L^NGQXS2K|uGYP*v6Z{nKs`pG!Ow2}
z=ZnS+RfYLxw4NGk<}I&1L4`(SE|BZyd7hkorkz+kOMe63*O1Nw^<81s<@eylbzG~-
zSHeJSy#~2E6akGmQ3B#FwVs`w0e-$uvg~Tfzg#?Y&uN$Mw`ldfxzb*AQ|_KG-wHp^
z6(UGt+eJ}R@6Y0E$0-x0&jXcGiV6&eER45I@c$?%dd!b#x<p}J_f)05G-`lD8Eu?e
zY2Q4R%BmpL;{x7Az{gY66?SLfmhX4-HVb@cu~_GkKGserqx`1U773^32m?#qQVoHg
zsBe!pex;OYoE|Rr%!n7Ms-+BR5_;`Pp$`z!jJ^T*y9!Es_swd}rQ_e}1T1V6L?44`
z6EY5c<H7V2!q`HnXONB0uqwW&lqBNDsj-?Y(Nz{LP3vp?Os>f`i}^Xo;??<CT5j-_
zwBX)-_jI<dW)MoTdb!tm75Us;c!@>n8`Iqb0-j+4+QP&!1=PIIz^FCvXt6Cl|HF|6
zi{=tR5Wbh~Og@+?rl4|{o<Iz37%&uVd-YpBEhnjQCdPJh2%FEv9yn}P$$92)18YYX
z>9v@KlXs_!-n<!6HI;Z&NjcQMoz<IRfqUl_J;%KhB0qUzT$A!uJ*A9raH;g~;4I2g
z#{3$a^WOUzmtirQ#*Q(Yw>lV6!5FV%M$4S1Q%l6OC{iZJU|H8e;nTLyNU6Cie%8AY
z`Mvz%Bay)czDm<R1#QpQJe`R@hWU=c_07$_uZv_Befzd@?rhUOUzzV1yobv#w(|rx
zC}o4BL|?x^C#BHsmoE03@;Y_unT)cXhC<P5L6a+iCay0OK=HoaVjP!Na2QYv!N&I$
zD2m=@CKfElTM<T!gU%)TtpEJ_xF;%NxYSy}K-Vz;D$%M?5x1e&wiEwhm*v3&x8THC
z2q_Q;O03+^!hv76YC<`7^+amdLdWst;(B@9{3c~?yU|tY3B3Ow5p%f3-K{>rMwJ=|
z?V}4|!k^$^Vp3|RWcj`HP;a_Ba}}=@w10NUK>T%?zUBQQ<r7@lfnn(%_ugsnKlC^1
zr+8Avh6O}uPIh12JC$~Hfq&ndsI8BG#XHSMRHR$XQ+K_BxBd2q=Km%-`i8j%XxZ1;
zTl)fa8&)D(P17wM03Fo^)b|sdZ*$9Q(%&;35zH}w5uezRZ%Cc{%cMkuQ+25NaY&Tn
zclvl%R{lVmTsS%HNpERJFPY%dJJl&mVFE%w9T$+8EAhGRljCAf@ZIB@{Gryrf@7*k
zPiURpB=vtXI>+_RR0m|Mf%)<<ZKc<sD7E<|$R4QEnOysZQLBAylTpSovNQ|Fp-WTe
znAL|#Q!?RWLz)Gg0ja;3wFf>jvrgM4D^#Bda=Zig&P&^^*ef4jaal4&oAw4z8BWT(
zy4n-!1L2cDJBLc){zT2Lvk5qJw~f6X;82M)Fv?l~lvrwX3ic@hICrVa?R@?MMTtOk
z>V2pxG`KK5?i|F8InO*+_<iVhdVMd&iFH`>;`t!d=qsgJ`q6`^Z(V~QYnS)ze=*Qk
zrkfh$G_?XR<tt_&(UoLXoGn%{SDQhOxjH?;_V5?ROWkGP<;5}Br;PxKR2tY=`=h5t
zl~j(lcQE>!p}(PZjG4&Z-{tJ5T_x;Co$9IbvXv{6q|t1Yl<=-zndxEH`wGfRMQYO7
zj|TS92_nUjl%=HLePxB647GcmGeA>T|8NB2m06eEUp46o|HB>~LLLYofo)wJ5dg;k
zpiNu3vhJDT+Layy>#>a%OxQ2l4sGOVb5P_$Zt_*b;@f$$5<7y73;u5gSQ0yCclBdj
zRY5$dY0{imPiuX<NEkyRyECgE9R^{{cM}j*=@v%cg@=@gbdIh8+(bv2|ASq&6q%y>
z%%?%WJOD_=sH2va>0&8)@PfuxOO6Nw)@h?pvh$5_zxMPU*=N5@I@Q#4+(-PKE@ry*
zmRj0jRj5n{n2E`gWB91;L2*QTT>z)yKo1gWfix*EcVWxRMNYaF%-;G3QOXoGCQi0E
z3Nw}Rw4kcD(ip*p8yI?rq>I_OCO{Kg!^pwRh)F+ZSEC-z52dt8hN0^PiBWP39P#Jo
z1jJW4Tan{Wfy|&Nv+9%6g#+2IM}f?0Pp|z{cG>d6M9LC&eL&EnU(qmid?e_pjpz5Z
zI0y9-%)i6WzTcLpx~AmhZz=Wv?k?UgOD<}I2vif#`<c>5`~+$+nlRB6YO44w*0caU
zz<zQn8y1`;CA@um)xvO0yu?U%p}&-gt#B)A(AB;j9Du{_MMlcvvQR*9+y^g<{`zV$
zvs%DnvJvCz3IykJh)&#^+nGaa%}E#M8Gug?bfGXO%4bx9gN^3fGLGhnfar|OOL@uZ
zEs}1=ACHRV4ysHQOO?&kTK^z~Q*Jpo<Pauo6?^`YGu>{tw3d^b6X72?ZbKmLH6B4%
zlSkO{7CM)4@fXk7$O*Ol%TdqApM*&?<}RJx-~7`YXU#$tKp-~3Wq{XHYP@*ynSX$v
z>j$;wTGhUHF(n43y5%$e=Go=xC!J?LOb^NKs2qPiB=7NQp5~0)K4qH`Q~<)axkkUB
zxyd}yo*A8Pfx+H<bhxBoeB8QrI<mgVGoFn^OIn3kgms{V+#_%l1DdQSK)}Rgdp=<?
zqnB;0*m38Vbaaytr4+=j0B@=ON#*p9SB^z#kEcAKr%%fIZD_mE?X;B_Dl-`uu$%*a
ziGZ#@2FFAN+EkWnaXVdXfIEJcwIBqGu)e-Ou1O^bBZ|2wV>Q#BU^Ynx0{BaQ?wkZd
z!DRIlQ}X+p;JARH1_8w|;pZR7*29jqyeN0h>G5`xtXC#OTrBpEt?x>S#?nSXL-|AJ
zoUc@sF1E8ya&q5S7y2-B<fynG02$_H%SIw!GHIJ=Cs8DV=WUxmHpOVz7t6u2w!aAq
zx~(-|I}SEW!GLMBJUVr3J(ZO_=?6FD?V)7m8SIM<U8#=HlwCLx|7)JlzeUc8Ali~)
zf<y4#F?FA-UVBhmo6h-ryQY^|O<SQ|b+IAze6uJrdwq$=`*sCI!tF?&j34ihtDsHm
ztKcy(KMc@y=cEIBG|;3(`O#RbUm?5jLVCJcxqUFaB-!Fvt;6Vv(7aG`_pxRDEP;o7
zYSVfFiM1Quq`dr{+J&w5*~k^3p48U9iJuGYp&12RRNv)A_?`0$aU57P;SUM50()67
zj)Z!q@gzNH(2)Y|^$o9W?_nvi$N2?Id~>4nOB*K&5`#|-4WUI-#62P#>n+n|fAO^5
z_Z|uhWjRN1gtwYVuDnT$|Iy$0ayhZVo<g|1MC(vjsP@`y`O+byw!U(v-9Wy<v^;V2
zt3}M=2W(g(D4ro<dfM)sUc`2WH1a?H{SXiA&+eM`sCT0csI<>0#lU$=ZnA%w!E=<l
ziZ|9+0UND7@Y8BY3K@R%C2phJb#}f^(*F~J|01%EvSd6jVo%CDe)ZRQPq14+JQzZ~
zlmBekV|Lp;Y>FcB8LBCz?5u=)U~?QQp()ZpQKE4ZpOuz|lgyw(a2k1Jw<ul0c}q60
zR%j&XO1tCN_cOJQ!vUcug7YfArAT}5@vS-7eW~Y{-BKrxRo1Q8Ee?;hoU2Q{dQ_>?
zB)330?P<we8L<uJb<gM^<^*h1JR_~<u7DIPM0)2UK#UrKV;%5qhv%INibO~D^X2Z&
z-7lh2#BW%<ova?lI21;WuAH^y<?Xas&o;%B_^LehPS&cv8?8U(ZUk_)cHcd!?LgEx
z`(V<{`8Q=E)X#D2E!t@c&d;8+rH%O)cCZTx(Q|TyM?hP9fI8^4P7&uCLCI-Dp{{&E
zOvb@=Q*l4PTCZo}PsD#BIzM9yC6tWnJ7!o1uXJV93uO{eGPW&o?rjR_YMU6ndB-J@
zK-M2boW(n<4zpZL7?)egoIv4alNIDXx(Wu%dM;E}r|9QO+K`q9)UOEapZrclfb$RT
zola)8>Up-7xSM>&&8_Hxv>5WaIQCNU4cxsu<&RxWMJ-n?q(;R{ek7i^^)_7djqX?}
zo~-%Vw-~X$6Rj}R#%3qiFqiz|`p)Cum1w7?9iG6CYO?S@T%H`7Y2+Aa_@`?N0>of%
z7HrEHnlPk#m<u(pFQ01;de-VZV(F}J`m-M}O>LKk^6`q_daVdcV|Ue_hM3aPA=9_>
z(Fsbq$RAd})AIai4N>8=2Y~YVmO9k){3YLM*b`gw6VcqeTQyE6-8)$a&IFki5es&C
z1tG@U!wh!Y+F$v0?6?}_mpu+pB9<_V%Q?=yxo;bKp8RHuVF*JwP&Hl88E-wz56Mco
zHw@)}5Xk@9@XB-wgK>?nh=xOf=F|xIIib4GcIJR&%IL~XqGQGj>RFm*bjKe|O(y4o
z15nTiU=BcP2smQow?)iDe@U1t_aevVfjE5_{$YIH@&2bD<KA12swSdlXRN1hNPL{*
zjM38zH1(RWS@T+e%Ms^ID-C;t##I#*`hh%Xh_`xeF>&f7QIjemu^5;>ruc_$l^zCF
ztNUJesQ|mkkX09gSrYlGE9O3x<PnoB%k6`r2j3|^FddfGP*~etOgdJsZ#Uqyt*T^L
zvhc)z4qYWCpMsgjd2DjP<>V@mIIhE+_xC3&(Unwr#b`LyZ6H%&qc(l6{Xc5S{!JfZ
zwBU5<;9-*$w2hO({Nip_Xev(Fj2o|7#p<N1ztry;+af7>MV<QEO}nJqAwB3fg}<ZA
zAZXmD_1dpdag4!x@<{0cq0npV47xh-AouD1rb4rFoOeZfy3w)#LF0LS3K5Y@kx<GW
z6IfU7wSq=!Ej!OfPJn|Ju8>G@+#~C_r+*-JGvdJ-p;6={`a5--Hqtwg``)-`Tuuj+
zKK$q|GL-I><6x&ZD<N-=7Oom0pTZuD4rh`fBGJ8>Dfzoo!XroW(p~N6<9*Z+7RGPS
zdviRI>*)>ZnDH_<Pxy}vEKc>Z$q}H@FB@IxZHA5Up<2^qLkEGO5hHQ=9SP|>;+vKQ
zN3D`ImjY{LYgY1dL%I2y)Ows1{5k_uSmjlH+pS!IFT1)2%4R$yi*u3AmkbN~EOJY7
z_Dsi`nkf<@!kK2hubRrg!v^3$O|uxo@8(*dkU*P*LPKGtPjJ7f{ASknJ;uxZ<Puq@
zx!;khuIZ?I;~7QI_nC$PkPnydb9)R|AT!wGZxuX!BZhD6g*1#Uah@K{WeN8i!{fUI
zdI|CU*{bh|w04JXz$Hn;mcf6Z+_t=+8v!N9kvmuV?oJ-gK8eRB^H<BA)$0U5Wm`>A
zysY(hQcU8je-_g?`4Z^-vJ1bhuwJsH!rw$x$vVw!M|Z7wjA{1l9S_B>(->t1nlmX&
zjZ0OREZ7Ok9ikSl1-|U@J7G*w9ngS=vE5v2zvL$t$_{WK)ZuxP>HCjGV0sWb8Dq83
zU#+C<<Wv9?VsF&p^lTt+9YYzkg~ikV4k&&jl?Td3nR?{FI5jg?=~_3^X-<T%zuv}(
z%w2yB_%JX2DQS&~5<ilkLy_PHdtq(&aeRppeBVI1+H`J3#Md_g#sdMJX;R}^%)zck
z4|&0Q-WL}HI?E8A2k7A?96>;ySJ$4)r$E)i!yrw@vVT=F+RH5SY@w~aynq!MiPjSj
zHc8eD3M?w`yyPM$CsKb)!^mqfzqIfc(NWQ~pm%_ZoBPkIsBXmhe-D@TeUTS+uNR~5
zbO9C`lR)vreRXV8Bm<NiUc3r7FxGxGKxoRT!xwFoy1I`48vJ6z6_2^cOdMm1R#Cy#
zKa|d6td2~_l;1EhqAe6O{zjt*1JdFSij~pUFS$U(h!c$FWElXl0!M`%?j+>RkzXcX
zbP3(LiHI?B<Kc0b14o-rur1cX6HD}VgH%oTvcZtA!roOtZZJn?cj~J53dllEOB9oz
zbNTY4^45AuW0Sf&gmupHk9~&dLHW8)21%(oi$CN>F)coKHgye3$U$&2qULgRK!dts
z!m|=@0ck%8KV)M*Gkzd!>k{V$L{%8mEnU#nm5efpJDaPZZuXX$?3WuZegkc*++I+m
zk9`7{x%7Y(a_Zw=Ef)Dnk^l7DiuAcFJTz&A5zjwG;?`6+gODc<2-5?{HfsLXODG_3
z4kx4U26o{$7Zx+koSnR*6E-yr4%cvAqfKm1GXvAZSjx5Iul*>=W&%Q>=r1Mn%P*M|
z$C{3CcMq`$cq<5|rD9B_nPnf&KF<cqrKRpy?WnLqa2-Y^7OQKR#QXuZ^AN&-!~K50
z<boO|`zE+DEe}MsV~O`2rrt1ycTsX<nXr!*-*%l_I8;AVR%|6Optn4@^r<Dz|0e=q
z+N4ry(R{*^pYbgr?@;(fS=Ee?%S6YWqpF^g<@+js>V(1$Ma<so%D+3=eMbXs3Op(q
z9Q$sqwf)<>nWxT1(q<Y#f8$ht^2v#!fkyNAUrhy4?!zdXUnN`ZtrH)gt16MLfF#bQ
zl%m9WMkB`R6z_$^i9D?Lmgri2O0N~eY4AgTtIZTbC^&H5R9alO{KUfH-yL}g&*ORU
z$c)AT!%@8;%kTYlkrYXr6-NHw^$61YRMs;SswU(q1DE!c0$w4!y7s`f);I3I9pogP
zrQOk%nUeZ<4lH)Hb~j}rXqji)yF?Nx5`l^H(K>|Rx=@fjgEs%`nE<We1FcL-Js1$`
z80yrQRqzT~tn^bEe$wXqB=VGJ7Z;+~iku5Rt6J_f{cI?&w0CtjaLOG?lQuo*dqylW
zA!p7xEv+0oN1Ar8FiscoIKNnVh8HwM4FAVKGS<YnT(o&;Zxf8zBhLT?dk0RNkb9KQ
zx`wu0Rv_jS<fHqCrdmxW5wRPLipp1CUjhT?KU*cmj?2Hp;$T7w`|R7}U&l3j{t2?m
zs#Mz4iBtNDMB-1@GtgYb=@}aS%pzy!L9_jPYEMDuqUWeN1FX*rfOF3%i&Cj}eY?GY
z#Ccm=Mci+_H$m?hhhJQ|I8^<#B5LAL_qx!wfvZiBuJ$vU+&=}bYmT4$qdNyH3n)W^
zUUN@y8~3Ci>>}mqD`nm0ga=AmG%JSj{!17!3e_*$R3QPi#mnF|{<_sP#$=yh&<ZyH
zvaPy?$lFIl71B`FsB=y~ouU;?7jdC*gfIGbfAl<ggd3fq+bB#ZXc9Tc-|RxHpyhuM
z4QIC9VFSHhyn*>^1<@Fq#}SwY*x%_>@0om`gJR1arH_oV^7AgXvf@*&-mpZCY*)(C
zzMI9z)aie|!*cGt!M@jOnmT4~*)y?ociB}=k|717E)pD@<ztmgSxRH0vXRrTw2wK>
z?_sBM$Q!5o*SoGtZgZdU*v++RV=F0aoSQUUKCD+q;rR#*?XMjd5jt2u)Zgg`I+b&I
zh9}-7w<=n!BHm`m%Bsg6i0IC+VQD>`JwK*vrxQrQDxt-Q1+=r^3D#@Q0R%UG2GH{K
z5g7C&P(QJM0my@DNIutrT@mheo6Ar0=&6o3gX@9P-}E@L0Atmg_1*ShYebDy4zK82
zB+d7iP8k(?p=?|V?EZh-gZS7`HQH)cj;nz`%b|#F;$O`DSzEUm)lLo7>9y2c=|#y%
zt(V{%7$&is-?h{Gc#Rcuj(PPcUSZvQxxStmpS?JKsd@Yr)@%9uW6B_(c8(vNlZo=|
zn=$6|^{kg}q>El2Eh-u0UDUG}aEEq;9WDd~w<5+cUC?gL4A_p6xHm1R-ao-ukG^Yz
zc^s)CBJ_5!=1fs1J^x6@K1#2o&tdi&E(ggePBAeP5ZG|C>t5uS-#bbii;92iw-I}a
z=8gdsg8FP#HBjOEDKkn+V^wFg=nu)2Li4%!FE3oILr>PP?}l|Qwg)~rs=u@$clEDo
zwY`-1rQyDf=bc4$hbX>0ztydq^NlHWzX*ZQ*0&FNu^a5^U}V6r7ARlzp}h71!=@hf
z<o1$wUSSMtO875zRK^~zEPtby5LWjWCzpSQpBGnlob3!49;PceJ9A;Qs*f`1;vW%+
zfF6)PtS`KN&Y{oc1~xoVThq;*XC>=bz|M|mKu|M0!?^e*md@!}Ku?1xH&H;lS6zfq
zEQq4Y#1eegx5Y5J3<3oLDz6*XHynRp9qzu}2*hc#F*1x);$C{~=IUBByS+K<8OX8f
zlzk$aZ>T`6#47scEfJj+WG2)ab41lEiW3|GhqEhRSa6uPdOS8Zrg`l4;06ihygs@~
z7pf88b=|@v$?G<}@`NxY3vot3!e)w%B(`<R_8POey?(})^vfrMLkEMeT@3ygRc{&4
zWc2orgNg_SDgp`uD%~n2jUXZ29U{`D42CoYpfpH#kKE{nDM~k^QyMm43Je(eKlA&2
ze$VrN$s2ax=bZaGSA2qB|M<OxpGBf|@b<}3+;igRUTS2bZhZovHS5sAF?3KYadcXt
z=<aN~i-kQ6@oCt>X!$k|FZskZzrNt66Di#+GG7{VY^0yQCya#euJ3o{9pPdWaegft
zjH&nFpV<@k>5X%Bg<o(;x=u?CV97`5ozjP4DN}^`{Pm?d$|FpXtT&-$)6T-m8gwgA
z8lt6v9!oSIn;=(>Htbk0HP1zS$`P>nb=jSFBgc~B1ol6pE`y&Doyt$Axi&tstxyzr
z{z_j^R~|QYp+Wy1<^>~jh75(;hNl9R$C99i9QW7HcG2?`SXtZ({w#0uCV(}SCM(<9
z*zUAX)5y;>H(SP}-z#vGWB1T~%L9~Rxo=DR_jSdkHp;f2qiN_0TDC3-SX$x`aXr{k
zCb<5cdz}%#!5wP_N0Ij!T)6n(<J4*FU!raH5~s~OROKVl13Pei4emYWz&o{L8>I7D
zVb!7k8Il#BGa!_{4x)F{zwtR9H{L(4tZ+yDclbMEmQ<@Ee2K=^FJYlZTLL+c{ruUS
z`(S-7^wCI8P#Hqh;yJIoJ^k-X{uw+F%!r@AaowQTd;6pa3{`G4{e_j%XX8uLO*s|Q
zT%N)S(^vWovxL3R><Pz49w6nG&J+p7YdEMK2UV668gT7cllMYw{Q3=o*19G6*tl#N
zguczTdvN#e)n%SDjnda4n}){9O7H9@3)Oq*Do^dI&zgKrcf;?bX#tpoJz_$;#NlU8
zb=A^?>B%wo`8fL%nc6uiCX-Sb(<z;Gh%?J}-^Q$*dF*;Rqp}lA--JOu>%!Fi3_oM+
z&^s(u&l`UahCB8H6OML4`iwk(*RwR^I*vLnvwvS1ri1k0oZ2uo;wYG}sI$M@O3VLN
zGIuSx;N!jAH^Eymfz&4HJ;p<xQb++K?78=A&-PUEnL=TytJ`aYf063@k{zu%T@@Le
zLr;F5XZ70=*&Vkzzbor}+{04stmxDxKX6t^wq;H$bp!Nj5oZwd^ere<RPto&wfp;q
zKZt1sWg(=3@G|~vs^AwpPVwN}B>w{+6?!jHX{2!RZ(l=@)6W{SgrP9KCNxG%0^(Tk
zNR~4)khD=?yXvuoK($JOzittY`W1*gi*sbp+8BQpg6r8UF<A<L)v%1qAupaU0HI$Z
zyiX;-`g<6w`0`(lOM!g`(gDi)_t8VdhGsa^S+h_dRF&f>7A?N+mdB=xoO|^K^B~+n
zMDJmb&7>O6<l)1k{R(1Qn&w|ndp;onc^8}2LI-OUecurz0pmVdbdiwZo;uLoDw*HD
zpQmR5U?YH`&|%Fg&Hux;b#-8E7gKG10q6cAarK7Uu=Ez<qI_y07-egkthMa`01q}~
zM<RK2$u({hlDefcU~UGdZ08-Sz9$P18BcpE+~s`2v~oQBAhGSQb<lL8&shJ#;iTlL
z06B^a?9W&J9J2X0nw!*1yZ0o04JP#X4_<1S*y*Re9duVR5;y!e_7iM8jE@80l&wO}
zXN%{Ku*(dQH~b+j&dRfAtSqB1dAbIv=*2j5+&^v!@cjP^qMt^96Vv_$T%L<}RVQ{%
z%6oGX#^o^szA-C&6sRQ9xsA;)_wV7;WLj%|`QFb;_KgvDOX97k3qK6NPUq5dj=#xI
z$Zt8ZtBuCZdU3K<q=8>3McHiN%^?34j(^<6<w+5sLv?~YN!4IQt;4}7F#e5dh`xH?
z*CCgmPh;tIN>IV`k6iq+md{>j4zcW)^qolB`8{WJ5<Qlx(Y}Z@m+crB{^_7FCBIe5
zF;n2bPg`*EN2mr>^`FwG@IAnC*gkN1{QrJsB87@30dHMwP^DN;VkUuih-E$CMKw&g
z(W6$h<bvCZA8eV*0o^tmCnr1kR3Vc;u_qs%*JwAlF!qgT_jpKho9LC9jqlSJE)KF!
z+liX21k%#&5=H_A{$ZRzM@?wc>zaV3wZOuU^W&t<n-LI-s0enhvF~~GRgYf5sS$^U
z^rWeIVd3;!_lz;aLkKhTnbLq5w8CI>#<v{d%F5V<1C9dY0?`w5Qn|gbGKJcj{qkx~
zGfl_hz6cCmHg<plvMnW8s-k|Pxjlo#WZs;GzAAvsCzcQ8I3T%3!?+$%-T7THE3x(|
z;$S_!TJ|5*!=91>oKV`lvCV*ML=!(JaCdE6@2Y;`@!f;%S$M{-hN)<|oWG^77{`OY
z7O4BUD{UNkINI{^VB#z;D&EtRo5v?U66w)!2N0_b6P!gwo4$=nRjZ|+pyypoUDk{I
za*j{kF{g?yHceg|<+3X`t_`&cAkHN6R2b8#;1vDW#!smZXmt0kMGhc}kvyYZY(c^y
zQG?HfkF9W#Q$mNJ_K<v*L+)>*1Ndq001_(s0pz*eN10d3+SJE;_F7?QGs1G3D`cYh
z-zl+G>!fY0Cmj0UYe2dT^Q?X~;=i&n3}k%5d%DIZou<~qgq%jj1au-BE>h)atf-gz
zi9$4VqCQSvK6mFbF)0X$BFdxS9ZUNeF*2-TXL~G7Kg6V{uz#(njxlp3DQ;k`ORC%5
zcKiWI(gq9ZJ_QV$ggcxQD$N3amop1LVxYVM0t;X**nR|yn9Qxbvz|oaggfpOh&wbD
z-3@4rt#|%vRDJgRp~ZBIjceshGXJ7p9L2<ZVb7@_4-e1i*{x_br%QDvqL0}Pe626B
z_aaZLuZO43yN*~Rg~+d5AB+S&^`(Vid#iYLx*Z>*3=CwOB7$Nt*)d}-89Vk<!7)8(
z#(<eweav@OpU`|hYAXQDN=pDr7I<Q9Bfe{FlgWCo-s}`xt9MlIpEYc>g06Zl+-<J$
zC;_W2SHl5Lw_YrEsCPS|;LSW`EC$!9LLPB_O7x~9&E4G1FvsxI!UQ9{{f+&Qaq416
z%cN|I&>DI>d7YRWO>g+<Po2vn?wOZ#L|j7!)JdQ2rrefz=T_inur&1hNgyG)%7?p%
z6CbYNEk^`>rpH0g;pk60)<M^xo$n(tkvAX~4*v3a#{ZHejP=)zx>-qy14vm*NP?c*
z%h6k8H0(mzIU$vE+S7+V-ecA)EM|R<kP31N$!Ta2%~OZ3W+@YfTRx*Mjxqd#3R!8g
zwUdW$PS5fhHp6$T7LV9Xn?1hFrJKX`vUuqSMKtt%bhG*TuaEP0eBNkMSJqj5w?8qp
zbRmR)&lyHWsIUE!CLb~O&k#_s``4fnmy>TI1`x6tiP_6Dx2K7rn~4_0q9RSwvNUcZ
z4Vi7pNS~P7N9lRJ%a_&;5ut4BFcL;CB(rhaYcEa?%RG6H&4L`GYS#$5gWP=f`8AZL
zre=c+igmhlncUTGaN_w+9KPygbtPnzv2bxTF6G0ow41PrCCjwq_8~j^Jruu`?ulh5
zY@RoCct!`okZzQpq%SYhv6Rj|I6xz3t9aaAX}y5@8@V2MUE<$&y>Xu&ZjQa1_g%i?
z2PodGEXFM}zvBJgaXx$qoysMV3|Dn1z30tV{O$7kpXl?!b{0nVmLASNLkT(a6MRU-
zJm%4?`zjZD1P+F&8^?z&`;{yi^N5YMHd+Si?Ga64;-hMPms780c6$6?3;Muq#hTrd
ze|MSdKqMu}tv){#qI@i_n)fme<#B3;H1pdK#*4ON#xAyw)Vl{XNp>~2Npe}!EQg?I
z<5HB`*(GC1Rso~c1<XkO3@UJZ%b><l1l>}~r~ATVtiRxfQR}1p%2Vr+&8R!;E;-s1
z4Z2;*E#o6AE|~AcZ0iAM9fh)P9%&xyedJfaj!<0n8=d&j;ZWU?Ly8*KS=`;&6LL!J
z;4G~>cUG%e6v{`pF&a5Yzww5-2t6UgGQi7tEkbDTuFUkFR*XDdd%t>+1kU_ea+7#<
z^X40v4OC1>?14YByL5atmTPcD3keO!Ao4Rmz6r-3sagS4ums)lw2?Oj$W8(KNZ=M^
zY|YkB3tk$KR?9J6tN@d<>&_Hk369-Zj;>{YVwEGmN1^jpait-F7*2G3y9RkXyK$qm
z3%e2Kj;Ws68Y@m~JgNTiRb;n0^*(*Mbu~Oq$TXovuVkApTc@eQU?^C=SiIC^#gMAD
z*EP<G6Eeolt;`1*<Kvz+D2kx*82Q%LgTsH%N!1MGyU&=fjN~3=LdI=up<3@S%pB$$
z<6a)=B)H8G24Uy{P%<XhKI|Y&$hgNqZ2bc8JULkECsZVjh*#UfJG_S`fXp}R;Vs^<
z*vaJn{dbGjpDs?0E2EzQK2jGgGyCpHIT^VxeA;yAYn6+L>sZtE(TLg)|1#+5l%u=8
zyHUEyt;)r#_u^Hi($9+{`=9TUe7?*M(aPVosb&~53RJ#Ib@Nu{M9%A#1ALt1LsPhP
zf~eVqCf_ysY|41`cl}PAGfrN%*iF*7wK*>ZTkyzJUuDJC^RCMO>yrMU1!p8W*0h8%
zK6jFQ!d<Q>pYwRFoO}x7llB(tpEgH|JT27Fuj<~J(@&X@f$6h6Dv67@@0zvUxT)&v
z^;@&yfv8c&+6qSxW=QhZtp;8pJ!hnOu+9u4sy^YVq`Ll#j4QZPb90<$ZX|iaoubh{
zdgRwAbY5VuuppC4;KFXYt$4DjKRcIawPOo1j_$ucuWIM{-?9-s@T)DQ>Iux%@-ax8
z0eoigQdmk&|K#7h6ZF>17OS-bijo=RtNw@$2hKC{xAn{9WP=}Bl4z$Ou@%BiIZvIm
z6kjEpW$ZDAXY9Oa>mU_y`0JKO{}$OVa>$IketmQ%=C*HI28=5v=FMDEC@1=qYcA)L
zOsn84Q{y<BSO>gnPnsY(1h!JNbndS6cj|Q@>u1s00%FbnRo1q`wuYYx*-~EH=6Ghh
z`iFG$<A!9P_d!6mf*;Sp>&`&;Eeq7^;U*SI3Iq-!RhffOi)&H^8&c~pA4TNyL7}*B
z+OU+L^pAHE%hz3s!Fv>$zEY=`Tx2w=bIpHx^>+1xzrt2DdO@$Hcn=Na@XpOkjJYom
z>KSXRX!wZE3ZAo;Tg|l*XDH`l`toZl8?*fiJ=Y4)Ubit?ck@X(c?4NJr<&lxD=Nsm
ziX8NKra|O^a%JO|RiuC!FH%3U&P?;oZ)#&f0J@`)EU7!=AO8RjG0+jnj6Qz5dYS5N
z^q1MF{lCbSKIK~7z)X!UV_syV&U2?l-I%0oxgKHkY0XvKpbet1ZYC$SRa`D8kgG<Q
zbWM9Fgx?)xjT`l39t98+|2*$zH7VB29mFl|Q$7jP@%CTqOC{V%TZ)${uq73_Pp!^l
zN=MJlwmyHfCSCp*NTN1C^;^p}IAl#LYs5GoBO6jxw)+_7+$#goTklIp5>D-rrUrUQ
z;iLjkk-uLd{~+J1BK8Co@nKf8!8v{RNfkz8&2nb)94bk>y}2B6cC&t$A2;vdj0y`I
z?RQ)L{ry$=8FKdy9lhf~$>GWGD>z#z#bRxm$%qjN=3itaedeqk)y{c;>pj(wPSOE8
z@wr`bYsU_%ts@6oX^~x)-{Std2Z@>w84^ECIj7~^xr0eojMQTWz@&DE`Q>+_l5p3b
zVC;bIsk8gaEd{v98Xyca?f<-88Rh;JM6@-Yu7s1g^Y2$MLOQOxCpO3`1NiU9ur;1u
zJ&j^0IkrBbVOH|_2bdI7ZAYmZz1VtPx;|RUCcT)5?b$WWq{bJusiH=+OI)9th)C?5
zq`y?kXMLqKCcR{9*|tV2{HtBWH_qGraB<(i^yS@2Hm%bPEW%Iy03sxUZ#>z#U^-f}
z_-+Z{#g>+L>Tz!C1|+0^B85Sr^|G6HC^rQ29DHT~*FX5B`LB0&GwEh>#fa{H`klK&
z@(;<HbsPLXm^@sFQ_axN!%(wVX`gpbaXO8vK`yg8oI_zcI=m#J9}KM6<8RLDW<6in
z>B^Z|^dTX+v{6y_zB%pNQW&oQDw<JA9VK6DyyAzP^Tkq_HdmaRJKWw@{0Ds+S9-bC
z0A!BuMAvH|_LHp%5w^nsPD)I4olq&|t~zxNrQ$?tE<iI7xf-PhBB~@;{i5bgSNBfL
zA}jSQMxt_3MR!wRX_579!w`oYxACGUYV<d6uKS$uze}}-CztS3G|BUw?Xs;29d$GA
zDZg);EPk<C;@J43>%+n=wJHPj0R~3H#-a5CEMFbdMxJ5A(}x6pR!v&F9idDVU>ygc
zenbKyVGAcv!mbcD7q`k-qWWc)W-2SPnJv!QB)gM1nA2;-YA1n4U+Ch6JO2H$<Y8e@
zC3U}`-655iW+|(q179WaCz4bNaiXVEtA06j11(ylH=Yd@hW}Dku6F$SdhINrQ?I{3
z20}MoU5w&qrMk2Jb^Vz{i-ik7Pb@DAm`(!ZRL-Ik?C(2ICEV)~W7qn`kJkY0!{wbR
z5F~j(cr1eY0V8!K!*!_ntM?8`eJ@qq^pl_I2Zs7-DX#UU1SZ}J%A!9OVIqV0(ZfDp
zJ!8|?_)^*R(sRm)1SejwsLgd=^ySLc@w#GjEySQBzyPo#(?U*8glqLrZV`(*4%(4#
zJez^$4Y&$NRyB&XG~Wmf(L$(Oqm%NOoIE<lsPfi}7<}VsH1E9;k|&g=fo2dwW;L5q
z_vV``C!Eks0Ll>3Ondm5aLxlgwfRd>eS?ErROj>NfBhw`RJ~r>Ejbs7-@KbW=ABk@
zeIPY2n*~|$2FDGf7u;d)TGK?=(WRx}#dGSaUg-P(aY+-}qo!iv({4PR7dRVdTi%c7
zc$!<SHi;$Qn#CBbndrBjpMBH22Te)b`Q53w)-r_eN%FG$ab*;GbFQfM`jJgW7Uwkw
zC$aE>uLSNw$_3DJ)u;t{6W=F%lZ0Jo{3w%o>*zf+27DMT`)lI4zYo*n0%5KKGSV-q
zZu7qHO>*57mPkkqR|`wjOyDR1f#__0<x-%-bHp9`(XH21xi)r3JB)WwoN6=?4W?N?
z7HEgJh}<I?A7q^D=%q4hz4I>f{WwLM;u|d-dh8r;mLj3@{A}t}u!>nqb9{f^nC0QE
z8dP0fcc_5S5n&praZo1->f%fKKp&YupGiz?+Ky<Va@DzW=$_@oOR8{vWCU?TwoTT)
zQEKLk1E12DX|OUOn}P>6n45eL2J@mnRE~NLr_@xIX3GX+&=(U5d#zr#(N80tq?)VV
z7RfZlrIZT@F+!UZJP`DN@lJ#uqZwx?xMfO*b-fQ-|2+R`ep>GS<@PfUYj=_hQIF&a
z8%F#@jXr!GwZHA#w1aBrVzt1~-}5y?S~nhOt=f4^^w&Is^^Z@OA91$U;=cS$Rv9qO
zG7e_o^^o4`cd=c2gDg4IgysNNIr?r6L8S$#bJ)HJ=@viodLB|5(9R_`4^!}u9L)U?
zNdCpP)KbADYfli%1@D<3Q{Pd(3Tfn8nF(I;5YnC0Ti=tT6{`=PI&5{cIri%_&G!ys
zWI=EZLTMujg=gq_Ct+7h!33tLZpM=Eehh@r=hOIDS8k;`<s;dqopYpmj{o%$HZq1h
zxdilHvy1K+`fCWbVkEtMa;M6+RP6j7{$p=Z;52!1qYlDvT(i8TFD2b^fZ{*MtuCx%
z+;AOpuFBZyf2zp_ZG+VzVXE;^@WVh{Bl8v>U@E*RY(?i%c*C`$;@!IkUtUD$zeKxM
zJDdlbd@#n&r2QXQtRv5>A*E)4tTa(ihuX%!`XZrwot>19qje_n02&tj4;t36d#h&z
zybEC#r&yxKH%ORjTu6>*r18ed7$sWclt;5n`?X)xn`=hTb3L1J8YqZOMUO91rbh|G
zE4Li`s$Z9;pH{_rdD+)$94mmI*!%L$arFJAJ2vPvHFH8u+`w<+8v&UGWL;m-PoVuu
zVY4%BA>b7Ht?6if_{!-M0oBtf`uuIDW6tlpg^#8jB`SFNXLCGB&yBYkJ~^$qjKRm3
z7=vsx#rlP6TuioQn#BPRK#;*y*snCD0bUK7z3#!9pb>Bc(0c+GoDu5gy~oq6H>D|K
z(=nr;P_2TVZ{e?v4u&P0)pXvizL)D*o8;&G2WT6-&Png}1-wK?Yzb+Hw_tYDr!B|%
z#3ngf;l20ZCxodZHDzq;2@MCji~&_BoDoDJz_^oUdhBVJToH1Ga!@?B@ze{Q@W6L2
zPlv@x)@|kwS6uU%Y@7R>*I!(W3;?~?Nw<-v0cpZr7o~Au7aB~!FdD{jK8phE#Rb4#
z9DQ~Ppsi=&^MqWb!2(X#hXWiDcfvWolqmUeb-ho@)Qjzf(R_<E>>5(D9>dDj(lgdb
z+}Pujd=FZ+6VW^jty%pKT*dvxI}b2AR|wTx?;%zI;`HljdxgB1Ujxs80_eNbD?ke3
zQs8%n_!#5tc|EHMa$B<&<Mr`Sk>^H(Or{<CNTuz)xR9;K+Pn$#=@0QuetjH_@Lm+Q
zBCQk;adq!YNpX7(u9U(g<f1=CZ0YDPzu?LK^tGb*Y6tJl^xVoipa8Y*yLvQaqHy6K
zhwy{M=C?_@mFd(ZqQ3r_7f1%<d-)p|wX0nc_(!^#s-4AN{>U=(mJbZc_z);!8s{_j
zA7E+{GE*ZV%oI@x^x)O{{tKiUp92W!behy!HSAvE8}Ru-GwS^W#-qWf!2;S-6e*80
zR8<B~^4=WpW!zghveT$(sGU}jn7*NrdCo6a#aU^iV^m%ketUqC$6T>s%klrBQDD}D
zQOXfYpt+-^rgH7NnwPl^n<Ih3(ugf4A-oMbo=a48>RwN58fcvY$h;iguG>y1a+=(h
z*ko9j^w3?!D5^EIIk{o^Vzs@0{LWLOX-ZD__1{`Z1Xfqt0>0(=kX=#AOw<6;##<Af
z97r0786Cb7u9$2i=B;PwW*)9`UK`SMl753oL%0RGar63m8E!s@2pu_(P3TyP9&c>h
zyqg(Ke(hSx;hJ`o$!PCX5s<&U_WWTPo5a!V(`F&}($awVrPzgGLn<0W)2GG`izoV2
zsI50v`M;)f;-=b2?EWAk*&q9Y1D>_W*JMX?eSG~hNsVS@!EeQI9`fPLWx1M4o4$3|
zz<yKr&)~#QNQ_6KOQ$1e{|?_Lf|`4J)@x~N>zbH2ib*fg+`5%@gI<)KnHjX>!8~;H
z`Kqucsg$H#7q?6}wf(#qaYL?Y{bfYt=<<q7p?mFVY)e*xgi)cpTUijVkLE)M>ZyKe
z6W+e#jybOqRD{CS8Zx_5VTc4erDg`Yf8Sra3?A-dG;j0kpO63?2m$)FoW3<CF5r{Q
zP$y_S%iFfKwTWaYJ1N)^dw=Y@uTlrJ+ZVzDwt$fJg$p%Om4GcW@yQy|GiHc5vE$0L
zLNj28ulx20yp~I~X7lH%4%d}OcZMKGh0NUo6)xMo*a;?2k!pk1)SNW=;;;-5C*4YD
z)(~xiZo&3F2S=L$jtKf}3l5K-t)<1=L}kY<&3|8AM^Cit5us)6><VvFQjQV?ls{7s
z>LlJO!;B*cZUJ|wsjVAF`JX=wWhVCS9KWiyDUrEil(0Si2_l2T1aM#9a&4MAx-crV
z%0@!sVz!%?+nHmyHJ~~4!)B^~?8yI_wtC5ZyW(W4IG`F(C!`dyVK3&b_G0x>^O!^O
zza1h_1P{Q_mp;7n0&Pl~@4(It(tRS(H*=vWKjwI~oN$PnpZ|nYMaWdUNWJjQCgpf$
z`>{2<d+T0IV=v4wOMw$xSL|rx@L%-HGj0{Gt`REw+p%-`pSCtdf?+LLvX(`YB_u=v
zX?wGe0F3vaisF92hC?NR?8HSRnPJYS2C?%AGoITY5-scC*tz3ZFjgM89~J^3#1Fds
zF#hfGv{Ls&`+T!>VG~}P=i$jt+;h2Hjr$tV<#bb~!4-~CWlfjv>KwLfMBi_e^l*+X
zE)xi}Wf)McN&GhU!(7$DeDm~c*5P&9G=N)@n!scB21enQ`4UDy_;|XvOO|&Tz9Ey_
za;8;NOUG?)=tlV;`!|>J%oG%RUDq&sZ#+H8Z<IGM7TRo0fDM@*Tt`I`3urC1higyQ
zR3o>~fO>vv_-j{4t<-V8_rW%;gjZFmhCcZ9%hvL0sz$9<mYJ+b#16)v?vnt*J3ivx
z`@HU9KTV$m_kG(usuUxKEqu-j#U%8}+?dqB=)^oJdoSY~u~B2qfAfidsH{qx)Tpy$
z`5KNgLQo0X=paH512c<_%|AYiU)cZwOowJJ4XE=P)w|}ELN~u(q|mXqFPf?<oXIWB
z&wMvlV%UH#LMO1c!T}(TcB0pPvYUIRX`eR0sdR1`^(j;aXPluzKd~lGvdYE@N1cQ)
zrNB1e>SV(^{26fw-LNf3>c7Vq0L8qPKrz>D4#YdS&j$GF(%yF#yFQ?6mMfe+Uru;5
zYguSHwey=TV<LCpOEEVH3|=yUP(LS&)q&9BHDH6`<I_|M<z{AnK}JT_U(mYsH8j+c
z6zv7L?E+<3yc3@WSAC%5sf|%t3pNhnXG)=8B6ElSp!h=V#4QoQQJ7qZ1gm=Rc1@*W
zXK$O=R<Lu(zLV6Y)Ni#)!W5D(w!d!$hu}E8P>fzpYchmG;4pD|SK5>vSluWv`sO;o
z>)Y=E1?@ej4GaP~2E_Su%E}(MwYQ^zaJ<J+Fr#1H7{VN3>|EbQhA;Zq!lQ60IXW;O
z>4SHL!FPZ*aFIU3tpAh;#*lJMa8lUW**Wv-JwI8K>i6_#Y_{!3E{1TW5|snL1kuGW
zOjW?1!CR;QR5M4uP`6mG|1WTwQLeP9yf!!wdNtQOf%@hn&`L1c^*Z%hrAU}_G0)ed
zKem<b)d&pqDIHX-m5}Z3{$o4mchEiSPzUzl{}AU3=NRjI+^5T!mdPg0+*Xd<p!-~C
zMqL8@0m^`Rb+O<o@SrI_IsgUv>Cwjd8TNc{HN{2rJYKNnbl;fmuK2=dN&%NSf>O2m
z6v6kzl3<P^>akrC%;43TB<kqwKVIu%z6JEFy?{Z3BP^znukQB+pwOKEFy-;!C2!qG
zPaw8EontHpM3dvv)8Sa;xfx`&cc?R($$dFmffE!6B7O^jG@=6oDuzNG*p_2w5>isJ
zjxr#?IT!%y22CT$M*53lnC3~p=KJfK&K+;*M^1I{J(8NmiI2Q>I6K`P^v)f0L>GZf
z0Qajd&gMhUum-PMWWY{r>VI)>`@QDj#Ci3!H2=mr6P|PsB>}0g;PZe+CP5u9$Sl<@
zML^_tPmeGNwbM?f$n~b(e$*!l$pYZ7VhhY?8rIUiQ!Sr7dD7nyWc@3h@Y<tKKFk8=
zkypjtnnA2}{HI8MR8$|3XlJ$<wUn2Wo6Jc$1!fS*B9MGZ{4yommrZbIq<f(`Y?zmT
zZv{HF(&Fc3diN1cwJY`!DX)ga{T&IpnDji)Yk`Ml#eQbI5=q;`-TiW+MOYTsHJ`l1
z&)xGkX!GP4`ohGN1B25o#f%N&3Sd$<^cg+GrVHi>u)E)1mR831$7Kuo$T+^a`yWt&
ziN~uo-^RBGW4A93R+Ji)x01~e9D-ms$jM!Wn4T<TJ@G&Dv5B4Ae*Ao?!5t&ud*lWa
z$|37pm!kZ=#mQefp_1f04o{<G)|&;lPqlR)?OH1EI2lb!c5H1Wco6yH$^}8mKz#bW
z%JNk$x9UFTL*Db`A%5eWBXe%^eryOf=1rthx@(3tDLs6K5?-G6AIuLaG3}<ai`eL~
zxJ~q#u<IJsqgXj%1)013kI4LL%?Fu?Q6*{wy1fjM3iM)7HyIg-H-04nH))dr<R1Fk
znHzh;$OSN@K!^WW%}G*EIQgwjVpN%I@C~)7`jx&*86Gq5f*}!x({H<CSo#}6rOr<(
zfjve65ZiAR3F;$+-3rm>?@2c<ygGP8eTYMBJWn3s()Y%R$XUp}48b%R_%$+B46KdM
zEdJ<zwkrvni;)u1rD(#8%~{bq!Mw0*+#~C^yji)gvG<RNrPaM6CfcNhG}m*Me%Aw9
zQLGPqfRgtf_-b6JYLbS$Sf2@?0)ubRqf3+xDEW0KFtbhgSE?$HZG}|uy8}|y&@CgI
zSPNDA-9+mbi}|W4sjn)5O^)$wZxEMmFYQ<B%D9)`SU1A>`v<}DTSaCP`eD+3hS3&S
z;t5mdNb~dK*}O>6_yWkm>Bz&!GXKN>eaO>|E(l+f;`Nu#+|t>B<ze8pSKZ&*(M%W4
z(bb3UO_hN{t*pWM#7NlP)PWEb`UiSYTM|SC%`Po?c@YtjhLfEh!S{cDmpa>|d*<^`
z{rN!3@b-f2?z_nfE2ApgXa@h2cgI)a#BQmliRyNBb#?dlR?RvkMZtl~*QDX(<_pJ<
zoymzE0!)`xrR^9h>)uaaC+c%sym;f8G%O983`C?0`+(a4ilB<V>1d**l?_7f+@##(
zX734bzj&6Coaj#d?~Hu_paFMmY0_}9g)@m8rsVmPpLhO&5rnZ{nw|<OIShE~oeh@4
z6c7Io3P=YVc+%$O(fO{%-r)b#S<M*)2I>XMOUd8+92s^zSlI<Wq)e9ma=g1Us&8(0
z_-CR2&g;s23#!Vca<UCC96GPA?%DKg{N$fyV0#3W=i0WNDxbt3qKgsGF(rXW{4YxN
z38s{!J~e_d487NS7T_={r$v9Vj?E?`nXYxgI#$HQ#pMC7s!kDTzsTD9;ZmfBkkyZ|
zf8yXKrA1rW#3Ri>KrKk>nc>P@Urrj3L9$3QZ4ml_NH4r~<b-1*4|}E=D3bE?$LG&P
zxbtm4l4XEdVbRygoomi5Zn3ZKh87)2zmQ6+ep69O+h4?MgIU*w5mJ#UGV-@}{m2Nt
zls~VgiOU+5l$F!MpLp%9XMtO7nuHda=7~*ykO&}S7ZYnlL!)jMC|ngf!hN?-poVe{
zS~T}3kR!F-j!nFEfSf%nutS{FCAd`K=F!#Ay-4BP?#^@j9tOuQU7WtC^DD-JsdFzg
z&=qPa!VbhlnL<FxJRkl>=qiXqguCpwKJQ3?S1rdl;@FxLJ<foiLSjY8xl`eF{T%xR
zv1uDaslM3g#)B)<h0A;#qlT9H=$O>!HI+OW^RVL{N}T1qtRu_<pb;g~6R7An%YnXv
zy$v}?w1^rBm`@^P$+FCK+bel1!?LJcK2a(=>3PeMB5}FDrty<GS{CWXl}Dzf!_hz}
zgvH;pUhQt<i*f5~)oD(ir)IMoszWXWzI4#7|E>P)*An9H?ch^&flgZiA<(4*g%TYt
zC=jO`X$<kFY<`MD2tVqfLOB$Ok}7ZrEvVOD;DntgP<smS@2gPJL({d-+m?nFfN+FU
z;ZG+^W9JNG0HzZx24FhW<I8N#h)PN!0%(uE2WZ!Q3{Oc|04yva5S_f*ojbm#|6O^F
zOy}M&%=K=%tU#e%JofF*Z9S2|aeyi>`7Rp=P~~c;G#Tp0%@PU+Y)%pqp2~T1PfZz3
zGV!MNH^3C22aEdo4`pWr1Lq*6;VEhkjDVno|G(cuo=<<#yL%JoCsEdq7@f^M70bvR
z{O)pRGJgaZzghP2&=%}fo~?}d|2-BYNI+Bo2?)pH{{q!Yeo9Xl`e%u7;j9PDK@0VJ
z#A!{4xxqyuD9{|%h*X+2Bhdb+0wf-COe2n08wHw;v-Yu`K_6$njS5N5GsIEbu(EHQ
zuq{(usY+Awl>~wh3FG&vsq3!d2F5-ZQO=J;(eo``E||k-^1*~%2D8^4Ao2rlv<|}K
z@2w?s$9X1lUfHw@%o|3+>i1MTUWc!H$Fz2@vDcth1<&>J<n8-BLCSo+HciR2C9#l(
zIwGn#sQNdgd)LjX@ru)zEekPR&k6*yF*r_j|NG(|*oNK1ljNFY^T)(Q_5kovpr9gl
znU(@+?&TL`?o!LEU+WiKkS1kHAQI;c|6iPV-u`?)&~ymqAZR)m$=eb1bTsYVK%6zd
zl@z*Xgs>w#`EfoRs3{PQfR>&{q@Q6|!((aCsFcY_=Qv=mQ}@SRaVVXLs9dg)y^IpV
zSN&dBSlJkvE-Zebo}BYfw&8pX^{qHJ{>^$w1by6OQS;Ua;-~ifVAhk(H)KF8vCt&)
zg6)IZMvw9Jp&X~c{BA0G`mGZTyI6|*NI*kuqG7J4dih_XK?7VEWFummibjBgI5|aB
zS1vHP$CP3DeyBZV?m|xo=bJWe7+lNsw}vUClaq>62RWyWE#UQnY`MzOSWT*(a(tOL
zmi^`&J#T)hr~uSCPkg2=sQj^VljPsw>^wZWuU}{XPjo3AIo)>IYCfvn_Gg>&uJ-6+
zNmvIS8Z~iuC@FJ%_a_wy{&GP#=<ORD`IwkwqobokzI-X87q~p_jXg{Aba|Y8vw#g*
z$#8A3ptSD~2Hxh!v%WeinHHh>;*dG8mJ<>|wdyHQJifv?i@6Jf-<EXBGCMDX8R2D|
zY#fTOe%l)``=oPotR0G0FW#H<Djz4ve`-|PIiSyJ42WoJmm<W}3JVMSw?I+`oJXS6
zL^qhdtDJwewcWZcbP@F6B$C>kJEU_G%pc8)&E|E{hgRz!P~N%qr+DfYwP;6oNOST%
zNCP<q@_S+Nr2(_-aaO3Fm^qH-c@O#6MzSB1?)}?#Vz{->d*cEXsvig~zPU|zlY|RA
zrna^Pw{PE0o&K}%(;YbFaRJxFdnC4r#{_etsTwCt7^fI+M7!E~R&*`VLY^fZI%VgD
zE`*I_$&vy`F|~11kF=TXK7OY&N!)w<&Wh;a?@wu(ju%O9j6_PEu_yH85p3Z)`j%3T
zKz=b^pqY~z^$w)6gul|3Cin^8P%Fv3L4iXbKM9eah=bQkqlf`b`%*dk@$#LIT}%6R
zdf%USi)>s5t6KLeu-%6WcF6^Ys-s>;4255$&@dd_58lV}>U&1deeok;4Rl<_8twzU
zL~d)V48e}F+4}%`L5gyp-g~p$ezYhKxakNJTnj@&LR{q^#wR3955(lFBxMUaj6GxQ
z15ll%c9B~2`(`sX1A&G4uzUP_Qx1p?aGzEx)LI|a&igg44rCx&e2>w<l?Jq{$`ytN
z32zaVYMdS01UM$P<n05y7|%Ek`23vGm0mr-omQL2ep{v5*PjBTS2QQw%3<$h&1tj`
zH3qE_VsgoIzUP`a^8r+<QrW_%SsmWI1WfPr)A9U5PnMbsgSUNwkEGh6jWg@b6L8b-
z0n;1~U|@$|-^B|+Hw_4$q8Be;BV=TG*Xe}T6U>DWjg0j4rNCHD6POKp<ns{RZ~6sR
z(JJZUlVnu$o@?|rv6=S_4?&GFkz>sNFw2vh^0p+{IwPcCGjJhuip(a==Wzi;pQTX(
zd5d1lQicqkNBbIxKQ$p30YtWOJ=0E1*#6YpAK!LJ9m{wBqTRjFOOJ7oj;Z!BzaG>4
z#vpnQMDfvV45nMekk3I{r<~Bkq0S-y5Z|Y=CCCKma;v>b{a0EEW;bLj)Z7NYFF{zP
zOUNnv_AD#Og2;}GuF(o8e)y1raOk_Uytn6O?BvuILPhZH<R7i?2K(WFb#m&tuG?!#
zD=5K>W(2W}!WulZ>R5>Ca9U5Z(KwTq?CT(Q)@@;u%id|0#oCXmj+)k%uTD3eWfBxL
zPW;+P)I0&oaB4Y~<!JoN(z5>Pmf9v~5325v0suw7*BD6A*-rL4|FSMBuTP?n>|6f<
z+(VnsjxhZ?%b+;MARd&XYg|{9OyB-k#Wj5T^l7VE$=dfh|Lu1kPWZajC*ck6O*U!4
zb<NPbDqJJ|E#8!QR-^+aCF&)Zz4XwYPEgJwIu29GoL5)1IRaY=pS*wVNLy&b92;*p
zU!hi0S&e{DZy=e}%XCj|Gj?*$MlA{5`3YKN=jAdM%FZOa4i**`T3|5;j0p394;-@f
zSCMgwkkh8kW-6$oMd)&YHPNJ6n}4u%U&X;cEl_uE#IMpgyG<E#0e9=u<zSn`y_aIO
zmvQ1+PCw6dFwi)FZTuft_4d+8kd%bBM^hZ^r&7aY|CnT#VJ;hij(+scZtku-g^jNc
zSfyT^o!`dl>`US*ZYwLRsVci~5aSxhB<H$?%QnmlU2GX8z^GCK_=@(cby)L%`}OOE
zjZ-U~OOqy@uya*p86-mT$QFklRR+hkoSN5U-7(7b{PaMqqe%XG_B&TO1qHECJ}aAD
zI@U~H6~lD6a>w5kVB;ZD;}XDo^_muR@xn?&1BY038Y<F}KKB+ExHs^t8J_x>F|VbV
z8_9R;JtY!&PAmIvno6A;8;>^U_Ooq7ji$i90J)o$Qssl80zV)(QO4iv<;yCK8OjN6
zZEba|wW|aET&boZ#fjBd`hu7}X5AC|#dlR;HWyxK`-3>i$<D3;Q%iFLtpgAZ)3q=m
z7~|c$_4V}x2U$qVJMhJdX~z}|iEqp`H=_83EkSH-AhcVeKTCM;j}WY+E`6h9Q*#?r
zG^uq?+x6;C5mx^hOyMEfadOWZb*Hj&XCatzd#}tJy4vh8me0(72|WSy*&TZMMoBLb
zCBuKvn>O%BYCObzi(4eq@Y2$UG14*=L>roO_^f)UIn_OSw0CATi<2vk1Lr8k`1<h5
zRb;L1EFJxMnY_z7L7joqRJbT%`&kXLlxQ<7|Nb2zYHOXW$<qnP)YtNK*%q6Q8l5AS
znGxlZ4+q70)c#`N)y`J9jm#EJClEoRPpHnhxc=H(r+m|W`|Es?pT+-OIq%&@J(}g~
zWof11yaw3^!S@}C8$4wH-evi$2QLH@F)FC!<-w?y!^NwrAP@nA67ca8oY#h*lhVIX
zoah8!uY1AF66#|(n92>#<gPWk9gAnIdR#|+hn`YpJT@hMF6sGSym!58a^M0V&!`=O
zZ=A~T6S!v2xlG`Eml>>z8>kEtvppL92xCi5o{~B>!SQ0E!JEBzR)ITNf6}UBK5xow
zJo02m+51j7&<oZGre;|y3Jc}SH01J7rs(~HZZxoy?(n6eI}Mg$>Rv${4rQ1RDx~zE
zMM_kDoG!JTGsvYI4xVhcwia0QSJKBEpW!O^m9V)3Zk{k^aIrs#Yw)ESFZQgt5OCx^
zBu8Vn(jC`7qF>3;UH5Kj1a7)wG;iAk?hMgiZZ|Sl-rGeeSjvi{Co$4()yc(rLv3pQ
z00TZ|{-+9Hz}0vV`oT?t>K^$zyn{^uCkgZJ5nf-D44zP%eb<F(oVC33p8}-!sYr<`
z1yKR$S7`*-{kdQi&zEq#r<kSi<aA%Nqw_@@v(8z?D^;aLy|m+0p9M`do(y$wq=Yd=
z38SH*%a5gl^&93z`M8;RC|d39nO8IFloY(mcfJ~8qG^CU9JvML@I)~6;2$T~)A=@d
z%hrpZ9u<1ODPL@07CQ~+7#`M6kKtqeQ5gOlJ1}BdTzma$kM9ZqRvAMYwynh6ZT_@V
zxH$)_f&{e64KfDQ;Xo|Y2?p6M6Q(jGPJ0t%>G8}W`VCgm3K;K>LUoLgJ<xeVsjKhW
zpA`fz1E_UjxLHQ;NTo9P*UC+K4ZKx~p`sMkX$=cI$9qu#vh@H1yFj#Tf=I@IJfH|L
zfJdV93i1040r3U7Gl)hTFPyPV;!)eao(!zsmE<TkWo0b&R&9~b_tnC-w3gJu1nRIT
zjLSvQ5b?GK(cxkslk5m{{=8Z;Vk`jzv)#dAo}~sVB8`h6qDOG6E_}Rd`}bs+A2Q>`
zCW9XJED){A$ou`amO!qUJiQ&a>76a18S?+I3Z>_q{r^!@t`cgg-5Lq^jhP=KdzVC5
zk2fbD=|BpeaekukGuWjOZ*Ka}9&pMIHc3v<Tti<$CXr~Yd}Cpd&_wIX3^b35Sbu#q
z6<gHwt2oI?P3uQA&17Y+kW~K=26dTpgwa+kuA;{kR2O4P_TxZ3DWhj?2$hB45C{N_
z^TFYFv*aV?=T&xf(`rwDB=)ShI{*0b!+yS{nGlMbfw%e&zNUqD6GSe^+};Mt2{sIT
z<w|~1NX_VJy?a*<{Q4LO0o%gDA|x~vWf4rD5B$xC)5}Xi?sSS1uW1UW7aL3e&<+IH
z3z$x<slUhPmmX|v->H>3zOHvr^D-o2;M@2X%5mPWTXKckJN}M{drSM-u>P%<SJQ>D
zX32$Il#A7cPHaGLbRj7eXaBEisnY5FOl%bY-%J@e+NOb?n|C;^pc3#^{6<KaJ;fQk
z^;jrR{#j}l&4CU|>44O^318EnkMVrw@UN6?Xy8k%rKcA!k>gcrTnkO_h_3~A(;$N!
z0mDA>VP?@4IFf<UG-v6+K4vw~d1Y@aYi`I2=$vs@4lSRY%uTuV%kFb?xE(zTPn(f-
z^0BDV<{;4Qq1#0Sn*F42a9&H{&#7`*F|er|RO6+dj;*9sceApxloS;S7lwfAvf?c8
zH17wkP1@vWKVvZIC{Dc<IPZIqw&jQ^MzpvxEPbX_dn^BtV8_?65Jcw&?8GPei-2Zv
z@>=-{kGS{@u>ZcdbqK8G3xPXd|E@49M)g5`9<bKk0FLT!8FGN<aX*BQo4ZPZ1$eZB
zyinI^y2d>M<b7$IM`l++IYIxswt~oBOM`P(Xu8xh&2j{08Vh*$u1CtKX}ePr^&ZB%
z%OlSr3FuL*DCZpA%E&*J?C$@nWH)wzF;-}_3&&vFoj1T8B0hI@(woTW5oH<3KYQ=p
ztIK1M@Os8{xo>0<sjdoteL<3vnflHh5V63}XN}N}#DF_<xHa&q`(}9uI#ye4s7N<%
zd{|CSPK{4g)Tq+BZx~oTXA^wsfuDIZWae>(%SR3Vz9V1=t`7|C2v>;r9YMmEL4=AR
zc8tWgtyn^4j<R*@yx82dgW;jeuJ~$J7M0?DU$vIbv3^hDP(5@YpXErGv7x@9Zr$_q
zO@5s~3*!S1T|zyUHGUt&I-_i>Lfip`50R?u`PpgOMyJ0ANJO}vJkbOrh4d}QEwCY|
zDmzrFrWY6@L^{{6P!kG?ecL`TS-C?+g&Xg?6e0M8I4kLbFEDE_G)MY*0cX!N%|PHA
z3XMR57BMHFVE}9D9N=9q_G2xSucZJCGxY83?D|DkO(@@|ziYoo`}kFWndb^swO!>d
zM!ZIVuv-90qCtn{hGIw}%}qrq3hH=t-WKT75yTuN9=bH%=of)gIRNQjP4vd3*QJG+
zlNUhU$|dgei;4bi5y>sVt=S-d<_prwZDDtbtZCs%H%>gPAu-b~NT4iyfYdcJb8bu_
zbPJ6dp{0ID8*Cs!BY4S2$=(?9KR-72md6=Y+vnkT*UsJfEiB!4c6Z}qVzNKo5bcC=
zCV7DtY`^dBP}rBSurN3KpZA4x9uS;KKgU>K|8=@QJ-`t6@#DuTV0k@F{+}&FMw4h5
zOR*ifnKvkudfm`F_#78vtD7GtfLLYR&lER3)=#g3egaxA1{Y_I5vtD!is$#;G6{<3
zK-q6b&P(Emp0HoEAfI^ED#SlpCu;44jET7&eviK$T4N2>5L(E*hZD9NX10+4EO9*=
zZauOqS2VD5&F2lc%}Er)bAmb9W<GEYDn^k3g~z#W6{NG7F1%vSceL0ydFs~+7Z919
z{OPPYnRzh{a`KYH>ur-hQ#Y3atzJ@kqgL&8F_Z0pQjeE&R6{9egOttGg!>@|K#F3g
zd%UWpm2sfH6-)V$>baU!Qz^(VcxZlpl)&J*9Bou8_w4O&X&X{2e){(wNwd*n(9OC&
zH*4(_sgB3mUui%gRHAFpc3;>cH>t=m|E|aS;B$WK-ZF(1aij>uz|TejBo4DWp3!an
zFNvUP&gE{qO|GRIV=sLdXG69U;s2y3>lNFMGd5F~=3@cgns@9&o@r`BH=jt48&Gjy
zhHRagFWK0%WD{#rsb3}<%#QW$<7*Vg-XPD!b8>NkE_h08YHCS6WDOvR8ArjFS_H!D
zOBz$RXbA^nYZ?p6x+EM?tsC&G#ef*=E+bsoo;5k~YxASH{RlhTa`9Ed%%hTb0n9L$
zRaii!)|j@@O$gGE6JY+XV_=ZT+j97t$E?YK;NlH6JL`}-%i7<X7F$b%oF5?1?OH#R
z838kCc=Nu|%Id0UhXxQZd?gGL(EwAc%dX<jU?x%uwYu2-X#06V&6PZ}z7SC}yn;D8
zbqOGYc$Qq<05S+nKxO-HpL+lLyW=qJZUqf0=2my<@CS?=Y2{YYK<S>x?-pO!xS1Yo
z&$`dN>k!GB0y~BP_n6j)4<CTmNzz7}wdmh@1+wJXpn1PzCwfTllm1Rg%E6>LFb{AX
znD7;zd!NI9im#b=Mnyf8O+_peBhHY`$3&482Gh^Z9KG05K1bcWVz)QvP0H~x`@MAT
z7jo)5xcegP`_PD2Sg(>-F0b&LA+LUX4CHKni6G9+TkGLZQv9wl>>+%fF>cnxk8Mnu
z6>Rv~Jkaa&0L*9w*FJsxxD34P`Ni&Gf;b!WUW4=87sN`k*Ft;WJ`p$>D^$uaimatt
z4lKU7uLeWK%50=u%{<&bdYdGEKI=7oAs}WWW0Q;Kc)7D?3-e~T{b;fC7-l#j`qk&0
z7&3Q@_7SRMEGANBED`!)p+Dbs*M)IXudDf{cj!!gOBV2WE&BM*^!Cc?b3E#hC^a?6
zs)4c$z5$DK3}|HU$2z}wafvEW+U~C^cR<CTjVYCSOBeWyb~feLX;h0_-*`gz*}7^L
zJW_V+NpEydter*eo|U*vk<86BzF=_l%y){LnebJAsim<o9!pGAM`7JgL=*w?&e-9d
zt!rgOvElO`tDREgHeZ>_TXILt_=q3gtMCcd229DQ<-^05+tEx<PwEAqdd-)QGV*O3
zKT@w|H#Jyye^c9AAcCqPBGM%mW4!pE|Jd4p(XImfHs6U@dSgqJ-L-GgZ8AEF9p|tW
zUsmv`!nru3gke8w`BLypXRn59e$XV7n#RIrg%-90zUX^>N7H&;BXcLwC;WbCU`@nl
z=bGMa!Y^*r0BLfNdUN`3TEH}jtoWFWm)qx`F2mLh3ibK5A31Et^BBv;r+a3+QE2=6
z#_A=OhPtPEI%V2>x$*q_Q_sq-do{XG_38a&USE9bc$Mh)#@Pg<6Bt<ntU+vd(CoDm
zqS%ZMYFHPh#Ue(BU-9*#aL;y{VMW=rQ%usJ0kfE~sOq_DzN51pqW>U6mTToxP_t9<
zVH1V(w*-gt48oJrn*(=jasa7Nvasa5$VIe*X|BHa6qi~1Yov(RJ!Y)uY~&igx@$CM
zuBuqk8D8asx2cEta(TO(>CZ{k<|Dohpgn3O+7g=V;!SSXc7a7r-=t`-BnprLAxY~u
zodFTmLhY7_>ume|zs07?=zPa0(6_;hIOpEq7WkFw@~7RW-eYvA?6H`zv2*7X^E|Uh
zg+$v@lu7-=-Iwo<tS1?W0$>D_ugu3F!@hHPnOa(I(of^fA~vZ432hQkoZ-BI6-Z)y
zA9Ui`-nQz~+Kb=m9L_;SRk~Izn@5=LSiTmU))sH^KYPf>;$v-0M5NwEGfx!IN_f19
zPT?{lP7SYk*|X*cvhnRBF-K&Dw@tP(PhuvGpcMF85yoSGsUB@)^-Tr1ost){!DOq_
zoO(nON)Ir*Z+0<H#i5OaRlKFVLG+(hv^|ejne=`JPFLpQ4Dy+(<c*LRFZT+T>~=H5
zCcfu2H_juMMepCnPx9?-o>(t_OF6&g&y4wEaxak=Iqvv+s%@dOFIsHHj%>fbTmn4o
zH!pVCGZjmfs}Ec@6NKY^K-S?{{HA;H$=eZ-g|mRfuZA<|=Z0Hy!>5rE9Tf5JJ?_aS
z^UG3a;2cV~VGK~ptU)WC`%eDdHB$D9ulrOAcl&XRanZaAqQVJ14e(e2g)`Al3x1=^
zfxh>&JUWz6yb<_nzG#bL<(6+xiN06+J}VCu_*x8BE+i&Co)sXw5<s^G+?-|2_~d?D
z`^fJ3n5zjBIVgV6c1(I=86>j*_iyx<FIViwN|M5W?R4tyj;N7Tjqfq^ooL!37VF}z
zwz)s;BK+Yu$n~7mTNcHGxV%qs<5nXDnyz4s-b1M_ZsEPVaa`jv-(q=T2&9jR^Wh{{
zsTD)1c^q9f>@?nkq$@c?UyJQ{RwDh(Peb!c>>y(y7>8)o`%NS>Y1fG48Z~L(j;ZZz
zD3z?RUzd%c)Ka~$#uKyFq7)rvA_duM2|INy<kvX+qV#lY(YDbl=vqn3G~w(9xswwQ
zj3NE~Cu^Ki$SMi=h>gigm<gm$@G0;U@9Gw9@HACXQ7OFGQt>`)xVx`UV%0tF7q}+)
zzOktbeaO1(qzhEIHDs<85Y>H@+F$D)Ev{gx)C&_R0B&*E-uS$W*tkt}^)Ht*Ezeby
z=wdIK!1%VBdfdAqwMlfC@D^&Nvnz)5B;%GpU;cxO0c?v`-+r&OdkZ5rGcif6vL97)
zZu%?l2~tp1+X5;Fl86kUCeK}KZO;N-Yf!HZ=d04;H((jPzT0(6Hw?iHygqV{oMG*-
z!=U2L*F8|5UATCW<>^x`USLfw^8QbzM2dNuFz|}62YD!qkkFV3WF<~t$$E8&<(8Qr
z-fFi}R#vtTQ}_Gh)i-PXY5OIeGxd<ZfzfePgS*47mpMpDwR!Nsetn{NN8;qqPc4`l
zeOH&r-#WcwETIys2c=4`S+mzuhcRw%R%DD8mjLdR>;2ZzZncqmwd3UQ9&UZ;XO;gM
z-ezOE7V$z(?q#+8XfA-D?SMoy2|`k3^rxbS_ZzLCePRfbRW-R20Gw<G7#zmormM}*
zz&wIkLSlA59*F2?eipiY=fc}t!8`3&#(Ddr+@A>MS$v}3S^L0Lk=auklQi+dhnhD5
zCK(pJp85*1wa?V}#-#7=q#@5(mAd}#?Ytf2GS&&i*q3J$eRb3Y_5w`~b4~as4-G76
zSM3U_t$L{Ozduo^uoqB4Y0IuNN}3St-tA`U$_sTyQugVwgITh}2y-cZD#MGFU?O1L
z0(wdHppe_7!h^0h6L@4nfBP%2EXxHVZP}lV+YLS9q}Lx-Kh?U}zGPP>?2gtk1o=&>
z`<US{FqZcOuJc=yK2wr@-MGJd$@~N2s7v0Wrv}AWuc{;qybQWdx33?UKPT#rX5L*J
z5MILpkLe%BUcbK+*Z*m~y3&Yk`9`Re&|{@sVD2Jtsx&_U07ISNu&C74J5D~`rEO|%
z?!&hVIZZKx(opdEA}B$$o#RqKX+h@ns>6~9&J5K1Ls4&>6{`da4q(fj89T~LUt{J<
zQr@4o7%^l}J^VX~zxvQcw8^x+gH6f)ZLD1ee0$m~YCGDSu#OxB?3ar2FJGrk94uug
z*x47Fp<cn26L@1{VqRaUh@clsMt_frx>>oJrFXcYdK>|Z%tArUy*5}Vo$a3CK_4)M
z{0D&7OcejR^mPg`pa7F~P!#swcl6d<UJT_EvM|!pig5#(FoW-&rnZDZ-BZn3P|W6g
z@rj5`>O7C26Yf``=PhVLDM^;TZCcL`RcU0Wov~9aB+e2&KiO67gy{w;nb)?AedJVa
z#^doXLHnZ5v-Hb|<SAasyizj0r3S2WH&}V5U<$@~1oCVub^Mj4to(IqTs_8N<Urco
z#ez#89^0QLmhxNoQ*ZXiUlpK&h#hR#Y4Ifa?Uj${jiRY6eyOFDf9cXzG`^f^`Tt|<
zE5oYlwze0dC@P|aNGKvA2m(q-NQ$WRR!Ul>q+2>vKtbtlM5IgU#-K~-2BoCC5xy~b
zp7Xxvdautv=RA9F)>?C}IY-?0J;pSjw7R2|9d>l+cyLKXz(k47QJzNKdLmudk*S4*
zi8{%k+E*(CS56)5{3l5#aokg?F8neDOeGRtvL9HFl}X-a*~v3}kjzT)BS-2RFHyzu
zXSz>+jYuV5q=;4B1$9cp$d^|PLPA5*!d;U0@-0U1uIS^%1geG08g$iyjKx+)4PQhf
z?gky*m%O*j)f8IclJ_&W<@t3V;g?Zp+QElX_&=9MYojD@XW~wtIKhdh|HZ0%qZqgZ
zJ?|AS8a~VK3M8?RurC8k6umgCq5|o*<V99awSs+>{Igs~MuaN*qOTS%EQR&xxO#c_
zvaaB7H|)8LGT45*vb8Xy*>*YCv)Huyg|N=;^0Ssb!r$}c?)_=e8v8V+h1LvV!MKl+
zjnj#E!=D$kADfhqk}J|Z(sXimo_iof^!0ex>1*K?8F>AGh!`ear#S3NNl7`;ddLG`
z;$w)5cFnsR<aQ33O1y?Pzw7^Sje<X1+0K9Z&<x24BS<tBqrJtF&l{af!HdgsOsQ41
zd9*knH|g9pEgo|>bLQ-{!s0S0xr3`F%3m|^bl=3Pj%3O-2N-paztM_$oElUl@6z~;
zuC%pS)3VSws9&?i|K=2Tv(4Lmbw=fz#_R?a$-?Joaz-f)<XK%c$T7E_c8g43GdzX!
zTFz@B5uUfK|KR$qGW41wBXCk;xe3pXg~d28v!An0%gka)d7_1<@m8+;Xogm0#T;KT
zIg3(Vte|64iL<I=vb^01W$IXOS>dj!ayg-`#9l&`^kvyQuD+%Zmusla!n-xi)p8!c
zm>n!t7TVvnveI~vt+CUw^mp4KyJFi={(VYF5Y_hFP<elBvum79dpPJgdt)oxH>8q{
zX6~}8o+-AOQF2Uj0tpjC&egRyaGZ8`zVINOGJA7C40p`K$}h4ipDRO+`Svf=_ZF*V
z#aZA=5<72p|NZQmuil@SuH!ICY%W_JV1GZ>ra}h=SXG;67u8Gd4nz7T!yTE`zA?PN
zr`#g6W1M?7R%w7--1b&i{<`&cmZ!!{S7uNIr+x#m@b2T5nN<yqLb+F5L>1nBFKox^
z0`w@fGSk#btW$e4bbf#L;&51fmiujC>c><K)mOpw9_<OfKQ+uHpX#UDavpYbmjMUY
zY{ai}B+k=9buQWH#&o3j5uO;KOi`^bNmsV}DA+ZPljLTMx|@{}K744_cHN#z)+<@s
z`@7Q&r=&ijRZi!zseR@wcU<^r%-ul{vy=8r=jl7k+58oEj{a(WJYPv++Ulnb@!GIH
zI#^lqarcYmUQZgVA+p84$k`%km+UM95!GD4+RjUzzi(bM>{QVePk0Dg*1W%LHCX1%
zqVsS?GjM!dyD$0ofRNn0j3$~Z+rpWPqiR+127eM~_6({%maZ8-PNshOY;C~nX7vwq
zS(ZOsSi66QL3>i|Y)$%?P@zzzqN%$VN(}0j06#fM{1m+a$O~C%xh3bYF>i8{jZb5{
zr=%c$K71hM0sRWieC582<NB()Wj%vl+Cpm5`5At9@SCy$M%eUBr~kuOq8e5>mP<A=
zcbr|Q5~s;@o#jxzEzumwEps}ZOTEMJJM8`lH-+>QYl5uO_>Y`jx#~K)Q%a>M6f;wW
z#fJ4Wr8{zRctb*}f0^^g=p7pOYLLL&9VE5ts&kGzui-?F4SaF46Q=y-i0jH+3d@NX
zN!|a|{5vL!jor^DjQF;4lo0`cRGr`nA@b}2`Rp%&Gg>kPdcqeQi3w2fUm7`3St0!=
z;Hetsn_RkKm>&k|rJ|)dt?G*u(GN;^O5)X9gPqMr;B6!y^9&aqG8c<8Zt^$S!Dpxt
z^-a{J^=J6I5RegnpYrdn17$_!i{gpVa;fo_Q2fivvgJ{c^v;z{Z}xTyYcXu&+dE1u
z_O2~O*VR_lFDde|7I4Dj3zEkdk5p;=t+=Ij<?k>5MKanYV(E}0F=nBwk!xdRlS=jC
zsXoozoEvNbj%qOmzH$r>GseZ-7R8Vk40O)Fs-3@Z9Gjm9MvH^mZS~L3(cpGp3o-~1
z4=F&nqMvGTiBuWZI{yn2@_Z>56Z4NW1|2E{0{f-XJ)KSJD-A={%g^4npEyxF?<g7g
za`^%oHd63>MVuES{$NBseT4<IkQ0R6ProBQHbWIp7B-;q+*iz0J&>XClGtS-i{xFJ
z6=J>)i#MxwPu@%Sb$wM|ncZVpHePu#v8hw$I~z*Lt>1SRt2(~~*AzLph{$obWIJQ=
zB&R>}GJ!J-As%#tI{TEPiG%O7#zSQ?o3`%lt21YF&6)YiC9O~Rjm0g^pybr_-0&d`
zjZ8YCm+$lbeaNNVb{x&bJO%7|ACXWe*K<@7e4dG>PMl&{85f>e{`S?8m@O>AXD56#
zsCasjl!RKOnj0(n;A}tIpHXH3r;i&#Ug~Yo`sHMOb3PHac)D`FAyBQrPO7=)QdIc|
zoyM(=`weQsjrfgf5~f4Kwii_BX>b0~&1Q?-_+qkbIk%t7in-nTxil9m=G2RiDZ)t*
zIBDrdY$UbdLVbu=y5;xMEU{CY+YKdWh@~?9C>pijs!5v4`VIts64mRTGt6dFZAgmX
z$m+V%e+VlI(lCB@2vbD*DCts=Xxim883)XSjn_@^(pns*4Imez4V)g%2uXG|Vk<80
zU0#UJT-LC>=V<dYtJUsdbcG6l0p=9%tne@hv2M&wL@8m4RroBQ$D&3sLf<}isqJC<
z_fqS1xx+kX?mhS2ZU3a^lGR?Lxn+BhyfPjnueM)!DN-V7PQ5Mz=(IqwV4@|)=z{BT
zg>yl&&Q0T<#~1W}ef20fI$r(Dn!nl52;@Ua_*M0S+_st0JJufXLiA^FgUW2DWWr)x
z4@>2Ww@N%;GcGRcH#{S(Wq+kvE7D9=CtE-%>zh=P`!J)K@!NbzLX~Zu_X#Y;{dD>d
z;U1}~MuL;l1j#i6=uOrq)P~~U3o^SBDPJqRmuv=cx#dh|VFSQ?mjT2)o!ox4If{qJ
zIp&t_O}qh!N?F7_Pk!29x<y5{KHDq5K0nCv>({S>!p+aQxy>_gyuC?iX=(f4wp)B2
z9vl_Fa|d!eG72NILn)Fj10h#!=N3ci61h|coQ#L=e<%^SbxXpD(`wASN?PSif1RfN
zwR@(%16Spwa^wo;059UNDR$GR;<rw@_9#b0uPK}k3a0{zg*HV%0Y>MzKKn_zsNmhZ
zlS}LCq2b}@Zht)vunHL|J`<+coFvw}oV~_J@`y)SsgwHJl&H`6l;7xgcENjW=@axb
z2{U~xe&dC<`O<RH+F-_&Yk4Ua1^CA|AZrN$V;#{@0g?Ir(&uwJ4Z&9}yHxah(|z-G
z>Pe<L)58uE5J>9iB&s`1eY9L05w$X%YWw(md|WqeC%8qnbA4+v&a7{GzH}j!O{1iz
zYq&X@Po9d$^xEFuUZB7KMPh+PH^Cseo%xa(HcC#tckUh@5pk}&9om^V2+tA~vNZ<<
zT0t-007SyGmiN|R!Ja<Fj>I$b2afwou;l8PoeyBO;jeq4T0T}!oc4D3*ELF7%1cp~
zNM}Q84RgmCC>5Lw!FH)rj;dF!xVyWDM`ekI$GS}K*ASoQzx;Q5jk7%nC2Xj6VjNPx
z;PkALhUjiLxo_W4jGV{qer-U>A%py__|{stmM-YJt~}}xS%#E9460JZljPz|v+EFv
z5;gTxl`wVEFWI><loiAeTX%qwW0MnH3yuhV*M_$K)MKh!_J>j;Ev>|pvKj)l=*x8E
zGRb;7|2WxOD-|8S&=hLHouK1r$Lcu#z&H9@aq9x*(nbTqO_Xh}$BbXX<UYvTaJ#n~
z)Rx?h&yui%dY*>g)o<s>YaIYWXo`H!UcMU0WzhCr;jGZ!=IHWrBYV^uQGQysTA``l
zoajeaP3xcHSKQS<J@wGh(`x{ti5(P-Jd=JKkO@ix(kk-<s%Zo%Z#~Z-q+2Lm5ONe3
z`df_TZ<iSvqxzR_nhr3rsucu7k`;dZyO8sC9fap|D#38n98UT*=Q$C)ls?TpdZ{52
zGd{A(U>Os(u$`e(!9Rqpbks9dKi|spET2xP5|kQ`7_&##L-8KR=53nAJ0*92b!DnG
z_ql_Ti|3anEbBd`>f}6rIhL)LuU?t>g`3}CWW1-8rEbtibqG#=RTWHmuPJJmqWFgD
z?6k9Yf}iUypGmf6d7ts4ha&h@LB$|K8G~9U|Ff*Bbz}8GGQ3`&f&3&R6{W-8IOTFm
zUAVs%ni0A8Icr6DJgX2tv2VzjGS2_f&dW=)iuY{#w_mQl=`lk4;5+OC^^$%Qut+it
zah`^%^|t*cg}u4eAKJZb`m#M8x0AE(r8rZO8JefiX@RJ*yhP{t(GYP;Ah>`Qqg`%w
z-D`J`SN+HfJdNYokLW4d1EdLXSbP_}?in6kDTnC7jCo6+fmKugJM;AcQu2{?FWd~*
z)0})~t?dQIjx0UD4hNB|cb)-Epy62u$Y1;x?Epjy1}^lxmFZBKz23LL?X{Vx=fG+-
zQ+bvccqy$;QN4j@x}Wmomsb~~!uIC2ori&1GTlr|P4#=~2z9$(9?K0Z*>ym7UuzXu
zc_;X)4d^%Tsq69_*a-Vk4)H6QEy3q4hCU}X9xh%VHTN2dU?H6@4E*L&>q1KNc}3Y?
zV2c7d5h`ZDmvZ%6FK}`{`o^UZW)AyF?^Pg>zXt)bW9NgCpd2MyLoE3gO=|?_y(_ZO
zOh6QdQgJVbg<pM?ya?pVUluZBz}8ff&B25+s>k7`N?tkm%o~;&b~5KaPsn=lXuz-v
z5xhgL`_3x4dOo{Q?Sqs<k*7&M0(wp+CM%njsQZuzAM+UhoBd!fms#wr$1NSP<hMGz
z1CP9VuUOiA@C}?NeVpCU?OL1L#<nYmo;@%x!<cjE$OvCvU$*nk`Z93M5$19{Oh2b;
zM{E6f@CKKx8y5BBoUee_X)7>M<69_OY04WK&F;L8>n6K)?0Eif9IckvchXF`6l;_3
zg+mUF8SE*o;`o&SJ+w=Eu$>YX7LMT1^(JImn>6H35V|7Sirg6Ei#-yIxA@hRO50dL
zD?}RRWfk0I<HoP=H&<&lIA(S=#`X;@FD7Jv=V5Hur2EX1l$$qT{t?-*`UTt7pvSJX
z;J8F=4|N%q0dy&EakS{|@7?*k|9F?9z!i^-RrCa~`q8$8WSX@2i?XOn&JkVeF8o8^
z>-)i|g}1OZXea1wF9b;;*Z-cw(r&`aI`?RV5|cHlj^ndjS-;jhkWp^kKOjDxVNsXK
zx+9gvJ4=2^Y(s#-M{K{s?Isp)d1L5^TN;#6F%eWeIpWry%TBMnS57CU)M0cjb3K;M
zM#-UmFq5D!_mc0b@Obrf20cEOHDP{*^BES;j7;GRIM7{I>$z`Tj8XeoX%YWJc4z<Z
z`}6c0`7}DM-gnGmSPL203L)NMd0ch^Q=|q9b5gn*bNjtB>`A};{C?thd!m58%A*aW
ztSx!^ci09t5-%V52xE%>{6CN8DQ2v92xD0Oxqi}~_m)WXi&u#g3$pg_d$INf8y&wg
z1*;@J0!*PoZ0emY-oKA!_6RS2EOak|g=b-fd?5$#p|d@!eYu2iyOz<)Jxh(4{E2fI
zuGm+H1C1Zr{WB4C8RNON^@gx<7(|J!-`cs~lUB0q@@*)|_3IbL%Qr86qru0RiAOcC
zls@FTc$+%3F{b=?GyzdOdW{V^S-*2DK00X@mfF$wv1NDc2|FHvAwcdb(h12snV8=5
zEJ$F3yFNtaj!O-n3e3+;cM9te59DbMmNGKQ)5pU?=%flWj=CK`aHhh$IVK^rufNeD
zHs9oz4x-2|)BY1Sc?teqQ;pcJKMspO*h8t)Nym6Z((A-uT;#&=mAQ>U21gF3ITcJq
zyu{)$esP}KXA?Xo|Nje-#}@6fI4bOAIhBM7@(V&h5QuiB&^D~CPuj0}V`L46%8IAb
zA?*i0bSDcE_Tr@)>N&w>uvpT_f2>S22LV_pg#g{++0Tt*0PhwkzqzJfgi|drHW;EH
z+VyVxaF2Kk3It7NQkt5imzI`pY?Q9|88v4L7~nP`l4t-f(pawZzk{mR-}VSGrdySB
zt%0dK)Ac2*u65J#O!lcQ`s*jL_yoRlONTD#{`v9#GZcU#R6j#CUlPQ?_@qN~y}9=i
z5)#HD^kZ+(jRZ1C%?jQb0y1=K@f&foGoXqxaRkz!u_?;{2b1?!dv|l`Gi0dRrc@+f
zxgo!(9(g=)7#n|Tq*^dgc2(9T^ahFfm~HXJ=TU<ASjv4^TCJbVhK05uU_iprwp@KV
zD8Kd117SHxvM=e!*n}3}-7f=3dJLFjE=3pB7j^(zH*}=R%TzzX6YQ!jno5c?Zk;-D
z{CHq^c(}GHV}jy4uuBCH%-jc}In}sBvhFJ?c$AQpJqtExr3_)+j#uJ5BL+)sIDhGV
zxa%_p;Zu&jIX_y1Bh*S5lkik=vE_{CGy7qqXmzqpkHb4T@j@6TB4N;z#G?_#j&SI`
zL3%%dr_3j9yqDYwNt>+4Kwi|Bd(Xg**J?r<s0}S+x!#8Q`Wtlb*?f}QL%2sE&WJfl
zD>R@<r?<Vx-K|cKVux!QB^}bQD*&<7X^G~WC=;qFo{TlR{XNcQyIwk^0>K=7(QvS6
z{JBj}a;#za12z5lR$lH{%l8lRk1>o~tb6Iu2&J{d0uV&aWWN^|&8G&6b5-7&Fa54w
z_jXb(-T?Tt0ckk4K&{?v@nE0*8ED{B7g<af*P(=Lk6d+HMyw*CDORvw`h^QbN{PTU
zw^cYh+E0B9lYX`dY)6z4!W9kzAFi3sbjJPd?n>$FDSxL?KnUnn_|BB-J5`mG>=VgQ
ztAb%g(L4p7jZGR7B(&jrj_{B#!cQ+=`|mg=473H2RdV>>zd}hH!+Cyd|DPZ3MO|%R
zv;^2PYO0BfDK;yB{$8Yy+;LO>wPL2mF!r#%e4{8eycqrry5v~-?PP*j4};Q0`*K%=
zU8vd2_WZo?3mtn<UB#1u;VdeKDXviaMLX%=#4w<$vpP|AaPfGk+StxQB@elM;UFwQ
z$6%$4v4%m=vj@k+i0F&UJUrd&vFboeTxMVx&yF%pIMfYCdywJZfP*kF0m|XG__0vG
z0nH$E)T(VE_lZ0oJZv{g)GvRN>ZUOhD6csR4?%#-8TI*(m6Ag<An;8VcqSA=*&E$4
zAt!bL=UzXS{0dn{0$I4?qRvU!0q?1U{{;V5*0itAkScQd>u?Zk4>>MyM|lP-fWED%
z&&^M0J7w-Fwe$9B0H`w}QyVJ(u17V+32W87qojv0H4H_aMte{Q8)eX5vhr!(bQhx5
zh76Tlowh^?SXQ1{8Y!i`?5cTn(m`zXvdxM}C3^B?G(5ye{UgJpi!>z`Z%mIJ_<0#Y
zYaZ<wmkjyW0H#_vD%L-{p6sU;y1Fk6HPaPf##WrTSEVE+19^s>zz1^xrIag`YpU5+
zWTCwU@SpxottpUE^DRK0^Zc%m<=7jvpKE-m8TYqZU7KJ%-y5pLI8)UN;|R<x+b1)_
z`uEKuz=Z=RH{Oy<-5BmmSa2j>1hUW6Iw@&sE~7oX`2^m|(lcky0FF}q1>P{4yLZp=
z{y`01M8m4XF8JWFV+sa`A>qDmd<Z^(%X!08p8_Wg=g}Y4&ijwA9D)PP-~x|@H2=r9
z(f#n-*MSd5ieK(J&z=ECd}$5yruz~0f)qX#P<~Tc2(Cs!99{kJ)(vyGzT4#S<<Ykm
zSV{x38xSJGM~o+)0Db+>Lmb`&jtax7td5X^#|oJMz^vH8KQhvgAB*lO(K!0C8(*vc
zEV`%4#BhgNf*8K>36U3hd0Z+`gK_!F6-kk*Py0Rs*PZ+!<?b%udJjHDyVf@Z62Wk7
zEiElCKfkaW+BJ0$%QFcHG3-ATp|yojd>K|wZ*0O`U%r%S`I^$!pAUXIwZ7+nTl0Uk
zUzteC2F2hyb8vFd-}wvdmoB~Zz8%l|C>JIOi+z_`>oz$xTnR^W6v#jk2rDvB15hqw
z3F1Tu>w{uqSfLWPz{U`&n?r!44bQRcOjBI`a+LNyGyu_QjTKx!UWCdW&b{n80>=Sh
z7aAJrNa`Nma;sh1*a(BX8yR<Xi)wPjdXe^|LTOIqak0!*WW9m03K#iQ^)Jz_K8yg(
zN2nx#a1X_{7Q8eQH*M$D9sNG!{a*Yx^_GBJHn##05hESJA>P72bInn4&n8Ucc?9sw
z-xSKY!OaToUaz!#h+ln%{_cICRqb75qHczOsBkcvCH~7OgxIWz%q6$jR^>h^UXLuu
z>EDw<8^WUfFaS*8O-t<0%0>J|V^9SJ1_V6uwK={7BB7@*t7u&|MJ=tYbVsUQ1V%&{
zw4{T2KPqPd?03+x>%InJswe@b(F*Z)nCVCjD&I~40?ev?s(xx}s$k=hYD~(nF)$Eg
zA<CKox{aar;M1!6Z|zH+h`HGhj4P*&JzxcvV1*l?icWWLcWc54kBAM5Ova%`>>!Jn
zFI$n_0{cFzLIy{s;7)34o+8xSzJVSacRg1h^Gl)|3Da`98t1$o0eo<y!YM<M6uifP
z+cfvR0KOp2xcBpTc>YmtE~n*sMwxSuDqWljfe3n{E&4HGXm@vaw(}k&OR51Wbg@bd
z(~<5aH-8_b)K6pmJY7Jf83<KSlEBPCrB0puYe^PDMw!UVtg3m}Cn1-4cBlb`{n6|{
zGE_K==L-50O$SSoZhwaP=RnNf+3JI|a|Wn*tcvv0=#7yGYpQIe^{G5fq7hGGTGONn
zHm!;Qcl){i!a`;5J9qC!UdOeP|2U0%RTTJx`*@-0py442qD^aWOGt{P-BO@-gb7S{
zAo!Gs^(AYW?}&Gm=Ib)3-sb1}Gf-slq5RVDQY-t-n@Z2;2MpAhPQg+Qzl{&6IXuD2
zbt{5J=@OxM0!vj<J3whGlcr+XGA~?f{(P7UXP7_2S~zeCUTk^9d`73MB<+rlb$iIY
z3-))iD)$_K*YLGJ5Bc4W(X=(*;Lqag&K1?Y)<^E480Ze}7z|PFdxv%vrvX!VVBjT)
z+LB)8h<x)TVqjru%$QLY;UQLmUMRgqV>)>axb(l0w`q5PW1e`#g2!VvWc>UNn|GFm
z-FmNnBNWgzb-<Z*P6<X2P<`&x<3zmcQE+55%wf*=Q@H#;4lYz*QQaHp?rtGf0O6Rm
zhRB?7guDCU+^%>}?^4?ZA-$ELLsb0Js&9a7)GYni=QQilAMqP5ceI`A%8ZIg$cXa$
z!yV_e?BxXH3Am7ZbKR16Voqh2(l7LU`W7v=g|cEV@7r)|yGzjCH!T)+>(5!{4C*)5
z;Es*$mLbRAH(_2_0%9Tmq)og3bZ2^0L*?j{!^@JrUt+|9I$x`R<`18$br=Ro-GC+o
z2ZT-r{RNpwN}@n58!NDtZCD*;R?(YbkkansxccYGO<76~oi}{1ml6N)Kjw5GSVd}V
zZL5|o8cjq|>50DDM%PvYLpAKUl#~=_r>U2hmtM1Al?K_QtuoKM_X($&l2ZID&32HH
zDk^<*v8EWqb)t7gc7EE-4?e_Nzfk<fFtk9@UO&`BziTC}hL3RL|NN{5L$``$WOfJe
zTEXTp_=Ov5(3lU4g>IZkvqdIv10955ZsMoG-Td=sV+*6KzeFnl-htZ+3!Aa0)|{ij
z(gff(hr?Y?!l!a1^}e;3n*dyo@J{Z^!CpS5<&J-VwI4c}2tOH-Fmwm}-YsDeOmka;
z_=)~Br&F)R!0Ze5Z<itkjS=jGXMJGkx#u8vk68cLrqYZqK+40ZObo59WRAMYmre$a
zFIQ%FLt+S59jdX;ptp@3{9b_3u(PttKxY|tm^PBr=EgY{Tb^cf54O^|^V0?S^Fg~T
zrKgvKmPNs2idp4fC4eBWfM6#O2+!W31Or^k7j@A^rCzR8M~LTi>-^~oCLh6>HlK~U
z*}VRNeM$cV2^$^yN`KF{?gjqQ%g}O6T`M$u0a|N>z<N;c%F-}$DcGwx3E2^315dM4
z?2rmb^B<j|#Pxrs+ui$i)e2&~5XD_L(Hv#c`T&}1B!EtPBAD)p_)l|oM#kC#$=d#Y
zwWm*?O5>D+tE#FhZ-4!~3MoY$NV-{+wVd+_&qLc!MsNk8uZ|M;u?*mYK|LfbNPwKW
z7f^r#E%BnS62Y|SrI|dTQZENx^OgJ845_k|x(zyqyxu{<gTl(7>;7L7YHAiJAGU-v
zC33p@5Ey$7fVZG;P|(Q8V*{wMNS$TDEm{dfeq{iF)#lDlBZNldlX0%0U`-<ptDr_z
z0z|3fpexDU;5Y0qFyVMyg^_MUsb4*SC)%yM&eKav$1C*&E1(uaTKD77J+nSrkdQ=e
zWM6l7rn(Nq@Cr=$wrZXOZn!%*m<$P5U`yTJg94KtmSuzZl*v`@nH}3sMde=3O8}C`
zbD8vYl<7k~Zzxpj(vWhU71(GM+L1;<Egc<Q8)&3fT!P8bG6gaOEy1U0unl7GvP?q&
zs{QrjfO_t9^n1GZN{a?>6dyucog3{&Ypp0!iF;poh|1+J<co;Et^@ZmPP@PPnlKMl
znP#8nbK1<2j=CuWIs?9~zZ=6c$CBk=LczxEEl6d@U=;)-c)RKazKrXW!U4;-C(rYD
z9Cm^g6AX!o7GTJxt+5rqzP)a=>DJJHd5frjHOU!TU2)16oH%L@9{Rm~i$evIYIREM
z7L+6B2)b@`$je3G*4m`lLqOpkZvH^5`jDok<}!pyksD&e-QX4*6d2AXwTg=Mf$vlS
z#*LaZ$B;=)35+etn+a-V*erIZlP=)LO0bM_{n$aNxZGZzHc@Zh)9l1(*<_Ws*`luq
zl9uP2I9r2zbM>RFsMM!ge~7^9&kBr=Hh!4_SbzB5A=URAkbp@-O-LftYLbwVT`qT6
z3xwuN5w)G(#n9!X=CHO$TxHwHgKuT9?&>vc2X&Jk2m=?sK0DR!eJ8V_9jEw8s2sFF
zR&Cd_+=OiZ7CSgUFfE<CDL)tH@Ber{JtWMme68z-d>ZOzL@KQb%C?E(LX-Y3X=S$f
z+LG7=A<qg5hjO92Pqr%rp|#QkccEctgZt+r3(hKF-6h@rvF;=Y$V_|@<*CU(sF<me
zTVt$~(5@{d#<FP5T6Kuu<2lI1z*UXsJ$>-%I#K6wQ>t}?XDU^#tqW#Gm*;yviPiYg
znlTe{*CCaOycxICwG0Sk*O}r9q#i!7<Dj~8_Hfj88Pea8mc_oQII1e1nyvM!DkI~X
z{Q1<7V8F3=azVE+HCS3$UOVgz$@N5;Z0{)|q7X<M8$mlE{YX^=Uy(@b1ewc1;~}(j
zzw8N-oW-qvO@X)Nb}RMl9~L_MQ8g@9LhK9p>d2{5Dkp=wM5FzyG1IDcs-Kz5x<<S<
zx3~K~IF%G=iH=7TI8t4L<U3n0rs`!BfxVx=@|)tj2IE6ZMs$WbN!`;nC=%f7;y%sE
z!7)otelOVsc!U;r*X*)o?_TalESKdzLZci#6VY-%(<>i%h$Pn5V&7$DrgTP7#ZFhU
zJMYKZ{U)@^TAX2@E*IV#eqw+W8NuhsjSrm9Mo3lB*~MoiUpxt3A~jVRG;v8{&bk=i
z-Ym-{B4GW;-++Z^Qt|_YjY$c(^a1O?<zIPX`W!h*<a6e!GG<858gG7b+%R=qXVN&4
zbKPV{VLb3h!(Hc!+IF{xJSIQQ6}z>NN@_NuJ()V6$=NmkHZGYg?pb6G!7Hi)p~Wiv
zHYo3x4@f0{LymAvIsyfl$Hl{50ix^2+!)&oDogNcgRjarP0*A)*Tft2d6fKl2pAVV
z)f`VR4<3fAghWNwug+xFMR6O2A_fsE=Giv}to)pyc6~i9VJcW#g94XM46+Qy6<%@0
z-&5PK`C}X)nb0#4ao+t}dX(a|r|mWk_r*@!LtA6E_;x=V`7_Q!s&jT6%IX##D(nxw
z$qxRw^G(W`nCl&DII}bGQ&AUjJlB5uXjtEye3?(qeZSLC*2IY6Lj`fk*(c%vt4cD_
z1tNF?oA+a{!fQ=#_X8`-0x?@qB)3tYCX%soimyXOYAB@G4WO?w{hHC%#w<WoZ#{Zy
zut$t##RZr!$hr!Z$>xB#<7t)WnfkG|l~;nZ6%!gdZ#(ehxk8sgi7G>CYiYbgc9FF<
zg~mM`&zYY%IofoQI3edID!1B7Gx48B+%z3Ta$MIsYl)5>yH4&7sQ{O;6O>alUtv?d
zkt*+V;`vM9E{X-9AYYI1Sxg10`j0fvPv8Ud5>XfZPYxNoan?A%X!x3j#7!6!uJ;08
zrAPGOrIrGWjDeN4Ss`YM--c>0-tfoTSsU#$L_)2C8|wWtn%*m=>0fSuP@nMA-2+qu
zZ&VfIRr<nK%^$)mAfSGbMb)f;d1v@eMg&*3J5-a8nP>P=^GG5vBGRYiY=WO$XD?+e
ztc>@DFDgjR%<2Ol1S%-6ChAttBby*G5Sb!igktE=2JKhSww=qQ0`mz64!q`t9~Rw6
zBgDfz;1(aNs!$j;e~m71=^8e|1RjQrgz^!J$9)*?-Vh_e%#q08xK}3>>44v<2&cox
zm=LslB*_r|uqx(8>=BF%Nx5!c8m>a=w$J~5l2hrYK)eP(IehH=hgYdK7sJTRd1G4C
z1@FtqaG%G#^?TZd>voBDH}K&%8*OZKw}(o~KA7O~M*MdkF5))VY<ti>Zdo}nE+58(
z(wVV#IpGk%UZjkTGfqMa29#}ky?d9Z>}Btaid~vwZguP2fumU3Ae)Q0X%flx>_?TR
zO$I11BWnNuX}Lnuf2HMlfgd8WV9+2{;XS+Pgyd6z^3*{PJq}!J7__UXgC}4Gf+-aA
zm3xX@p%D>RA>IoCqOcJmKTveMJP~Ck3DlP^00R?|3E({ypwq%ds3-CVWmr8lj=L!6
zu<8#L={+nXrsx$JD&$52(t%+EM@Ju3t!UVfhy0$LWJKNetQUqfevgjoR=MFV1HRb+
z^$gNS-fx4~)&;a-896iPES4x6!=H3%5#0C9xrAqKo6uz?()$}2>Byb`hIPxC_e&bt
zN~H}uQl2pPMRFNjLf)D$`Ni)yXXr1pvB`quN&0%~3%w^)0-DZiogDVdI`T_rNlE43
zD@H34!J?4#G4kw%=E3l8xt`FRu;a=+y9+%Jb)a~N<lMPujw=Q|H=)>4o;y4$ilsAM
znS!029W<l1m!Z?2ri~@UH52O)G)p)*l*|b#$;$c?UO^!svf$U$3Z#={W0;4AhQQOj
z?VM`n|Nmv<nU7AMIu!~~t;Br!hGsFyvc?aP<OiV#GkK2m%8=$MAQUi6J<eB)x(4u|
zSm|VHqhr96i}hPwn;R~*%~sLJv1}u-Ah#esi?b(PnY|dQ)SEiSNg+!Nm}*asI?WEs
ze}#+4z<#z{dg|yA-XKo&*P1_9)<hOiI0!Z(7I9OpF<b_LdCz`+jgI2ANLXDM)*5n{
zVYR9dfjqs5|1F@pA%GTzPj&D+Q$gdl(@Y;lgv}(ppE^^(^A-7xO@AR7iPHLs4+`{0
zcKp_n%b@5R2Y7^gh5}kJ_5-*#8l*HoMdblFHn$O}VO28qd(fyi9DZX6GL(nuO022M
z*|7$+a_JP@{vB6q`7<A}kmVn@glG(aXezR^Nz|Wb2a4MZaA<Zos#dkpeS>N;<c`^u
zL68an&u3^{iKeA{S~TXl`b91-1p?v=*AQr^^D{xbE#F8vSN2!^pOROqtagp8g>{Id
zhd_e6({+0DYHKYhPIjOj!-W8_-I^f7)_z$HftAGFyPoBj;<B@|1sjsHrINWn%!1+3
zjhCRoM~0z@xZ)3ifEH*p2p6qi1wv%mGvst6<Q0H9Jnz*W<W<7-TK@S#*Kg$j!t~W{
z=R6W~plS5(jV1i)^FU0)JE%a8<S{c%qK*5bs&Eoa*h#LZ@hHXPxh+nI;}!t5f!>ER
znQc3;8FgSYE(5C*i9P5(+R-5TF~o_gXG-r%$*(%_LSx`o!jLw1l|tP1S{EeEK_vh3
z#wDLkZ$31q9W*FLdIj&#vQN5<P{g!C6P(4D@>kU>h1|E~)-qUvCO!oOY@EFQ16H0}
z>5t#<Yb>085-A*^`u-P04@nQrVELgy^!eF&D0cuQKe3*M$j6yuS1w<!120Agcni<W
z$?4$7Cd1b4G82&~VRxAO?|l7$0@i&2k(4B)C%WI?oJs04UmmM>oy%~7#urg>A4T;5
z5o|JT0tL{GNgN-d+A<7N`}OddinBIc7@{8fu}(s6g{jLp-SKzgEKUZSdmhSQlc?Bk
z-1wPM{|{|zXf6#icsCNKh!7N>s%>}7jTDlxhGY0_=-uJhWd7%anFFl#JeRNbz;TR;
z3hcw(N2jUaNAqqBRv5;J#M%LWeqgB=rp*qV)r?mQbvB3I5iI%`{Ma)xXXpfao^vy#
zhcH=B*dJmtMjrhK_GRt5Cj1QAPvboMuJF#Cf!~cd^fBD&fp7PG(N8mHc&lq0pZs&-
z#kJ?*OU(b?^Zi9(S_7I|HcR*;b3q>?r6AaLU=zA?pz$VJ^X9*9_sa_*ZI??6B!I@m
z-oO6~+6ZoO71m^Hb;<>|4*$B%RSGXhaO6NS9+U6?bx}M!={i6^I&7#K`N_(`{3n76
zVi{g<f2>n`vRs%Egp%1mP(4oAt@)yFG>(prQg(JlT!tO@TOc+-!jSL7`+rQQw!^ht
z|K{^`?Ik8&MpX^Sq$XuEQT;fN(BtJn+u?|K$Se^8JgKV5#WV}c2o%ZPWff_^bt+41
z-@bVh4-kt{#tyQ5${lP07R+v>Mv#RfWEl~ikRb-R?vB!0LQrxaGN3WY@Icjp)>Stf
z7+(<MUjahoBhvY<8~@aFS`xR4d)bc~owinmK&-5rVKRih(>(|ZB(0tLJlXT`qTT)c
z{Jwwxejg~Ik08wAfC5i>z9Q?XhsgVuGb0H~u~Ir=KGi2cB9l+<<$233$eXuM=ac@7
z>(A1-CI9IhB=0-}=C5>gb$fF!LGEt3)~PH7CrG3Q&Oqa#UEt8xjVmCNd<1To5g_5D
zKpYE&h2dcj5z2H(GS&>;A^3r4Y-_sKJ;H(+BfIyCfJg^CCaQ|*m**lH<>25jPPZ;F
z?!5%H8o>o7{S67?Z^xj>HV_~H&3Q=F96gXOM;9y@hjz`$EpVW~Mu~%pWuyDE1LBz4
zla3N!Fzynf;W3RSq&~Pi-?P@d12F4!O)@4a`RyyI;;62^ej`hE*`>D>?4eMX1IUaI
zfB^7suLRoUI<7Z;igj9+NYyAUKqhKJpO}*4dq&(QbYs2`-jIgh8ZceJZ{i4V*sxZE
zrR#DJp<-edj04j#FAq>LB}mW^?h*a19xUp3yvEbSgUErI7WNQR>cGH2rODldC$XN+
zR4r2u9;okda}p!t3eu8HSG-h%m}D+On^mhqo&Wi)T~lj^kKCyX0!&dnW}$#YNCLz(
z#WFH8W0b@^;~cWr3!J2tx(F?4GK%)_37*0<n=`zVdy#ha+BNC*g<&(bdsC*hkVE8V
z2DSf?v29|NW?AK$Z6CDG|GEGi1sQvG&^_rAw)e7U*ovUFZ$GCw1H3oBlnc}B5)XFe
zh~a`E?5PepcRV)x&$^}ENgkZ0a;a?>8vHY=pp@~54jg?d!XMVh+WjAVt0*cek|%Jl
z?gU@H1%exC2JII>ut-2ZwT?8!M(L~TD=VDNNAkYncsPF=)Jf86BM85!3Kq{ZKXVRr
z=U-~bU=$tdVmzG27IW%A(<7FXMPCFhrR4u^K>B$AYh*VhmmY`uIE@0+L1wAYYXP+v
z9HmQa7uW!4_Xlcscs*^I=gHT@xs+b>B^jdQz;Lo7esgz5YoFtNqSB@5nYPJ9x{1%a
zjZLeQ;Mf`&!qlH$7zJk#260i8(JFT(C<r*9>8{l&MpSZ3dVpLO9jf^#(isvQe0kVu
z#fNZUdv!{?Yt9j9&oNk&p&+L3PhUpeg%RWh!3t6)SPep2I0p0#_skh3vdo8w@{|#O
z3?5VFPcq&Jv=K4RJ{`etla^{p1C7T~ksEaTrbi3~5Q|otTCe84GpLjPXroTg%RnY}
z!|LK&9=apnsFLHs<@WiL{lb$e4in!4x-evPhuT4+c~Jy3KP2Ei^aO=8(%F$z^-xy!
z{}6`bA456s|32prv2;AilwGj@Y0SI?Vi3!Y8+>h0U<(X&HtFaCOymX_mhlw*zt0?j
z%fl4PVu{ZAfipmz#e7S;-jdL=zdpDvd2M$;oyN>v1e_kM#t%7|mVpMNYc~V@UHql|
zR8r`u23N#nDd2Bg9BvHa!xtfL7ED-t5xR2?hBB*=_xi7<*N<Ut?a-<wIJboRHazJM
zWa!<Nm2X|bJxmaTLYaea6|m>R;4ekQr>i$fG29_oK1UuOP(92KiEHApfgUK<15th*
zav^eC;X=+O?yq0>pGDad9{-hll5Xt##b^R{k8C?g)h6DD85?>!aV;Z9%>tUWD0!Zw
ze5$quRhVqhlPVbOJ|gUZa&H6?qb^9#){h4Oe?Zz%4uTZ`eF3oqSnD%6Q<0__Dn(3F
zWI?R;TyJGR_%*F=iV8>-8#G@u+_uD1aC0mBqMAI$bPx$Q$T6-k<b&w6>H*ac=qjjM
zu|3UF43V1-^hZXKktA?><DkFGQyy=}0M*pW%XAXn+x$RC#eGs>D8_c^Duf(C;Ct?)
z&;vT;E<*y+pDVrt%emS4xG8GnDEO)Y{JnyI>{_o4vWnx`jG+9At^%Qk^!U*3)(TR)
zJOnkTJl$rt>)%FqHxC~gzK0;UFzSW&Wpiijp%J)rCAgD0K4u6*0XJ^aHXNZicaCX)
z!*yT3^(-p~N83R12vkdOJ5DU<wL}}lrYngW9vQ_a7I@q`)(?R_bPl`=`TF4_N9x`1
z@O7Z#Y~5HW^W{4~Kc2}}zDXK@2K@wI9lXgWRS0MHt|}rGd4RzAwRojdXBE%b?W#I+
z8+Q0Z6k88hliq<IjVPmQfLSr_WBeeR08y=uj!sW(+kfP@mU~;1QOtF)0X3jKNvL*`
z@C?_Cmdlnn((@oQ1ri5k=s(RA5fL%5D<}N-a+tcMm%2@-A__$0#qE&*!-^Mp^OTGE
z(V`Et@4h)$^19hBJ~*!v#Cfb3uOax?D*{G8;$O`1aT6Wke%HQJ4!IA6l-Ix_<><dn
z`ZXfBF+jhwu@Lr;-?5qQkT~!=Q+eYF2-RpSwKXF>Wmuiy`I2gLYSrLl$SbPTLVysV
zARnou%C@J|!CsxU2d!2UH-g_#Msr0j*7(9GfFU<UnS4Q*p>VNc5CUxx`=@1uBX_uF
zS+bylPaZiDWU(TiJAF3%3dz8byEA{LE$E9lpzzXaKj`Oi@yvOaBAD8`SiY|1@y3r3
z))a)u^;4bJ)7Ot$QLXL)XXAL&Rn-dMp=Q31u4jd^!ACvw!$Ei76p`|2PIK7MB3o1N
z3?ql3?$W4>5ebLUd<@_9yTFRfZ$wG@3~6j#<^EqY(sh%evfd1elrO(h|9D=7f3Abp
ze?=A8UfzyBlrQndKjpOWKf6PA4d-egUu&QShzkOwI+b{+_yF&l6NL6m&g*|3sfwpW
zMMgu%QoRrUq(G){Jc%=vOn9NAV%U@OzA1{QwO|><tfwKii&{}pQMuA|EuK0gL%n!8
zn_0X(Y0=(hmw*kRUFP7zFtKeOuTLlkil05%M6K^I?!$uzvv|29wFL5c&eCHu9U3u#
zJAjPGnp0&F7z1$_iYUHyg)+!cW%XKPSy5X&P>VGf=PZMvZ%mX3YO>D^?YL+KLNF93
z)<bNg16(`_1%>{0NR~uORPg|CBolCEbH0x@L=EJ|=DCqz0x{61y^7*&Ic#nzAt7;4
z5PaU1+sUXc(Q9?CzuVm$NyW>j7p%)GtEw9Mna}|R%Ux<__0UJ~N$g5y;SjU!kbQD*
zN1_`+1hjSvMOpC=`EDKLfSTtU(?GI-PDF^5k+IGVLS3OuE4K8kPTfP0no9G-!g>PS
z-m0t8`GqaXg8c|2Tf*GhQdL+*CI)|`Hzn`j)rI{Zxu4q%OUpu*tXwj*hJDO$cPm#V
z<6x_NOdgfG4QGcK!0<xc4Cv6<q~5XPVY;B}OgYSI_*x2bo`at<gq^0m+-&H9WFQRS
zcohOgr4P(J<+<;A_Lv(7vSK7j(03S%zji(AFm}Mf1aiG23M%<YcR(YOX_ZsaJrusu
zQGf*(Mn}^)9xi(Qd#{B*T2?>nLSj-<<SC4NGJsvVQA{iA^TEru%bHP>yRx1I8t#U-
zo~-H0*=Nnn%u+SWOE$N*KDG0ztD2f-fmNx?(kKP2L=BY{YicrPQ@nfg2Cba-|JJVH
z1gsd>{M}O?gFlJovPPBkG(t{2>sS^$6Vv^t+S)Qj&di5B+)nVW{4^Wi$aFmjkIfw-
zYZQa_qk5_fFonaJZ4C_#9OSBQ>FviK(bC4XXSpyi9agVu*UAn_jmyYEPd&0az?<_z
zy^pmQ+#}O@qT{_yhf{Q3MOGh|LNQc4uk|i(3MHJ+fHlB5&$xO+zE_Dd=OL?vFO$0p
zWZgSXBHM*EfE<71kS8=3LqNNm{H@CKqxUe8UciUdt41cc8Lm~;9ynl96wc#E)u89q
zg(h|8cz6{<9ErNo2bW}gE<058pcbwX4Bfb^#NR!mIG~N)NVWT*eMK1r5^M=ijKjII
z&zqv>s~XOKM;u0Q;|aVokzVM%tX}t~!08q+zHX${KSNcRz~e&<P~@Mh+7W!(^(Hqw
zch#`Rgb(RaZhcZxFg1|%s^9mI^CN_l6*0HbDc%RQZ{hB6PFhv<^%xYdh(B4m1*Q;<
zM7mwIGf{%(gaTNpk(4A0{<|5d8%8iO{Q5|YoFZD2$N4JHM-Aa&4G`Xpy!6a_7j*F;
zF~vj_lSaShs(nY%%{UslXvxabh@P<_O6G2i-ab!z2*V8l4@gnHN&+9HoS9PzCBSeu
z&_|sdLsyBkdpqEP;+fl*9>4ATg@(L^hTJ0_Ljuw&=**WORdTrxlIMeae{C^Ukx#h2
z3u15R(jp=K$Sr#CrA;~>MviX&WKU>_BTei)GLIsPmQRuoFRe{v8-us}mV9dDHy6|D
z$}eF>n3A;1J*{eNkI`fup?AjA)fL`Uo_x|k2!9sBkzry291yBnKmbh@k$M|LJ&OFQ
z+U*_r#(uXLKRtw{*ugrbPN5}b{x`J41XT8~+<18FQXQ;_6khl?>fCTh+HG{Rk<X^@
zb|8WSEuT5*;Iv|x=O^@Tfxz!zyKy_R^Eg7CnPDl8+}(Um2{+2U@%Au=i-0-e;Yd-*
z`0jD^U?&JjJY0J`)qcGX-QwT@mX_87Ei`)ZARVb9^_dC0eCqYL|9lz6S7}nl`^pKT
zLJ%5U<mi!WF(F6TJ3@S_nh$T=H~u+gb1;#ykF9I@Nk(Q&4!(WeKGoFuPt%a9wK=|U
zHjSj_0Q!jDf};R02L-u2T6f;@rqTTSYK&%x-Q}mm?^&zV&Dt)`Nn6)de;QT(ej18n
z_l+62JqHccTx}nJshtSTcYSTJbGKT`F8K^e_&`mb;`FS3^C-U){^hbA50bW`WI=k%
zXVtb7>Z|sJy%!GR&c-r`*6-xR%|S>0-~SYR6@92X?Yff52{?^$YqFn2pQi^2_aA<*
z@=XiE`^Hyq4Hc<;J~dmQ{Oo#<s-ec#vQ}YA?v;K{@s(3PWcnK?7}meOZf1>_wd&=Y
zF|F@ed(G!+*DPoGY^$3@aF)$tz3BeKl~}R$Uw<dmWw+^iH=3nLENaM;h!lb!oc~P-
zBm^7SWOMm2Te;B3!b!=1ddth|mC$JN$$fRyyo{G0^(H$v$=#MRVnaWJ=Fy^8x#ag>
zqbx&oEguTqPCF(&6TLdeaJ@Kl^X~VEsNDW@OUozxS2J0fx0(c_mR&UEm;5qWzW9{9
z{l@+$d-_|sm1gjdQ2c7fcN+Q+Eb<~3KbKj+!2wwiQ<%$dXRdg}kf2w`6BNW67)5_-
zL7V4~<>sc;_QbG>)Mb-VlHS#x`@PGvx}PU=887eD#jQ7`j!*o3C)QXI8r{UT<Y)AF
zdpC_yvSyt-Fy=X~ZDp^iS(1WQUq+&FCxY@;m*lgVFBAOn3D3Bnz}5gWhAV#b;k3E-
z&ME!--3C@;A`YSOVyc{tUF`$k6#CsE+AFj>`nvJ`_;6jU-vts{{fzHE`*DO@*5^gz
z7O4XBZKER2&Muzt4}Y-n_S?*N#Wl*(o8h%B%?)*>Lbx>ISe>+!CuVo%75P?o)GeSx
zlU;Yf#6ZDRx8zvFe()-5<9L-Bt+(yt@H?xelDlcS9Y-7dlt^71o#kHM#@wVp;02Tq
z&&CKv`q<CjbhP3(0*Y;;X1B)9NDSvGeE-GZa-;tD%sb8y7mHC)$)67?HY+v$JIw2K
z!KLu<mAssC*RZIVt17PZ98n)>G`C`C)K`l;iXNwJidXlu_~tK^b~kOi)5+}A`4*Z6
zL{bRT-Ro-NdGTbn=iaQMNG~;X7Bl6~4LF#mo~FZ#*yu7rc;_L%7}(}+w|=Z0(`E~2
z&fnki{Vo&E_DTB!N4tmfH|<&S+BTQ$s_XTAh0W_^GRd4Xk+1h|T>U*Oq_mqrI$p(2
z+ml<{#(jdAHH!Y1#yyY?;^jxavBhx{8vf{%7VpYA!$h1Ra||;FrKwxgi4%(<&~fWv
z@E@XlHr?-p+u-|U?8_XQd7h*18?rWOTF+-GQuc}-B=Ggk&D@Hfwe2n%8$WuD)Q7B&
zaT#5inCKZ7IKJ03gWrH}1jwd3oP0Tg$2J|v)N(Nm(6jmRx)QBsnPf6rl}eH4WkTXk
z^o9{vtN1AI=`2K3Ty}0ep3AZnKy*U4JEOE|+v9~-<}Cf2S-a7@TPxjAavM;tB^Q<_
zBh~C|oq5|N*-ZV?7axZn7GM6NKb*N|-_HkU?2b}N_R+p=Zrxp(+^FW^&@7Yv)X0G&
z`QkEU$=B(QVHDq~JltN}8P2OltWTlxi>kHrs(YEUJ9?fv=X+R(@ZOUsR0g@*Qqybh
zeF+STU@O%dWTm{-Eg{=Sw{*(Ozv_Fao_CIIPP@>{x`|}AQ2(TIhO)-{?L&W;=mXbl
zFVzbL8(yf*c6jNYFWfp%m@_NpsM{~qEzy*+^PQ2aZQXk|YNI3~X_j0;CZT0Fd9ypi
ztQFIpOpCqBkxE+$*0cMo-W9i_e9-|6gYz-;rNnwY7r^=!Mdo0%TkG4J88?V9b3Q1h
zvGWJ0Hz@~w$2(XBt>3VbG%)wX$a{I6(tThI-zbxj|7N7Hkwr0$Ix)No(L+w<y0?kZ
ztH9KMk_$d;x&{=rIy5C7d2%<;FD$b2(1AJ6x_Hyf>1LW(8LY>VNOajz(2{kprXrt)
znIGAom2Z954*yRV*3HrFdoz7)OgEdrZ-CE<{O(b2pJ{~rdDh$b(~BaY6D`)o(I2=}
z-IDR9yLwIpm|HqT4gw0bWA~@Ji#*{rSUktcXC(A<L6^|_>ju=#E+>lMCW)}w9w)es
zl#?z(nwFzgo@hVJ(2HUMkDPS;)jRmU9Naa4Z9bYQpZ+C!`fdnq?TXSJKHgV&gBp<m
zL;@IFV~AkT!O8})oL$imOlwPdcpLdpH*fPn%C#n5h>mPg0E{<Tn8`|{{q0~P#wBVs
zzV&w$zyuB;(d!XAd%m$y(QAoBFw`@q=R4}&Rl+pz06;?i^D3X@_RX{dSe}Vkf6S*4
zkPzf{=RF`2zimp@gWE0JYK7MsFYt$VCW$km8V@tqx=bKK9(bDkn)WTm9{4fV5a^pb
zeTM)A>GP;v@zX2ok^%o_Y$7T@mO^}iS2ov2cO<16VF_wUIbax=PViT>S)e}xzB=Wl
zCk(=bH2PqGZO_6^KdAvFQPHiJx8sjn^3qtg7R&VZpr|Q$*Qso*(tecrycWFb`TK-!
z%*+h@3R!;wjM1xR@*=b!O%48Y8ts&FNHG+9LImY67xUj*fr$-vCvYcq$az5svU7+*
z6~kpiBKY$nuFC_y5N~I_s}pKjPb~-6y}GG@pH@^rc*fGD-wrK=s;P57*@oVI0GY?-
z!ycGULlprDXd%%pc`48H3|^0aftDU0EWP`W+_DF57JWi*azw{eIQ<i)FnnbIU!Bvx
z`8Gs|=mUDMnD|tCj^{~ZDzrrH&Vp5UEjGGOO1QLfkaUtIjV6|QUO#~kntS-mU4{bH
zcy-&mf(NVeNzihQ1ivN>Q67fKTjOz_G*Nuc9DV23w)8W+%mO0MSeVzU8)aoQ95&D7
zm+E&&;hs-x#QBBV{^#3at~Z21go1(SdEyPDesEU5gP48M8b;`CZL?6)R;I*_E}9Y<
z*?lT3-SH!O;jtij5eaZAD<6CRi}mu4?*4VSumY>7%h0m<klp=SarmzzPQUSZ-zQGf
zS+++I{d4u77PzMhIcSo$U_8+sDW_}_m0vwOxIEQ1*SpYwxfyhMMUWP{$w%JIi?~Cu
zgEpm`{@deAL8<nmv=ADDd>%_y5bTKi!U2!Pu`1P;a@rNH5kC#Nm$@n|XFB@6PPF{7
zR;~n%vQ^VZ2jQVAx@UnJ0e7H#-9>aysJOAHXMNREM}*;Q&?K6Ox(F@*SUmfCbUX*D
zrm<MjS|0wEpGyFcDT2Lmdul+r5Dc3XJ)@g`cu#s(UdloCq9B8&YYr@88%OL5F1Ykb
z{;XebaTo^o40iJ?3=`mzPM)yqM|N?8ESe|Q-p=mClAZw^Vu5}keOn<1)(di_SW$96
z0Z%A@z!%sD2UUFW-#rU`!mQM)4`#xVFWZKdva6r~{T628<MOaoq~xn`92${1F&Kfd
zc{&+n2tX==eT4XyRnE_l^*x>tie#(ur;5g>9%MH0!g8kpY$m?Ly8P?T{?CB|crx{{
zZ*<EeIcGDZjzRAW^k7~tKH6iSO(oEt9EoI`3BBe_-HA*y?i|bq2WPP>{**u2f%(Y#
zsQoZ;w^Yj+JxDEBN}OI<In8p<8>NTzO~dPO`67bzaRSdpr8qU=(UIN=mz4H;yOES4
zkA#-s7d)K!ro*kV`hd*K%<k-*c(AKr1iD!=x7`Q+*;|-G7BvA^aF@-a3t&;@A>qTZ
z)!4`ca{iNqij4CD!T^cOPZ&%UDpX+NX>T#QQs4RNVEsLv;vE}$-;Cxa8ct<%vn2h!
zK#wK|)-9Tx_@{>_eT4UTO7h`<@1YHk?vORzbu7fdDG0I+=AMqSrF)XrDKPhL?V!z%
zA0RT-l+T*i=tk4m(4Fr*9k~QoVuE@!jQqEj^Gtm&>$x0!$X!2<`WWqWKno5GM+1w6
zxv6}TJE+U%z}n#o`o?@Xt;=9qB!O2I@mShe3e~?`7`pl9Vm~CPxSQ5aOHJW7_5Sx4
z-Y1vBC~67<a<JzY!6xd8)snNnGhsRN#RZKd_%ICbc=D~&LfmQjn|6H0@bDt_f9!78
zl3xW>1pNYFZ#T)Gd<>HFRBa$=hC5Hpmo2&bvcNB=U^Ap}(f3t1Zf1F*SC112doC5Y
zvQh&EB;FV%Hbp@mUIZuA!CG)@Z_l<MDt_;Zk6t~(a6~>XFI(2pPZkDWv3P=RH!_Cc
zjMuLVxkdrW!aawzrBDJiul?TF0unXWDzrSvWNJ^eYW38-gH3*b0F00rx*w^tvVXPr
znBXs5<FIvf{HVvDG7FdzCP$b=^}C~yonxsFGOJso_5l!Z)1KNCsU_ssgsY9es`SA(
zzlsvi*R5uBLm7N9P1nv-2n6y7{jh-NWD-VKXsJs2WZB9mQ!T0lYd$1-^o3)K2{Zn3
z4Lo$b6U>9T#J9e#Q1I#q8^I|~**$&~)raP!0ks1N<IXY)l%5TNc05>oS~0&FP5dal
z#e+=0C~u}Eg<bm=12PvW%&RN=TK1#xWH<{LeNh?g@<1!K8nmewttSh-Ipg->8c)$J
z?Ln+QFPI&%YNGHB&5WGQ-J!|9&Xe3c|NEO0LPMI%n@3nb%3CJR!7XExtRxc!LO1Le
z=EU#AP;|i<j@;aJE*tN?VRGOZVAcdYTq=Y)OMJG<V0b7qcT*!=-w2qZ$Pd}(zHI`l
z#N2kfI4f>pn-48_2*0pG(hFmZ>{@NI;NPJE5jK+boBn0fWQj`!tm+1^AXTj5uaDHF
zkM>E;y%9mHb->4EYGeE3`KC#J7`GG5@_-VnzJHm8!995|7|nnbB=q((pM6OvTEbkw
zEF6c;Vk)z5xiq1B{_+chI{3)Pf&2DYv(zm~B4$WI&99=1Xd35>$g6~tksCXL`As)G
zP0F0@w{Wpj?C-&Ylf!QWZcFE5_M>g5^r&E^n#;(HrbV>Q)SbS48;l#o^_buL6YpoV
zgn%|eTf&?ipvK1Z(f-`h8yLn0&eH9k*QsXW6Vx@HXsozi5HpO2Sj++D)s0?+G8C#*
zjiShmdi2))6+mua9u-1;B?34`e?KSry`X*YXaMDm1f(6=YCyA6>V6E(3bSf=$%EzJ
z;wB7reh~O#wh+@*X&a2cRJ#60>mjW8>gmpls<EXxK8H6Qke?WthGk-x2b*LiELe!h
z2*uR6p_XR~VzC!GRd=0_p^0HcgO1%}KsJ3WV}cva1QYwVJ@hYD`aStgiyH>X<K%#!
zLV}!iz=~Sk$H71}bS9%PYYDEn!tG+Ph6BWLBUsu=sQczQWz1AaWO^AySpW-3vM$go
zC7pbBvGAm!j*uB_Fh>{~ZX80`2eC!*A)A~Ga3J2pm9^(}uf9b#>JA1Syb0x9R!Wf&
zu6TotGLEcr_oG{V=+V_h_1bd^EM*&2(WDhYziLcTso(vW{p7MN3B`qHFmqK?-Y3_C
zx@&Fy=hxB>=3pKf3IniN%k%ECC|-xR;3hBe?s%w*eOz3#(d&a>5u#t&|9pbC+%<mw
zqtPG}ns8Z!ZZ?%91pU97t~?&<t&Jb_w%j(kEf=}+ViIZYRZ1ZvONna4RG6eP`dCIT
z!dzjhw-hPMn2GFbNu;q8-kV}fsmLxyj4hd(Bw63*Ouhfk=b5uT>-nB@zQ4CORun@v
zud#u+MM{zlQD&U>aFFi|(`7^97Io>+*%u1cjZQ}RKL$WnicVC4XVp9!^rpO8i+}tD
zFjWgY-Tx~FmvI8UnCTYILPE1CBsrK6Gsn_swaB2N06^GOy^R-lO2eyBkV{#r+SL|y
zuC9<x2Hpi3$mr?GSEd<yS!XXxycTQ@9ZorZML|3so2b4e>{+K2q8z~vBFbqT`~rqz
zyApKlB?oITNwj!_*X~uDzQ{*3r=@S{{Z$r^Fh?2|Q|~Gqu`)cZ6nE~HLIDORFO!W#
zNiS!*m%p5u1sO^>(Bck`8pBtlft)v?z0R_jmr=5T*LTwcnqZz=I{AeSbpUnojtES0
zl%jb<azzD&optItmE>}0Sncx~W8C|<>|}Q?!Iz-62&IHU5@((PPb4T)TkOhPBOb$F
zONny^&9924|4hZ=wiFmXS-Q_SSZ6NHPp8T~4dz`lH#~GFIB8@EUq1pqBhr>9B~Ibp
zf4CQ9&<3%gQyrN394o_;xD~GQ=fE;ZlsW}yX7L2kPDJgoc>j+KwzND;qx=aU_zWi0
zGWcC}11YA|%_S%s{1JEEmY!@g&B#o4fKG5h!qkzIe^1Q6<xX4}bvT0cwgEy|cCuxg
zFlg_{5GxqhC2Ozhg4Q<9R;p0)7(tgj-X-Icj(Z#Tv`m5f9Ju?#n?L#IS}#Sy40_M0
z=X=Yt?oPN<aik`Hp70s&e^4POCk+Jx+-*ZFE+?dYlYdAdwTaulP98D?gyexi;|OQp
z&^>sNf`P)cNEo|jP1whfhT69E^`nVP@Z^N)p1#*{x#TMQtK_idaK!yOL^hrvy2E0d
zHJ*3CRX2HZ!pGd`JPrmV3!sNW>&BiwbD%Zks(WwJ=3{|9Q2OD$6OGJ`#~r2w-1&P2
zigmUbJsmeSEp1ooDnT2a?cc8A)R`BuI)A7+WlADux}fu|QK%#okMrJpwI4<(%-G0i
z!pGF;h@?w9xW$AtJ1TW6Xkz_v8ox>vx?skHFJH|HeC19^v`Lec9wYcA61Dcf6I;uM
z`i0`o*@$TO`F!}id#~%dzWT|}Iy90AB%*>RpefABg0>CL6jcbP<HBh+nk`o$u|M0t
zi1#-2P^OIz1rU)Gd_j@9d=DTF&3o-sh;vg*KnmHI>1CNHl?9VzmWk8Dz$!4DkGxJB
z<#nCSS-#Nj1E(%1CmzcGIM`bh9tkT1bA?I)mY>=kb<?Bl8+V;f|IEs0lM5=yR^D+{
zR6(Mguy=0MG9|g>BjkKZ%^)BIcSO4RnLC!uM1m~`<Ye4);->%g(=y2O;Po{T88jEZ
zOmaSJsM_HOG#0Sw;lC?0EYo277PRbBCLWvZRy;P7>iL4>glg`A*73A*S!7`5{ne>V
zr2I0IQrQfH{V8Q*e{!leL04RTzSY9~*ew`JsiKiGv8>V|+G;p%-#QhrP+Rab!QjrZ
zy=wlmy&|1+!foK!UK^e$n(`lBQM5>`cfz59%)rAlxme~A+Womt^cWZ}VGgA^P-&LY
zy;MiuJ-UYDk|b>ljD7cr@exz@U|y_mmZ}VszwFc3Xsz<>dI<G*TmXHb!Y4%G{obMb
zp~A-19Nq@LA9yc`rk`%T65}WLmDV_e_aN$WEcR%(mVbki^6WOn$&C<^nPF^r&5<Sl
z?Vd7SB7_U7fYOOv560x(3*y>@B5$?rU6azN!67BTgxaEI2DSd$5ald+m<I+-5T%wK
zw0~e6I^Jwq0-1oskbkXa?)m%M13v=<pf2F{nuA>}6$6b64ul8(zk|w|kB{!!W9q5Y
zeW1Mcp(pMd<0Qz|xMO#j&X=~A;@6x9&Rz36x|So2`v5NubXEbi;jyAxKL2zeEKWC`
zjqPdIxDIjCYQ+IwnLDkw&kCgVPBv~j757@z%-la$RjMl2WGM&(_Y5M<Tk%=hLwT_q
zhUiXDe?@vL%dL6p@S%XFaSOTi0(VKPSWrOJU$BY^J(tfe3GPv|+dY^LAoTUy921O<
zv`yq`L6U>0g=)4#GDGt&@A9sQYla>S^k;UdaVlj|ZJ(@s`;KFTMC(&>>6ht5yibKq
z3`%(Y{^g8wXSSAePrM<xXin0$E!N(^W7kv&+k03~K^)ix%AWW*deU2ztwrOp=RnNh
zRCB2tVbj>rT@Bb61AyuW)wlwT8he}L!KtgV*VZale)I$h7z)p?@hFBi&Q8t0{WY9$
z7W&nMPa7ffR)yah9jk1T?o^ns_vk(sC{;68l-JMF3M5$OFV>X=hZaDvkVb*1ZJfP%
zC^uHrItIoe2!?DDtreJcAQW!mV8g{^Dd-^mO;!+?hOYRTSZOSJMUD3G&G*3(XRJu|
z1a%l8#uX6F<?AgO@j!QxI3&FI;IUOVR8U)gzc7*;-^N;I7^AKZ7t~+_fY}{ULwDBO
zr`WF=x~e_c6S*5fjj?sTb(ZsQve?vCZ9BL9i#i;kW&DByY3$Npox%Iko5wjG(y6he
znd<?33JFkB$am~@+%^)g@g`NG9%P0WomDXxx?Py5yt7`*Xii0c-m2sYA_t#&@UJ^e
zFW=Bb_ty_d6pwGZA?7bJafzzR#16vts@_f2bi7n4W4=~ltUr}L)XPVlt?l|@e3*j;
zSbNTV9t_e6>RJ5V>+?=ty^E3wQr|E(q&-xeLzDieT(><117#T!QMa~BzKo!Gb4IKy
z4~1<h`}@(&aq|9a#d+$fQdUI30W^Rw9L^K!8ycgC98u))V4&G)9cNR&@D`!Erjc44
zLV$3hDbtgMgCGe%d;<!T3l*#46Qg^-U*L`zMY{${+0tP5sZ&X(%eSQ7!l!q5*;wkh
zZT><23-*FTA;s~#Yx>sC+QH2v%G)%*(l|$hdyL$vnSd^d>=G>NaDw|K<;66eTL~qB
zB>hSSqz#ipc4t!(X45ZdTikH*0cZ;z-ho2AwBQMi_-VPJ&W93h@krB0?>`LrNm7DF
zfCw|rrz?0nez0$P=y`#=9zvw#v=P<Nm3Z~+R~$Mgu9_ajaQCzHyY*d9MquviRxoaV
z@fbJ$sP^^5aPV_Y9FS^M#|$C~B4WGd_K>cvKg^wK4KP;1yR@tou4^_gW7I*@Ubsp_
zx49R)lEvefwOtIKCN62B6PXPd&b|`g!t$|yZh<!p_$@)+f50^a1-_bMe|JCr{_v6p
z4&VRaXzGf<#U!)qPy+X?Os6?DpBQN<zXIahfQ4e;yt2^A`t&&50f1kSh1p@#ynRlW
F{|9eO0Yv}+

literal 0
HcmV?d00001

diff --git a/ACI IoT Network Traffic Dataset Analysis/Model/.ipynb_checkpoints/ACI_IoT_Network_Traffic_Dataset_Analysis-checkpoint.ipynb b/ACI IoT Network Traffic Dataset Analysis/Model/.ipynb_checkpoints/ACI_IoT_Network_Traffic_Dataset_Analysis-checkpoint.ipynb
new file mode 100644
index 000000000..a6577c761
--- /dev/null
+++ b/ACI IoT Network Traffic Dataset Analysis/Model/.ipynb_checkpoints/ACI_IoT_Network_Traffic_Dataset_Analysis-checkpoint.ipynb	
@@ -0,0 +1,1977 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "YwuxWrIj26L7"
+   },
+   "source": [
+    "# ACI IoT Network Traffic"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "eA-t2jeQ2_Ay"
+   },
+   "source": [
+    "## Get dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "id": "f2-gDXPihjaF"
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import tensorflow as tf\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "D:\\ML\\ACI IoT Network Traffic Dataset Analysis\\Model\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "print(os.getcwd())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>srcip</th>\n",
+       "      <th>sport</th>\n",
+       "      <th>dstip</th>\n",
+       "      <th>dsport</th>\n",
+       "      <th>protocol_m</th>\n",
+       "      <th>sttl</th>\n",
+       "      <th>total_len</th>\n",
+       "      <th>payload</th>\n",
+       "      <th>stime</th>\n",
+       "      <th>label</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>192.168.1.81</td>\n",
+       "      <td>60683</td>\n",
+       "      <td>239.255.255.250</td>\n",
+       "      <td>1900</td>\n",
+       "      <td>udp</td>\n",
+       "      <td>2</td>\n",
+       "      <td>362</td>\n",
+       "      <td>4e4f54494659202a20485454502f312e310d0a4e54533a...</td>\n",
+       "      <td>1698670981</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>192.168.1.9</td>\n",
+       "      <td>53160</td>\n",
+       "      <td>239.255.255.250</td>\n",
+       "      <td>1900</td>\n",
+       "      <td>udp</td>\n",
+       "      <td>1</td>\n",
+       "      <td>204</td>\n",
+       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
+       "      <td>1698670984</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>192.168.1.9</td>\n",
+       "      <td>53160</td>\n",
+       "      <td>239.255.255.250</td>\n",
+       "      <td>1900</td>\n",
+       "      <td>udp</td>\n",
+       "      <td>1</td>\n",
+       "      <td>204</td>\n",
+       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
+       "      <td>1698670985</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>192.168.1.9</td>\n",
+       "      <td>53160</td>\n",
+       "      <td>239.255.255.250</td>\n",
+       "      <td>1900</td>\n",
+       "      <td>udp</td>\n",
+       "      <td>1</td>\n",
+       "      <td>204</td>\n",
+       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
+       "      <td>1698670986</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>192.168.1.9</td>\n",
+       "      <td>53160</td>\n",
+       "      <td>239.255.255.250</td>\n",
+       "      <td>1900</td>\n",
+       "      <td>udp</td>\n",
+       "      <td>1</td>\n",
+       "      <td>204</td>\n",
+       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
+       "      <td>1698670987</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          srcip  sport            dstip  dsport protocol_m  sttl  total_len  \\\n",
+       "0  192.168.1.81  60683  239.255.255.250    1900        udp     2        362   \n",
+       "1   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
+       "2   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
+       "3   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
+       "4   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
+       "\n",
+       "                                             payload       stime   label  \n",
+       "0  4e4f54494659202a20485454502f312e310d0a4e54533a...  1698670981  Benign  \n",
+       "1  4d2d534541524348202a20485454502f312e310d0a484f...  1698670984  Benign  \n",
+       "2  4d2d534541524348202a20485454502f312e310d0a484f...  1698670985  Benign  \n",
+       "3  4d2d534541524348202a20485454502f312e310d0a484f...  1698670986  Benign  \n",
+       "4  4d2d534541524348202a20485454502f312e310d0a484f...  1698670987  Benign  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.read_csv('D:\\ML\\ACI IoT Network Traffic Dataset Analysis\\Dataset\\ACI-IoT-2023-Payload.csv')\n",
+    "pd.set_option('display.max_columns', None)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "dW7fRPpahgGd"
+   },
+   "source": [
+    "## EDA"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "id": "t4ChRqiXsIZZ"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "srcip         0\n",
+       "sport         0\n",
+       "dstip         0\n",
+       "dsport        0\n",
+       "protocol_m    0\n",
+       "sttl          0\n",
+       "total_len     0\n",
+       "payload       0\n",
+       "stime         0\n",
+       "label         0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "id": "CxOR0kJM3SWR"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "label\n",
+       "Benign                601868\n",
+       "DNS Flood              18577\n",
+       "Dictionary Attack       4645\n",
+       "Slowloris               2974\n",
+       "SYN Flood               2113\n",
+       "Port Scan                582\n",
+       "Vulnerability Scan       445\n",
+       "OS Scan                  156\n",
+       "UDP Flood                 68\n",
+       "ICMP Flood                58\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.label.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "id": "mrlQp4My4faj"
+   },
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "labels = ['Benign', 'DNS Flood', 'Dictionary Attack', 'Slowloris', 'SYN Flood',\n",
+    "          'Port Scan', 'Vulnerability Scan', 'OS Scan', 'UDP Flood', 'ICMP Flood']\n",
+    "sizes = [601868, 18577, 4645, 2974, 2113, 582, 445, 156, 68, 58]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "id": "Actc2Dc-4l4W"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABAcAAAJ3CAYAAADoNji5AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy80BEi2AAAACXBIWXMAAA9hAAAPYQGoP6dpAACcM0lEQVR4nOzdeZyN9f//8eeZGTNjm8U2Y1/Lvq9DSGESIktIkVQfhSzJkhJRirTI1q5NEWVfI0tIItklS0RjiZmxzYyZef3+8Jvr60ShcIzrcb/d5lbnut7nnNe5nHOd63qe9/V+e8zMBAAAAAAAXMvP1wUAAAAAAADfIhwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAuEyDBw+Wx+PR0aNHfV0KAABXFeEAAADQxIkT5fF4vP5y5cqlevXqad68ede9nlmzZqlp06aKiIhQYGCgsmXLpjp16mjUqFGKj4+/7vUAAHCzC/B1AQAA4MbxwgsvqHDhwjIzHTp0SBMnTtTdd9+tWbNmqUmTJtf8+VNTU9W5c2dNnDhRZcuW1RNPPKH8+fPrxIkTWr16tZ599lnNnTtXixcvvua1AADgJoQDAADA0ahRI1WpUsW53blzZ0VEROjzzz+/KuFAamqqkpKSFBwcfNH1I0aM0MSJE9WrVy+NGjVKHo/HWdejRw/98ccf+vjjj//TcwAAgAtxWQEAAPhbYWFhypgxowICvH9PePXVV1WzZk1lz55dGTNmVOXKlTV16tQL7u/xeNStWzd99tlnKl26tIKCgjR//vyLPtfp06f1yiuvqHTp0ho5cqRXMJAmd+7c6tev32U/x7+ps3jx4goODlblypW1fPnyi9YaGxurhx56SGFhYQoNDVWnTp10+vTpi29EAADSAXoOAAAAR1xcnI4ePSoz0+HDh/XWW2/p5MmTeuCBB7zavfnmm7rnnnvUvn17JSUl6YsvvlDr1q01e/ZsNW7c2KvtkiVLNGXKFHXr1k05cuRQoUKFLvrc3333nWJjY9WnTx/5+/tfUd1/9xxXUueyZcs0efJkPfnkkwoKCtK4ceN011136YcfflCZMmW82t53330qXLiwhg8frvXr1+u9995Trly59Morr1xR3QAA3Cg8Zma+LgIAAPjWxIkT1alTpwuWBwUF6e2331bHjh29lp85c0YZM2Z0bp89e1aVKlVSrly5vMYD8Hg88vPz06ZNm1SqVKl/rGH06NHq0aOHpk+frmbNmjnLU1JSdPz4ca+22bNnd3oW/NNzXEmdkvTjjz+qcuXKkqR9+/apePHiatSokb766itJ52YrGDJkiB5++GG9//77zv1btGih5cuXM4sBACDdoucAAABwjB07Vrfeeqsk6dChQ/r000/1yCOPKGvWrGrRooXT7vwT7uPHjyslJUW1a9fW559/fsFj1q1b95LBgCRnFoIsWbJ4Ld+0aZMqVqzotezIkSPKkSPHJZ/jSuqMiopyggFJKlCggJo1a6ZZs2YpJSXFqzdDly5dvO5bu3Ztff3114qPj1dISMglXysAADcawgEAAOCoVq2a14CE7dq1U8WKFdWtWzc1adJEgYGBkqTZs2dr2LBh2rBhgxITE532FxsnoHDhwpf13FmzZpUknTx50mt5sWLFtGjRIknSxx9/rE8++eSyn+NK6rzlllsuWHbrrbfq9OnTOnLkiCIjI53lBQoU8GoXHh4u6VwAQTgAAEiPGJAQAAD8LT8/P9WrV09//PGHdu7cKUlasWKF7rnnHgUHB2vcuHGaO3euFi1apPvvv18Xu1rx/F/v/0mJEiUkSZs3b/ZaniVLFtWvX1/169dXkSJFLnrfiz3HldZ5Jf5uTASu1gQApFf0HAAAAP8oOTlZ0v/9oj9t2jQFBwdrwYIFCgoKctp9+OGH/+l5ateurdDQUH3xxRcaMGCA/Pz+228YV1pnWvhxvl9++UWZMmVSzpw5/1MtAADc6Og5AAAA/tbZs2e1cOFCBQYGqmTJkpLO/Wru8XiUkpLitNu7d6+mT5/+n54rU6ZM6tu3rzZv3qz+/ftf9Ff4K/ll/krrXL16tdavX+/c3r9/v2bMmKGGDRte8ewJAACkN/QcAAAAjnnz5mn79u2SpMOHD2vSpEnauXOn+vfv71xL37hxY7322mu66667dP/99+vw4cMaO3asihUrpo0bN/6n5+/fv7+2bdumkSNHauHChWrZsqXy5cun48ePa/369fryyy+VK1cuBQcHX/KxrrTOMmXKKDo62msqQ0kaMmTIf3pNAACkB4QDAADAMWjQIOf/g4ODVaJECY0fP17/+9//nOV33HGH3n//fb388svq2bOnChcurFdeeUV79+79z+GAn5+fPvnkE7Vs2VLvvvuu3nrrLR0/flxZsmRRmTJl9OKLL+rRRx+9YEaDi7nSOuvWrauoqCgNGTJE+/btU6lSpTRx4kSVK1fuP70mAADSA48xcg4AAHA5j8ejrl27asyYMb4uBQAAn2DMAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5RiQEAAAuB5DMAEA3I6eAwAAAAAAuBw9B66j1NRUHTx4UFmzZpXH4/F1OQAAAACAm5yZ6cSJE8qTJ4/8/P6+fwDhwHV08OBB5c+f39dlAAAAAABcZv/+/cqXL9/friccuI6yZs0q6dw/SkhIiI+rAQAAAADc7OLj45U/f37nfPTvEA5cR2mXEoSEhBAOAAAAAACum0td2s6AhAAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4nM/DgQMHDuiBBx5Q9uzZlTFjRpUtW1Y//vijs97MNGjQIOXOnVsZM2ZU/fr1tXPnTq/HOHbsmNq3b6+QkBCFhYWpc+fOOnnypFebjRs3qnbt2goODlb+/Pk1YsSIC2r58ssvVaJECQUHB6ts2bKaO3eu1/rLqQUAAAAAgPTGp+HA8ePHVatWLWXIkEHz5s3T1q1bNWrUKIWHhzttRowYodGjR2vChAlas2aNMmfOrOjoaCUkJDht2rdvry1btmjRokWaPXu2li9frscee8xZHx8fr4YNG6pgwYJat26dRo4cqcGDB+udd95x2qxatUrt2rVT586d9dNPP6l58+Zq3ry5Nm/efEW1AAAAAACQ3njMzHz15P3799fKlSu1YsWKi643M+XJk0dPPfWU+vTpI0mKi4tTRESEJk6cqLZt22rbtm0qVaqU1q5dqypVqkiS5s+fr7vvvlu///678uTJo/Hjx2vgwIGKiYlRYGCg89zTp0/X9u3bJUlt2rTRqVOnNHv2bOf5a9SooQoVKmjChAmXVculxMfHKzQ0VHFxcQoJCfn3G+46KNR/jq9LuOHsfbmxr0sAAAAAgCtyueehPu05MHPmTFWpUkWtW7dWrly5VLFiRb377rvO+j179igmJkb169d3loWGhqp69epavXq1JGn16tUKCwtzggFJql+/vvz8/LRmzRqnTZ06dZxgQJKio6O1Y8cOHT9+3Glz/vOktUl7nsup5a8SExMVHx/v9QcAAAAAwI3Gp+HA7t27NX78eN1yyy1asGCBHn/8cT355JP66KOPJEkxMTGSpIiICK/7RUREOOtiYmKUK1cur/UBAQHKli2bV5uLPcb5z/F3bc5ff6la/mr48OEKDQ11/vLnz3+pTQIAAAAAwHXn03AgNTVVlSpV0ksvvaSKFSvqscce06OPPqoJEyb4sqyrZsCAAYqLi3P+9u/f7+uSAAAAAAC4gE/Dgdy5c6tUqVJey0qWLKl9+/ZJkiIjIyVJhw4d8mpz6NAhZ11kZKQOHz7stT45OVnHjh3zanOxxzj/Of6uzfnrL1XLXwUFBSkkJMTrDwAAAACAG41Pw4FatWppx44dXst++eUXFSxYUJJUuHBhRUZGavHixc76+Ph4rVmzRlFRUZKkqKgoxcbGat26dU6bJUuWKDU1VdWrV3faLF++XGfPnnXaLFq0SMWLF3dmRoiKivJ6nrQ2ac9zObUAAAAAAJAe+TQc6NWrl77//nu99NJL+vXXXzVp0iS988476tq1qyTJ4/GoZ8+eGjZsmGbOnKlNmzapQ4cOypMnj5o3by7pXE+Du+66S48++qh++OEHrVy5Ut26dVPbtm2VJ08eSdL999+vwMBAde7cWVu2bNHkyZP15ptvqnfv3k4tPXr00Pz58zVq1Cht375dgwcP1o8//qhu3bpddi0AAAAAAKRHAb588qpVq+rrr7/WgAED9MILL6hw4cJ644031L59e6dN3759derUKT322GOKjY3Vbbfdpvnz5ys4ONhp89lnn6lbt26688475efnp5YtW2r06NHO+tDQUC1cuFBdu3ZV5cqVlSNHDg0aNEiPPfaY06ZmzZqaNGmSnn32WT3zzDO65ZZbNH36dJUpU+aKagEAAAAAIL3xmJn5ugi3uNz5JW8EhfrP8XUJN5y9Lzf2dQkAAAAAcEUu9zzUp5cVAAAAAAAA3yMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5XwaDgwePFgej8frr0SJEs76hIQEde3aVdmzZ1eWLFnUsmVLHTp0yOsx9u3bp8aNGytTpkzKlSuXnn76aSUnJ3u1Wbp0qSpVqqSgoCAVK1ZMEydOvKCWsWPHqlChQgoODlb16tX1ww8/eK2/nFoAAAAAAEiPfN5zoHTp0vrjjz+cv++++85Z16tXL82aNUtffvmlli1bpoMHD6pFixbO+pSUFDVu3FhJSUlatWqVPvroI02cOFGDBg1y2uzZs0eNGzdWvXr1tGHDBvXs2VOPPPKIFixY4LSZPHmyevfureeff17r169X+fLlFR0drcOHD192LQAAAAAApFceMzNfPfngwYM1ffp0bdiw4YJ1cXFxypkzpyZNmqRWrVpJkrZv366SJUtq9erVqlGjhubNm6cmTZro4MGDioiIkCRNmDBB/fr105EjRxQYGKh+/fppzpw52rx5s/PYbdu2VWxsrObPny9Jql69uqpWraoxY8ZIklJTU5U/f351795d/fv3v6xaLkd8fLxCQ0MVFxenkJCQf73drodC/ef4uoQbzt6XG/u6BAAAAAC4Ipd7HurzngM7d+5Unjx5VKRIEbVv31779u2TJK1bt05nz55V/fr1nbYlSpRQgQIFtHr1aknS6tWrVbZsWScYkKTo6GjFx8dry5YtTpvzHyOtTdpjJCUlad26dV5t/Pz8VL9+fafN5dRyMYmJiYqPj/f6AwAAAADgRuPTcKB69eqaOHGi5s+fr/Hjx2vPnj2qXbu2Tpw4oZiYGAUGBiosLMzrPhEREYqJiZEkxcTEeAUDaevT1v1Tm/j4eJ05c0ZHjx5VSkrKRduc/xiXquVihg8frtDQUOcvf/78l7dhAAAAAAC4jgJ8+eSNGjVy/r9cuXKqXr26ChYsqClTpihjxow+rOzqGDBggHr37u3cjo+PJyAAAAAAANxwfH5ZwfnCwsJ066236tdff1VkZKSSkpIUGxvr1ebQoUOKjIyUJEVGRl4wY0Da7Uu1CQkJUcaMGZUjRw75+/tftM35j3GpWi4mKChIISEhXn8AAAAAANxobqhw4OTJk9q1a5dy586typUrK0OGDFq8eLGzfseOHdq3b5+ioqIkSVFRUdq0aZPXrAKLFi1SSEiISpUq5bQ5/zHS2qQ9RmBgoCpXruzVJjU1VYsXL3baXE4tAAAAAACkVz69rKBPnz5q2rSpChYsqIMHD+r555+Xv7+/2rVrp9DQUHXu3Fm9e/dWtmzZFBISou7duysqKsqZHaBhw4YqVaqUHnzwQY0YMUIxMTF69tln1bVrVwUFBUmSunTpojFjxqhv3756+OGHtWTJEk2ZMkVz5vzfaPy9e/dWx44dVaVKFVWrVk1vvPGGTp06pU6dOknSZdUCAAAAAEB65dNw4Pfff1e7du30559/KmfOnLrtttv0/fffK2fOnJKk119/XX5+fmrZsqUSExMVHR2tcePGOff39/fX7Nmz9fjjjysqKkqZM2dWx44d9cILLzhtChcurDlz5qhXr1568803lS9fPr333nuKjo522rRp00ZHjhzRoEGDFBMTowoVKmj+/PlegxReqhYAAAAAANIrj5mZr4twi8udX/JGUKj/nEs3cpm9Lzf2dQkAAAAAcEUu9zz0hhpzAAAAAAAAXH+EAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuNwNEw68/PLL8ng86tmzp7MsISFBXbt2Vfbs2ZUlSxa1bNlShw4d8rrfvn371LhxY2XKlEm5cuXS008/reTkZK82S5cuVaVKlRQUFKRixYpp4sSJFzz/2LFjVahQIQUHB6t69er64YcfvNZfTi0AAAAAAKRHN0Q4sHbtWr399tsqV66c1/JevXpp1qxZ+vLLL7Vs2TIdPHhQLVq0cNanpKSocePGSkpK0qpVq/TRRx9p4sSJGjRokNNmz549aty4serVq6cNGzaoZ8+eeuSRR7RgwQKnzeTJk9W7d289//zzWr9+vcqXL6/o6GgdPnz4smsBAAAAACC98piZ+bKAkydPqlKlSho3bpyGDRumChUq6I033lBcXJxy5sypSZMmqVWrVpKk7du3q2TJklq9erVq1KihefPmqUmTJjp48KAiIiIkSRMmTFC/fv105MgRBQYGql+/fpozZ442b97sPGfbtm0VGxur+fPnS5KqV6+uqlWrasyYMZKk1NRU5c+fX927d1f//v0vq5bLER8fr9DQUMXFxSkkJOSqbcNroVD/Ob4u4Yaz9+XGvi4BAAAAAK7I5Z6H+rznQNeuXdW4cWPVr1/fa/m6det09uxZr+UlSpRQgQIFtHr1aknS6tWrVbZsWScYkKTo6GjFx8dry5YtTpu/PnZ0dLTzGElJSVq3bp1XGz8/P9WvX99pczm1XExiYqLi4+O9/gAAAAAAuNEE+PLJv/jiC61fv15r1669YF1MTIwCAwMVFhbmtTwiIkIxMTFOm/ODgbT1aev+qU18fLzOnDmj48ePKyUl5aJttm/fftm1XMzw4cM1ZMiQv10PAAAAAMCNwGc9B/bv368ePXros88+U3BwsK/KuKYGDBiguLg452///v2+LgkAAAAAgAv4LBxYt26dDh8+rEqVKikgIEABAQFatmyZRo8erYCAAEVERCgpKUmxsbFe9zt06JAiIyMlSZGRkRfMGJB2+1JtQkJClDFjRuXIkUP+/v4XbXP+Y1yqlosJCgpSSEiI1x8AAAAAADcan4UDd955pzZt2qQNGzY4f1WqVFH79u2d/8+QIYMWL17s3GfHjh3at2+foqKiJElRUVHatGmT16wCixYtUkhIiEqVKuW0Of8x0tqkPUZgYKAqV67s1SY1NVWLFy922lSuXPmStQAAAAAAkF75bMyBrFmzqkyZMl7LMmfOrOzZszvLO3furN69eytbtmwKCQlR9+7dFRUV5cwO0LBhQ5UqVUoPPvigRowYoZiYGD377LPq2rWrgoKCJEldunTRmDFj1LdvXz388MNasmSJpkyZojlz/m80/t69e6tjx46qUqWKqlWrpjfeeEOnTp1Sp06dJEmhoaGXrAUAAAAAgPTKpwMSXsrrr78uPz8/tWzZUomJiYqOjta4ceOc9f7+/po9e7Yef/xxRUVFKXPmzOrYsaNeeOEFp03hwoU1Z84c9erVS2+++aby5cun9957T9HR0U6bNm3a6MiRIxo0aJBiYmJUoUIFzZ8/32uQwkvVAgAAAABAeuUxM/N1EW5xufNL3ggK9Z9z6UYus/flxr4uAQAAAACuyOWeh/pszAEAAAAAAHBjIBwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACX+1fhQJEiRfTnn39esDw2NlZFihT5z0UBAAAAAIDr51+FA3v37lVKSsoFyxMTE3XgwIH/XBQAAAAAALh+Aq6k8cyZM53/X7BggUJDQ53bKSkpWrx4sQoVKnTVigMAAAAAANfeFYUDzZs3lyR5PB517NjRa12GDBlUqFAhjRo16qoVBwAAAAAArr0rCgdSU1MlSYULF9batWuVI0eOa1IUAAAAAAC4fq4oHEizZ8+eq10HAAAAAADwkX8VDkjS4sWLtXjxYh0+fNjpUZDmgw8++M+FAQAAAACA6+NfhQNDhgzRCy+8oCpVqih37tzyeDxXuy4AAAAAAHCd/KtwYMKECZo4caIefPDBq10PAAAAAAC4zvz+zZ2SkpJUs2bNq10LAAAAAADwgX8VDjzyyCOaNGnS1a4FAAAAAAD4wL+6rCAhIUHvvPOOvvnmG5UrV04ZMmTwWv/aa69dleIAAAAAAMC196/CgY0bN6pChQqSpM2bN3utY3BCAAAAAADSl38VDnz77bdXuw4AAAAAAOAj/2rMAQAAAAAAcPP4Vz0H6tWr94+XDyxZsuRfFwQAAAAAAK6vfxUOpI03kObs2bPasGGDNm/erI4dO16NugAAAAAAwHXyr8KB119//aLLBw8erJMnT/6nggAAAAAAwPV1VccceOCBB/TBBx9czYcEAAAAAADX2FUNB1avXq3g4OCr+ZAAAAAAAOAa+1eXFbRo0cLrtpnpjz/+0I8//qjnnnvuqhQGAAAAAACuj38VDoSGhnrd9vPzU/HixfXCCy+oYcOGV6UwAAAAAABwffyrcODDDz+82nUAAAAAAAAf+VfhQJp169Zp27ZtkqTSpUurYsWKV6UoAAAAAABw/fyrcODw4cNq27atli5dqrCwMElSbGys6tWrpy+++EI5c+a8mjUCAAAAAIBr6F/NVtC9e3edOHFCW7Zs0bFjx3Ts2DFt3rxZ8fHxevLJJ692jQAAAAAA4Br6V+HA/PnzNW7cOJUsWdJZVqpUKY0dO1bz5s277McZP368ypUrp5CQEIWEhCgqKsrr/gkJCeratauyZ8+uLFmyqGXLljp06JDXY+zbt0+NGzdWpkyZlCtXLj399NNKTk72arN06VJVqlRJQUFBKlasmCZOnHhBLWPHjlWhQoUUHBys6tWr64cffvBafzm1AAAAAACQHv2rcCA1NVUZMmS4YHmGDBmUmpp62Y+TL18+vfzyy1q3bp1+/PFH3XHHHWrWrJm2bNkiSerVq5dmzZqlL7/8UsuWLdPBgwe9plFMSUlR48aNlZSUpFWrVumjjz7SxIkTNWjQIKfNnj171LhxY9WrV08bNmxQz5499cgjj2jBggVOm8mTJ6t37956/vnntX79epUvX17R0dE6fPiw0+ZStQAAAAAAkF55zMyu9E7NmjVTbGysPv/8c+XJk0eSdODAAbVv317h4eH6+uuv/3VB2bJl08iRI9WqVSvlzJlTkyZNUqtWrSRJ27dvV8mSJbV69WrVqFFD8+bNU5MmTXTw4EFFRERIkiZMmKB+/frpyJEjCgwMVL9+/TRnzhxt3rzZeY62bdsqNjZW8+fPlyRVr15dVatW1ZgxYySdCz/y58+v7t27q3///oqLi7tkLReTmJioxMRE53Z8fLzy58+vuLg4hYSE/OttdD0U6j/H1yXccPa+3NjXJQAAAADAFYmPj1doaOglz0P/Vc+BMWPGKD4+XoUKFVLRokVVtGhRFS5cWPHx8Xrrrbf+VcEpKSn64osvdOrUKUVFRWndunU6e/as6tev77QpUaKEChQooNWrV0uSVq9erbJlyzrBgCRFR0crPj7e6X2wevVqr8dIa5P2GElJSVq3bp1XGz8/P9WvX99pczm1XMzw4cMVGhrq/OXPn/9fbRsAAAAAAK6lfzVbQf78+bV+/Xp988032r59uySpZMmSF5yEX45NmzYpKipKCQkJypIli77++muVKlVKGzZsUGBgoDMbQpqIiAjFxMRIkmJiYryCgbT1aev+qU18fLzOnDmj48ePKyUl5aJt0l5bTEzMJWu5mAEDBqh3797O7bSeAwAAAAAA3EiuKBxYsmSJunXrpu+//14hISFq0KCBGjRoIEmKi4tT6dKlNWHCBNWuXfuyH7N48eLasGGD4uLiNHXqVHXs2FHLli27sldxgwoKClJQUJCvywAAAAAA4B9d0WUFb7zxhh599NGLXqcQGhqq//3vf3rttdeuqIDAwEAVK1ZMlStX1vDhw1W+fHm9+eabioyMVFJSkmJjY73aHzp0SJGRkZKkyMjIC2YMSLt9qTYhISHKmDGjcuTIIX9//4u2Of8xLlULAAAAAADp1RWFAz///LPuuuuuv13fsGFDrVu37j8VlJqaqsTERFWuXFkZMmTQ4sWLnXU7duzQvn37FBUVJUmKiorSpk2bvGYVWLRokUJCQlSqVCmnzfmPkdYm7TECAwNVuXJlrzapqalavHix0+ZyagEAAAAAIL26ossKDh06dNEpDJ0HCwjQkSNHLvvxBgwYoEaNGqlAgQI6ceKEJk2apKVLl2rBggUKDQ1V586d1bt3b2XLlk0hISHq3r27oqKinNkBGjZsqFKlSunBBx/UiBEjFBMTo2effVZdu3Z1uvN36dJFY8aMUd++ffXwww9ryZIlmjJliubM+b/R+Hv37q2OHTuqSpUqqlatmt544w2dOnVKnTp1kqTLqgUAAAAAgPTqisKBvHnzavPmzSpWrNhF12/cuFG5c+e+7Mc7fPiwOnTooD/++EOhoaEqV66cFixY4Ixj8Prrr8vPz08tW7ZUYmKioqOjNW7cOOf+/v7+mj17th5//HFFRUUpc+bM6tixo1544QWnTeHChTVnzhz16tVLb775pvLly6f33ntP0dHRTps2bdroyJEjGjRokGJiYlShQgXNnz/fa5DCS9UCAAAAAEB65TEzu9zG3bt319KlS7V27VoFBwd7rTtz5oyqVaumevXqafTo0Ve90JvB5c4veSMo1H/OpRu5zN6XG/u6BAAAAAC4Ipd7HnpFPQeeffZZffXVV7r11lvVrVs3FS9eXJK0fft2jR07VikpKRo4cOB/qxwAAAAAAFxXVxQOREREaNWqVXr88cc1YMAApXU68Hg8io6O1tixY7264gMAAAAAgBvfFYUDklSwYEHNnTtXx48f16+//ioz0y233KLw8PBrUR8AAAAAALjGrjgcSBMeHq6qVatezVoAAAAAAIAP+Pm6AAAAAAAA4FuEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALicT8OB4cOHq2rVqsqaNaty5cql5s2ba8eOHV5tEhIS1LVrV2XPnl1ZsmRRy5YtdejQIa82+/btU+PGjZUpUyblypVLTz/9tJKTk73aLF26VJUqVVJQUJCKFSumiRMnXlDP2LFjVahQIQUHB6t69er64YcfrrgWAAAAAADSG5+GA8uWLVPXrl31/fffa9GiRTp79qwaNmyoU6dOOW169eqlWbNm6csvv9SyZct08OBBtWjRwlmfkpKixo0bKykpSatWrdJHH32kiRMnatCgQU6bPXv2qHHjxqpXr542bNignj176pFHHtGCBQucNpMnT1bv3r31/PPPa/369Spfvryio6N1+PDhy64FAAAAAID0yGNm5usi0hw5ckS5cuXSsmXLVKdOHcXFxSlnzpyaNGmSWrVqJUnavn27SpYsqdWrV6tGjRqaN2+emjRpooMHDyoiIkKSNGHCBPXr109HjhxRYGCg+vXrpzlz5mjz5s3Oc7Vt21axsbGaP3++JKl69eqqWrWqxowZI0lKTU1V/vz51b17d/Xv3/+yavmrxMREJSYmOrfj4+OVP39+xcXFKSQk5NpsxKukUP85vi7hhrP35ca+LgEAAAAArkh8fLxCQ0MveR56Q405EBcXJ0nKli2bJGndunU6e/as6tev77QpUaKEChQooNWrV0uSVq9erbJlyzrBgCRFR0crPj5eW7Zscdqc/xhpbdIeIykpSevWrfNq4+fnp/r16zttLqeWvxo+fLhCQ0Odv/z58/+7DQMAAAAAwDV0w4QDqamp6tmzp2rVqqUyZcpIkmJiYhQYGKiwsDCvthEREYqJiXHanB8MpK1PW/dPbeLj43XmzBkdPXpUKSkpF21z/mNcqpa/GjBggOLi4py//fv3X+bWAAAAAADg+gnwdQFpunbtqs2bN+u7777zdSlXTVBQkIKCgnxdBgAAAAAA/+iG6DnQrVs3zZ49W99++63y5cvnLI+MjFRSUpJiY2O92h86dEiRkZFOm7/OGJB2+1JtQkJClDFjRuXIkUP+/v4XbXP+Y1yqFgAAAAAA0iOfhgNmpm7duunrr7/WkiVLVLhwYa/1lStXVoYMGbR48WJn2Y4dO7Rv3z5FRUVJkqKiorRp0yavWQUWLVqkkJAQlSpVymlz/mOktUl7jMDAQFWuXNmrTWpqqhYvXuy0uZxaAAAAAABIj3x6WUHXrl01adIkzZgxQ1mzZnWu3Q8NDVXGjBkVGhqqzp07q3fv3sqWLZtCQkLUvXt3RUVFObMDNGzYUKVKldKDDz6oESNGKCYmRs8++6y6du3qdOnv0qWLxowZo759++rhhx/WkiVLNGXKFM2Z838j8vfu3VsdO3ZUlSpVVK1aNb3xxhs6deqUOnXq5NR0qVoAAAAAAEiPfBoOjB8/XpJ0++23ey3/8MMP9dBDD0mSXn/9dfn5+ally5ZKTExUdHS0xo0b57T19/fX7Nmz9fjjjysqKkqZM2dWx44d9cILLzhtChcurDlz5qhXr1568803lS9fPr333nuKjo522rRp00ZHjhzRoEGDFBMTowoVKmj+/PlegxReqhYAAAAAANIjj5mZr4twi8udX/JGUKj/nEs3cpm9Lzf2dQkAAAAAcEUu9zz0hhiQEAAAAAAA+A7hAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALufTcGD58uVq2rSp8uTJI4/Ho+nTp3utNzMNGjRIuXPnVsaMGVW/fn3t3LnTq82xY8fUvn17hYSEKCwsTJ07d9bJkye92mzcuFG1a9dWcHCw8ufPrxEjRlxQy5dffqkSJUooODhYZcuW1dy5c6+4FgAAAAAA0iOfhgOnTp1S+fLlNXbs2IuuHzFihEaPHq0JEyZozZo1ypw5s6Kjo5WQkOC0ad++vbZs2aJFixZp9uzZWr58uR577DFnfXx8vBo2bKiCBQtq3bp1GjlypAYPHqx33nnHabNq1Sq1a9dOnTt31k8//aTmzZurefPm2rx58xXVAgAAAABAeuQxM/N1EZLk8Xj09ddfq3nz5pLO/VKfJ08ePfXUU+rTp48kKS4uThEREZo4caLatm2rbdu2qVSpUlq7dq2qVKkiSZo/f77uvvtu/f7778qTJ4/Gjx+vgQMHKiYmRoGBgZKk/v37a/r06dq+fbskqU2bNjp16pRmz57t1FOjRg1VqFBBEyZMuKxaLiYxMVGJiYnO7fj4eOXPn19xcXEKCQm5uhvwKivUf46vS7jh7H25sa9LAAAAAIArEh8fr9DQ0Eueh96wYw7s2bNHMTExql+/vrMsNDRU1atX1+rVqyVJq1evVlhYmBMMSFL9+vXl5+enNWvWOG3q1KnjBAOSFB0drR07duj48eNOm/OfJ61N2vNcTi0XM3z4cIWGhjp/+fPn/7ebAwAAAACAa+aGDQdiYmIkSREREV7LIyIinHUxMTHKlSuX1/qAgABly5bNq83FHuP85/i7Nuevv1QtFzNgwADFxcU5f/v377/EqwYAAAAA4PoL8HUBN7OgoCAFBQX5ugwAAAAAAP7RDdtzIDIyUpJ06NAhr+WHDh1y1kVGRurw4cNe65OTk3Xs2DGvNhd7jPOf4+/anL/+UrUAAAAAAJBe3bDhQOHChRUZGanFixc7y+Lj47VmzRpFRUVJkqKiohQbG6t169Y5bZYsWaLU1FRVr17dabN8+XKdPXvWabNo0SIVL15c4eHhTpvznyetTdrzXE4tAAAAAACkVz4NB06ePKkNGzZow4YNks4N/Ldhwwbt27dPHo9HPXv21LBhwzRz5kxt2rRJHTp0UJ48eZwZDUqWLKm77rpLjz76qH744QetXLlS3bp1U9u2bZUnTx5J0v3336/AwEB17txZW7Zs0eTJk/Xmm2+qd+/eTh09evTQ/PnzNWrUKG3fvl2DBw/Wjz/+qG7duknSZdUCAAAAAEB65dMxB3788UfVq1fPuZ12wt6xY0dNnDhRffv21alTp/TYY48pNjZWt912m+bPn6/g4GDnPp999pm6deumO++8U35+fmrZsqVGjx7trA8NDdXChQvVtWtXVa5cWTly5NCgQYP02GOPOW1q1qypSZMm6dlnn9UzzzyjW265RdOnT1eZMmWcNpdTCwAAAAAA6ZHHzMzXRbjF5c4veSMo1H+Or0u44ex9ubGvSwAAAACAK3K556E37JgDAAAAAADg+iAcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcLsDXBQBuUqj/HF+XcMPZ+3JjX5cAAAAAuB49BwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHC5AF8XkN6MHTtWI0eOVExMjMqXL6+33npL1apV83VZgOsV6j/H1yXccPa+3NjXJQAAACCdIBy4ApMnT1bv3r01YcIEVa9eXW+88Yaio6O1Y8cO5cqVy9flAcBVR+hyIUIXAABwMyIcuAKvvfaaHn30UXXq1EmSNGHCBM2ZM0cffPCB+vfvf0H7xMREJSYmOrfj4uIkSfHx8den4P8gNfG0r0u44VyNfze264Wu1ueBbXsh3rPXxtXYrmWeX3AVKrm5bB4S7esSAAC4KaUdu5jZP7bz2KVaQJKUlJSkTJkyaerUqWrevLmzvGPHjoqNjdWMGTMuuM/gwYM1ZMiQ61glAAAAAAAX2r9/v/Lly/e36+k5cJmOHj2qlJQURUREeC2PiIjQ9u3bL3qfAQMGqHfv3s7t1NRUHTt2TNmzZ5fH47mm9d4s4uPjlT9/fu3fv18hISG+LuemwXa9Ntiu1wbb9dph214bbNdrg+167bBtrw2267XBdr1yZqYTJ04oT548/9iOcOAaCgoKUlBQkNeysLAw3xSTzoWEhPDhvwbYrtcG2/XaYLteO2zba4Ptem2wXa8dtu21wXa9NtiuVyY0NPSSbZjK8DLlyJFD/v7+OnTokNfyQ4cOKTIy0kdVAQAAAADw3xEOXKbAwEBVrlxZixcvdpalpqZq8eLFioqK8mFlAAAAAAD8N1xWcAV69+6tjh07qkqVKqpWrZreeOMNnTp1ypm9AFdfUFCQnn/++Qsuz8B/w3a9Ntiu1wbb9dph214bbNdrg+167bBtrw2267XBdr12mK3gCo0ZM0YjR45UTEyMKlSooNGjR6t69eq+LgsAAAAAgH+NcAAAAAAAAJdjzAEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQD/yeLFi3XmzBlfl4F/wLizuNbGjRunxYsXKzU11delAMBNZ+TIkXrwwQd9XcZN7ZtvvvF1CTcEwgEA/9qKFSvUtWtXDRgwQAkJCb4uBxdhZvJ4PJKkAwcO+Lga3KzGjRunhx56SCtXriQguEYI+W5cF3vP8++Fqylv3ryaPHmyunXr5utSbko//fSTGjZsqCeffNLXpfgc4QCAf61y5cpq3bq11qxZowEDBtCD4AaTkpLiBAOvvvqqnnnmGUnuO2hNe72//fab/vjjDx9Xc3NJ27abN29W0aJF1aFDB61YsULJyck+riz9S9u2f/75p06dOuV8lnFjSU1NlZ/fucPp3377TUePHnX2vSkpKT6uDjeL++67T1988YU+/vhjPf74474u56ZTqFAhjR07VpMnT1aPHj18XY5PEQ7gpnCx1J5fr66t5ORkZcqUSUOHDtVdd92ljRs36vnnn1diYqKvS3O9Tp06aeXKlfL393dO0jZt2qQiRYpIclc4kNZzYvr06WrTpo1mz56t2NhYX5d10/B4PEpKSpJ0rktmWFiY+vbtq++++44To/8o7X17zz33qHz58nruuee0bt06X5eFv0gLBp577jnVq1dP9erVU5s2bZSYmCh/f/+b+nOQ9l2yZcsWzZkzR7t37+ZHgqvMzGRmCggIUNmyZfXSSy/p7bffdsJ+/HdmpvDwcP3vf//T8OHDNXnyZD377LO+LstnCAeQ7p2f2n/zzTeaOXOmNm/e7CzDteHv7y9J+vHHH5WQkKD9+/fr7bff1uDBg7nEwId+//13/f7772rVqpXWrl2rgIAASdLBgwcVFBQkSa76bHg8Hs2cOVP333+/7rvvPjVp0kRhYWG+LuumYWYKDAzU5MmT9dBDDylXrlxau3atunTpwiUG/9FPP/2khx9+WHfffbeaN2+uuXPn6sUXX9SyZct8XRrk/QPEV199pXfeeUfDhw/XAw88oN9++00VK1ZUQkLCTR0QeDweTZs2TbfffrseffRR3XHHHRo+fDg9tK4ij8cjj8ejr776So0aNdL69etVoEABvfzyy+ratauvy7sppIVcK1eu1I4dO5Q1a1a99NJL6t+/v48r8w33HCHippV2otOvXz+1aNFCvXv3VsWKFTV27FhOUq8hj8ejOXPmqEaNGsqSJYt69uyp2267TTNnztTAgQPZ9j6SL18+vfnmm7r99tvVpEkTrVmzRtK5SwzSwoG0X3qlm68XwYYNG7xuHzp0SEOHDtVLL72k3r17K1u2bDp69KimT5+ulStX+qbIm4jH49HKlSvVqVMn3XHHHRo5cqTWrVunkJAQPfTQQ/Qg+Jd+/fVXzZkzR71799bAgQP16quv6sUXX1R8fLxee+01AoIbQNqxxxdffKHjx4/rlVdeUZs2bdS3b1+NHz9egYGBqlSp0k0ZEKR9b+zdu1djx47Viy++qHXr1unBBx/UwoULNWzYMB08eNDHVd48fvnlF3Xu3Fm9evXS22+/rdWrV2vChAn68MMPGYPgKvDz89OsWbPUoEEDhYeHq0ePHnrggQc0fvx49erVy9flXX8GpFOpqanO/2/YsMEqVKhga9assb1799obb7xhHo/Hhg8fbqdPn/ZhlTen1NRUO336tDVp0sR69OjhLE9MTLQBAwZY8eLFrX///paQkOC7Il0oOTnZ+f9t27ZZq1atLGfOnLZ161Z78sknbdSoUXb69Gn7/fffLT4+3pKTk23jxo0+rPjqmj59umXLls1iY2OdZfHx8RYVFWVjx461Y8eO2cCBA6127doWERFhmTNntk8++cSHFd8cxo8fb5UqVfLa1yYnJ1uVKlWsZMmStmzZMjt79qwPK0xffv/9d6tSpYrlzJnTnn76aa918+bNszvuuMNatGhhixYt8lGFSPPrr79a/vz5zePx2Ntvv+0sT01NtR9//NEqVKhgZcqUuSmPQ3788Ufr06ePtW/f3k6cOOEsHzFihFWvXt2eeOIJO3DggA8rvHmsWrXKChUqZPv373eWnT592saNG2cej8eee+45H1aX/iUkJFjr1q2te/fuzrIjR47Ym2++aVmzZrX+/fv7sLrrj3AA6d4rr7xivXv3tieffNJredpOk4Dg2mnUqJE99NBDXsuSk5Otfv36liNHDnv88cftzJkzPqrOXVJSUpz/P3bsmJmZ7dy501q1amVhYWGWIUMGK1GihBUsWNCyZ89u+fLlszx58tjdd9/tq5KvibSD0YMHD5qZWWxsrLVo0cJq1aplwcHBdu+999q4ceNs9+7d1rx5c+vatasvy70pvPLKK1awYEHndtr+dvny5ebxeKxw4cK2cuVKH1WXPn300UdWokQJi4qKsp9//tlr3fz5861SpUp2//33893mYwkJCTZjxgwrV66cVa9e3WtdamqqrVu3zvLkyWP333+/jyq8drp3726hoaF2yy23eAWyZucCglq1almHDh3sjz/+8FGFN49ff/3VgoODberUqV7L9+zZY5GRkebxeKxXr14+qi79S05OtqioKHvwwQe9lh89etRatWplHo/ngnOMm1mAr3suAFfKzpuaTTp3LfXo0aN1++23KyEhQcHBwZLkjOb65JNP6sSJE3r++ecVGBjok5pvFmnbPjU1VampqSpUqJC2bt2qP/74Q5GRkfJ4PPL391e9evX022+/KSYmRnFxcc6/Ca6N88fdeOmll7R//3516NBBUVFRev755xUeHq7PPvtMXbt2VevWrXXw4EGlpqYqISFBNWrU8HH1V0faezNPnjzavXu3ihUrpokTJ6pDhw567bXXtH79ep04cUKtW7dWxowZJZ3rEp8lSxYfV57+tW3bViNGjFDfvn01YsQIZ/tmyJBBrVq10tGjR5UrVy4fV5m+dOjQQf7+/ho1apRGjx6tJ598UuXKlZMkRUdHKyAgQMWKFXO2Na698/ezaYKCgtSgQQP5+/urZ8+eql+/vjNXusfjUcWKFbVkyRIVK1bMFyVfU6NHj1ZoaKg+/vhjjRw5Uk899ZTCw8MlSU8//bTOnDmjFStW+LjK9Oevx7jSuWkMmzVrpg8++EARERG67bbbJEnZs2dXw4YN1aBBA1WrVs0X5d4U/P391bRpUy1cuFA//fSTKlasKOnc9q1cubK2bt2qhQsXKiYmRpGRkT6u9jrwbTYB/Ht//vmn8//Dhg0zPz8/+/DDDy9oN3LkSKtVq5bXZQi4Mmnb7ujRo3bq1Ck7evSomZnt3bvXsmXLZm3atLHff//dad+zZ08bNmyYHTlyxCf1ulW/fv0sR44c9sUXX3h15/z555+tffv2ljt3blu3bt0F9zv/coT0Ku09umrVKtu7d6/17t3bMmfObJMmTbqg7bFjx6x///6WI0cO27Zt2/UuNd1K28bbtm2zBQsWOJdxmZm98cYbVrRoUXvqqafMzJxLOB5++GEuKfgHadt07dq19sEHH9g777xjmzZtctZ/8MEHVqlSJXv44YdvqkuA0pvze2Z9/vnn9vzzz9uQIUOcXh1nzpyx2bNnW4kSJaxBgwYXfYz0vJ9Ne58mJiZaUlKS17qePXtalSpVbOjQoRf0IDj/OA2Xlradv/vuOxs9erT16dPH1q5da2fOnLE1a9ZYnTp1rGHDhvbpp5/ali1b7Omnn7aSJUtyrHUF0rbx8ePH7fjx487yNWvWWOnSpa1Lly5ex0m9evWyIUOGWHx8/PUu1WcIB5BunP/l/Prrr1udOnVsy5YtzrL+/ftbhgwZLnoNcdrOgIDgyqVtsxkzZliNGjWsdOnSVrZsWXvvvffMzOynn36y7NmzW61atezee++1tm3bWnBwsP3yyy++LNt1li1bdkH37fPf71u3brU2bdqYx+OxrVu3+qLEa27+/PmWLVs2mzVrlpmZPfXUUxYYGGhffPGF0+aLL76w+++/3woVKmTr16/3Vanp1tSpUy1XrlxWvHhxy549u1WtWtWmT59uZmZjxoyxHDlyWGRkpJUoUcLCw8MvGkbhnLTP57Rp0yxbtmx25513WsGCBa1hw4Y2fvx4p92HH35o1atXt9atW3t95+H669u3rxUoUMAaNmxozZo1s9DQUFu2bJmZ/V9AULp0aatQoYKPK7160t6n8+bNsw4dOljlypXt1VdftdWrVzttevToYZUrV7YXX3zRuawN/87UqVMtc+bM1qBBAytatKjlz5/fHn/8cTt27Jj98MMP1rFjRwsODraiRYtanjx5+B67Aucfz1arVs2KFy9uJUqUsPfee8+Sk5Nt4cKFVrZsWYuKirJmzZpZ69atLSQkxLZv3+7jyq8vwgGkC+cHAytXrrQRI0aYx+Oxtm3b2o4dO5x1/fr1s8DAQPvss88ueAyCgX9v/vz5FhgYaCNGjLDx48fbgAEDzOPx2IABA8zMbN++fda3b19r06aNPfDAA/zC5QMzZsywYsWK2YEDBy4Iw9I+P1u3brVnn302Xf+C9XdiYmLs8ccft1GjRnktTwsIJk+ebGbn3qtjx4613bt3+6LMdO3HH3+0kJAQGzt2rB09etSWLVtmjz/+uOXOndtmzJhhZmaHDh2yd955xz7//HPbtWuXjyu+8S1btswiIiLsnXfeMbNzPV8yZ85s5cqVs9dee81pN378eLv99tudsTRw/U2YMMHy5ctna9euNTOzzz77zDwejwUFBdns2bPN7FxAMHXqVGvXrp3XcUt6N336dMuUKZP16dPHnnnmGatdu7ZFR0d7DYrZu3dvK1KkiI0cOZLjrX9p586dVrhwYXv33Xed7+nRo0db3bp1rWvXrpaYmGjJycm2f/9+27Rpkx06dMjHFac/CxYssMDAQBs6dKhNnjzZ/ve//1nRokVtwIABlpKSYj/++KONHj3a7r77bnv00UddeTxLOIB0pW/fvpYnTx4bOnSodezY0bJmzWp33XWXV0CQduK6YMECH1Z680hNTbUOHTpY586dvZZPmjTJPB6PTZw40cz+r8vkX7sc4vp4//33LSQkxE6dOmVm3v8OixYtumBAuJspIPjhhx+sWrVqVrZsWecg/fwD86eeesoyZ87sXHbEgeu/8+6771rNmjW93ju7du2yxx57zGrXrs2J6xVKTk62F154wZ544gkzM9u9e7cVKVLE7rvvPrvvvvuscOHCNm7cOKf9X7ts4/qJjY21Pn362AcffGBmZrNmzbKsWbPaqFGjrEOHDpYxY0ZbsmSJmZ3rep/mZtjPbty40YoXL+4EWCdPnrRs2bJZsWLFrF69erZ48WKnbf/+/Qle/4P169db3rx5L+hx9cYbb1i+fPm4DO4/SE1NtbNnz1rbtm3tscce81o3YsQIK1SokH366adey2+Gz++/QTiAG9ZfR7n/4YcfLHv27M4XsNm5KQzDw8OtUaNGXt1+xo0bx3WuV8nZs2etdu3azhQvycnJzrbt2bOnRUVFWVxcnLMT5cTr2vq7X6P+/PNPK1GihDVr1sxr+cmTJy06OtpeffXV61CdbyQkJFiDBg2cKZ3S3p/nb6suXbpYrly5LC4uzldlpnsfffSR5cmTx3777Tev5XPnzrXQ0FDbvHmzjypLP9L2j2n7y99//902bNhgp06dsqioKOvUqZOZmW3ZssXCwsKsYMGC9sYbb3jdF9fexfaz69ats127dtn27dutWLFi9tZbb5mZ2ddff20ej8c8Ho99991317vUa+7nn3+27t272+nTp+23336zIkWK2OOPP25z5861iIgIq1evnhPK4sqd/7les2aN5cuXz3kfnR805cmTx4YPH37d67vZNG3a1B5//HEzM6/ptjt06GAVK1Y0M/a1fpceshC4/tq1a6cFCxZ4LUtOTlZwcLAKFCggSTp79qzKly+vuXPnasmSJRo6dKh27Ngh6dxMBQEBAUpOTr7utd9sAgICVLt2bc2ePVu7d++Wv7+/M5JuRESEUlNTlSVLFvn7+0vSBaPs4uo5f7Ts5cuXa/bs2Vq9erVSU1OVLVs2DRw4ULt371bdunW1fPlyTZkyRa1bt1ZMTIx69Ojh4+qvnaCgIM2aNUuNGjXStGnTNH36dJ09e1Z+fn5KTU2VJI0fP16bNm1SSEiIj6tNvwoXLqyMGTNq5syZiouLc5aXKlVKuXPn1qlTp3xY3Y3P/v8o5CtXrtTnn3+u33//XXnz5lX58uWd2TT69esn6dz3W5UqVdSiRQvde++9kti3Xi/n72ffe+89vfbaa5KkSpUqqUiRItqyZYty5cql9u3bS5LCw8P12GOPaezYsapevbrP6r5azEySFBcXp6SkJJUrV079+vVTxowZ9cwzz6hWrVoaNWqUGjVqpAoVKmj79u368MMPderUKee+uLS0bXX+57patWrKmzevnnzySZ08edKZYevUqVMqUKCA8uXL55NabwZp2zt37tzOjCJBQUFKSkqSJNWoUUMZMmRQUlKS6/e1hAO4IRUuXFiNGjWSdO4gSZIiIyN19OhRLVu2TNK5k1YzU7FixVS4cGFNnjxZAwcO9PpyCghgts4rkbbt4uPjdeTIEWd5mzZtVLBgQfXr10979uxxgoA//vhDYWFhSkhI8Em9bmJmzgHrM888o3bt2mnAgAG6/fbb9dRTT2n37t26//779frrr8vM1KpVKw0bNkwBAQFau3atAgIClJKS4uNX8d+lvUc3bdqkKVOmaP78+fr5558VFBSkadOmKU+ePBo+fLhmzpzpBARp92E6vcuTtr22bt2qFStWaM6cOZKk2rVrq23btnr++ec1ceJE7dixQydPntS4ceOUmJioggUL+rLsG1paMDBt2jQ1atRIu3bt0okTJ7zWx8XF6aeffpIkTZs2TZGRkRo0aJATiOP6SNvPPv300xoyZIhSU1O1b98+Z/2pU6e0evVqHThwQH/++adGjRqllJSUm+JHibT36ezZs9WtWzctWrRIycnJyps3rxITE7V9+3aVLVtWGTNm1NmzZ5UnTx499dRTeuutt5Q5c2bXn1RdrrTtvHr1ar388ssaNWqUpk6dKkmaMmWKTp8+rdq1a2v+/Plavny5hg8frp07dyoqKsrHlacfad9jx44d0/HjxxUfHy9JGjZsmFJTU3XHHXcoJSXFCWB+/vlnhYSE3BTHSf/Z9e6qAPyTv3blGzdunI0dO9a51nLAgAGWP39++/LLL502J06csG7dutnChQstKCjIa5RnXL7zR3G97bbbLH/+/NawYUMbNWqUpaam2qxZs6xu3bqWN29ea9++vTVt2tSyZs1qGzZs8HHl7vLyyy9b3rx5nTEEnn/+ecuQIYM99NBDXjNE/PLLL3bkyBHn3/Vmusxm6tSpliNHDitTpozlz5/f8uXL51wPe/r0aatfv75Vr17dPvvsM8bAuEJp75cvv/zScufObcWKFbPQ0FArV66cMyr7s88+ayVKlLCwsDCrXLmyRUREMGL2ZVi7dq3lzJnT3n///Qs+j7/99pvdc889VrRoUStVqpSFh4fbTz/95JtCYZ999plFRETY999/f8G6Y8eOWbNmzczj8dgtt9xiZcqUcfYzN0N35K+//tqCg4PtxRdf9PpOiY2NtSZNmli7du1s5syZNnDgQCtatKjFxMT4sNr0a9q0aZYlSxa74447rGLFihYYGGhdunSx1NRUO3DggNWpU8cKFSpkBQsWtDJlyrCPvQJpn8Pp06dbnTp1nFlgXnzxRTMzW7FihRUrVswKFy5sbdq0sXvvvdeyZMniTE3qdoQDuKE1bdrUihYtahMnTrTExET77bffrEuXLhYeHm79+vWzt956y+644w6rUqWKJScnW+3ata1bt26+LjtduNhBzPz58y0oKMgGDx5sn376qXXo0MEqVapkXbt2tdTUVNu2bZu9+OKL1qJFC+vRowfTal0H5wdm+/fvt9atW9ukSZPMzOyrr76ysLAw69Kli2XJksXat29/0ROK9D5q9vn1p40zMn78eDtx4oRt3LjRnn32WfPz87N3333XzM6NV1K9enW7/fbbXTU38dWyZs0aCw0NtYkTJ9quXbvs4MGDdvvtt1vx4sWdUOrHH3+0r7/+2qZNm3bBGATwlravfeeddywqKspOnDjhrDv/vb1792775JNP7NVXX2UqWB9JGwuiX79+1rZtWzO7cNYXs3PXKk+bNs2+/PJL5z43QwC7f/9+K1eunDOewl999tlnVrNmTcuXL58VK1aMqUr/pV27dlm+fPlszJgxZmYWFxdns2bNspCQEOd6eLNzMwzt2LHDDh8+7KtS06158+ZZUFCQvfLKKzZ27FgbMGCAZcmSxXr27GlmZsePH7fevXtbp06d7Iknnrhpp3j+NwgHcMP4uxOYBx54wG699Vb78MMPLTk52Q4fPmyjR4+2okWLWvXq1a1JkyZOal+3bl0bNmzY9Sw73Ur7sklJSbGUlBRLSEiw+++/33r16uW0SUhIsDFjxljFihVt7NixvirVtf4aDJiZzZ492+Li4uyHH36wAgUK2JtvvmlmZi+88IJlyZLF7rvvPtu5c6dP6r3avvrqK+f/07bFtGnTrHLlys6sDGbnftEaMGCAFStWzBnNOSEhgZPWy/Ddd9/Z77//7rXsww8/tMqVK9vJkye93oO1a9e2ypUrX+8S06UjR47Y1q1bvQbW7du3rzPglZn353vt2rWcAPjIzz//fEEPgf/9739Wv379C45LEhISbO7cuRc8Rnod1fyvr2/Pnj1WsGBBW758ubPsrz8k/PHHH/bLL7/QY+Ayvf322xeceP74449WtGjRC2Z2+Prrry1TpkwM8HiF0gZuTHs/nz171jp16uQMpG127keDKVOmWNasWW3kyJFe978ZevxcTYw5gBvC+QMAbdiwQb/++qsOHDggSfrkk09UuXJlDR8+XJ988omyZMmi7t27a8OGDVq1apVmzZqlDBkyqF+/fvr111/Vpk0bX76UdGHKlCmqVauWNm3aJD8/P/n5+SkoKEjHjh3T0aNHnXZBQUH63//+p6JFi14wQCSurWnTpunrr7+WJD311FPq3LmzUlJSVK9ePYWEhGjWrFmqUKGCHnnkEUnnxteoWrWqUlNTVaRIEV+WflXs3btXLVu2VMuWLSX933XA/v7+2rZtm/bv3y/p3HWFoaGhatasmU6cOKE///xT0rn3Ltdq/7NVq1apQYMGev/99xUTE+MsP3TokP78809lzpxZfn5+On36tCTp/fff16+//qoVK1b4quR0YevWrWrevLnGjh2rbdu2OcvvuOMObdq0SdOmTZP0f+/phIQEffbZZ1q2bJkzgCauj0mTJunhhx/W22+/rV27djnLb731Vm3cuFE//PCD1zhGp06d0tixYzVz5kyvx0kbhyc9+e233/TRRx9pw4YNzrIjR47ojz/+UKZMmSSdG/MpbRyBn376SXPnzlW2bNl0yy23KCIiwhdlpytnzpzRq6++qmbNmmnnzp3O8qxZs2r//v3avHmzV/uaNWsqb968OnTo0PUuNd16//33VbRoUcXFxXmNMbR9+3bFxsY67YKDg9WkSRN16tRJq1at0pkzZxhA828QDuCGkHaQ1K9fPzVv3lxVq1ZVz5499dVXX0k69wVeuXJlvfLKK5o8ebLi4uKUJUsW+fn5af369erVq5c+/fRTzZo1S8WKFfPlS0kXMmfOrEKFCqlLly7Ol1NSUpIKFSqkAwcO6NChQ85BakBAgOrWrau9e/d6DaCFa8fMtHTpUrVu3VrNmjXTu+++q5EjR8rf31/BwcGSzh3EJSUlOf8ma9as0ZNPPqkvv/zSa5T+9KpgwYKaP3++Vq5c6RX4FS9eXKVLl9ZHH32kAwcOOAeuRYoUUbZs2Rgx/zKkHRDVrFlTffr00Ycffqj3339ff/zxhySpVatWio2N1XPPPSdJzonCmTNnlCNHDoWGhvqm8HRg06ZNuu2221SlShW1adNGFStWdNZVqVJFHTp0UN++fTVlyhRJ0tGjR/XSSy9p0qRJqlixovNdiGvvww8/VJcuXfToo49q4MCBKlq0qLOud+/eKlGihNq2bat58+Zp9+7d2r17t9q3b68///xTjRs39mHl/92mTZsUHR2tWbNmOZ97SapataruvPNOPfLIIzp06JAyZMjgrPvwww81Y8aMdP/dcj2kbaOMGTNqzZo1yp49u5o1a6ZffvlFkpQvXz7nu/3777937pc9e3Zlz57dGYgbl1atWjVlzZpV9erVU3x8vDwejwICAtS4cWPt27dPGzdudNpmzJhRuXPndoKatOMHBtL8C192WwDO78qzePFiK1KkiC1dutQmTpxo9913n1WtWtU+/fRTp80DDzxg4eHhXl2u4uPjbc6cObZ3797rWnt6k9bdKq371eLFi61x48ZWrVo1ZxCWbdu2WdasWa1jx4528OBB576PPPKI3X333V5zwuLaOL976q233moBAQE2atSoC9pNmzbNgoODLSoqyooXL26lSpVyrnlN713kzp8LfuHChRYWFmatW7d21g8dOtRKlixpTz/9tG3YsMEOHz5s/fr1s3z58tmBAwd8VXa6kLYfOL8767Bhwyxfvnw2bNgwZ/u9+uqrVrRoUXvmmWfMzOzo0aP2/PPPW7FixeyPP/64/oWnAzExMVa+fHkbMGDABevS3tO//fabde3a1fz9/a1EiRJWrlw5y5MnD4ONXWdr1661/PnzO+O3nO/48eNmdu6zcu+991rBggUtJCTEKlSoYNWrV3cuY0yvlxJs3brVwsLCrH///rZv374L1i9cuNBq1qxppUuXtqVLl9rMmTOtT58+FhYWZhs3bvRBxelL2j52y5YtNnnyZDM7t/+sVq2alSxZ0hlPZM6cOVa3bl2766677IsvvrCffvrJ+vTpYzly5LjgcgN4S9vGJ0+eNLNzx67ly5e3smXLWlxcnJmdex+XKVPGnnzySa+Bs7t162ZNmjTxujQR3ggHcEP46quvrEuXLjZ8+HBn2bp166xDhw5WpUoVr4Bg8ODBzpdyej8Jul7SdqTr16+3u+++2zkgWLBggd19991WrVo15+D0u+++s5CQEKtdu7Y1bdrU2rdvb1myZGFWguvg/PDl119/tejoaGvTpo0FBwfblClTnHXnj8T73HPP2aBBg5xgIL0esJ4v7fUdPXrUzM69T7Nly2YtWrRw2rz44osWFRVl/v7+Vr58eU6wLkPafmDDhg3m8Xjsiy++cNalBQRDhw6148ePW2xsrL3++usWHh5uuXPnttKlS1tkZCQDkP2DlStXWoUKFZxxL8zMfvrpJ3v33XftrrvuskcffdQ56F++fLm98cYb9vnnnxNs+8Ann3xiNWvWtNOnTzvL5s6daz169LBbb73V7r//fvv111/NzGzVqlU2c+ZMW7x4cboffPDUqVN27733el2LbXbue+PAgQPO2DabNm2yZs2aWVhYmN16661WvXp1Zs+4DGn72J9++skyZszodW370aNHrWrVqla8eHFnXKB58+ZZ+/btLSgoyEqUKGElSpTge+wSzv8eq1u3ru3YscPMzoUx5cuXtzJlyjgBwaeffmply5a16tWrW9OmTa1169bMsnUZCAfgc7t27bI6depYWFiY9enTx2vdunXrrGPHjla9enVnqrI0N8NJ0PVw/o40MDDwgm08b948JyBI22H+8ssv1r9/f2vXrp117dqVWQmug0WLFlmXLl3MzKxLly7WtGlTJ9nu0aOHBQUFeU3haWYXDCSXXg9YL2br1q1WuXJlW7t2rZmd+xXgrwHBb7/9ZosXL7YlS5ZcsC3g7fyD1ixZsjg9As4fkGzIkCGWN29eJyAwMztw4IC9++67Nn36dE5iLyFt+se0A/8PPvjA6tataxUrVrQ777zTKlWqZIUKFWKgzBvARx99ZLfeequtXr3azMy6d+9ut912m9WsWdOeeeYZy58/v912220XvW96PvZISEiwmjVr2ttvv+0sW7hwodMzoEiRItayZUtn3bZt2+zQoUN27NgxX5Sbrpx/rJUpUybr37//BW3+/PNPq1atmt16663OfiI5Odn27t1rO3fudAJxXNz52zhDhgw2cOBAr/VpAUGpUqWcgODbb7+1N99805o2bWq9e/fmePYyEA7gurvYr/0LFiyw+vXrW9GiRW3RokVe69avX29Nmza1hx9++G/vj4u7nC8rs3NTGP61B0F67zqZniQnJ9uQIUOsatWqVrVqVQsPD7ft27d7tenZs6dlzJjRPv30Uztw4IA1b97c7rvvPjO7OT8TP/zwg9WtW9deffVVMzsXfCxcuNCyZ8/udfCKS0t7f2zatMkyZsxoQ4YM8Vp//kjaQ4cOdQICApcrc/r0abvlllssb968VqVKFQsODrbBgwc7+9QVK1ZYZGSkff3112Z2c35u04t169ZZ7dq1rVixYpY3b14rWLCgvffee85lNevWrTOPx+NM3XmzOHr0qBUpUsR69uxpu3fvtldeecVKlixp9957r40cOdLGjh1r+fPnv2h4iEvbuHGjhYaGOtsvzffff2+HDh0ys/+7xKB48eJMWXoF0t6LP//8s2XMmPGCYCBNWkBQunRpJyAwO7e/ZZ97eQgHcF2d/0Vz+PBhr+vdVq5caY0aNbIGDRrY4sWLve63Y8cOvqT+pX379llAQIATDKSd7A8dOtRGjx7ttEu7xKBmzZpe3drYmV4/0dHR5vF4rF27ds6y88OZp59+2jwej5UuXdpKly7tBDg3g7T32fnTY40cOdJCQ0Od7r1JSUm2cOFCi4yMtLvuussndaZXR44cscKFC1u1atW83lPDhw+3Jk2aeI0jMHToUCtcuLA988wzTFd2mdK2aXx8vD3zzDP2zDPP2M8//+zVm2fbtm1WqlQpW7p0qa/KxHlWrlxpn3zyib366qsWGxvrtW7BggVWsWJF27Vrl4+qu/rS9rEzZswwj8djBQsWtMyZM9u4ceOck9QzZ87Y7bffbo899pgvS013UlNTLTk52cqXL29BQUFex7aDBw+2fPnyefW8Onr0qNWsWdMiIyOd7zdc2u7du83j8dhTTz3ltXzEiBH2ySefOLfTAoIKFSo4veBw+QgHcN2cf5L5wgsvWNWqVa1w4cJWtWpVmzFjhpn93yB5DRo0sCVLllzwGAQEV27RokVWtGhRa9CggfNv8NJLL1lISIjNmzfPq+3ChQvttttuszvvvNMZuBDXXkJCgsXHx9ugQYOsR48edtttt1nXrl0tPj7ezMwrBPj2229txowZ6f7a14tZuHCh5c6d2/r16+csu++++6xGjRp24sQJMzt3EjZ79mwrUqQIv2xfgZSUFHv44YetZs2a9vLLL5uZ2euvv25Zs2a1BQsWOG3SDBgwwEqXLk031ytwqV5WzzzzjFWoUIEBHX3sUoH3mTNn7J577rF77733pjvmSHvtO3futFWrVtnhw4e91icnJ9u9997r9C7ix4Ers2vXLouIiLC77rrLYmNjbfjw4ZYzZ06bM2fOBW2PHDlid955J+HAFdi4caMFBwfb/fff7/QKeOWVVywgIOCCXsdbt261AgUKWK1atXgfXyHCAVx3gwcPtoiICJsyZYodPXrUSpcubaVKlXIGalq0aJE1bdrUKlasyOBXV0FSUpItWLDAypQpYw0bNrQXX3zRcubM6RUMnL/jXLJkyUVHMMbV9f3339uKFSsuum7o0KFWo0YN69q1q3NSnJqaesG1cjfbJR+zZ882j8djfn5+Fh0dbV999ZVNnTrV2rRpY6NHj/YaiJSRhi9f2glOcnKyPfHEE1ajRg2Ljo62sLCwC96D558MHTly5LrWmZ5cSSj366+/2lNPPWXh4eEMhHWdXc7Jfdr334kTJ2zp0qXWqFEjK1OmjBPK3qwBwV8lJSXZs88+a3nz5nWuh8flS9sn7Nq1y8LDwy1v3ryWI0cOJ3y92Ha/2d5b18PatWste/bs1qFDBxsyZIhly5btgmAgzfbt22+q3j/Xi8fs/094DFxjKSkp+vPPP9WsWTP16dNHLVu21OLFi3Xvvffq1Vdf1WOPPea0nT17tpYtW6ZXXnmFeZ//AzOTx+NRcnKyFi9erIEDB2r9+vWaO3eu7rrrLiUnJysgIMCrLa69NWvWKCoqSqGhoWrTpo0aN26s6OhoBQYGSpKSkpL0yiuvaP78+SpVqpQGDBig//3vf8qUKZNmzJjh4+qvnr++5xISEvTiiy8qODhYv//+uxISEvTHH38oLi5ORYsW1ZgxYxQWFua7gtOx1NRU+fn5KSUlRb1799akSZPUrFkzTZgwQQEBAV7/Fmlt2Sdc6MiRIwoLC1OGDBm0ePFihYeHq1KlSn/b/tVXX9WUKVMkSe+9957KlSt3vUrFeWbPnq2KFSsqT548F31PJyUlqX///tq2bZsyZsyoKVOmKCAgwOs7Mj05dOiQDh06pKJFiypz5syXbD958mStXr1an3/+uebPn6+KFStehypvPikpKfL399fevXtVp04dhYeHa9asWSpQoIAkjrOulrVr1+ree+/VwYMH9dVXX6l58+a+Lunm4rtcAm6QmJjo9Qvf3r177ZZbbrGEhASbP3++ZcmSxcaPH29m5+YrHT9+/AXX/pGsXh1JSUk2d+5cq1Chgt1+++03Zbf09GLdunXWuHFj++abb6xLly7WqFEjK126tC1atMgZiDAxMdFef/11K1++vOXOnduqV69+U17q8e2331qjRo1s69atlpKSYnPnzrUGDRrY9u3bbefOnTZ06FDz9/c3j8dzwUB6uNA/dZ9M+8ynpKRY9+7drVq1avbyyy87vVPY1/6zw4cPW4MGDezZZ5+1zz//3Dwez0W7C5/vyJEj9vnnn3MJjI+kpKTYzp07zePx2OzZs/+x7bp16+zbb791Pgfp9btxy5YtVq1aNXvggQcuq6fKxo0b7bbbbrNmzZoxkvtVkLaf3b17t2XLls2io6MZePAaWL9+vUVERNh99913wXkD/hvCAVwzU6dOtRYtWljFihVt6NChzvJq1apZy5YtLWvWrPbuu+86y3fu3Gm33XabzZo1yxflpmtpBzOXOrg/e/aszZ8/38qUKWN16tTx6m6M6+uOO+6wxx9/3MzODcL33HPPWZ06daxUqVI2duxYZyC4gwcP2rfffnvThTnnj6BfvHhxq169ug0YMMBOnTplAwcOtAoVKjjdeufNm2f33nsvB66X6Z+mHUt7H6VdYlClShUbMWKEM74F/l5cXJw988wzdsstt1iGDBns/fffN7O/339yneuN49FHH7U777zT/vzzz8tqn16Dsk2bNjnTQq9ateqy73fgwAEGbrsMae+LhIQES0xM9Arsz/+8p+0Tdu3aZdmzZ7fGjRvbtm3brm+x6dTfffYutj/94YcfnBmMCAiuHsIBXBMTJkywkJAQ69Wrl/Xs2dP8/f1tzJgxZmY2evRoy507tzVv3txpf/r0aWcgQk5Ur0zajvS3336zjz/+2H7++ed/bJ8WEFSoUMHKlSuXbg+C0qu07b1p0ya7/fbbbfny5c66yMhIq1atmkVGRlqdOnWsadOmlpCQ4Ky/GT4bf3fC9PLLL1v9+vWtWLFiNmPGDKtXr569+uqrXgdjuLTjx49bzpw5/7GXxfkBwZNPPmnFihWzN954g5PZf5AWyi1ZssTCw8OtQIECNnjwYKZ8vcH89T2c9u82depUK1OmjPNL+s3473X48GGrXLmyDRgw4IJ1iYmJXsEyn/Url/ZdtG3bNmvfvr1Vq1bNOnbs+Le9h87vQeDxeKxVq1Y31QxD10LaNo6JibElS5bYN9984zWA698FBJGRkdagQQOvqQvx76W/C6lww3vvvffUvXt3TZkyxbkO6NChQ0pJSdGJEyfUvHlzbdu2TStWrNDdd9+t/Pnza9u2bYqNjdW6devk7+/vXPOKf5a2nTZv3qzWrVurYsWKCgsL+8frWgMCAnTnnXfqhRde0Msvv6z9+/erYMGC17Fqd0t7X+fMmVMpKSnaunWrateurfLly6to0aL67rvvtHv3bs2cOVPLly/3ut7V39/fV2VfFfb/r7f87rvvtGjRIiUnJ6tEiRJ68MEH1a9fP7Vr106jRo3SAw88oMyZM+v48eNq2bKlChUqpKCgIF+Xny6EhYXp6aef1nPPPadMmTKpT58+F7Tx9/d3ro197bXXFBgYqHvuuYdrYf9BQECAPv30U7322muaMmWKvvvuO82dO1cJCQkaOnSoAgICnG0K30l7Dy9cuFDFixd3vttatmypkSNH6vnnn9f06dNvyn+nQ4cOKTU1VW3atHGWrV27Vj/88IM+/vhjlSxZUs2aNdO9997LZ/0KpR1r/fzzz7r99tvVoEEDlSpVSkuWLNHPP/+sTJky6fbbb/e6T9p+tnDhwtq9e7cSExOVIUMG37yAdCBtG2/atEmtWrVSSkqKdu/erfr166tv376qX7/+Rd+3VatW1VdffaUHHnhA8fHxCgkJ8UH1NxlfpxO4uXz77bcXvTa4fPnyVrZsWcuSJYvdfffdNmTIEJsyZYrdc8899tBDD9mgQYOcVPtm6TZ9raUlqFu2bLGwsDDr27ev7dmz56JtL9Y74OzZs3by5MlrWSIuYerUqZYtWzbLkyeP1a5d2w4dOuSsO/+XrZvpV65p06ZZ5syZrWHDhlanTh3z8/OzBx980Ou1z50715o0aWI5c+a0AwcO+LDaG9/FfklJTU21t956y/z8/GzkyJF/e9+b6X11raRt36NHj1qJEiXs9ddfN7Nzlxj079/fqlWrZgMHDnS25Ycffmjr16/3VbmwczMeValSxUJDQ+311193pkWeO3euRUVF2erVq31c4bWxcOFCCwwMtK1bt5qZ2XvvvWe1atWyqlWrWosWLezOO++0kiVL2g8//ODjStOnrVu3WsaMGb0uk125cqWFhITYc88997f3Yz97aWnHqD///LNlypTJBgwYYD///LPNmDHDsmXLZi1btrzkpW9nzpy5HqW6AuEArqpffvnFateubffcc4+tXbvWzMxatGhhxYoVs8mTJ9u8efOsVKlSVqFChYsO0MRO9MqcPHnSmjVrZr169fJanpycbEeOHPGaP5duhDeeo0eP2h133GF169b9x+vEbxZ79+61QoUK2dixY51lK1assLCwMOvUqZNX24MHDzKV3iWkHVD9+eefXl0vzc593t944w3zeDz/GBDg0r755ht76qmn7NFHH7WTJ0862z0+Pt6eeeYZq1GjhrVu3dr69OljHo/HduzY4eOK3WXZsmXOWALDhw+3zz77zPbu3Wuvvfaa3XbbbVakSBF77LHH7IsvvrDChQvbW2+95eOKr67zv9sbNGhgGTJksEqVKllgYKANHTrUmRJ6zZo1FhERYZ9//rmvSk23Tp06ZbVr17YCBQrYxo0bzez/fshq0KCBPfbYY74s76awc+dOy5Ili3Xu3Nlr+ciRIy0kJORvf/zC1cdlBbiqbrnlFr3//vt68sknNXjwYMXGxurMmTNatGiRChUqJEnKlSuXqlSporVr1ypv3rxe978Zu/pdSx6PRwcOHFDTpk2dZYsXL9aiRYv0wQcfKDg4WI0bN9b48ePl8XiYRuc6+uulMRfrcpw9e3bVqVNH7777rjPd1M1ySc348eNVsmRJ1alTx3k9Z86ckZ+fn2677TZJ517rbbfdpunTp6t+/fpq1qyZmjVrJknKnTu3z2pPL/z8/LRr1y7dcccdSk1N1RNPPKGcOXPqwQcfVEBAgHr06CF/f3/17NlTqamp6tu3r69LTneSkpK0dOlSvfnmmypevLjzOU1KSlLWrFk1YMAA5ciRQ4sXL9bq1av1008/6dZbb/Vx1e6xZ88ePf300woLC1ORIkX09ttva8uWLSpYsKB69eqlVq1aac+ePerTp49iY2O1d+9evfjii6pfv75KlCjh6/L/k7T96aFDh5QjRw5lypRJCxcu1Ouvv66kpCR99tlnXq8xb968yps3r7JkyeLDqtOnTJkyqWfPnho1apSGDx+url27qlatWtq7d6+WLVumdu3a+brEdG/Xrl1KTExUSEiItm/f7rx3c+TIobCwMKWkpPi4QhfxdTqBm9Mvv/xi9evXt9DQUJsyZYqZnfuVKzU11datW2elSpWy7777zsdVpj9/vTxgz549VqpUKRsyZIjt3r3bXnvtNStTpow1a9bMhgwZYmPGjLHg4GB+OfSh995776KD5KT92pOYmGjlypWzp5566nqXdk2kva7ixYtbgQIFbOXKlc779tdff7WAgACbNm2amZ17P6ekpNjp06etYsWKNmrUKJ/VnZ6cvx+YOHGi5cyZ0/z9/a1Ro0ZWvHhxK1asmNWvX9+++OIL+/HHH+3DDz80j8djb7/9tg+rTr92795tQ4YMMY/HY6NHj3aWnz8YYWpqqjMlJK69+fPnO/8/a9Ysi4iIsIwZM9rSpUvN7MIBTE+ePGmrVq2yvn37WrZs2WzixIlmln57K27dutVatGhhZcqUsYCAACtfvrz169fPWX+xSwmfeeYZK1WqFJdqXaa077LzL3WdNm2aVa1a1R5++GH76quvrECBAta1a1dflZiupb1Hz5w542zryZMnW758+ex///ufHT161A4fPmw5cuSwgQMH+rJU1yEcwDXz66+/WnR0tDVq1MhrRPYmTZrY7bffzij5/9LevXtt0KBBzu3XXnvNMmbMaAULFrTMmTPbmDFjnG6tCQkJVq9ePevSpYuvynW1ffv2WbFixZwTiotd2nH27Fm799577eGHH77e5V11f/1M161b14oUKWIrVqxwTqQ6d+5s1apVs2XLlnm1rVmzpnM9Ny5tx44dNnHiREtISLC33nrL7rzzTnvggQcsNjbWvvzyS+vUqZPdcsstlitXLmvYsKHlzJnTPB6PffTRR74u/YaW9hk9efKk18n+sWPHrF+/fpYxY0abMGGCszy9nlymZ2+99ZZFRUU5J23fffedFStWzMqXL29NmjRxxi9JW//X/W737t2tZMmS6fZSu40bN1poaKh17drV3nvvPfvqq6+sWbNmFhgYaHfffbfX9Hpm567j7tOnj4WHhzuzNeDvpX2PJSUlWWpqqv3yyy9e4zN9+eWXVqVKFcuSJYvXrFvsC67ctm3b7MEHH7TFixc7n8cvvvjC8uXLZ+3bt7fcuXN7hS+cN1wfhAO4pn755Re766677O6777YVK1ZYixYt7NZbb3VOFPigX5nU1FQbOXKkFSlSxOuX5lWrVtny5csvuO44ISHBGjVqZMOHD7/epcLOHZy2adPGmjZt+o/tDh065BxYpNcD1rTP8p49e+ytt95yxruoXr26FS1a1OkptHLlSmvevLlVrFjRPv30U1u6dKk9/fTTli1bNq8xMnBxqamplpycbA899JC1bdvWzM5NX/jmm29a6dKlrVu3bk7bXbt22Y8//mhPPPGERUdHW0BAgG3ZssVXpd/w0j57s2bNsrp161qZMmWsVq1aNm3aNDt58qTFx8fbgAEDLGvWrPbOO+/4uFr3OnDggLO/THs/Hz582KZNm2a1atWyu+66y2uAU7Nz14yn+f77761ixYq2b9++61f0VXL48GGrWLGi9e/f/4LlY8aMscyZM1ubNm2c5R999JFVr17doqKinGvl8ffO7+XWvXt3K1u2rGXIkMHKlStnvXv3dtrNnDnTKlasaO3atbPvv//eV+WmW6mpqXb69GkrWbKkeTweu//++23FihVePQhy5sxpJUuW9PrOSq/HR+kN4QCuuV9++cUaN25sGTJksOLFizvBALMS/Dt//vmnDRs2zCpXrmw9evRwlv81aDl79qwNHDjQ8ufPb7t27brOVbrP3wVdW7dutWzZstmnn356yful118e0l7Dxo0b7dZbb7V7773Xvv76a2d99erVrXDhwrZq1SozM1u9erU9/vjjFhwcbCVLlrSyZcsywvsVGjVqlJUpU8a5ZCU+Pt5Gjx5t5cqVu2Bwx7QDKjcMevlfzZs3zwIDA23gwIH27rvvWrNmzaxEiRI2fPhwO336tB05csSee+4583g89uGHH/q6XFd5/vnnvW4vWrTIPB6P1yUCn332md12223WuHFjO3z4sJmZPfLII86lTGZmTz31lIWHh9vRo0evW+1Xy/r1661MmTK2adMm5/sibf8bGxtrw4YNs0yZMjn734MHD9q8efPs4MGDvio53Th/xPwCBQpY586dbfjw4TZv3jy75557LFu2bFavXj2n/dSpU61q1ar2wAMP2IoVK3xVdro2YsQIy5cvn+XMmdPq169vK1eudL6vvvrqK8uXL589/vjjtn37dh9X6i6EA7gutm3bZt27d2e6wiv0dyecx44dsyFDhlilSpW80uw0s2bNsu7du1vOnDk56boOzk+z586da/v373eWnThxwjp06GCPPvqomd28vWW2bdtm4eHh1r9//4te01qzZk3Lnz+/ExCYmf3+++924MABTlqvQNr7Z+bMmVa4cGE7ffq0sy4tIChfvrzXiM9p3Yz51eWfnTx50u65554LZn/p16+f3XrrrTZnzhwzO3dp17BhwzhgvY62b99uAQEB1rBhQ2fZrl27rGfPnhYeHu4VEEyaNMlq165thQoVsttvv93y5s3rdczxyiuvpNvp/D788EMLDg52bv/1M717924LDQ21ESNGXO/S0rW0/eqGDRssc+bM1q9fP6+p8WJjY+3111+3sLAwr0sJZsyYYbfccos98sgjTKV3BdKCrZ9++skeeeQRmzlzppUpU8Zq165tq1at8rrEoFChQvbggw/aL7/84suSXYVwANcdwcDlSds5bt++3d58802bO3eunT171hlo6ejRozZs2DArX76818Hs4sWLrVKlSnbPPffQhfg6OP9k/7vvvjOPx2O1a9e2du3aOd1WlyxZYoGBgTdtt84zZ85Y69atLxiYKSkpyXbv3u38gnfXXXdZ/vz5beXKlU4PIvyztPfX6dOnvQ4+T506ZbfeeqstXbrUudTA7P8CgsqVK9t9993nk5rTi+PHj9uuXbu8elbVqVPHGdjt/EHtoqOjrX79+s7t9NrLJz1btWqVFSxY0OvfYe/evfbUU09Z1qxZnYAgJSXFli9fbs8995z16tXrpvpRYsWKFRYcHGxTp0792zYVK1a0nj17Xseqbg579+614OBg69Onj5nZBe+b+Ph4e/bZZy1nzpxePVHmzp1ru3fvvv4FpyPnj+Pw1x9I7rzzTuvWrZudOnXKSpUqZXXr1vXqQfDxxx9b6dKlL7hsFtdO+p8vC+lOQAAzaF4Oj8ej2NhY1ahRQz179lS7du1UuXJlderUSVOnTtWZM2c0cOBAtWzZUuvXr1fPnj0lSXfccYc+++wzTZw4UaVKlfLti7jJmZkzTV/Xrl31wQcfaOPGjXrooYd08OBBRUVFqWPHjjpz5oyaN2+ucePGKSkpycdVX30BAQGKiYnxmjZrwYIF6tu3rypUqKBKlSqpdevWmjdvnkqXLq27775b69at82HF6Yefn5/27NmjWrVqqW7duho8eLDGjx+vlStXKjExUYcPH5bH45G/v79SU1OVNWtWderUSffdd5/++OMP/fHHH75+CTekzZs3q2nTpqpbt67q16+v7t27S5KKFCmib7/9VpIUFBTkfF5vv/12JSYmKjk5WRLT7l4v9erV05IlSyRJUVFR+vzzz7V9+3Y1aNBAklSwYEF1795djz32mLp3766PP/5Yfn5+ql27tl544QW99tprCggIUEpKyk1x7FGoUCGFhITo448/1m+//eYsT01NlSQdP35cGTNmVOXKlX1VYrqTtu2+++475cmTRzExMUpISPB635iZsmbNqq5du8rMtGXLFuf+jRo1UuHChX1Vfrrg5+enrVu3qmPHjnr99dd19OhRZ93YsWO1evVq7du3T998840OHjyogQMH6vvvv5eZ6cEHH9Tq1asVGRnpw1fgLoQDwA0sLCxM/fr1U44cOdSpUyfVq1dP4eHh6tKli2rVqqV27drp1KlTKlKkiBYvXqxevXpJkkqUKKHw8HAfV3/z83g8kqTff/9d33//vTp06KAyZcro4Ycf1tKlSzV8+HCFh4erefPmmj17tr755hudOnVK0v8dkNwMTp8+rSNHjmjjxo3asWOHhg8frh49emj//v0aOnSohgwZorVr12rYsGGaN2+eqlSpohw5cvi67Bta2vvDzBQeHq5HHnlE0dHR2rx5s1566SW9+OKL2rdvn6ZOnaqdO3dKOncAlpqaqixZsuiJJ57QjBkzlDt3bl++jBvSzz//rKioKJUrV04jRoxQnTp1NHXqVL300kvq27ev9u7dq/bt20uSAgMDJUk7duxQeHj4TfW5TQ+io6NVq1Yt53ZUVJSmTJly0YDgf//7n3r06KG33377gse5WcKcfPnyafz48Zo/f76ee+455yQ1LaR+7bXXdPDgQdWuXduXZaYLZiZJOnPmjCTp3nvv1bPPPqsdO3bowQcf1JkzZ+Tv76+UlBTnuz4yMlKRkZGKi4vzWd3pjZnpzJkzatmypb744gu99957qlSpkt566y0tWbJExYsXV968eTV//nzlzp1bS5Ys0ZEjR/TEE09o7dq1kqQsWbL4+FW4jA97LQC4iPO7X6UZNGiQ3XLLLfbyyy9bYmKi7du3z5YuXWqtWrWyBg0amMfjMY/HYxEREU4XblwfL730krVo0cIeeOABp9v3X7sc//TTT/b8889bvnz5vGaZuJksXrzYAgICrGDBgpY1a1abMGGC7dy508zOvZcbNmxo7dq183GV6cP5Mz+MGzfOfv75Z6/1iYmJFhMTY2+++abVqFHDHnvsMdu2bdsF98eFdu7cacHBwfbcc885y06fPm316tWzWrVqWUJCgn311VcWERFhVapUsUceecTuv/9+y5w58017WVB6MHz4cPv888+d26tWrbJ8+fJdcInBI488Yg0aNPBFiddNcnKyTZgwwQICAqx48eL28MMP28CBA+3++++38PBwxhm6AjExMVakSBH76quvzOzcvuC9996zqlWrWqtWrZzv9LRLC7Zu3Wo1atSw2bNnmxnjuPyTv26bGTNmWKFChaxbt27WrVs369q1q+XLl8+GDBlinTp1svDwcGccl99//92qVq1qe/fu9UXprpf++1gBN4nU1FT5+fk5CfXp06cVGhoqSRoyZIhSU1P11ltvKTk5WY888ojq1q2r2rVry+Px6Ntvv9X27dt15513KmfOnL58Ga6SmpqqoKAgzZ07V7fccovz603af6VzqXmFChVUokQJZcmSRQsWLNCJEyeUNWtWX5V9Tdxxxx3avXu3Dh8+rIIFC3r1DPD391doaKiKFi3q/PJ6/jbC/0nbD2zatEmtWrVS6dKlVaBAAZUrV06SlJycrMDAQEVEROjJJ59UUFCQ3n77bb311lt64oknVLp0abbt30hNTdUHH3ygrFmzer0/M2bMqHr16mn27NlKTU1V06ZNVa5cOQ0bNkyxsf+vvbsPq/F+/AD+PqfSKaEtKUSYvhghLSIu8w1tZDJdmMlKS+VXHsaUp4yKZNWUNmm1JEbI81Ni8hSmxQh5mGHI8pAilTqf3x+u7nVkG/ua0+m8X9fVdek+9333OV353J/z/jwVon79+jh27Bg6duyoxtJrt7y8PMyePRsKhQIuLi7SCIIRI0Zg4MCBSE9Ph6WlJYKDg2FmZqbu4v6rdHR04O3tja5duyI8PBzHjh2DsbExunTpgiNHjqhM76K/9vjxY3Tv3h3e3t6oV68eBg8ejNGjRwMA4uLi4ObmhuTkZBgYGAAAvvvuO8hkMmnaRlV7jVRVPceKi4tx584dmJub44MPPoBSqcTkyZPx4Ycf4qOPPoKPjw/mzp2LoqIiFBYWoqSkBEqlEs2bN0dWVladGfGjcdSdThCRak9hcHCw6N27t7C0tBSjR48WK1eulM6bM2eOsLCwEKGhoc9dEZ7+Xc/rJSgqKhLffvut0NXVFUFBQX953fHjx4WpqanUo64NysrKxOzZs0WzZs242vAL+rudH4T4YwcCIYSIj48XrVu3FlOmTOFCj3/jxo0bYtKkSaJHjx4iNDRUCCFEQUGBMDIyEmFhYc+9hosPvl5/NvLF399fKBQKqZdXiD8WKezatavKudrSo1tRUSG9V44Y+mcuX74svLy8hLGxsTQi4NkRBEIIERYWJho2bFhjJBepqvo7PHfunBg0aJDo1auXmDBhgsoWhS1atBAeHh7i999/F0+ePBH5+fnihx9+ULmPtvwfro0YDhCpWfU94q2srMRHH30kxo8fL0JCQkTr1q1Fs2bNxPTp06Xzg4KChIWFhQgLC2NA8BpVb3gVFhaKwsJC6fuSkhKxdOlSIZfLxYIFC6Tjzz7cYmJihKmpqdasurty5UoxceJEYWZmxqGuL+ivdn64fv26yvZ51VfTT0pK4orZL+jWrVvCz89P9OrVS3z++efCwsJC+Pv7S68rlUqV/7tspKrHtWvXagSpPj4+NQKCH374Qbi4uGjlh2P+nb64Z/8+qu9ecenSJeHl5SUaNWpUIyDo1auXMDMzE/r6+uLEiROvtcyapnp7tnHjxiIwMFBkZ2erhNlCCLFp0yZhYWEhPD09VXbV4t9w7cBwgEiNqu+ta2RkJKZPny7u378vvZ6Xlyfc3NyEmZmZCAkJkY4HBwcLQ0NDERERwV6t16B6o2LRokXCwcFBdOvWTQwbNkyak1hWViZiYmKEjo7Oc3sgy8rKRFBQkNb0Opw/f168++67YtiwYeLs2bPqLo7GePLkiejTp4+IiYmRju3atUtMnjxZNGzYULRu3Vo4OjpKjai6sD2bOty8eVP4+fmJpk2binfeeUc6zt+nekRHR6vML54+fbpo3769UCgU4r333hPh4eHSa76+vsLQ0FBs3Lixxn34PKS/cu3aNZVtIKv/vVQFBGZmZiIjI0MI8TSAjY2NFX379tWaZ/f/6tatW8La2rrGdprPhq6bN28WFhYWwsfHh7/bWobhAJGaVS2QNXv2bCHEHw+rqkbqpUuXxHvvvSesra3FmTNnpOvCw8M5TPs1mzlzpmjatKmIiYkRO3fuFKampmLAgAHi0qVLQoinvbuxsbFCJpOJ5OTkGtdrWyp++/ZtlREW9PcePHgg2rdvL7y8vMT58+fFggULRLt27cTw4cPFkiVLREJCgmjbtq347LPP1F1UjZefny/8/f1Fjx49VAI9beyBVqdz584JmUwmPvnkE3H79m2RmJgomjdvLlJTU8XWrVuFh4eHsLW1FVOmTJGumThxopDJZGL//v1qLDlpkidPnoiPPvpI2NjYqCxuWT0gOHv2rBg5cqTo16+ftLhzWVkZn2MvYceOHcLa2lqcO3fuuW2e6r/vjRs3CkNDQzFp0qQaowtIfRgOEKlRZWWlmDFjhjA1NRVLliyRjldVnlUV64EDB4RcLn9uTwm9Hrt37xbW1tbiwIEDQgghdu7cKRo0aCBMTU1F586dxeXLl4UQTxsS69evZw8k/WMvsvPDJ598ot5C1hFVUwwcHBz+dM0Q+vdUPeMOHTokFAqF8PX1FV988YWIjY2Vzrl7964ICwsTNjY2IjU1VToeFRXFepZeysWLF8XQoUNFv379xKpVq6Tj1T+wrlu3TpiZmUmhP72cOXPmiJYtW0rfP2/qy8OHD0VJSYkQQojt27ezo6uW4ZLGRGokl8vh5+eH0aNHY/Xq1QgLCwPwdDXi6vtp29rawsTEBDdv3gTwx/689Pro6OjAw8MDffr0we7duzFmzBgsXrwYx44dw40bN+Dj44O8vDzUq1cPw4cPh66uLioqKtRdbNJAVTs/bNiwAb/88gu8vb3Rtm1bAH/s/NCiRQuIpwG/mkur2czNzTFr1ixYWVnhyJEjuHv3rrqLpFVkMhmUSiUcHByQnp6OhIQEzJs3T3rWAcCbb76J//u//4O+vj72798vHZ88eTLrWXopbdu2RVRUFAwNDfHtt9/i+++/B/C0Xn3y5AkA4D//+Q+aNGnCuvUFVG+nVrGwsEBRURHOnTsHQHVHh6p/z5o1C1OmTIEQAoMGDYKVldXrKTC9EIYDRGrWrFkzBAYGws7ODps2bcKiRYsAPA0OqirenJwcNGvWDPb29gC4fc6/7XkPPEdHR7i6uqK0tBRhYWGYMGECvL29YWxsjFatWiEjIwMhISEq1+jqcrdY+mdatGgBW1tblS33ysvLMXfuXBw+fBhjx46FTCZjXfAKmJubIywsDCkpKTAxMVF3cbSOXC5HZWUl+vTpg8OHD8PAwAA//PADLly4IJ1jZGSEnj174sqVKygvL1e5nvUsvYzWrVsjJiYGhoaGiI+Px4oVKwAAenp6AIBVq1bB0NBQpe6l55PL5bh27Rqio6OlY82aNUNRURE2bdqEhw8f1rimvLwcT548QZcuXfj8qqUYDhDVAlW9V3Z2dti4caMUEFTt8bphwwaYmZmhVatWaiyldqjanxcATp8+jatXr6KgoADA0w9sBQUF+O2339CzZ08ATxsUnTp1wtmzZ5GUlKSuYlMdl5KSgs8//xzx8fHYtm0be1peMTMzM5iZmam7GFrj2QC26ln3zjvvYM+ePThx4gTmzp2Ln3/+GQBQXFyMQ4cOoXnz5qhXr95rLy/VLVUBgbGxMb7++mtMmjQJa9euhZ+fH5KSkrB8+XIYGxuru5i1XmVlJb7++mvExsYiPDwcAODs7IxPP/0UwcHBWLlyJe7cuaNyfnBwMPbu3QsnJyd1FZv+hkxw3AxRrZGfn4/Q0FD8+OOPGDZsGAICAhASEoLIyEgcOHAAnTp1UncRtUZgYCBSU1NRVFSEgQMHwsPDAwMGDIBSqUT79u3RsmVLeHp6Ij4+HiUlJThy5IjUA1bV0CV6FfLy8uDj44M33ngDoaGh6NChg7qLRPSPVQ9gU1JScP36dRQWFmLChAkwMzODQqHAwYMHMWDAAJiamsLGxgY6Ojq4fv06srKyoKenByEEex3pf/bbb78hISEBaWlp0NHRQYsWLbBgwQJ07NhR3UXTGDdu3MDixYtx9OhRfPDBB5g5cyYePXoET09PpKam4sMPP4SzszPu3r2L06dPY8uWLdi3bx+6du2q7qLTn2A4QFTLVAUEp06dQllZGX7++WccPnwY3bp1U3fR6rTqjc09e/bAy8sLCQkJuHDhAvbs2YNbt24hICAALi4uyMnJwccffwx9fX00btwYO3bsgJ6enkqjl+hV+v3336Gvr49GjRqpuyhEr0RgYCC+++479OnTB+fOnYOenh5mzJiBwYMHw8jICEePHoWTkxMMDAywYsUK9O/fHzo6OqioqOBUAnqllEolHj9+DB0dHSgUCnUXR+NUtVuPHz+O4cOHY/r06QCAkJAQrF27Fr/88gtatWoFW1tbzJgxgwF3LcdwgKgWys/Px8yZM3Hw4EGsW7eOCetrtHnzZuzZswetW7fG1KlTAQBZWVmIjo7GL7/8gqCgIAwePBgVFRW4ffs2mjVrBplMxgYrEdEL+vrrrxEWFoYtW7aga9euyMjIwMCBA9GpUycphK1fvz7279+PuXPnYv/+/ZDJZByZRa8cR6G8GtUDgmHDhiEwMBAAcP/+fZSXl8PExARKpZLTgjQAwwGiWqqgoABKpZLzYF+jCxcuYNy4ccjNzYW/vz/mz58vvZaVlYWYmBhcuXIFkyZNwqhRo6TXOGKAiOjPVf9QX1paisWLF8PU1BQ+Pj7YsGEDPv30UyxcuBAbN27EuXPnsHDhQjg7O6uMlGE9S1S7VZ8aWzXFAPjj/z+DGM3AcICItFbVg6r6A2vr1q348ssvcfv2bSQkJMDBwUE6/+jRo/jiiy/QokULxMfHq6vYREQaKS4uDkOHDsXNmzdhYWGB+/fvw8XFBd7e3pg8eTJ++ukn9OrVC02bNsWyZcvg5OTEDxREGqQqIMjJyYGjoyPmzZun7iLRS2IES0RaSalUSg3O8vJylJWVAQCGDBmCwMBAtGzZEqGhocjKypKusbe3R0REBOLi4tRSZiIiTVJ9V4KlS5fC19cX9+7dg42NDZo0aYLc3FwYGhrCxcUFAHDnzh2MHTsWI0aMQP/+/QFw614iTVK1+5aVlRWOHDmCu3fvqrtI9JI4QZaItE714akRERHYs2cPysvL0aZNG0REROD999+HEAJLlixBcHAwgoKCYG9vDwDSKsYc4kpE9Neq6sjMzEzI5XKkpaXh7bffRtWg1Tt37uDu3bu4evUq9PT0sHTpUnTs2BELFy4EAK4xQKSBzM3NERYWBgAwMTFRc2noZXFaARFprVmzZmH58uXw8/NDWVkZ1qxZA4VCgTVr1qBz587YvHkzli9fjoKCAiQmJnIrSSKil3T8+HH07NkTenp6WLNmDVxcXKQP/WVlZejVqxdu3LgBPT09NG7cGMePH4eenp66i01EpJUYDhCRVigrK4O+vr70/aVLl/D+++8jKioKzs7OAICSkhL069cPpaWlOHXqFAAgNTUVR48exZdffsmRAkRELyk/Px+rV69GSEgI3NzcsGTJEgB/1Mnl5eXYvn07ZDIZhgwZwu0KiYjUiC1dIqrz+vbti507d6ocKykpQWFhIVq3bg3g6boDhoaG2Lp1K27fvo2YmBgAwIgRIxAZGQm5XK4yf5aIiFQ9W0cqlUqYm5vD29sbgYGBWLZsmbRAmb6+PsrKylCvXj0MGzYMLi4u0NHRQWVlJYMBIiI1Ye1LRHXeBx98gPfffx8ApB4pKysr6OrqYt26dejYsSPq1auHyspKGBoawsLCAqWlpTXuw5EDRETPV30dliVLliA3NxenT5+Gt7c3+vbti2nTpkEulyM0NBQymQxBQUHQ19evsX4L1xggIlIfhgNEVGdVbYE1depUAMCCBQvQqFEjjB07Fg0aNICvry82b94MMzMz+Pr6QkdHBwqFAgBUpiAQEdFfq/qAHxgYiMTERAQEBMDY2BjBwcHYuXMnkpOT4e7uLgUExcXFWLx4MUNXIqJahOEAEdVZz26BlZ+fj9mzZ8PQ0BAeHh5wd3fH7du3ERERgYMHD6JTp07Ys2cPSktLMWHCBDWVmohIMx06dAhpaWnYvn077OzscODAAURFRWHevHnQ19eHvr4+xo8fj6KiImRlZUkBLhER1Q4MB4ioTsrKyoK9vT1kMhkWLVqELl26IDo6GgqFAt7e3lAqlfD09MTs2bNhb2+PpUuXorCwEJaWlkhPT4euri630SIiegllZWVo2LAh7OzssHbtWnh5eSE6OhpjxozBw4cPcfToUfTr1w9Tp06FkZERZDIZAwIiolqE4QAR1TmXLl3C+PHj0blzZzRu3BixsbHIyckBAISHh0OpVMLHxwcA4O7uDjc3N7i5uak0UrlaNhHRn6teX1b9+9GjR1Aqldi6dSu8vb2xcOFC+Pr6AgAyMzOxYcMGWFlZwdLSssY9iIhI/biVIRHVOWVlZVi3bh0mT56M0tJSZGZmwtbWFo8fP4aBgQEAYNq0aYiJicGyZcswfPhwNGzYULqeDVYioj9XfRHBZ+tLW1tb5OTkID4+Hp6engCA0tJSuLq6wsjICN9//z3rVyKiWordYkRUZ1Q1WPX19WFmZgaFQgETExNER0dj+fLlMDAwkPbW/vLLLyGTyeDp6QlTU1M4OztL92HDlYjo+YQQUjAQGxuLw4cPo23btujbty8cHR2xdOlSeHh4YPny5TA1NcXdu3exZs0a3Lx5Ezk5OZDJZDV2KCAiotqBIweIqE6o3tg8e/YslEolTExMkJGRga+++grt2rVDUlIS6tWrp3JuXFwcPD09OYWAiOhvVB8lEBwcjKioKAwaNAgnT56EsbExfHx8MGbMGOTk5GDq1Km4evUqzMzM8NZbbyExMRF6enpcy4WIqBZja5iINF71nqxZs2YhPT0ds2bNQqdOneDq6orS0lLExcVh3LhxSEpKgq6uLiZMmIDhw4fD29sbANcYICL6K9XryOzsbBQUFGDz5s3o06cPzpw5g6+++goRERFQKpUYO3Ys9u3bh+vXr8PExAQGBgaQyWSsZ4mIajmOHCCiOiM4OBhLly5FcnIy7Ozs8OabbwJ4Ot81JSUF33zzDSorK9GkSRPk5ubi6tWrbKgSEf2Fb775RlpUEADS0tIwf/58AMD27dvRvHlzAEBubi6++uor/PTTT5gwYYK03kAVruVCRFT7ccIXEWmk8vJyle9v3bqFjRs3IjIyEk5OTlIwUFlZCYVCgbFjxyIsLAwODg5o27atFAxUVlaqo/hERLXejh07MH/+fIwfP146Vr9+fTRr1gyXL19GVlaWdLxjx46YMmUK7Ozs8MUXX2DHjh0q92IwQERU+3HkABFpnH79+mHatGkYPHiwdOzy5cuwt7fH1q1bYW9vr7KuQGlpKR49egQTExOV+3CIKxHRnysqKkJycjISExNhY2ODhIQEAEBWVhYWLFiAwsJCBAQEqCzoeurUKezatQvTpk3j2gJERBqGIweISOMMGDAA/fv3BwCp59/U1BRyuRwZGRkAALlcLr124sQJpKWl4eHDhyr3YTBARPR8SqUSDRs2hLu7Ozw8PJCdnY1x48YBAHr27Ilp06ahcePGiIiIwLZt26TrunTpgoCAAOjo6HBkFhGRhuHIASLSGM/OWQ0LC0Pjxo0xatQoGBkZYebMmdixYwf8/f2l+a6VlZUYNGgQTE1NsXLlSg5tJSL6G8/Wtffv38fKlSuRmJiIbt26ITExEQCwf/9+REdHo6ioCD4+PnB1dVVXkYmI6BVgtxkRaYTq0wSqGq5nzpzB2rVrYWBggI8//hgeHh4oKChAaGgo9u7diyZNmiA7OxuFhYXYtm0bZDIZF8UiIvobVXXkokWL0KNHD7z77rtwc3MDACQmJmLcuHFITEzEu+++C5lMhqCgIGRmZjIcICLScBw5QEQa4cmTJ6ioqMC9e/fQpEkT6OnpAQB8fX3x3XffIT4+Hm5ubrh58yb27t2L+Ph4mJqaonnz5oiMjISuri7XGCAiekHFxcUYM2YMtm3bhgMHDsDBwUFlBIGtra20BkFOTg66dOkiBbhERKSZGA4QUa2Xnp6OTZs2Ydu2bSguLoaDgwOGDBkCb29vAIC3tzdWrFiB+Ph4jB49+rmLYDEYICL6c1Wjs6qPrrp+/Tpmz56NNWvWYO/evejduzfu37+PlJQUJCUlwdLSEmlpaTXuQUREmoktZSKq1RITExEUFISRI0fCz88PxsbGiImJwbx583D58mWEh4cjLi4OMpkM3t7ekMvlGDp0KIyMjFTuw2CAiOj5zpw5g06dOgEA7t27BxMTEwgh0KJFC4SGhkKpVMLR0RH79u2Dg4MD3Nzc8PDhQ+Tl5akEAgwGiIg0G0cOEFGtFRcXh4kTJ2LFihUYPny4NJXg4sWLCA0Nxa5du/DZZ59h+vTpAAB/f3/ExsZi586dcHJyUmfRiYg0wsWLF9GuXTvs3LkTurq6GDJkCH766Se0b99eGkVw7do1TJw4ERkZGcjMzIStrS2Ki4thZGQEmUzGEQNERHUEa3IiqpU2bdoEX19frF+/HqNGjZKGuVZWVsLKygpz5sxBhw4dsH79ely9ehUAEBMTg8WLF8PR0VGdRSci0hjm5uYYMGAA0tLSoKenBwcHBwwaNAh5eXnSB/+WLVvi448/RklJCezs7HDq1Ck0aNBAWuSVwQARUd3A2pyIap2ysjLs3r0bbdq0kT746+rqorKyEjo6OhBC4K233sKMGTOQnZ2N69evS9dOnTpVWnyQiIj+WoMGDdC3b19s2bIFHTp0QFxcHNq1a4cBAwbg/Pnz0gf/pk2bwsvLCxEREejYsaN0PXd/ISKqOxgOEFGto6+vj6CgIDg7OyMlJQWLFi0CAOjo6ECpVErntWrVCvXq1cOjR49q3INrDBAR1VQ1m1QIIf07MDAQb7zxBubNm4c2bdogLCwMnTt3xn//+1/s27cPZ8+eRWRkJHR0dDBlyhQGsEREdRTDASKqlZo2bYrAwEDY2dlh48aNUkAgl8tRWVkJADh9+jRsbW3x9ttvq7OoREQa48GDBwCe9vjLZDJUVFRACAEXFxf8+OOPuHfvHrp06YKFCxeiX79+6N+/P4YOHYorV65gyZIlAJ4GCwxgiYjqHoYDRFRrmZubY9asWTUCAl1dXRQXFyMxMRHt27eHhYWFmktKRFT77dq1C/3790dsbCx+//13AE/rUx0dHXh6euLMmTNISEgAAFhbW2PVqlU4cuQIkpOTceLECejp6aGiooJTCYiI6ijuVkBEtV5+fj5CQ0Px448/wtXVFdOmTYOLiwt+/fVXnDhxArq6uip7cxMRUU25ubmIiorCqlWrYG1tDTs7O8yZMwdGRkYwMjJCQEAADh06hNWrV6Nly5Y16tSqdV+IiKhuYjhARBohPz8fCxYsQHZ2Ni5dugRjY2OcOXMGenp6bLASEb2ECxcuICkpCWlpaXj06BEGDhwIPz8/FBQU4JNPPsG6devQu3dvblFIRKRlGA4QkcbIz89HQEAACgoKsHnzZmmIK+e+EhG9nMrKSlRUVGDx4sXIzMzEvn374O/vj+joaPTu3Ru7d++GgYGBuotJRESvEcMBItIo9+/fR6NGjSCXyxkMEBH9Q9WnYpWVlWHLli1YvXo1du7cie7duyMzM5NTtYiItAzDASLSSBzuSkT0v3l2rZYHDx7g1q1bsLKykraOZT1LRKQ9GA4QERERkQqu5UJEpH0YDhARERERERFpOY4VIyIiIiIiItJyDAeIiIiIiIiItBzDASIiIiIiIiItx3CAiIiIiIiISMsxHCAiIiIiIiLScgwHiIiIiIiIiLQcwwEiIiIiIiIiLcdwgIiIiIiIiEjLMRwgIiKiWiUpKQnGxsb/831kMhk2bdr0P9+HiIhIGzAcICIiolfO3d0dLi4u6i4GERERvSCGA0RERERERERajuEAERERvVaRkZGwtrZG/fr10aJFC0yYMAEPHz6scd6mTZtgZWUFhUIBJycnXL9+XeX1zZs3o1u3blAoFGjTpg3mzZuHioqK5/7M8vJy+Pn5oWnTplAoFLC0tMTChQv/lfdHRESkiRgOEBER0Wsll8sRHR2N3NxcrFixAvv27cP06dNVzikpKUFoaCiSk5Nx+PBhFBYWYtSoUdLrBw8exNixYzFp0iScPXsWcXFxSEpKQmho6HN/ZnR0NLZs2YLU1FTk5eVh1apVaNWq1b/5NomIiDSKTAgh1F0IIiIiqlvc3d1RWFj4QgsCrl+/Hj4+Prhz5w6ApwsSenh44OjRo+jRowcA4Pz58+jQoQOOHTuG7t27o3///nB0dMSMGTOk+6SkpGD69Om4efMmgKcLEm7cuBEuLi6YOHEicnNzkZGRAZlM9urfMBERkYbjyAEiIiJ6rTIyMuDo6IjmzZujQYMGcHNzw927d1FSUiKdo6urCzs7O+n79u3bw9jYGOfOnQMAnDp1CvPnz4eRkZH05eXlhVu3bqncp4q7uztOnjyJdu3aYeLEiUhPT//33ygREZEGYThAREREr82vv/4KZ2dndO7cGRs2bEB2djZiY2MBPF0X4EU9fPgQ8+bNw8mTJ6Wv06dP4+LFi1AoFDXO79atG65cuYLg4GA8fvwYI0aMgKur6yt7X0RERJpOV90FICIiIu2RnZ0NpVKJiIgIyOVP+yhSU1NrnFdRUYETJ06ge/fuAIC8vDwUFhaiQ4cOAJ5+2M/Ly0Pbtm1f+Gc3bNgQI0eOxMiRI+Hq6or33nsP9+7dw5tvvvkK3hkREZFmYzhARERE/4oHDx7g5MmTKscaN26MJ0+eICYmBkOGDMHhw4exbNmyGtfq6enB398f0dHR0NXVhZ+fH+zt7aWwICgoCM7OzmjZsiVcXV0hl8tx6tQpnDlzBiEhITXuFxkZiaZNm8LGxgZyuRzr1q2Dubk5jI2N/423TkREpHE4rYCIiIj+Ffv374eNjY3K18qVKxEZGYlFixahU6dOWLVq1XO3FDQ0NERAQABGjx4NBwcHGBkZYe3atdLrTk5O2LZtG9LT02FnZwd7e3tERUXB0tLyuWVp0KABwsPD8c4778DOzg6//vorduzYIY1eICIi0nbcrYCIiIiIiIhIyzEuJyIiIiIiItJyDAeIiIiIiIiItBzDASIiIiIiIiItx3CAiIiIiIiISMsxHCAiIiIiIiLScgwHiIiIiIiIiLQcwwEiIiIiIiIiLcdwgIiIiIiIiEjLMRwgIiIiIiIi0nIMB4iIiIiIiIi0HMMBIiIiIiIiIi33/zcnunQplIbhAAAAAElFTkSuQmCC",
+      "text/plain": [
+       "<Figure size 1200x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.figure(figsize=(12, 6))\n",
+    "plt.bar(labels, sizes)\n",
+    "plt.title('Bar Graph')\n",
+    "plt.xlabel('Labels')\n",
+    "plt.ylabel('Count')\n",
+    "plt.xticks(rotation=45)\n",
+    "plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "id": "YtSxaBSZ5C_h"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1400x1000 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "fig, ax = plt.subplots(figsize=(14, 10))\n",
+    "wedges, texts, autotexts = ax.pie(sizes, autopct='%1.1f%%', startangle=140)\n",
+    "\n",
+    "ax.axis('equal')\n",
+    "plt.legend(wedges, labels, title=\"Activities\", loc=\"center left\", bbox_to_anchor=(1, 0, 0.5, 1))\n",
+    "\n",
+    "plt.title('Distribution of Network Activities')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "KObpx4wfj3aQ"
+   },
+   "source": [
+    "## Data Preprocessing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "id": "LuWeKTG2j0hF"
+   },
+   "outputs": [],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "from sklearn.preprocessing import StandardScaler"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "id": "x0UovuBRjmE0"
+   },
+   "outputs": [],
+   "source": [
+    "X = df.drop('label', axis=1)\n",
+    "y = df['label']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from scipy import sparse\n",
+    "from sklearn.preprocessing import OneHotEncoder\n",
+    "\n",
+    "encoder = OneHotEncoder(sparse_output=True, dtype=np.float32)\n",
+    "\n",
+    "X_sparse = encoder.fit_transform(X)\n",
+    "\n",
+    "y_encoded = encoder.fit_transform(np.array(y).reshape(-1, 1))\n",
+    "y_train_dense = y_encoded.toarray()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "id": "pbRTAjhy6Yb3"
+   },
+   "outputs": [],
+   "source": [
+    "X_train, X_test, y_train, y_test = train_test_split(X_sparse, y_train_dense, test_size=0.2, random_state=42)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "id": "FBpz07hL_cxj"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((505188, 646287), (126298, 646287))"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X_train.shape, X_test.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((505188, 10), (126298, 10))"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "y_train.shape, y_test.shape"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "jNDgEG-88ff9"
+   },
+   "source": [
+    "## Model Training"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "lxFMcxYX-wMg"
+   },
+   "source": [
+    "### Model 1: Random Forest Classifier"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {
+    "id": "2IhE9rN0_ZSE"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-1 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-1 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-1 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-1 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-1 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(n_estimators=10, random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;RandomForestClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.ensemble.RandomForestClassifier.html\">?<span>Documentation for RandomForestClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestClassifier(n_estimators=10, random_state=42)</pre></div> </div></div></div></div>"
+      ],
+      "text/plain": [
+       "RandomForestClassifier(n_estimators=10, random_state=42)"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "\n",
+    "model_1 = RandomForestClassifier(n_estimators=10, random_state=42)\n",
+    "model_1.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = model_1.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {
+    "id": "m76sl7hf_mMY"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.9977196788547721\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       1.00      1.00      1.00    126154\n",
+      "           1       1.00      1.00      1.00    126186\n",
+      "\n",
+      "   micro avg       1.00      1.00      1.00    252340\n",
+      "   macro avg       1.00      1.00      1.00    252340\n",
+      "weighted avg       1.00      1.00      1.00    252340\n",
+      " samples avg       1.00      1.00      1.00    252340\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.preprocessing import MultiLabelBinarizer\n",
+    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
+    "\n",
+    "# Assuming y_test and y_pred are in multi-label format\n",
+    "mlb = MultiLabelBinarizer()\n",
+    "y_test_binary = mlb.fit_transform(y_test)\n",
+    "y_pred_binary = mlb.transform(y_pred)\n",
+    "\n",
+    "# Compute and print accuracy\n",
+    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
+    "print(f\"Accuracy: {accuracy}\")\n",
+    "\n",
+    "# Print classification report\n",
+    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "FsWqdWgf_PCW"
+   },
+   "source": [
+    "### Model 2: XGBClassifier"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {
+    "id": "uPcz1c688h5U"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-2 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-2 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-2 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-2 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-2 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-2 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-2 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
+       "              colsample_bylevel=None, colsample_bynode=None,\n",
+       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
+       "              gamma=None, grow_policy=None, importance_type=None,\n",
+       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
+       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
+       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
+       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
+       "              num_parallel_tree=None, random_state=None, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;XGBClassifier<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
+       "              colsample_bylevel=None, colsample_bynode=None,\n",
+       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
+       "              gamma=None, grow_policy=None, importance_type=None,\n",
+       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
+       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
+       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
+       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
+       "              num_parallel_tree=None, random_state=None, ...)</pre></div> </div></div></div></div>"
+      ],
+      "text/plain": [
+       "XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
+       "              colsample_bylevel=None, colsample_bynode=None,\n",
+       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
+       "              gamma=None, grow_policy=None, importance_type=None,\n",
+       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
+       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
+       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
+       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
+       "              num_parallel_tree=None, random_state=None, ...)"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from xgboost import XGBClassifier\n",
+    "\n",
+    "model_2 = XGBClassifier()\n",
+    "model_2.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = model_2.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.9979176233986287\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       1.00      1.00      1.00    126154\n",
+      "           1       1.00      1.00      1.00    126186\n",
+      "\n",
+      "   micro avg       1.00      1.00      1.00    252340\n",
+      "   macro avg       1.00      1.00      1.00    252340\n",
+      "weighted avg       1.00      1.00      1.00    252340\n",
+      " samples avg       1.00      1.00      1.00    252340\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.preprocessing import MultiLabelBinarizer\n",
+    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
+    "\n",
+    "# Assuming y_test and y_pred are in multi-label format\n",
+    "mlb = MultiLabelBinarizer()\n",
+    "y_test_binary = mlb.fit_transform(y_test)\n",
+    "y_pred_binary = mlb.transform(y_pred)\n",
+    "\n",
+    "# Compute and print accuracy\n",
+    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
+    "print(f\"Accuracy: {accuracy}\")\n",
+    "\n",
+    "# Print classification report\n",
+    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Model 3: SVM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-1 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-1 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-1 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-1 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-1 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MultiOutputClassifier(estimator=SVC(), n_jobs=-1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;MultiOutputClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.multioutput.MultiOutputClassifier.html\">?<span>Documentation for MultiOutputClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>MultiOutputClassifier(estimator=SVC(), n_jobs=-1)</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">estimator: SVC</label><div class=\"sk-toggleable__content fitted\"><pre>SVC()</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;SVC<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.svm.SVC.html\">?<span>Documentation for SVC</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>SVC()</pre></div> </div></div></div></div></div></div></div></div></div>"
+      ],
+      "text/plain": [
+       "MultiOutputClassifier(estimator=SVC(), n_jobs=-1)"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.multioutput import MultiOutputClassifier\n",
+    "from sklearn.svm import SVC\n",
+    "\n",
+    "svm = SVC(kernel='rbf', gamma='scale', C=1.0)\n",
+    "\n",
+    "model_3 = MultiOutputClassifier(svm, n_jobs=-1)\n",
+    "\n",
+    "model_3.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = model_3.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.9999287399642116\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       1.00      1.00      1.00    126298\n",
+      "           1       1.00      1.00      1.00    126298\n",
+      "\n",
+      "   micro avg       1.00      1.00      1.00    252596\n",
+      "   macro avg       1.00      1.00      1.00    252596\n",
+      "weighted avg       1.00      1.00      1.00    252596\n",
+      " samples avg       1.00      1.00      1.00    252596\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.preprocessing import MultiLabelBinarizer\n",
+    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
+    "\n",
+    "# Assuming y_test and y_pred are in multi-label format\n",
+    "mlb = MultiLabelBinarizer()\n",
+    "y_test_binary = mlb.fit_transform(y_test)\n",
+    "y_pred_binary = mlb.transform(y_pred)\n",
+    "\n",
+    "# Compute and print accuracy\n",
+    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
+    "print(f\"Accuracy: {accuracy}\")\n",
+    "\n",
+    "# Print classification report\n",
+    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
+   ]
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "gpuType": "T4",
+   "provenance": [],
+   "toc_visible": true
+  },
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/ACI IoT Network Traffic Dataset Analysis/Model/ACI_IoT_Network_Traffic_Dataset_Analysis.ipynb b/ACI IoT Network Traffic Dataset Analysis/Model/ACI_IoT_Network_Traffic_Dataset_Analysis.ipynb
new file mode 100644
index 000000000..a6577c761
--- /dev/null
+++ b/ACI IoT Network Traffic Dataset Analysis/Model/ACI_IoT_Network_Traffic_Dataset_Analysis.ipynb	
@@ -0,0 +1,1977 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "YwuxWrIj26L7"
+   },
+   "source": [
+    "# ACI IoT Network Traffic"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "eA-t2jeQ2_Ay"
+   },
+   "source": [
+    "## Get dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "id": "f2-gDXPihjaF"
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import tensorflow as tf\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "D:\\ML\\ACI IoT Network Traffic Dataset Analysis\\Model\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "print(os.getcwd())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>srcip</th>\n",
+       "      <th>sport</th>\n",
+       "      <th>dstip</th>\n",
+       "      <th>dsport</th>\n",
+       "      <th>protocol_m</th>\n",
+       "      <th>sttl</th>\n",
+       "      <th>total_len</th>\n",
+       "      <th>payload</th>\n",
+       "      <th>stime</th>\n",
+       "      <th>label</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>192.168.1.81</td>\n",
+       "      <td>60683</td>\n",
+       "      <td>239.255.255.250</td>\n",
+       "      <td>1900</td>\n",
+       "      <td>udp</td>\n",
+       "      <td>2</td>\n",
+       "      <td>362</td>\n",
+       "      <td>4e4f54494659202a20485454502f312e310d0a4e54533a...</td>\n",
+       "      <td>1698670981</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>192.168.1.9</td>\n",
+       "      <td>53160</td>\n",
+       "      <td>239.255.255.250</td>\n",
+       "      <td>1900</td>\n",
+       "      <td>udp</td>\n",
+       "      <td>1</td>\n",
+       "      <td>204</td>\n",
+       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
+       "      <td>1698670984</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>192.168.1.9</td>\n",
+       "      <td>53160</td>\n",
+       "      <td>239.255.255.250</td>\n",
+       "      <td>1900</td>\n",
+       "      <td>udp</td>\n",
+       "      <td>1</td>\n",
+       "      <td>204</td>\n",
+       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
+       "      <td>1698670985</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>192.168.1.9</td>\n",
+       "      <td>53160</td>\n",
+       "      <td>239.255.255.250</td>\n",
+       "      <td>1900</td>\n",
+       "      <td>udp</td>\n",
+       "      <td>1</td>\n",
+       "      <td>204</td>\n",
+       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
+       "      <td>1698670986</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>192.168.1.9</td>\n",
+       "      <td>53160</td>\n",
+       "      <td>239.255.255.250</td>\n",
+       "      <td>1900</td>\n",
+       "      <td>udp</td>\n",
+       "      <td>1</td>\n",
+       "      <td>204</td>\n",
+       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
+       "      <td>1698670987</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          srcip  sport            dstip  dsport protocol_m  sttl  total_len  \\\n",
+       "0  192.168.1.81  60683  239.255.255.250    1900        udp     2        362   \n",
+       "1   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
+       "2   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
+       "3   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
+       "4   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
+       "\n",
+       "                                             payload       stime   label  \n",
+       "0  4e4f54494659202a20485454502f312e310d0a4e54533a...  1698670981  Benign  \n",
+       "1  4d2d534541524348202a20485454502f312e310d0a484f...  1698670984  Benign  \n",
+       "2  4d2d534541524348202a20485454502f312e310d0a484f...  1698670985  Benign  \n",
+       "3  4d2d534541524348202a20485454502f312e310d0a484f...  1698670986  Benign  \n",
+       "4  4d2d534541524348202a20485454502f312e310d0a484f...  1698670987  Benign  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.read_csv('D:\\ML\\ACI IoT Network Traffic Dataset Analysis\\Dataset\\ACI-IoT-2023-Payload.csv')\n",
+    "pd.set_option('display.max_columns', None)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "dW7fRPpahgGd"
+   },
+   "source": [
+    "## EDA"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "id": "t4ChRqiXsIZZ"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "srcip         0\n",
+       "sport         0\n",
+       "dstip         0\n",
+       "dsport        0\n",
+       "protocol_m    0\n",
+       "sttl          0\n",
+       "total_len     0\n",
+       "payload       0\n",
+       "stime         0\n",
+       "label         0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "id": "CxOR0kJM3SWR"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "label\n",
+       "Benign                601868\n",
+       "DNS Flood              18577\n",
+       "Dictionary Attack       4645\n",
+       "Slowloris               2974\n",
+       "SYN Flood               2113\n",
+       "Port Scan                582\n",
+       "Vulnerability Scan       445\n",
+       "OS Scan                  156\n",
+       "UDP Flood                 68\n",
+       "ICMP Flood                58\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.label.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "id": "mrlQp4My4faj"
+   },
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "labels = ['Benign', 'DNS Flood', 'Dictionary Attack', 'Slowloris', 'SYN Flood',\n",
+    "          'Port Scan', 'Vulnerability Scan', 'OS Scan', 'UDP Flood', 'ICMP Flood']\n",
+    "sizes = [601868, 18577, 4645, 2974, 2113, 582, 445, 156, 68, 58]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "id": "Actc2Dc-4l4W"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1200x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.figure(figsize=(12, 6))\n",
+    "plt.bar(labels, sizes)\n",
+    "plt.title('Bar Graph')\n",
+    "plt.xlabel('Labels')\n",
+    "plt.ylabel('Count')\n",
+    "plt.xticks(rotation=45)\n",
+    "plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "id": "YtSxaBSZ5C_h"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 1400x1000 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "fig, ax = plt.subplots(figsize=(14, 10))\n",
+    "wedges, texts, autotexts = ax.pie(sizes, autopct='%1.1f%%', startangle=140)\n",
+    "\n",
+    "ax.axis('equal')\n",
+    "plt.legend(wedges, labels, title=\"Activities\", loc=\"center left\", bbox_to_anchor=(1, 0, 0.5, 1))\n",
+    "\n",
+    "plt.title('Distribution of Network Activities')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "KObpx4wfj3aQ"
+   },
+   "source": [
+    "## Data Preprocessing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "id": "LuWeKTG2j0hF"
+   },
+   "outputs": [],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "from sklearn.preprocessing import StandardScaler"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "id": "x0UovuBRjmE0"
+   },
+   "outputs": [],
+   "source": [
+    "X = df.drop('label', axis=1)\n",
+    "y = df['label']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from scipy import sparse\n",
+    "from sklearn.preprocessing import OneHotEncoder\n",
+    "\n",
+    "encoder = OneHotEncoder(sparse_output=True, dtype=np.float32)\n",
+    "\n",
+    "X_sparse = encoder.fit_transform(X)\n",
+    "\n",
+    "y_encoded = encoder.fit_transform(np.array(y).reshape(-1, 1))\n",
+    "y_train_dense = y_encoded.toarray()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "id": "pbRTAjhy6Yb3"
+   },
+   "outputs": [],
+   "source": [
+    "X_train, X_test, y_train, y_test = train_test_split(X_sparse, y_train_dense, test_size=0.2, random_state=42)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "id": "FBpz07hL_cxj"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((505188, 646287), (126298, 646287))"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X_train.shape, X_test.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((505188, 10), (126298, 10))"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "y_train.shape, y_test.shape"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "jNDgEG-88ff9"
+   },
+   "source": [
+    "## Model Training"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "lxFMcxYX-wMg"
+   },
+   "source": [
+    "### Model 1: Random Forest Classifier"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {
+    "id": "2IhE9rN0_ZSE"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-1 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-1 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-1 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-1 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-1 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(n_estimators=10, random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;RandomForestClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.ensemble.RandomForestClassifier.html\">?<span>Documentation for RandomForestClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestClassifier(n_estimators=10, random_state=42)</pre></div> </div></div></div></div>"
+      ],
+      "text/plain": [
+       "RandomForestClassifier(n_estimators=10, random_state=42)"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "\n",
+    "model_1 = RandomForestClassifier(n_estimators=10, random_state=42)\n",
+    "model_1.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = model_1.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {
+    "id": "m76sl7hf_mMY"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.9977196788547721\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       1.00      1.00      1.00    126154\n",
+      "           1       1.00      1.00      1.00    126186\n",
+      "\n",
+      "   micro avg       1.00      1.00      1.00    252340\n",
+      "   macro avg       1.00      1.00      1.00    252340\n",
+      "weighted avg       1.00      1.00      1.00    252340\n",
+      " samples avg       1.00      1.00      1.00    252340\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.preprocessing import MultiLabelBinarizer\n",
+    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
+    "\n",
+    "# Assuming y_test and y_pred are in multi-label format\n",
+    "mlb = MultiLabelBinarizer()\n",
+    "y_test_binary = mlb.fit_transform(y_test)\n",
+    "y_pred_binary = mlb.transform(y_pred)\n",
+    "\n",
+    "# Compute and print accuracy\n",
+    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
+    "print(f\"Accuracy: {accuracy}\")\n",
+    "\n",
+    "# Print classification report\n",
+    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "FsWqdWgf_PCW"
+   },
+   "source": [
+    "### Model 2: XGBClassifier"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {
+    "id": "uPcz1c688h5U"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-2 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-2 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-2 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-2 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-2 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-2 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-2 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
+       "              colsample_bylevel=None, colsample_bynode=None,\n",
+       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
+       "              gamma=None, grow_policy=None, importance_type=None,\n",
+       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
+       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
+       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
+       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
+       "              num_parallel_tree=None, random_state=None, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;XGBClassifier<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
+       "              colsample_bylevel=None, colsample_bynode=None,\n",
+       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
+       "              gamma=None, grow_policy=None, importance_type=None,\n",
+       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
+       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
+       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
+       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
+       "              num_parallel_tree=None, random_state=None, ...)</pre></div> </div></div></div></div>"
+      ],
+      "text/plain": [
+       "XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
+       "              colsample_bylevel=None, colsample_bynode=None,\n",
+       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
+       "              gamma=None, grow_policy=None, importance_type=None,\n",
+       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
+       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
+       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
+       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
+       "              num_parallel_tree=None, random_state=None, ...)"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from xgboost import XGBClassifier\n",
+    "\n",
+    "model_2 = XGBClassifier()\n",
+    "model_2.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = model_2.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.9979176233986287\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       1.00      1.00      1.00    126154\n",
+      "           1       1.00      1.00      1.00    126186\n",
+      "\n",
+      "   micro avg       1.00      1.00      1.00    252340\n",
+      "   macro avg       1.00      1.00      1.00    252340\n",
+      "weighted avg       1.00      1.00      1.00    252340\n",
+      " samples avg       1.00      1.00      1.00    252340\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.preprocessing import MultiLabelBinarizer\n",
+    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
+    "\n",
+    "# Assuming y_test and y_pred are in multi-label format\n",
+    "mlb = MultiLabelBinarizer()\n",
+    "y_test_binary = mlb.fit_transform(y_test)\n",
+    "y_pred_binary = mlb.transform(y_pred)\n",
+    "\n",
+    "# Compute and print accuracy\n",
+    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
+    "print(f\"Accuracy: {accuracy}\")\n",
+    "\n",
+    "# Print classification report\n",
+    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Model 3: SVM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-1 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-1 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-1 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-1 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-1 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MultiOutputClassifier(estimator=SVC(), n_jobs=-1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;MultiOutputClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.multioutput.MultiOutputClassifier.html\">?<span>Documentation for MultiOutputClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>MultiOutputClassifier(estimator=SVC(), n_jobs=-1)</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">estimator: SVC</label><div class=\"sk-toggleable__content fitted\"><pre>SVC()</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;SVC<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.svm.SVC.html\">?<span>Documentation for SVC</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>SVC()</pre></div> </div></div></div></div></div></div></div></div></div>"
+      ],
+      "text/plain": [
+       "MultiOutputClassifier(estimator=SVC(), n_jobs=-1)"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.multioutput import MultiOutputClassifier\n",
+    "from sklearn.svm import SVC\n",
+    "\n",
+    "svm = SVC(kernel='rbf', gamma='scale', C=1.0)\n",
+    "\n",
+    "model_3 = MultiOutputClassifier(svm, n_jobs=-1)\n",
+    "\n",
+    "model_3.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = model_3.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.9999287399642116\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       1.00      1.00      1.00    126298\n",
+      "           1       1.00      1.00      1.00    126298\n",
+      "\n",
+      "   micro avg       1.00      1.00      1.00    252596\n",
+      "   macro avg       1.00      1.00      1.00    252596\n",
+      "weighted avg       1.00      1.00      1.00    252596\n",
+      " samples avg       1.00      1.00      1.00    252596\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.preprocessing import MultiLabelBinarizer\n",
+    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
+    "\n",
+    "# Assuming y_test and y_pred are in multi-label format\n",
+    "mlb = MultiLabelBinarizer()\n",
+    "y_test_binary = mlb.fit_transform(y_test)\n",
+    "y_pred_binary = mlb.transform(y_pred)\n",
+    "\n",
+    "# Compute and print accuracy\n",
+    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
+    "print(f\"Accuracy: {accuracy}\")\n",
+    "\n",
+    "# Print classification report\n",
+    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
+   ]
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "gpuType": "T4",
+   "provenance": [],
+   "toc_visible": true
+  },
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/ACI IoT Network Traffic Dataset Analysis/requirements.txt b/ACI IoT Network Traffic Dataset Analysis/requirements.txt
new file mode 100644
index 000000000..8493c72c5
--- /dev/null
+++ b/ACI IoT Network Traffic Dataset Analysis/requirements.txt	
@@ -0,0 +1,4 @@
+sci-kit learn
+matplotlib
+numpy
+pandas
\ No newline at end of file

From 108134e3b5bcf1632df71c582816cb60f89e741b Mon Sep 17 00:00:00 2001
From: Aditi Kala <130339327+why-aditi@users.noreply.github.com>
Date: Tue, 18 Jun 2024 23:50:10 +0530
Subject: [PATCH 02/10] Create README.md

---
 ACI IoT Network Traffic Dataset Analysis/Dataset/README.md | 1 +
 1 file changed, 1 insertion(+)
 create mode 100644 ACI IoT Network Traffic Dataset Analysis/Dataset/README.md

diff --git a/ACI IoT Network Traffic Dataset Analysis/Dataset/README.md b/ACI IoT Network Traffic Dataset Analysis/Dataset/README.md
new file mode 100644
index 000000000..e4f69271e
--- /dev/null
+++ b/ACI IoT Network Traffic Dataset Analysis/Dataset/README.md	
@@ -0,0 +1 @@
+Link: https://www.kaggle.com/datasets/emilynack/aci-iot-network-traffic-dataset-2023

From 422f0d78c6151aef9e0438a846eb2f2235df7241 Mon Sep 17 00:00:00 2001
From: Aditi Kala <130339327+why-aditi@users.noreply.github.com>
Date: Wed, 19 Jun 2024 00:00:55 +0530
Subject: [PATCH 03/10] Create README.md

---
 .../Model/README.md                           | 49 +++++++++++++++++++
 1 file changed, 49 insertions(+)
 create mode 100644 ACI IoT Network Traffic Dataset Analysis/Model/README.md

diff --git a/ACI IoT Network Traffic Dataset Analysis/Model/README.md b/ACI IoT Network Traffic Dataset Analysis/Model/README.md
new file mode 100644
index 000000000..5c4759bb3
--- /dev/null
+++ b/ACI IoT Network Traffic Dataset Analysis/Model/README.md	
@@ -0,0 +1,49 @@
+## **ACI IoT Network Traffic Dataset Analysis**
+
+### 🎯 **Goal**
+
+Analyze the traffic dataset
+
+### 🧵 **Dataset**
+
+https://www.kaggle.com/datasets/emilynack/aci-iot-network-traffic-dataset-2023
+
+### 🧾 **Description**
+
+The project aims to analyze the ACI IoT Network Traffic Dataset 2023 to identify patterns and anomalies in network traffic. The goal is to build an accurate predictive model for network anomaly detection.
+
+### 🧮 **What I had done!**
+
+Load the data using appropriate tools and conduct an initial inspection to identify missing values and outliers. Perform exploratory data analysis (EDA) to understand feature distributions and relationships. Clean the data by handling missing values and outliers, and engineer new features if necessary. Split the data into training and testing sets, scaling features as needed. Build and evaluate various models. Finalize the best model, evaluate it on the test set, and prepare it for deployment. Document each step and report the findings to ensure clarity and reproducibility.
+### 🚀 **Models Implemented**
+
+1. Random Forest Classifier
+2. XGBoost
+3. SVM
+
+### 📚 **Libraries Needed**
+
+1. numpy
+2. Pandas
+3. Matplotlib
+4. sci-kit learn
+
+### 📊 **Exploratory Data Analysis Results**
+
+<img src = "https://github.com/why-aditi/ML-Crate/blob/main/ACI%20IoT%20Network%20Traffic%20Dataset%20Analysis/Images/Bar%20Graph.png"/>
+<img src = "https://github.com/why-aditi/ML-Crate/blob/main/ACI%20IoT%20Network%20Traffic%20Dataset%20Analysis/Images/Pie%20Chart.png"/>
+
+### 📈 **Performance of the Models based on the Accuracy Scores**
+
+1. Random Forest Classifier: 99.77%
+2. XGBoost: 99.79%
+3. SVM: 99.99%
+
+
+### 📢 **Conclusion**
+
+SVM is proven to be the best model with the accuracy score of 99.99%
+
+### ✒️ **Your Signature**
+
+Aditi Kala

From d5dffe594bed2c7dcbb5e5a667ae52270fca9274 Mon Sep 17 00:00:00 2001
From: Aditi Kala <130339327+why-aditi@users.noreply.github.com>
Date: Wed, 19 Jun 2024 11:32:09 +0530
Subject: [PATCH 04/10] Delete ACI IoT Network Traffic Dataset Analysis/.idea
 directory

---
 .../.idea/.gitignore                                 |  3 ---
 .../ACI IoT Network Traffic Dataset Analysis.iml     | 12 ------------
 .../.idea/inspectionProfiles/profiles_settings.xml   |  6 ------
 .../.idea/misc.xml                                   |  4 ----
 .../.idea/modules.xml                                |  8 --------
 5 files changed, 33 deletions(-)
 delete mode 100644 ACI IoT Network Traffic Dataset Analysis/.idea/.gitignore
 delete mode 100644 ACI IoT Network Traffic Dataset Analysis/.idea/ACI IoT Network Traffic Dataset Analysis.iml
 delete mode 100644 ACI IoT Network Traffic Dataset Analysis/.idea/inspectionProfiles/profiles_settings.xml
 delete mode 100644 ACI IoT Network Traffic Dataset Analysis/.idea/misc.xml
 delete mode 100644 ACI IoT Network Traffic Dataset Analysis/.idea/modules.xml

diff --git a/ACI IoT Network Traffic Dataset Analysis/.idea/.gitignore b/ACI IoT Network Traffic Dataset Analysis/.idea/.gitignore
deleted file mode 100644
index 26d33521a..000000000
--- a/ACI IoT Network Traffic Dataset Analysis/.idea/.gitignore	
+++ /dev/null
@@ -1,3 +0,0 @@
-# Default ignored files
-/shelf/
-/workspace.xml
diff --git a/ACI IoT Network Traffic Dataset Analysis/.idea/ACI IoT Network Traffic Dataset Analysis.iml b/ACI IoT Network Traffic Dataset Analysis/.idea/ACI IoT Network Traffic Dataset Analysis.iml
deleted file mode 100644
index 408235d99..000000000
--- a/ACI IoT Network Traffic Dataset Analysis/.idea/ACI IoT Network Traffic Dataset Analysis.iml	
+++ /dev/null
@@ -1,12 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<module type="PYTHON_MODULE" version="4">
-  <component name="NewModuleRootManager">
-    <content url="file://$MODULE_DIR$" />
-    <orderEntry type="inheritedJdk" />
-    <orderEntry type="sourceFolder" forTests="false" />
-  </component>
-  <component name="PackageRequirementsSettings">
-    <option name="requirementsPath" value="D:\ML\ACI IoT Network Traffic Dataset Analysis\requirements.txt" />
-    <option name="versionSpecifier" value="Greater or equal (&gt;=x.y.z)" />
-  </component>
-</module>
\ No newline at end of file
diff --git a/ACI IoT Network Traffic Dataset Analysis/.idea/inspectionProfiles/profiles_settings.xml b/ACI IoT Network Traffic Dataset Analysis/.idea/inspectionProfiles/profiles_settings.xml
deleted file mode 100644
index 105ce2da2..000000000
--- a/ACI IoT Network Traffic Dataset Analysis/.idea/inspectionProfiles/profiles_settings.xml	
+++ /dev/null
@@ -1,6 +0,0 @@
-<component name="InspectionProjectProfileManager">
-  <settings>
-    <option name="USE_PROJECT_PROFILE" value="false" />
-    <version value="1.0" />
-  </settings>
-</component>
\ No newline at end of file
diff --git a/ACI IoT Network Traffic Dataset Analysis/.idea/misc.xml b/ACI IoT Network Traffic Dataset Analysis/.idea/misc.xml
deleted file mode 100644
index a971a2c93..000000000
--- a/ACI IoT Network Traffic Dataset Analysis/.idea/misc.xml	
+++ /dev/null
@@ -1,4 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.11" project-jdk-type="Python SDK" />
-</project>
\ No newline at end of file
diff --git a/ACI IoT Network Traffic Dataset Analysis/.idea/modules.xml b/ACI IoT Network Traffic Dataset Analysis/.idea/modules.xml
deleted file mode 100644
index 1983d66b9..000000000
--- a/ACI IoT Network Traffic Dataset Analysis/.idea/modules.xml	
+++ /dev/null
@@ -1,8 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="ProjectModuleManager">
-    <modules>
-      <module fileurl="file://$PROJECT_DIR$/.idea/ACI IoT Network Traffic Dataset Analysis.iml" filepath="$PROJECT_DIR$/.idea/ACI IoT Network Traffic Dataset Analysis.iml" />
-    </modules>
-  </component>
-</project>
\ No newline at end of file

From 3a4d2b385e788c6bb73f3ea9df5a7db408f093d3 Mon Sep 17 00:00:00 2001
From: Aditi Kala <130339327+why-aditi@users.noreply.github.com>
Date: Sat, 22 Jun 2024 17:33:36 +0530
Subject: [PATCH 05/10] Increased number of models

---
 .../.idea/workspace.xml                       | 48 +++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100644 ACI IoT Network Traffic Dataset Analysis/.idea/workspace.xml

diff --git a/ACI IoT Network Traffic Dataset Analysis/.idea/workspace.xml b/ACI IoT Network Traffic Dataset Analysis/.idea/workspace.xml
new file mode 100644
index 000000000..4d9da96b1
--- /dev/null
+++ b/ACI IoT Network Traffic Dataset Analysis/.idea/workspace.xml	
@@ -0,0 +1,48 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<project version="4">
+  <component name="AutoImportSettings">
+    <option name="autoReloadType" value="SELECTIVE" />
+  </component>
+  <component name="ChangeListManager">
+    <list default="true" id="c27e9cb0-7f6f-48b9-b9f6-c3e0a69c1deb" name="Changes" comment="" />
+    <option name="SHOW_DIALOG" value="false" />
+    <option name="HIGHLIGHT_CONFLICTS" value="true" />
+    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
+    <option name="LAST_RESOLUTION" value="IGNORE" />
+  </component>
+  <component name="ProblemsViewState">
+    <option name="selectedTabId" value="CurrentFile" />
+  </component>
+  <component name="ProjectColorInfo">{
+  &quot;associatedIndex&quot;: 8
+}</component>
+  <component name="ProjectId" id="2hxWBFRsa0jkviGNkjNzHrOeywG" />
+  <component name="ProjectViewState">
+    <option name="hideEmptyMiddlePackages" value="true" />
+    <option name="showLibraryContents" value="true" />
+  </component>
+  <component name="PropertiesComponent">{
+  &quot;keyToString&quot;: {
+    &quot;RunOnceActivity.ShowReadmeOnStart&quot;: &quot;true&quot;,
+    &quot;ignore.virus.scanning.warn.message&quot;: &quot;true&quot;
+  }
+}</component>
+  <component name="SharedIndexes">
+    <attachedChunks>
+      <set>
+        <option value="bundled-python-sdk-babbdf50b680-746f403e7f0c-com.jetbrains.pycharm.community.sharedIndexes.bundled-PC-241.15989.155" />
+      </set>
+    </attachedChunks>
+  </component>
+  <component name="SpellCheckerSettings" RuntimeDictionaries="0" Folders="0" CustomDictionaries="0" DefaultDictionary="application-level" UseSingleDictionary="true" transferred="true" />
+  <component name="TaskManager">
+    <task active="true" id="Default" summary="Default task">
+      <changelist id="c27e9cb0-7f6f-48b9-b9f6-c3e0a69c1deb" name="Changes" comment="" />
+      <created>1718536072691</created>
+      <option name="number" value="Default" />
+      <option name="presentableId" value="Default" />
+      <updated>1718536072691</updated>
+    </task>
+    <servers />
+  </component>
+</project>
\ No newline at end of file

From 65bb2f1158df70bdf3b264b4b0914080e293e120 Mon Sep 17 00:00:00 2001
From: Aditi Kala <130339327+why-aditi@users.noreply.github.com>
Date: Sat, 22 Jun 2024 17:34:39 +0530
Subject: [PATCH 06/10] Delete ACI IoT Network Traffic Dataset Analysis/.idea
 directory

---
 .../.idea/workspace.xml                       | 48 -------------------
 1 file changed, 48 deletions(-)
 delete mode 100644 ACI IoT Network Traffic Dataset Analysis/.idea/workspace.xml

diff --git a/ACI IoT Network Traffic Dataset Analysis/.idea/workspace.xml b/ACI IoT Network Traffic Dataset Analysis/.idea/workspace.xml
deleted file mode 100644
index 4d9da96b1..000000000
--- a/ACI IoT Network Traffic Dataset Analysis/.idea/workspace.xml	
+++ /dev/null
@@ -1,48 +0,0 @@
-<?xml version="1.0" encoding="UTF-8"?>
-<project version="4">
-  <component name="AutoImportSettings">
-    <option name="autoReloadType" value="SELECTIVE" />
-  </component>
-  <component name="ChangeListManager">
-    <list default="true" id="c27e9cb0-7f6f-48b9-b9f6-c3e0a69c1deb" name="Changes" comment="" />
-    <option name="SHOW_DIALOG" value="false" />
-    <option name="HIGHLIGHT_CONFLICTS" value="true" />
-    <option name="HIGHLIGHT_NON_ACTIVE_CHANGELIST" value="false" />
-    <option name="LAST_RESOLUTION" value="IGNORE" />
-  </component>
-  <component name="ProblemsViewState">
-    <option name="selectedTabId" value="CurrentFile" />
-  </component>
-  <component name="ProjectColorInfo">{
-  &quot;associatedIndex&quot;: 8
-}</component>
-  <component name="ProjectId" id="2hxWBFRsa0jkviGNkjNzHrOeywG" />
-  <component name="ProjectViewState">
-    <option name="hideEmptyMiddlePackages" value="true" />
-    <option name="showLibraryContents" value="true" />
-  </component>
-  <component name="PropertiesComponent">{
-  &quot;keyToString&quot;: {
-    &quot;RunOnceActivity.ShowReadmeOnStart&quot;: &quot;true&quot;,
-    &quot;ignore.virus.scanning.warn.message&quot;: &quot;true&quot;
-  }
-}</component>
-  <component name="SharedIndexes">
-    <attachedChunks>
-      <set>
-        <option value="bundled-python-sdk-babbdf50b680-746f403e7f0c-com.jetbrains.pycharm.community.sharedIndexes.bundled-PC-241.15989.155" />
-      </set>
-    </attachedChunks>
-  </component>
-  <component name="SpellCheckerSettings" RuntimeDictionaries="0" Folders="0" CustomDictionaries="0" DefaultDictionary="application-level" UseSingleDictionary="true" transferred="true" />
-  <component name="TaskManager">
-    <task active="true" id="Default" summary="Default task">
-      <changelist id="c27e9cb0-7f6f-48b9-b9f6-c3e0a69c1deb" name="Changes" comment="" />
-      <created>1718536072691</created>
-      <option name="number" value="Default" />
-      <option name="presentableId" value="Default" />
-      <updated>1718536072691</updated>
-    </task>
-    <servers />
-  </component>
-</project>
\ No newline at end of file

From 2267e68900608be2c9e2bf7a4e70618ad0c55962 Mon Sep 17 00:00:00 2001
From: Aditi Kala <130339327+why-aditi@users.noreply.github.com>
Date: Sat, 22 Jun 2024 17:36:08 +0530
Subject: [PATCH 07/10] Delete ACI IoT Network Traffic Dataset
 Analysis/Model/.ipynb_checkpoints directory

---
 ..._Traffic_Dataset_Analysis-checkpoint.ipynb | 1977 -----------------
 1 file changed, 1977 deletions(-)
 delete mode 100644 ACI IoT Network Traffic Dataset Analysis/Model/.ipynb_checkpoints/ACI_IoT_Network_Traffic_Dataset_Analysis-checkpoint.ipynb

diff --git a/ACI IoT Network Traffic Dataset Analysis/Model/.ipynb_checkpoints/ACI_IoT_Network_Traffic_Dataset_Analysis-checkpoint.ipynb b/ACI IoT Network Traffic Dataset Analysis/Model/.ipynb_checkpoints/ACI_IoT_Network_Traffic_Dataset_Analysis-checkpoint.ipynb
deleted file mode 100644
index a6577c761..000000000
--- a/ACI IoT Network Traffic Dataset Analysis/Model/.ipynb_checkpoints/ACI_IoT_Network_Traffic_Dataset_Analysis-checkpoint.ipynb	
+++ /dev/null
@@ -1,1977 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "YwuxWrIj26L7"
-   },
-   "source": [
-    "# ACI IoT Network Traffic"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "eA-t2jeQ2_Ay"
-   },
-   "source": [
-    "## Get dataset"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "id": "f2-gDXPihjaF"
-   },
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "import pandas as pd\n",
-    "import tensorflow as tf\n",
-    "import matplotlib.pyplot as plt"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "D:\\ML\\ACI IoT Network Traffic Dataset Analysis\\Model\n"
-     ]
-    }
-   ],
-   "source": [
-    "import os\n",
-    "print(os.getcwd())"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>srcip</th>\n",
-       "      <th>sport</th>\n",
-       "      <th>dstip</th>\n",
-       "      <th>dsport</th>\n",
-       "      <th>protocol_m</th>\n",
-       "      <th>sttl</th>\n",
-       "      <th>total_len</th>\n",
-       "      <th>payload</th>\n",
-       "      <th>stime</th>\n",
-       "      <th>label</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>192.168.1.81</td>\n",
-       "      <td>60683</td>\n",
-       "      <td>239.255.255.250</td>\n",
-       "      <td>1900</td>\n",
-       "      <td>udp</td>\n",
-       "      <td>2</td>\n",
-       "      <td>362</td>\n",
-       "      <td>4e4f54494659202a20485454502f312e310d0a4e54533a...</td>\n",
-       "      <td>1698670981</td>\n",
-       "      <td>Benign</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>192.168.1.9</td>\n",
-       "      <td>53160</td>\n",
-       "      <td>239.255.255.250</td>\n",
-       "      <td>1900</td>\n",
-       "      <td>udp</td>\n",
-       "      <td>1</td>\n",
-       "      <td>204</td>\n",
-       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
-       "      <td>1698670984</td>\n",
-       "      <td>Benign</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>192.168.1.9</td>\n",
-       "      <td>53160</td>\n",
-       "      <td>239.255.255.250</td>\n",
-       "      <td>1900</td>\n",
-       "      <td>udp</td>\n",
-       "      <td>1</td>\n",
-       "      <td>204</td>\n",
-       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
-       "      <td>1698670985</td>\n",
-       "      <td>Benign</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>192.168.1.9</td>\n",
-       "      <td>53160</td>\n",
-       "      <td>239.255.255.250</td>\n",
-       "      <td>1900</td>\n",
-       "      <td>udp</td>\n",
-       "      <td>1</td>\n",
-       "      <td>204</td>\n",
-       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
-       "      <td>1698670986</td>\n",
-       "      <td>Benign</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>192.168.1.9</td>\n",
-       "      <td>53160</td>\n",
-       "      <td>239.255.255.250</td>\n",
-       "      <td>1900</td>\n",
-       "      <td>udp</td>\n",
-       "      <td>1</td>\n",
-       "      <td>204</td>\n",
-       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
-       "      <td>1698670987</td>\n",
-       "      <td>Benign</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "          srcip  sport            dstip  dsport protocol_m  sttl  total_len  \\\n",
-       "0  192.168.1.81  60683  239.255.255.250    1900        udp     2        362   \n",
-       "1   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
-       "2   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
-       "3   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
-       "4   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
-       "\n",
-       "                                             payload       stime   label  \n",
-       "0  4e4f54494659202a20485454502f312e310d0a4e54533a...  1698670981  Benign  \n",
-       "1  4d2d534541524348202a20485454502f312e310d0a484f...  1698670984  Benign  \n",
-       "2  4d2d534541524348202a20485454502f312e310d0a484f...  1698670985  Benign  \n",
-       "3  4d2d534541524348202a20485454502f312e310d0a484f...  1698670986  Benign  \n",
-       "4  4d2d534541524348202a20485454502f312e310d0a484f...  1698670987  Benign  "
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df = pd.read_csv('D:\\ML\\ACI IoT Network Traffic Dataset Analysis\\Dataset\\ACI-IoT-2023-Payload.csv')\n",
-    "pd.set_option('display.max_columns', None)\n",
-    "df.head()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "dW7fRPpahgGd"
-   },
-   "source": [
-    "## EDA"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "id": "t4ChRqiXsIZZ"
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "srcip         0\n",
-       "sport         0\n",
-       "dstip         0\n",
-       "dsport        0\n",
-       "protocol_m    0\n",
-       "sttl          0\n",
-       "total_len     0\n",
-       "payload       0\n",
-       "stime         0\n",
-       "label         0\n",
-       "dtype: int64"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df.isnull().sum()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "id": "CxOR0kJM3SWR"
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "label\n",
-       "Benign                601868\n",
-       "DNS Flood              18577\n",
-       "Dictionary Attack       4645\n",
-       "Slowloris               2974\n",
-       "SYN Flood               2113\n",
-       "Port Scan                582\n",
-       "Vulnerability Scan       445\n",
-       "OS Scan                  156\n",
-       "UDP Flood                 68\n",
-       "ICMP Flood                58\n",
-       "Name: count, dtype: int64"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df.label.value_counts()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {
-    "id": "mrlQp4My4faj"
-   },
-   "outputs": [],
-   "source": [
-    "import matplotlib.pyplot as plt\n",
-    "\n",
-    "labels = ['Benign', 'DNS Flood', 'Dictionary Attack', 'Slowloris', 'SYN Flood',\n",
-    "          'Port Scan', 'Vulnerability Scan', 'OS Scan', 'UDP Flood', 'ICMP Flood']\n",
-    "sizes = [601868, 18577, 4645, 2974, 2113, 582, 445, 156, 68, 58]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "id": "Actc2Dc-4l4W"
-   },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1200x600 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "plt.figure(figsize=(12, 6))\n",
-    "plt.bar(labels, sizes)\n",
-    "plt.title('Bar Graph')\n",
-    "plt.xlabel('Labels')\n",
-    "plt.ylabel('Count')\n",
-    "plt.xticks(rotation=45)\n",
-    "plt.show()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {
-    "id": "YtSxaBSZ5C_h"
-   },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1400x1000 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "fig, ax = plt.subplots(figsize=(14, 10))\n",
-    "wedges, texts, autotexts = ax.pie(sizes, autopct='%1.1f%%', startangle=140)\n",
-    "\n",
-    "ax.axis('equal')\n",
-    "plt.legend(wedges, labels, title=\"Activities\", loc=\"center left\", bbox_to_anchor=(1, 0, 0.5, 1))\n",
-    "\n",
-    "plt.title('Distribution of Network Activities')\n",
-    "plt.show()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "KObpx4wfj3aQ"
-   },
-   "source": [
-    "## Data Preprocessing"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "id": "LuWeKTG2j0hF"
-   },
-   "outputs": [],
-   "source": [
-    "from sklearn.model_selection import train_test_split\n",
-    "from sklearn.preprocessing import LabelEncoder\n",
-    "from sklearn.preprocessing import StandardScaler"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {
-    "id": "x0UovuBRjmE0"
-   },
-   "outputs": [],
-   "source": [
-    "X = df.drop('label', axis=1)\n",
-    "y = df['label']"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from scipy import sparse\n",
-    "from sklearn.preprocessing import OneHotEncoder\n",
-    "\n",
-    "encoder = OneHotEncoder(sparse_output=True, dtype=np.float32)\n",
-    "\n",
-    "X_sparse = encoder.fit_transform(X)\n",
-    "\n",
-    "y_encoded = encoder.fit_transform(np.array(y).reshape(-1, 1))\n",
-    "y_train_dense = y_encoded.toarray()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {
-    "id": "pbRTAjhy6Yb3"
-   },
-   "outputs": [],
-   "source": [
-    "X_train, X_test, y_train, y_test = train_test_split(X_sparse, y_train_dense, test_size=0.2, random_state=42)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {
-    "id": "FBpz07hL_cxj"
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "((505188, 646287), (126298, 646287))"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "X_train.shape, X_test.shape"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "((505188, 10), (126298, 10))"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "y_train.shape, y_test.shape"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "jNDgEG-88ff9"
-   },
-   "source": [
-    "## Model Training"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "lxFMcxYX-wMg"
-   },
-   "source": [
-    "### Model 1: Random Forest Classifier"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "metadata": {
-    "id": "2IhE9rN0_ZSE"
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<style>#sk-container-id-1 {\n",
-       "  /* Definition of color scheme common for light and dark mode */\n",
-       "  --sklearn-color-text: black;\n",
-       "  --sklearn-color-line: gray;\n",
-       "  /* Definition of color scheme for unfitted estimators */\n",
-       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
-       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
-       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
-       "  --sklearn-color-unfitted-level-3: chocolate;\n",
-       "  /* Definition of color scheme for fitted estimators */\n",
-       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
-       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
-       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
-       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
-       "\n",
-       "  /* Specific color for light theme */\n",
-       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
-       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
-       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
-       "  --sklearn-color-icon: #696969;\n",
-       "\n",
-       "  @media (prefers-color-scheme: dark) {\n",
-       "    /* Redefinition of color scheme for dark theme */\n",
-       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
-       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
-       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
-       "    --sklearn-color-icon: #878787;\n",
-       "  }\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 pre {\n",
-       "  padding: 0;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 input.sk-hidden--visually {\n",
-       "  border: 0;\n",
-       "  clip: rect(1px 1px 1px 1px);\n",
-       "  clip: rect(1px, 1px, 1px, 1px);\n",
-       "  height: 1px;\n",
-       "  margin: -1px;\n",
-       "  overflow: hidden;\n",
-       "  padding: 0;\n",
-       "  position: absolute;\n",
-       "  width: 1px;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
-       "  border: 1px dashed var(--sklearn-color-line);\n",
-       "  margin: 0 0.4em 0.5em 0.4em;\n",
-       "  box-sizing: border-box;\n",
-       "  padding-bottom: 0.4em;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-container {\n",
-       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
-       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
-       "     so we also need the `!important` here to be able to override the\n",
-       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
-       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
-       "  display: inline-block !important;\n",
-       "  position: relative;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       "div.sk-parallel-item,\n",
-       "div.sk-serial,\n",
-       "div.sk-item {\n",
-       "  /* draw centered vertical line to link estimators */\n",
-       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
-       "  background-size: 2px 100%;\n",
-       "  background-repeat: no-repeat;\n",
-       "  background-position: center center;\n",
-       "}\n",
-       "\n",
-       "/* Parallel-specific style estimator block */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item::after {\n",
-       "  content: \"\";\n",
-       "  width: 100%;\n",
-       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
-       "  flex-grow: 1;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel {\n",
-       "  display: flex;\n",
-       "  align-items: stretch;\n",
-       "  justify-content: center;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  position: relative;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item {\n",
-       "  display: flex;\n",
-       "  flex-direction: column;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
-       "  align-self: flex-end;\n",
-       "  width: 50%;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
-       "  align-self: flex-start;\n",
-       "  width: 50%;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
-       "  width: 0;\n",
-       "}\n",
-       "\n",
-       "/* Serial-specific style estimator block */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-serial {\n",
-       "  display: flex;\n",
-       "  flex-direction: column;\n",
-       "  align-items: center;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  padding-right: 1em;\n",
-       "  padding-left: 1em;\n",
-       "}\n",
-       "\n",
-       "\n",
-       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
-       "clickable and can be expanded/collapsed.\n",
-       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
-       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
-       "*/\n",
-       "\n",
-       "/* Pipeline and ColumnTransformer style (default) */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable {\n",
-       "  /* Default theme specific background. It is overwritten whether we have a\n",
-       "  specific estimator or a Pipeline/ColumnTransformer */\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "}\n",
-       "\n",
-       "/* Toggleable label */\n",
-       "#sk-container-id-1 label.sk-toggleable__label {\n",
-       "  cursor: pointer;\n",
-       "  display: block;\n",
-       "  width: 100%;\n",
-       "  margin-bottom: 0;\n",
-       "  padding: 0.5em;\n",
-       "  box-sizing: border-box;\n",
-       "  text-align: center;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
-       "  /* Arrow on the left of the label */\n",
-       "  content: \"▸\";\n",
-       "  float: left;\n",
-       "  margin-right: 0.25em;\n",
-       "  color: var(--sklearn-color-icon);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "}\n",
-       "\n",
-       "/* Toggleable content - dropdown */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content {\n",
-       "  max-height: 0;\n",
-       "  max-width: 0;\n",
-       "  overflow: hidden;\n",
-       "  text-align: left;\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
-       "  margin: 0.2em;\n",
-       "  border-radius: 0.25em;\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
-       "  /* Expand drop-down */\n",
-       "  max-height: 200px;\n",
-       "  max-width: 100%;\n",
-       "  overflow: auto;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
-       "  content: \"▾\";\n",
-       "}\n",
-       "\n",
-       "/* Pipeline/ColumnTransformer-specific style */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Estimator-specific style */\n",
-       "\n",
-       "/* Colorize estimator box */\n",
-       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
-       "#sk-container-id-1 div.sk-label label {\n",
-       "  /* The background is the default theme color */\n",
-       "  color: var(--sklearn-color-text-on-default-background);\n",
-       "}\n",
-       "\n",
-       "/* On hover, darken the color of the background */\n",
-       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Label box, darken color on hover, fitted */\n",
-       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Estimator label */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label label {\n",
-       "  font-family: monospace;\n",
-       "  font-weight: bold;\n",
-       "  display: inline-block;\n",
-       "  line-height: 1.2em;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label-container {\n",
-       "  text-align: center;\n",
-       "}\n",
-       "\n",
-       "/* Estimator-specific */\n",
-       "#sk-container-id-1 div.sk-estimator {\n",
-       "  font-family: monospace;\n",
-       "  border: 1px dotted var(--sklearn-color-border-box);\n",
-       "  border-radius: 0.25em;\n",
-       "  box-sizing: border-box;\n",
-       "  margin-bottom: 0.5em;\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "/* on hover */\n",
-       "#sk-container-id-1 div.sk-estimator:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
-       "\n",
-       "/* Common style for \"i\" and \"?\" */\n",
-       "\n",
-       ".sk-estimator-doc-link,\n",
-       "a:link.sk-estimator-doc-link,\n",
-       "a:visited.sk-estimator-doc-link {\n",
-       "  float: right;\n",
-       "  font-size: smaller;\n",
-       "  line-height: 1em;\n",
-       "  font-family: monospace;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  border-radius: 1em;\n",
-       "  height: 1em;\n",
-       "  width: 1em;\n",
-       "  text-decoration: none !important;\n",
-       "  margin-left: 1ex;\n",
-       "  /* unfitted */\n",
-       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-unfitted-level-1);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link.fitted,\n",
-       "a:link.sk-estimator-doc-link.fitted,\n",
-       "a:visited.sk-estimator-doc-link.fitted {\n",
-       "  /* fitted */\n",
-       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-fitted-level-1);\n",
-       "}\n",
-       "\n",
-       "/* On hover */\n",
-       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
-       ".sk-estimator-doc-link:hover,\n",
-       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
-       ".sk-estimator-doc-link:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
-       ".sk-estimator-doc-link.fitted:hover,\n",
-       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
-       ".sk-estimator-doc-link.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "/* Span, style for the box shown on hovering the info icon */\n",
-       ".sk-estimator-doc-link span {\n",
-       "  display: none;\n",
-       "  z-index: 9999;\n",
-       "  position: relative;\n",
-       "  font-weight: normal;\n",
-       "  right: .2ex;\n",
-       "  padding: .5ex;\n",
-       "  margin: .5ex;\n",
-       "  width: min-content;\n",
-       "  min-width: 20ex;\n",
-       "  max-width: 50ex;\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  box-shadow: 2pt 2pt 4pt #999;\n",
-       "  /* unfitted */\n",
-       "  background: var(--sklearn-color-unfitted-level-0);\n",
-       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link.fitted span {\n",
-       "  /* fitted */\n",
-       "  background: var(--sklearn-color-fitted-level-0);\n",
-       "  border: var(--sklearn-color-fitted-level-3);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link:hover span {\n",
-       "  display: block;\n",
-       "}\n",
-       "\n",
-       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
-       "\n",
-       "#sk-container-id-1 a.estimator_doc_link {\n",
-       "  float: right;\n",
-       "  font-size: 1rem;\n",
-       "  line-height: 1em;\n",
-       "  font-family: monospace;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  border-radius: 1rem;\n",
-       "  height: 1rem;\n",
-       "  width: 1rem;\n",
-       "  text-decoration: none;\n",
-       "  /* unfitted */\n",
-       "  color: var(--sklearn-color-unfitted-level-1);\n",
-       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
-       "  /* fitted */\n",
-       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-fitted-level-1);\n",
-       "}\n",
-       "\n",
-       "/* On hover */\n",
-       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-3);\n",
-       "}\n",
-       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(n_estimators=10, random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;RandomForestClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.ensemble.RandomForestClassifier.html\">?<span>Documentation for RandomForestClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestClassifier(n_estimators=10, random_state=42)</pre></div> </div></div></div></div>"
-      ],
-      "text/plain": [
-       "RandomForestClassifier(n_estimators=10, random_state=42)"
-      ]
-     },
-     "execution_count": 19,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from sklearn.ensemble import RandomForestClassifier\n",
-    "\n",
-    "model_1 = RandomForestClassifier(n_estimators=10, random_state=42)\n",
-    "model_1.fit(X_train, y_train)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 37,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "y_pred = model_1.predict(X_test)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 38,
-   "metadata": {
-    "id": "m76sl7hf_mMY"
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Accuracy: 0.9977196788547721\n",
-      "              precision    recall  f1-score   support\n",
-      "\n",
-      "           0       1.00      1.00      1.00    126154\n",
-      "           1       1.00      1.00      1.00    126186\n",
-      "\n",
-      "   micro avg       1.00      1.00      1.00    252340\n",
-      "   macro avg       1.00      1.00      1.00    252340\n",
-      "weighted avg       1.00      1.00      1.00    252340\n",
-      " samples avg       1.00      1.00      1.00    252340\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "from sklearn.preprocessing import MultiLabelBinarizer\n",
-    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
-    "\n",
-    "# Assuming y_test and y_pred are in multi-label format\n",
-    "mlb = MultiLabelBinarizer()\n",
-    "y_test_binary = mlb.fit_transform(y_test)\n",
-    "y_pred_binary = mlb.transform(y_pred)\n",
-    "\n",
-    "# Compute and print accuracy\n",
-    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
-    "print(f\"Accuracy: {accuracy}\")\n",
-    "\n",
-    "# Print classification report\n",
-    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "FsWqdWgf_PCW"
-   },
-   "source": [
-    "### Model 2: XGBClassifier"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 35,
-   "metadata": {
-    "id": "uPcz1c688h5U"
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<style>#sk-container-id-2 {\n",
-       "  /* Definition of color scheme common for light and dark mode */\n",
-       "  --sklearn-color-text: black;\n",
-       "  --sklearn-color-line: gray;\n",
-       "  /* Definition of color scheme for unfitted estimators */\n",
-       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
-       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
-       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
-       "  --sklearn-color-unfitted-level-3: chocolate;\n",
-       "  /* Definition of color scheme for fitted estimators */\n",
-       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
-       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
-       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
-       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
-       "\n",
-       "  /* Specific color for light theme */\n",
-       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
-       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
-       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
-       "  --sklearn-color-icon: #696969;\n",
-       "\n",
-       "  @media (prefers-color-scheme: dark) {\n",
-       "    /* Redefinition of color scheme for dark theme */\n",
-       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
-       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
-       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
-       "    --sklearn-color-icon: #878787;\n",
-       "  }\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 pre {\n",
-       "  padding: 0;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 input.sk-hidden--visually {\n",
-       "  border: 0;\n",
-       "  clip: rect(1px 1px 1px 1px);\n",
-       "  clip: rect(1px, 1px, 1px, 1px);\n",
-       "  height: 1px;\n",
-       "  margin: -1px;\n",
-       "  overflow: hidden;\n",
-       "  padding: 0;\n",
-       "  position: absolute;\n",
-       "  width: 1px;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-dashed-wrapped {\n",
-       "  border: 1px dashed var(--sklearn-color-line);\n",
-       "  margin: 0 0.4em 0.5em 0.4em;\n",
-       "  box-sizing: border-box;\n",
-       "  padding-bottom: 0.4em;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-container {\n",
-       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
-       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
-       "     so we also need the `!important` here to be able to override the\n",
-       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
-       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
-       "  display: inline-block !important;\n",
-       "  position: relative;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-text-repr-fallback {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       "div.sk-parallel-item,\n",
-       "div.sk-serial,\n",
-       "div.sk-item {\n",
-       "  /* draw centered vertical line to link estimators */\n",
-       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
-       "  background-size: 2px 100%;\n",
-       "  background-repeat: no-repeat;\n",
-       "  background-position: center center;\n",
-       "}\n",
-       "\n",
-       "/* Parallel-specific style estimator block */\n",
-       "\n",
-       "#sk-container-id-2 div.sk-parallel-item::after {\n",
-       "  content: \"\";\n",
-       "  width: 100%;\n",
-       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
-       "  flex-grow: 1;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-parallel {\n",
-       "  display: flex;\n",
-       "  align-items: stretch;\n",
-       "  justify-content: center;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  position: relative;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-parallel-item {\n",
-       "  display: flex;\n",
-       "  flex-direction: column;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
-       "  align-self: flex-end;\n",
-       "  width: 50%;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
-       "  align-self: flex-start;\n",
-       "  width: 50%;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
-       "  width: 0;\n",
-       "}\n",
-       "\n",
-       "/* Serial-specific style estimator block */\n",
-       "\n",
-       "#sk-container-id-2 div.sk-serial {\n",
-       "  display: flex;\n",
-       "  flex-direction: column;\n",
-       "  align-items: center;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  padding-right: 1em;\n",
-       "  padding-left: 1em;\n",
-       "}\n",
-       "\n",
-       "\n",
-       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
-       "clickable and can be expanded/collapsed.\n",
-       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
-       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
-       "*/\n",
-       "\n",
-       "/* Pipeline and ColumnTransformer style (default) */\n",
-       "\n",
-       "#sk-container-id-2 div.sk-toggleable {\n",
-       "  /* Default theme specific background. It is overwritten whether we have a\n",
-       "  specific estimator or a Pipeline/ColumnTransformer */\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "}\n",
-       "\n",
-       "/* Toggleable label */\n",
-       "#sk-container-id-2 label.sk-toggleable__label {\n",
-       "  cursor: pointer;\n",
-       "  display: block;\n",
-       "  width: 100%;\n",
-       "  margin-bottom: 0;\n",
-       "  padding: 0.5em;\n",
-       "  box-sizing: border-box;\n",
-       "  text-align: center;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
-       "  /* Arrow on the left of the label */\n",
-       "  content: \"▸\";\n",
-       "  float: left;\n",
-       "  margin-right: 0.25em;\n",
-       "  color: var(--sklearn-color-icon);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "}\n",
-       "\n",
-       "/* Toggleable content - dropdown */\n",
-       "\n",
-       "#sk-container-id-2 div.sk-toggleable__content {\n",
-       "  max-height: 0;\n",
-       "  max-width: 0;\n",
-       "  overflow: hidden;\n",
-       "  text-align: left;\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-toggleable__content pre {\n",
-       "  margin: 0.2em;\n",
-       "  border-radius: 0.25em;\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
-       "  /* Expand drop-down */\n",
-       "  max-height: 200px;\n",
-       "  max-width: 100%;\n",
-       "  overflow: auto;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
-       "  content: \"▾\";\n",
-       "}\n",
-       "\n",
-       "/* Pipeline/ColumnTransformer-specific style */\n",
-       "\n",
-       "#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Estimator-specific style */\n",
-       "\n",
-       "/* Colorize estimator box */\n",
-       "#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
-       "#sk-container-id-2 div.sk-label label {\n",
-       "  /* The background is the default theme color */\n",
-       "  color: var(--sklearn-color-text-on-default-background);\n",
-       "}\n",
-       "\n",
-       "/* On hover, darken the color of the background */\n",
-       "#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Label box, darken color on hover, fitted */\n",
-       "#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Estimator label */\n",
-       "\n",
-       "#sk-container-id-2 div.sk-label label {\n",
-       "  font-family: monospace;\n",
-       "  font-weight: bold;\n",
-       "  display: inline-block;\n",
-       "  line-height: 1.2em;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-label-container {\n",
-       "  text-align: center;\n",
-       "}\n",
-       "\n",
-       "/* Estimator-specific */\n",
-       "#sk-container-id-2 div.sk-estimator {\n",
-       "  font-family: monospace;\n",
-       "  border: 1px dotted var(--sklearn-color-border-box);\n",
-       "  border-radius: 0.25em;\n",
-       "  box-sizing: border-box;\n",
-       "  margin-bottom: 0.5em;\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-estimator.fitted {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "/* on hover */\n",
-       "#sk-container-id-2 div.sk-estimator:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
-       "\n",
-       "/* Common style for \"i\" and \"?\" */\n",
-       "\n",
-       ".sk-estimator-doc-link,\n",
-       "a:link.sk-estimator-doc-link,\n",
-       "a:visited.sk-estimator-doc-link {\n",
-       "  float: right;\n",
-       "  font-size: smaller;\n",
-       "  line-height: 1em;\n",
-       "  font-family: monospace;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  border-radius: 1em;\n",
-       "  height: 1em;\n",
-       "  width: 1em;\n",
-       "  text-decoration: none !important;\n",
-       "  margin-left: 1ex;\n",
-       "  /* unfitted */\n",
-       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-unfitted-level-1);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link.fitted,\n",
-       "a:link.sk-estimator-doc-link.fitted,\n",
-       "a:visited.sk-estimator-doc-link.fitted {\n",
-       "  /* fitted */\n",
-       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-fitted-level-1);\n",
-       "}\n",
-       "\n",
-       "/* On hover */\n",
-       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
-       ".sk-estimator-doc-link:hover,\n",
-       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
-       ".sk-estimator-doc-link:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
-       ".sk-estimator-doc-link.fitted:hover,\n",
-       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
-       ".sk-estimator-doc-link.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "/* Span, style for the box shown on hovering the info icon */\n",
-       ".sk-estimator-doc-link span {\n",
-       "  display: none;\n",
-       "  z-index: 9999;\n",
-       "  position: relative;\n",
-       "  font-weight: normal;\n",
-       "  right: .2ex;\n",
-       "  padding: .5ex;\n",
-       "  margin: .5ex;\n",
-       "  width: min-content;\n",
-       "  min-width: 20ex;\n",
-       "  max-width: 50ex;\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  box-shadow: 2pt 2pt 4pt #999;\n",
-       "  /* unfitted */\n",
-       "  background: var(--sklearn-color-unfitted-level-0);\n",
-       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link.fitted span {\n",
-       "  /* fitted */\n",
-       "  background: var(--sklearn-color-fitted-level-0);\n",
-       "  border: var(--sklearn-color-fitted-level-3);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link:hover span {\n",
-       "  display: block;\n",
-       "}\n",
-       "\n",
-       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
-       "\n",
-       "#sk-container-id-2 a.estimator_doc_link {\n",
-       "  float: right;\n",
-       "  font-size: 1rem;\n",
-       "  line-height: 1em;\n",
-       "  font-family: monospace;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  border-radius: 1rem;\n",
-       "  height: 1rem;\n",
-       "  width: 1rem;\n",
-       "  text-decoration: none;\n",
-       "  /* unfitted */\n",
-       "  color: var(--sklearn-color-unfitted-level-1);\n",
-       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 a.estimator_doc_link.fitted {\n",
-       "  /* fitted */\n",
-       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-fitted-level-1);\n",
-       "}\n",
-       "\n",
-       "/* On hover */\n",
-       "#sk-container-id-2 a.estimator_doc_link:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-3);\n",
-       "}\n",
-       "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
-       "              colsample_bylevel=None, colsample_bynode=None,\n",
-       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
-       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
-       "              gamma=None, grow_policy=None, importance_type=None,\n",
-       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
-       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
-       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
-       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
-       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
-       "              num_parallel_tree=None, random_state=None, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;XGBClassifier<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
-       "              colsample_bylevel=None, colsample_bynode=None,\n",
-       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
-       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
-       "              gamma=None, grow_policy=None, importance_type=None,\n",
-       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
-       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
-       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
-       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
-       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
-       "              num_parallel_tree=None, random_state=None, ...)</pre></div> </div></div></div></div>"
-      ],
-      "text/plain": [
-       "XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
-       "              colsample_bylevel=None, colsample_bynode=None,\n",
-       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
-       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
-       "              gamma=None, grow_policy=None, importance_type=None,\n",
-       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
-       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
-       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
-       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
-       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
-       "              num_parallel_tree=None, random_state=None, ...)"
-      ]
-     },
-     "execution_count": 35,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from xgboost import XGBClassifier\n",
-    "\n",
-    "model_2 = XGBClassifier()\n",
-    "model_2.fit(X_train, y_train)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 39,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "y_pred = model_2.predict(X_test)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 40,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Accuracy: 0.9979176233986287\n",
-      "              precision    recall  f1-score   support\n",
-      "\n",
-      "           0       1.00      1.00      1.00    126154\n",
-      "           1       1.00      1.00      1.00    126186\n",
-      "\n",
-      "   micro avg       1.00      1.00      1.00    252340\n",
-      "   macro avg       1.00      1.00      1.00    252340\n",
-      "weighted avg       1.00      1.00      1.00    252340\n",
-      " samples avg       1.00      1.00      1.00    252340\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "from sklearn.preprocessing import MultiLabelBinarizer\n",
-    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
-    "\n",
-    "# Assuming y_test and y_pred are in multi-label format\n",
-    "mlb = MultiLabelBinarizer()\n",
-    "y_test_binary = mlb.fit_transform(y_test)\n",
-    "y_pred_binary = mlb.transform(y_pred)\n",
-    "\n",
-    "# Compute and print accuracy\n",
-    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
-    "print(f\"Accuracy: {accuracy}\")\n",
-    "\n",
-    "# Print classification report\n",
-    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Model 3: SVM"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<style>#sk-container-id-1 {\n",
-       "  /* Definition of color scheme common for light and dark mode */\n",
-       "  --sklearn-color-text: black;\n",
-       "  --sklearn-color-line: gray;\n",
-       "  /* Definition of color scheme for unfitted estimators */\n",
-       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
-       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
-       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
-       "  --sklearn-color-unfitted-level-3: chocolate;\n",
-       "  /* Definition of color scheme for fitted estimators */\n",
-       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
-       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
-       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
-       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
-       "\n",
-       "  /* Specific color for light theme */\n",
-       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
-       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
-       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
-       "  --sklearn-color-icon: #696969;\n",
-       "\n",
-       "  @media (prefers-color-scheme: dark) {\n",
-       "    /* Redefinition of color scheme for dark theme */\n",
-       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
-       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
-       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
-       "    --sklearn-color-icon: #878787;\n",
-       "  }\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 pre {\n",
-       "  padding: 0;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 input.sk-hidden--visually {\n",
-       "  border: 0;\n",
-       "  clip: rect(1px 1px 1px 1px);\n",
-       "  clip: rect(1px, 1px, 1px, 1px);\n",
-       "  height: 1px;\n",
-       "  margin: -1px;\n",
-       "  overflow: hidden;\n",
-       "  padding: 0;\n",
-       "  position: absolute;\n",
-       "  width: 1px;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
-       "  border: 1px dashed var(--sklearn-color-line);\n",
-       "  margin: 0 0.4em 0.5em 0.4em;\n",
-       "  box-sizing: border-box;\n",
-       "  padding-bottom: 0.4em;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-container {\n",
-       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
-       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
-       "     so we also need the `!important` here to be able to override the\n",
-       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
-       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
-       "  display: inline-block !important;\n",
-       "  position: relative;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       "div.sk-parallel-item,\n",
-       "div.sk-serial,\n",
-       "div.sk-item {\n",
-       "  /* draw centered vertical line to link estimators */\n",
-       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
-       "  background-size: 2px 100%;\n",
-       "  background-repeat: no-repeat;\n",
-       "  background-position: center center;\n",
-       "}\n",
-       "\n",
-       "/* Parallel-specific style estimator block */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item::after {\n",
-       "  content: \"\";\n",
-       "  width: 100%;\n",
-       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
-       "  flex-grow: 1;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel {\n",
-       "  display: flex;\n",
-       "  align-items: stretch;\n",
-       "  justify-content: center;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  position: relative;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item {\n",
-       "  display: flex;\n",
-       "  flex-direction: column;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
-       "  align-self: flex-end;\n",
-       "  width: 50%;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
-       "  align-self: flex-start;\n",
-       "  width: 50%;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
-       "  width: 0;\n",
-       "}\n",
-       "\n",
-       "/* Serial-specific style estimator block */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-serial {\n",
-       "  display: flex;\n",
-       "  flex-direction: column;\n",
-       "  align-items: center;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  padding-right: 1em;\n",
-       "  padding-left: 1em;\n",
-       "}\n",
-       "\n",
-       "\n",
-       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
-       "clickable and can be expanded/collapsed.\n",
-       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
-       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
-       "*/\n",
-       "\n",
-       "/* Pipeline and ColumnTransformer style (default) */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable {\n",
-       "  /* Default theme specific background. It is overwritten whether we have a\n",
-       "  specific estimator or a Pipeline/ColumnTransformer */\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "}\n",
-       "\n",
-       "/* Toggleable label */\n",
-       "#sk-container-id-1 label.sk-toggleable__label {\n",
-       "  cursor: pointer;\n",
-       "  display: block;\n",
-       "  width: 100%;\n",
-       "  margin-bottom: 0;\n",
-       "  padding: 0.5em;\n",
-       "  box-sizing: border-box;\n",
-       "  text-align: center;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
-       "  /* Arrow on the left of the label */\n",
-       "  content: \"▸\";\n",
-       "  float: left;\n",
-       "  margin-right: 0.25em;\n",
-       "  color: var(--sklearn-color-icon);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "}\n",
-       "\n",
-       "/* Toggleable content - dropdown */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content {\n",
-       "  max-height: 0;\n",
-       "  max-width: 0;\n",
-       "  overflow: hidden;\n",
-       "  text-align: left;\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
-       "  margin: 0.2em;\n",
-       "  border-radius: 0.25em;\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
-       "  /* Expand drop-down */\n",
-       "  max-height: 200px;\n",
-       "  max-width: 100%;\n",
-       "  overflow: auto;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
-       "  content: \"▾\";\n",
-       "}\n",
-       "\n",
-       "/* Pipeline/ColumnTransformer-specific style */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Estimator-specific style */\n",
-       "\n",
-       "/* Colorize estimator box */\n",
-       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
-       "#sk-container-id-1 div.sk-label label {\n",
-       "  /* The background is the default theme color */\n",
-       "  color: var(--sklearn-color-text-on-default-background);\n",
-       "}\n",
-       "\n",
-       "/* On hover, darken the color of the background */\n",
-       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Label box, darken color on hover, fitted */\n",
-       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Estimator label */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label label {\n",
-       "  font-family: monospace;\n",
-       "  font-weight: bold;\n",
-       "  display: inline-block;\n",
-       "  line-height: 1.2em;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label-container {\n",
-       "  text-align: center;\n",
-       "}\n",
-       "\n",
-       "/* Estimator-specific */\n",
-       "#sk-container-id-1 div.sk-estimator {\n",
-       "  font-family: monospace;\n",
-       "  border: 1px dotted var(--sklearn-color-border-box);\n",
-       "  border-radius: 0.25em;\n",
-       "  box-sizing: border-box;\n",
-       "  margin-bottom: 0.5em;\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "/* on hover */\n",
-       "#sk-container-id-1 div.sk-estimator:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
-       "\n",
-       "/* Common style for \"i\" and \"?\" */\n",
-       "\n",
-       ".sk-estimator-doc-link,\n",
-       "a:link.sk-estimator-doc-link,\n",
-       "a:visited.sk-estimator-doc-link {\n",
-       "  float: right;\n",
-       "  font-size: smaller;\n",
-       "  line-height: 1em;\n",
-       "  font-family: monospace;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  border-radius: 1em;\n",
-       "  height: 1em;\n",
-       "  width: 1em;\n",
-       "  text-decoration: none !important;\n",
-       "  margin-left: 1ex;\n",
-       "  /* unfitted */\n",
-       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-unfitted-level-1);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link.fitted,\n",
-       "a:link.sk-estimator-doc-link.fitted,\n",
-       "a:visited.sk-estimator-doc-link.fitted {\n",
-       "  /* fitted */\n",
-       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-fitted-level-1);\n",
-       "}\n",
-       "\n",
-       "/* On hover */\n",
-       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
-       ".sk-estimator-doc-link:hover,\n",
-       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
-       ".sk-estimator-doc-link:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
-       ".sk-estimator-doc-link.fitted:hover,\n",
-       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
-       ".sk-estimator-doc-link.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "/* Span, style for the box shown on hovering the info icon */\n",
-       ".sk-estimator-doc-link span {\n",
-       "  display: none;\n",
-       "  z-index: 9999;\n",
-       "  position: relative;\n",
-       "  font-weight: normal;\n",
-       "  right: .2ex;\n",
-       "  padding: .5ex;\n",
-       "  margin: .5ex;\n",
-       "  width: min-content;\n",
-       "  min-width: 20ex;\n",
-       "  max-width: 50ex;\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  box-shadow: 2pt 2pt 4pt #999;\n",
-       "  /* unfitted */\n",
-       "  background: var(--sklearn-color-unfitted-level-0);\n",
-       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link.fitted span {\n",
-       "  /* fitted */\n",
-       "  background: var(--sklearn-color-fitted-level-0);\n",
-       "  border: var(--sklearn-color-fitted-level-3);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link:hover span {\n",
-       "  display: block;\n",
-       "}\n",
-       "\n",
-       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
-       "\n",
-       "#sk-container-id-1 a.estimator_doc_link {\n",
-       "  float: right;\n",
-       "  font-size: 1rem;\n",
-       "  line-height: 1em;\n",
-       "  font-family: monospace;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  border-radius: 1rem;\n",
-       "  height: 1rem;\n",
-       "  width: 1rem;\n",
-       "  text-decoration: none;\n",
-       "  /* unfitted */\n",
-       "  color: var(--sklearn-color-unfitted-level-1);\n",
-       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
-       "  /* fitted */\n",
-       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-fitted-level-1);\n",
-       "}\n",
-       "\n",
-       "/* On hover */\n",
-       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-3);\n",
-       "}\n",
-       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MultiOutputClassifier(estimator=SVC(), n_jobs=-1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;MultiOutputClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.multioutput.MultiOutputClassifier.html\">?<span>Documentation for MultiOutputClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>MultiOutputClassifier(estimator=SVC(), n_jobs=-1)</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">estimator: SVC</label><div class=\"sk-toggleable__content fitted\"><pre>SVC()</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;SVC<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.svm.SVC.html\">?<span>Documentation for SVC</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>SVC()</pre></div> </div></div></div></div></div></div></div></div></div>"
-      ],
-      "text/plain": [
-       "MultiOutputClassifier(estimator=SVC(), n_jobs=-1)"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from sklearn.multioutput import MultiOutputClassifier\n",
-    "from sklearn.svm import SVC\n",
-    "\n",
-    "svm = SVC(kernel='rbf', gamma='scale', C=1.0)\n",
-    "\n",
-    "model_3 = MultiOutputClassifier(svm, n_jobs=-1)\n",
-    "\n",
-    "model_3.fit(X_train, y_train)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "y_pred = model_3.predict(X_test)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Accuracy: 0.9999287399642116\n",
-      "              precision    recall  f1-score   support\n",
-      "\n",
-      "           0       1.00      1.00      1.00    126298\n",
-      "           1       1.00      1.00      1.00    126298\n",
-      "\n",
-      "   micro avg       1.00      1.00      1.00    252596\n",
-      "   macro avg       1.00      1.00      1.00    252596\n",
-      "weighted avg       1.00      1.00      1.00    252596\n",
-      " samples avg       1.00      1.00      1.00    252596\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "from sklearn.preprocessing import MultiLabelBinarizer\n",
-    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
-    "\n",
-    "# Assuming y_test and y_pred are in multi-label format\n",
-    "mlb = MultiLabelBinarizer()\n",
-    "y_test_binary = mlb.fit_transform(y_test)\n",
-    "y_pred_binary = mlb.transform(y_pred)\n",
-    "\n",
-    "# Compute and print accuracy\n",
-    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
-    "print(f\"Accuracy: {accuracy}\")\n",
-    "\n",
-    "# Print classification report\n",
-    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
-   ]
-  }
- ],
- "metadata": {
-  "accelerator": "GPU",
-  "colab": {
-   "gpuType": "T4",
-   "provenance": [],
-   "toc_visible": true
-  },
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.0"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

From d7e8a5f779a500c259a4416ffd7b00c47b22c8e7 Mon Sep 17 00:00:00 2001
From: Aditi Kala <130339327+why-aditi@users.noreply.github.com>
Date: Sat, 22 Jun 2024 17:36:38 +0530
Subject: [PATCH 08/10] Delete ACI IoT Network Traffic Dataset
 Analysis/Model/ACI_IoT_Network_Traffic_Dataset_Analysis.ipynb

---
 ...IoT_Network_Traffic_Dataset_Analysis.ipynb | 1977 -----------------
 1 file changed, 1977 deletions(-)
 delete mode 100644 ACI IoT Network Traffic Dataset Analysis/Model/ACI_IoT_Network_Traffic_Dataset_Analysis.ipynb

diff --git a/ACI IoT Network Traffic Dataset Analysis/Model/ACI_IoT_Network_Traffic_Dataset_Analysis.ipynb b/ACI IoT Network Traffic Dataset Analysis/Model/ACI_IoT_Network_Traffic_Dataset_Analysis.ipynb
deleted file mode 100644
index a6577c761..000000000
--- a/ACI IoT Network Traffic Dataset Analysis/Model/ACI_IoT_Network_Traffic_Dataset_Analysis.ipynb	
+++ /dev/null
@@ -1,1977 +0,0 @@
-{
- "cells": [
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "YwuxWrIj26L7"
-   },
-   "source": [
-    "# ACI IoT Network Traffic"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "eA-t2jeQ2_Ay"
-   },
-   "source": [
-    "## Get dataset"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 1,
-   "metadata": {
-    "id": "f2-gDXPihjaF"
-   },
-   "outputs": [],
-   "source": [
-    "import numpy as np\n",
-    "import pandas as pd\n",
-    "import tensorflow as tf\n",
-    "import matplotlib.pyplot as plt"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 2,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "D:\\ML\\ACI IoT Network Traffic Dataset Analysis\\Model\n"
-     ]
-    }
-   ],
-   "source": [
-    "import os\n",
-    "print(os.getcwd())"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 3,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<div>\n",
-       "<style scoped>\n",
-       "    .dataframe tbody tr th:only-of-type {\n",
-       "        vertical-align: middle;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe tbody tr th {\n",
-       "        vertical-align: top;\n",
-       "    }\n",
-       "\n",
-       "    .dataframe thead th {\n",
-       "        text-align: right;\n",
-       "    }\n",
-       "</style>\n",
-       "<table border=\"1\" class=\"dataframe\">\n",
-       "  <thead>\n",
-       "    <tr style=\"text-align: right;\">\n",
-       "      <th></th>\n",
-       "      <th>srcip</th>\n",
-       "      <th>sport</th>\n",
-       "      <th>dstip</th>\n",
-       "      <th>dsport</th>\n",
-       "      <th>protocol_m</th>\n",
-       "      <th>sttl</th>\n",
-       "      <th>total_len</th>\n",
-       "      <th>payload</th>\n",
-       "      <th>stime</th>\n",
-       "      <th>label</th>\n",
-       "    </tr>\n",
-       "  </thead>\n",
-       "  <tbody>\n",
-       "    <tr>\n",
-       "      <th>0</th>\n",
-       "      <td>192.168.1.81</td>\n",
-       "      <td>60683</td>\n",
-       "      <td>239.255.255.250</td>\n",
-       "      <td>1900</td>\n",
-       "      <td>udp</td>\n",
-       "      <td>2</td>\n",
-       "      <td>362</td>\n",
-       "      <td>4e4f54494659202a20485454502f312e310d0a4e54533a...</td>\n",
-       "      <td>1698670981</td>\n",
-       "      <td>Benign</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>1</th>\n",
-       "      <td>192.168.1.9</td>\n",
-       "      <td>53160</td>\n",
-       "      <td>239.255.255.250</td>\n",
-       "      <td>1900</td>\n",
-       "      <td>udp</td>\n",
-       "      <td>1</td>\n",
-       "      <td>204</td>\n",
-       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
-       "      <td>1698670984</td>\n",
-       "      <td>Benign</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>2</th>\n",
-       "      <td>192.168.1.9</td>\n",
-       "      <td>53160</td>\n",
-       "      <td>239.255.255.250</td>\n",
-       "      <td>1900</td>\n",
-       "      <td>udp</td>\n",
-       "      <td>1</td>\n",
-       "      <td>204</td>\n",
-       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
-       "      <td>1698670985</td>\n",
-       "      <td>Benign</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>3</th>\n",
-       "      <td>192.168.1.9</td>\n",
-       "      <td>53160</td>\n",
-       "      <td>239.255.255.250</td>\n",
-       "      <td>1900</td>\n",
-       "      <td>udp</td>\n",
-       "      <td>1</td>\n",
-       "      <td>204</td>\n",
-       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
-       "      <td>1698670986</td>\n",
-       "      <td>Benign</td>\n",
-       "    </tr>\n",
-       "    <tr>\n",
-       "      <th>4</th>\n",
-       "      <td>192.168.1.9</td>\n",
-       "      <td>53160</td>\n",
-       "      <td>239.255.255.250</td>\n",
-       "      <td>1900</td>\n",
-       "      <td>udp</td>\n",
-       "      <td>1</td>\n",
-       "      <td>204</td>\n",
-       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
-       "      <td>1698670987</td>\n",
-       "      <td>Benign</td>\n",
-       "    </tr>\n",
-       "  </tbody>\n",
-       "</table>\n",
-       "</div>"
-      ],
-      "text/plain": [
-       "          srcip  sport            dstip  dsport protocol_m  sttl  total_len  \\\n",
-       "0  192.168.1.81  60683  239.255.255.250    1900        udp     2        362   \n",
-       "1   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
-       "2   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
-       "3   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
-       "4   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
-       "\n",
-       "                                             payload       stime   label  \n",
-       "0  4e4f54494659202a20485454502f312e310d0a4e54533a...  1698670981  Benign  \n",
-       "1  4d2d534541524348202a20485454502f312e310d0a484f...  1698670984  Benign  \n",
-       "2  4d2d534541524348202a20485454502f312e310d0a484f...  1698670985  Benign  \n",
-       "3  4d2d534541524348202a20485454502f312e310d0a484f...  1698670986  Benign  \n",
-       "4  4d2d534541524348202a20485454502f312e310d0a484f...  1698670987  Benign  "
-      ]
-     },
-     "execution_count": 3,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df = pd.read_csv('D:\\ML\\ACI IoT Network Traffic Dataset Analysis\\Dataset\\ACI-IoT-2023-Payload.csv')\n",
-    "pd.set_option('display.max_columns', None)\n",
-    "df.head()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "dW7fRPpahgGd"
-   },
-   "source": [
-    "## EDA"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {
-    "id": "t4ChRqiXsIZZ"
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "srcip         0\n",
-       "sport         0\n",
-       "dstip         0\n",
-       "dsport        0\n",
-       "protocol_m    0\n",
-       "sttl          0\n",
-       "total_len     0\n",
-       "payload       0\n",
-       "stime         0\n",
-       "label         0\n",
-       "dtype: int64"
-      ]
-     },
-     "execution_count": 4,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df.isnull().sum()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 5,
-   "metadata": {
-    "id": "CxOR0kJM3SWR"
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "label\n",
-       "Benign                601868\n",
-       "DNS Flood              18577\n",
-       "Dictionary Attack       4645\n",
-       "Slowloris               2974\n",
-       "SYN Flood               2113\n",
-       "Port Scan                582\n",
-       "Vulnerability Scan       445\n",
-       "OS Scan                  156\n",
-       "UDP Flood                 68\n",
-       "ICMP Flood                58\n",
-       "Name: count, dtype: int64"
-      ]
-     },
-     "execution_count": 5,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "df.label.value_counts()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 6,
-   "metadata": {
-    "id": "mrlQp4My4faj"
-   },
-   "outputs": [],
-   "source": [
-    "import matplotlib.pyplot as plt\n",
-    "\n",
-    "labels = ['Benign', 'DNS Flood', 'Dictionary Attack', 'Slowloris', 'SYN Flood',\n",
-    "          'Port Scan', 'Vulnerability Scan', 'OS Scan', 'UDP Flood', 'ICMP Flood']\n",
-    "sizes = [601868, 18577, 4645, 2974, 2113, 582, 445, 156, 68, 58]"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "id": "Actc2Dc-4l4W"
-   },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAABAcAAAJ3CAYAAADoNji5AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy80BEi2AAAACXBIWXMAAA9hAAAPYQGoP6dpAACcM0lEQVR4nOzdeZyN9f//8eeZGTNjm8U2Y1/Lvq9DSGESIktIkVQfhSzJkhJRirTI1q5NEWVfI0tIItklS0RjiZmxzYyZef3+8Jvr60ShcIzrcb/d5lbnut7nnNe5nHOd63qe9/V+e8zMBAAAAAAAXMvP1wUAAAAAAADfIhwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAuEyDBw+Wx+PR0aNHfV0KAABXFeEAAADQxIkT5fF4vP5y5cqlevXqad68ede9nlmzZqlp06aKiIhQYGCgsmXLpjp16mjUqFGKj4+/7vUAAHCzC/B1AQAA4MbxwgsvqHDhwjIzHTp0SBMnTtTdd9+tWbNmqUmTJtf8+VNTU9W5c2dNnDhRZcuW1RNPPKH8+fPrxIkTWr16tZ599lnNnTtXixcvvua1AADgJoQDAADA0ahRI1WpUsW53blzZ0VEROjzzz+/KuFAamqqkpKSFBwcfNH1I0aM0MSJE9WrVy+NGjVKHo/HWdejRw/98ccf+vjjj//TcwAAgAtxWQEAAPhbYWFhypgxowICvH9PePXVV1WzZk1lz55dGTNmVOXKlTV16tQL7u/xeNStWzd99tlnKl26tIKCgjR//vyLPtfp06f1yiuvqHTp0ho5cqRXMJAmd+7c6tev32U/x7+ps3jx4goODlblypW1fPnyi9YaGxurhx56SGFhYQoNDVWnTp10+vTpi29EAADSAXoOAAAAR1xcnI4ePSoz0+HDh/XWW2/p5MmTeuCBB7zavfnmm7rnnnvUvn17JSUl6YsvvlDr1q01e/ZsNW7c2KvtkiVLNGXKFHXr1k05cuRQoUKFLvrc3333nWJjY9WnTx/5+/tfUd1/9xxXUueyZcs0efJkPfnkkwoKCtK4ceN011136YcfflCZMmW82t53330qXLiwhg8frvXr1+u9995Trly59Morr1xR3QAA3Cg8Zma+LgIAAPjWxIkT1alTpwuWBwUF6e2331bHjh29lp85c0YZM2Z0bp89e1aVKlVSrly5vMYD8Hg88vPz06ZNm1SqVKl/rGH06NHq0aOHpk+frmbNmjnLU1JSdPz4ca+22bNnd3oW/NNzXEmdkvTjjz+qcuXKkqR9+/apePHiatSokb766itJ52YrGDJkiB5++GG9//77zv1btGih5cuXM4sBACDdoucAAABwjB07Vrfeeqsk6dChQ/r000/1yCOPKGvWrGrRooXT7vwT7uPHjyslJUW1a9fW559/fsFj1q1b95LBgCRnFoIsWbJ4Ld+0aZMqVqzotezIkSPKkSPHJZ/jSuqMiopyggFJKlCggJo1a6ZZs2YpJSXFqzdDly5dvO5bu3Ztff3114qPj1dISMglXysAADcawgEAAOCoVq2a14CE7dq1U8WKFdWtWzc1adJEgYGBkqTZs2dr2LBh2rBhgxITE532FxsnoHDhwpf13FmzZpUknTx50mt5sWLFtGjRIknSxx9/rE8++eSyn+NK6rzlllsuWHbrrbfq9OnTOnLkiCIjI53lBQoU8GoXHh4u6VwAQTgAAEiPGJAQAAD8LT8/P9WrV09//PGHdu7cKUlasWKF7rnnHgUHB2vcuHGaO3euFi1apPvvv18Xu1rx/F/v/0mJEiUkSZs3b/ZaniVLFtWvX1/169dXkSJFLnrfiz3HldZ5Jf5uTASu1gQApFf0HAAAAP8oOTlZ0v/9oj9t2jQFBwdrwYIFCgoKctp9+OGH/+l5ateurdDQUH3xxRcaMGCA/Pz+228YV1pnWvhxvl9++UWZMmVSzpw5/1MtAADc6Og5AAAA/tbZs2e1cOFCBQYGqmTJkpLO/Wru8XiUkpLitNu7d6+mT5/+n54rU6ZM6tu3rzZv3qz+/ftf9Ff4K/ll/krrXL16tdavX+/c3r9/v2bMmKGGDRte8ewJAACkN/QcAAAAjnnz5mn79u2SpMOHD2vSpEnauXOn+vfv71xL37hxY7322mu66667dP/99+vw4cMaO3asihUrpo0bN/6n5+/fv7+2bdumkSNHauHChWrZsqXy5cun48ePa/369fryyy+VK1cuBQcHX/KxrrTOMmXKKDo62msqQ0kaMmTIf3pNAACkB4QDAADAMWjQIOf/g4ODVaJECY0fP17/+9//nOV33HGH3n//fb388svq2bOnChcurFdeeUV79+79z+GAn5+fPvnkE7Vs2VLvvvuu3nrrLR0/flxZsmRRmTJl9OKLL+rRRx+9YEaDi7nSOuvWrauoqCgNGTJE+/btU6lSpTRx4kSVK1fuP70mAADSA48xcg4AAHA5j8ejrl27asyYMb4uBQAAn2DMAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5RiQEAAAuB5DMAEA3I6eAwAAAAAAuBw9B66j1NRUHTx4UFmzZpXH4/F1OQAAAACAm5yZ6cSJE8qTJ4/8/P6+fwDhwHV08OBB5c+f39dlAAAAAABcZv/+/cqXL9/friccuI6yZs0q6dw/SkhIiI+rAQAAAADc7OLj45U/f37nfPTvEA5cR2mXEoSEhBAOAAAAAACum0td2s6AhAAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4nM/DgQMHDuiBBx5Q9uzZlTFjRpUtW1Y//vijs97MNGjQIOXOnVsZM2ZU/fr1tXPnTq/HOHbsmNq3b6+QkBCFhYWpc+fOOnnypFebjRs3qnbt2goODlb+/Pk1YsSIC2r58ssvVaJECQUHB6ts2bKaO3eu1/rLqQUAAAAAgPTGp+HA8ePHVatWLWXIkEHz5s3T1q1bNWrUKIWHhzttRowYodGjR2vChAlas2aNMmfOrOjoaCUkJDht2rdvry1btmjRokWaPXu2li9frscee8xZHx8fr4YNG6pgwYJat26dRo4cqcGDB+udd95x2qxatUrt2rVT586d9dNPP6l58+Zq3ry5Nm/efEW1AAAAAACQ3njMzHz15P3799fKlSu1YsWKi643M+XJk0dPPfWU+vTpI0mKi4tTRESEJk6cqLZt22rbtm0qVaqU1q5dqypVqkiS5s+fr7vvvlu///678uTJo/Hjx2vgwIGKiYlRYGCg89zTp0/X9u3bJUlt2rTRqVOnNHv2bOf5a9SooQoVKmjChAmXVculxMfHKzQ0VHFxcQoJCfn3G+46KNR/jq9LuOHsfbmxr0sAAAAAgCtyueehPu05MHPmTFWpUkWtW7dWrly5VLFiRb377rvO+j179igmJkb169d3loWGhqp69epavXq1JGn16tUKCwtzggFJql+/vvz8/LRmzRqnTZ06dZxgQJKio6O1Y8cOHT9+3Glz/vOktUl7nsup5a8SExMVHx/v9QcAAAAAwI3Gp+HA7t27NX78eN1yyy1asGCBHn/8cT355JP66KOPJEkxMTGSpIiICK/7RUREOOtiYmKUK1cur/UBAQHKli2bV5uLPcb5z/F3bc5ff6la/mr48OEKDQ11/vLnz3+pTQIAAAAAwHXn03AgNTVVlSpV0ksvvaSKFSvqscce06OPPqoJEyb4sqyrZsCAAYqLi3P+9u/f7+uSAAAAAAC4gE/Dgdy5c6tUqVJey0qWLKl9+/ZJkiIjIyVJhw4d8mpz6NAhZ11kZKQOHz7stT45OVnHjh3zanOxxzj/Of6uzfnrL1XLXwUFBSkkJMTrDwAAAACAG41Pw4FatWppx44dXst++eUXFSxYUJJUuHBhRUZGavHixc76+Ph4rVmzRlFRUZKkqKgoxcbGat26dU6bJUuWKDU1VdWrV3faLF++XGfPnnXaLFq0SMWLF3dmRoiKivJ6nrQ2ac9zObUAAAAAAJAe+TQc6NWrl77//nu99NJL+vXXXzVp0iS988476tq1qyTJ4/GoZ8+eGjZsmGbOnKlNmzapQ4cOypMnj5o3by7pXE+Du+66S48++qh++OEHrVy5Ut26dVPbtm2VJ08eSdL999+vwMBAde7cWVu2bNHkyZP15ptvqnfv3k4tPXr00Pz58zVq1Cht375dgwcP1o8//qhu3bpddi0AAAAAAKRHAb588qpVq+rrr7/WgAED9MILL6hw4cJ644031L59e6dN3759derUKT322GOKjY3Vbbfdpvnz5ys4ONhp89lnn6lbt26688475efnp5YtW2r06NHO+tDQUC1cuFBdu3ZV5cqVlSNHDg0aNEiPPfaY06ZmzZqaNGmSnn32WT3zzDO65ZZbNH36dJUpU+aKagEAAAAAIL3xmJn5ugi3uNz5JW8EhfrP8XUJN5y9Lzf2dQkAAAAAcEUu9zzUp5cVAAAAAAAA3yMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5XwaDgwePFgej8frr0SJEs76hIQEde3aVdmzZ1eWLFnUsmVLHTp0yOsx9u3bp8aNGytTpkzKlSuXnn76aSUnJ3u1Wbp0qSpVqqSgoCAVK1ZMEydOvKCWsWPHqlChQgoODlb16tX1ww8/eK2/nFoAAAAAAEiPfN5zoHTp0vrjjz+cv++++85Z16tXL82aNUtffvmlli1bpoMHD6pFixbO+pSUFDVu3FhJSUlatWqVPvroI02cOFGDBg1y2uzZs0eNGzdWvXr1tGHDBvXs2VOPPPKIFixY4LSZPHmyevfureeff17r169X+fLlFR0drcOHD192LQAAAAAApFceMzNfPfngwYM1ffp0bdiw4YJ1cXFxypkzpyZNmqRWrVpJkrZv366SJUtq9erVqlGjhubNm6cmTZro4MGDioiIkCRNmDBB/fr105EjRxQYGKh+/fppzpw52rx5s/PYbdu2VWxsrObPny9Jql69uqpWraoxY8ZIklJTU5U/f351795d/fv3v6xaLkd8fLxCQ0MVFxenkJCQf73drodC/ef4uoQbzt6XG/u6BAAAAAC4Ipd7HurzngM7d+5Unjx5VKRIEbVv31779u2TJK1bt05nz55V/fr1nbYlSpRQgQIFtHr1aknS6tWrVbZsWScYkKTo6GjFx8dry5YtTpvzHyOtTdpjJCUlad26dV5t/Pz8VL9+fafN5dRyMYmJiYqPj/f6AwAAAADgRuPTcKB69eqaOHGi5s+fr/Hjx2vPnj2qXbu2Tpw4oZiYGAUGBiosLMzrPhEREYqJiZEkxcTEeAUDaevT1v1Tm/j4eJ05c0ZHjx5VSkrKRduc/xiXquVihg8frtDQUOcvf/78l7dhAAAAAAC4jgJ8+eSNGjVy/r9cuXKqXr26ChYsqClTpihjxow+rOzqGDBggHr37u3cjo+PJyAAAAAAANxwfH5ZwfnCwsJ066236tdff1VkZKSSkpIUGxvr1ebQoUOKjIyUJEVGRl4wY0Da7Uu1CQkJUcaMGZUjRw75+/tftM35j3GpWi4mKChIISEhXn8AAAAAANxobqhw4OTJk9q1a5dy586typUrK0OGDFq8eLGzfseOHdq3b5+ioqIkSVFRUdq0aZPXrAKLFi1SSEiISpUq5bQ5/zHS2qQ9RmBgoCpXruzVJjU1VYsXL3baXE4tAAAAAACkVz69rKBPnz5q2rSpChYsqIMHD+r555+Xv7+/2rVrp9DQUHXu3Fm9e/dWtmzZFBISou7duysqKsqZHaBhw4YqVaqUHnzwQY0YMUIxMTF69tln1bVrVwUFBUmSunTpojFjxqhv3756+OGHtWTJEk2ZMkVz5vzfaPy9e/dWx44dVaVKFVWrVk1vvPGGTp06pU6dOknSZdUCAAAAAEB65dNw4Pfff1e7du30559/KmfOnLrtttv0/fffK2fOnJKk119/XX5+fmrZsqUSExMVHR2tcePGOff39/fX7Nmz9fjjjysqKkqZM2dWx44d9cILLzhtChcurDlz5qhXr1568803lS9fPr333nuKjo522rRp00ZHjhzRoEGDFBMTowoVKmj+/PlegxReqhYAAAAAANIrj5mZr4twi8udX/JGUKj/nEs3cpm9Lzf2dQkAAAAAcEUu9zz0hhpzAAAAAAAAXH+EAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuNwNEw68/PLL8ng86tmzp7MsISFBXbt2Vfbs2ZUlSxa1bNlShw4d8rrfvn371LhxY2XKlEm5cuXS008/reTkZK82S5cuVaVKlRQUFKRixYpp4sSJFzz/2LFjVahQIQUHB6t69er64YcfvNZfTi0AAAAAAKRHN0Q4sHbtWr399tsqV66c1/JevXpp1qxZ+vLLL7Vs2TIdPHhQLVq0cNanpKSocePGSkpK0qpVq/TRRx9p4sSJGjRokNNmz549aty4serVq6cNGzaoZ8+eeuSRR7RgwQKnzeTJk9W7d289//zzWr9+vcqXL6/o6GgdPnz4smsBAAAAACC98piZ+bKAkydPqlKlSho3bpyGDRumChUq6I033lBcXJxy5sypSZMmqVWrVpKk7du3q2TJklq9erVq1KihefPmqUmTJjp48KAiIiIkSRMmTFC/fv105MgRBQYGql+/fpozZ442b97sPGfbtm0VGxur+fPnS5KqV6+uqlWrasyYMZKk1NRU5c+fX927d1f//v0vq5bLER8fr9DQUMXFxSkkJOSqbcNroVD/Ob4u4Yaz9+XGvi4BAAAAAK7I5Z6H+rznQNeuXdW4cWPVr1/fa/m6det09uxZr+UlSpRQgQIFtHr1aknS6tWrVbZsWScYkKTo6GjFx8dry5YtTpu/PnZ0dLTzGElJSVq3bp1XGz8/P9WvX99pczm1XExiYqLi4+O9/gAAAAAAuNEE+PLJv/jiC61fv15r1669YF1MTIwCAwMVFhbmtTwiIkIxMTFOm/ODgbT1aev+qU18fLzOnDmj48ePKyUl5aJttm/fftm1XMzw4cM1ZMiQv10PAAAAAMCNwGc9B/bv368ePXros88+U3BwsK/KuKYGDBiguLg452///v2+LgkAAAAAgAv4LBxYt26dDh8+rEqVKikgIEABAQFatmyZRo8erYCAAEVERCgpKUmxsbFe9zt06JAiIyMlSZGRkRfMGJB2+1JtQkJClDFjRuXIkUP+/v4XbXP+Y1yqlosJCgpSSEiI1x8AAAAAADcan4UDd955pzZt2qQNGzY4f1WqVFH79u2d/8+QIYMWL17s3GfHjh3at2+foqKiJElRUVHatGmT16wCixYtUkhIiEqVKuW0Of8x0tqkPUZgYKAqV67s1SY1NVWLFy922lSuXPmStQAAAAAAkF75bMyBrFmzqkyZMl7LMmfOrOzZszvLO3furN69eytbtmwKCQlR9+7dFRUV5cwO0LBhQ5UqVUoPPvigRowYoZiYGD377LPq2rWrgoKCJEldunTRmDFj1LdvXz388MNasmSJpkyZojlz/m80/t69e6tjx46qUqWKqlWrpjfeeEOnTp1Sp06dJEmhoaGXrAUAAAAAgPTKpwMSXsrrr78uPz8/tWzZUomJiYqOjta4ceOc9f7+/po9e7Yef/xxRUVFKXPmzOrYsaNeeOEFp03hwoU1Z84c9erVS2+++aby5cun9957T9HR0U6bNm3a6MiRIxo0aJBiYmJUoUIFzZ8/32uQwkvVAgAAAABAeuUxM/N1EW5xufNL3ggK9Z9z6UYus/flxr4uAQAAAACuyOWeh/pszAEAAAAAAHBjIBwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACX+1fhQJEiRfTnn39esDw2NlZFihT5z0UBAAAAAIDr51+FA3v37lVKSsoFyxMTE3XgwIH/XBQAAAAAALh+Aq6k8cyZM53/X7BggUJDQ53bKSkpWrx4sQoVKnTVigMAAAAAANfeFYUDzZs3lyR5PB517NjRa12GDBlUqFAhjRo16qoVBwAAAAAArr0rCgdSU1MlSYULF9batWuVI0eOa1IUAAAAAAC4fq4oHEizZ8+eq10HAAAAAADwkX8VDkjS4sWLtXjxYh0+fNjpUZDmgw8++M+FAQAAAACA6+NfhQNDhgzRCy+8oCpVqih37tzyeDxXuy4AAAAAAHCd/KtwYMKECZo4caIefPDBq10PAAAAAAC4zvz+zZ2SkpJUs2bNq10LAAAAAADwgX8VDjzyyCOaNGnS1a4FAAAAAAD4wL+6rCAhIUHvvPOOvvnmG5UrV04ZMmTwWv/aa69dleIAAAAAAMC196/CgY0bN6pChQqSpM2bN3utY3BCAAAAAADSl38VDnz77bdXuw4AAAAAAOAj/2rMAQAAAAAAcPP4Vz0H6tWr94+XDyxZsuRfFwQAAAAAAK6vfxUOpI03kObs2bPasGGDNm/erI4dO16NugAAAAAAwHXyr8KB119//aLLBw8erJMnT/6nggAAAAAAwPV1VccceOCBB/TBBx9czYcEAAAAAADX2FUNB1avXq3g4OCr+ZAAAAAAAOAa+1eXFbRo0cLrtpnpjz/+0I8//qjnnnvuqhQGAAAAAACuj38VDoSGhnrd9vPzU/HixfXCCy+oYcOGV6UwAAAAAABwffyrcODDDz+82nUAAAAAAAAf+VfhQJp169Zp27ZtkqTSpUurYsWKV6UoAAAAAABw/fyrcODw4cNq27atli5dqrCwMElSbGys6tWrpy+++EI5c+a8mjUCAAAAAIBr6F/NVtC9e3edOHFCW7Zs0bFjx3Ts2DFt3rxZ8fHxevLJJ692jQAAAAAA4Br6V+HA/PnzNW7cOJUsWdJZVqpUKY0dO1bz5s277McZP368ypUrp5CQEIWEhCgqKsrr/gkJCeratauyZ8+uLFmyqGXLljp06JDXY+zbt0+NGzdWpkyZlCtXLj399NNKTk72arN06VJVqlRJQUFBKlasmCZOnHhBLWPHjlWhQoUUHBys6tWr64cffvBafzm1AAAAAACQHv2rcCA1NVUZMmS4YHmGDBmUmpp62Y+TL18+vfzyy1q3bp1+/PFH3XHHHWrWrJm2bNkiSerVq5dmzZqlL7/8UsuWLdPBgwe9plFMSUlR48aNlZSUpFWrVumjjz7SxIkTNWjQIKfNnj171LhxY9WrV08bNmxQz5499cgjj2jBggVOm8mTJ6t37956/vnntX79epUvX17R0dE6fPiw0+ZStQAAAAAAkF55zMyu9E7NmjVTbGysPv/8c+XJk0eSdODAAbVv317h4eH6+uuv/3VB2bJl08iRI9WqVSvlzJlTkyZNUqtWrSRJ27dvV8mSJbV69WrVqFFD8+bNU5MmTXTw4EFFRERIkiZMmKB+/frpyJEjCgwMVL9+/TRnzhxt3rzZeY62bdsqNjZW8+fPlyRVr15dVatW1ZgxYySdCz/y58+v7t27q3///oqLi7tkLReTmJioxMRE53Z8fLzy58+vuLg4hYSE/OttdD0U6j/H1yXccPa+3NjXJQAAAADAFYmPj1doaOglz0P/Vc+BMWPGKD4+XoUKFVLRokVVtGhRFS5cWPHx8Xrrrbf+VcEpKSn64osvdOrUKUVFRWndunU6e/as6tev77QpUaKEChQooNWrV0uSVq9erbJlyzrBgCRFR0crPj7e6X2wevVqr8dIa5P2GElJSVq3bp1XGz8/P9WvX99pczm1XMzw4cMVGhrq/OXPn/9fbRsAAAAAAK6lfzVbQf78+bV+/Xp988032r59uySpZMmSF5yEX45NmzYpKipKCQkJypIli77++muVKlVKGzZsUGBgoDMbQpqIiAjFxMRIkmJiYryCgbT1aev+qU18fLzOnDmj48ePKyUl5aJt0l5bTEzMJWu5mAEDBqh3797O7bSeAwAAAAAA3EiuKBxYsmSJunXrpu+//14hISFq0KCBGjRoIEmKi4tT6dKlNWHCBNWuXfuyH7N48eLasGGD4uLiNHXqVHXs2FHLli27sldxgwoKClJQUJCvywAAAAAA4B9d0WUFb7zxhh599NGLXqcQGhqq//3vf3rttdeuqIDAwEAVK1ZMlStX1vDhw1W+fHm9+eabioyMVFJSkmJjY73aHzp0SJGRkZKkyMjIC2YMSLt9qTYhISHKmDGjcuTIIX9//4u2Of8xLlULAAAAAADp1RWFAz///LPuuuuuv13fsGFDrVu37j8VlJqaqsTERFWuXFkZMmTQ4sWLnXU7duzQvn37FBUVJUmKiorSpk2bvGYVWLRokUJCQlSqVCmnzfmPkdYm7TECAwNVuXJlrzapqalavHix0+ZyagEAAAAAIL26ossKDh06dNEpDJ0HCwjQkSNHLvvxBgwYoEaNGqlAgQI6ceKEJk2apKVLl2rBggUKDQ1V586d1bt3b2XLlk0hISHq3r27oqKinNkBGjZsqFKlSunBBx/UiBEjFBMTo2effVZdu3Z1uvN36dJFY8aMUd++ffXwww9ryZIlmjJliubM+b/R+Hv37q2OHTuqSpUqqlatmt544w2dOnVKnTp1kqTLqgUAAAAAgPTqisKBvHnzavPmzSpWrNhF12/cuFG5c+e+7Mc7fPiwOnTooD/++EOhoaEqV66cFixY4Ixj8Prrr8vPz08tW7ZUYmKioqOjNW7cOOf+/v7+mj17th5//HFFRUUpc+bM6tixo1544QWnTeHChTVnzhz16tVLb775pvLly6f33ntP0dHRTps2bdroyJEjGjRokGJiYlShQgXNnz/fa5DCS9UCAAAAAEB65TEzu9zG3bt319KlS7V27VoFBwd7rTtz5oyqVaumevXqafTo0Ve90JvB5c4veSMo1H/OpRu5zN6XG/u6BAAAAAC4Ipd7HnpFPQeeffZZffXVV7r11lvVrVs3FS9eXJK0fft2jR07VikpKRo4cOB/qxwAAAAAAFxXVxQOREREaNWqVXr88cc1YMAApXU68Hg8io6O1tixY7264gMAAAAAgBvfFYUDklSwYEHNnTtXx48f16+//ioz0y233KLw8PBrUR8AAAAAALjGrjgcSBMeHq6qVatezVoAAAAAAIAP+Pm6AAAAAAAA4FuEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALicT8OB4cOHq2rVqsqaNaty5cql5s2ba8eOHV5tEhIS1LVrV2XPnl1ZsmRRy5YtdejQIa82+/btU+PGjZUpUyblypVLTz/9tJKTk73aLF26VJUqVVJQUJCKFSumiRMnXlDP2LFjVahQIQUHB6t69er64YcfrrgWAAAAAADSG5+GA8uWLVPXrl31/fffa9GiRTp79qwaNmyoU6dOOW169eqlWbNm6csvv9SyZct08OBBtWjRwlmfkpKixo0bKykpSatWrdJHH32kiRMnatCgQU6bPXv2qHHjxqpXr542bNignj176pFHHtGCBQucNpMnT1bv3r31/PPPa/369Spfvryio6N1+PDhy64FAAAAAID0yGNm5usi0hw5ckS5cuXSsmXLVKdOHcXFxSlnzpyaNGmSWrVqJUnavn27SpYsqdWrV6tGjRqaN2+emjRpooMHDyoiIkKSNGHCBPXr109HjhxRYGCg+vXrpzlz5mjz5s3Oc7Vt21axsbGaP3++JKl69eqqWrWqxowZI0lKTU1V/vz51b17d/Xv3/+yavmrxMREJSYmOrfj4+OVP39+xcXFKSQk5NpsxKukUP85vi7hhrP35ca+LgEAAAAArkh8fLxCQ0MveR56Q405EBcXJ0nKli2bJGndunU6e/as6tev77QpUaKEChQooNWrV0uSVq9erbJlyzrBgCRFR0crPj5eW7Zscdqc/xhpbdIeIykpSevWrfNq4+fnp/r16zttLqeWvxo+fLhCQ0Odv/z58/+7DQMAAAAAwDV0w4QDqamp6tmzp2rVqqUyZcpIkmJiYhQYGKiwsDCvthEREYqJiXHanB8MpK1PW/dPbeLj43XmzBkdPXpUKSkpF21z/mNcqpa/GjBggOLi4py//fv3X+bWAAAAAADg+gnwdQFpunbtqs2bN+u7777zdSlXTVBQkIKCgnxdBgAAAAAA/+iG6DnQrVs3zZ49W99++63y5cvnLI+MjFRSUpJiY2O92h86dEiRkZFOm7/OGJB2+1JtQkJClDFjRuXIkUP+/v4XbXP+Y1yqFgAAAAAA0iOfhgNmpm7duunrr7/WkiVLVLhwYa/1lStXVoYMGbR48WJn2Y4dO7Rv3z5FRUVJkqKiorRp0yavWQUWLVqkkJAQlSpVymlz/mOktUl7jMDAQFWuXNmrTWpqqhYvXuy0uZxaAAAAAABIj3x6WUHXrl01adIkzZgxQ1mzZnWu3Q8NDVXGjBkVGhqqzp07q3fv3sqWLZtCQkLUvXt3RUVFObMDNGzYUKVKldKDDz6oESNGKCYmRs8++6y6du3qdOnv0qWLxowZo759++rhhx/WkiVLNGXKFM2Z838j8vfu3VsdO3ZUlSpVVK1aNb3xxhs6deqUOnXq5NR0qVoAAAAAAEiPfBoOjB8/XpJ0++23ey3/8MMP9dBDD0mSXn/9dfn5+ally5ZKTExUdHS0xo0b57T19/fX7Nmz9fjjjysqKkqZM2dWx44d9cILLzhtChcurDlz5qhXr1568803lS9fPr333nuKjo522rRp00ZHjhzRoEGDFBMTowoVKmj+/PlegxReqhYAAAAAANIjj5mZr4twi8udX/JGUKj/nEs3cpm9Lzf2dQkAAAAAcEUu9zz0hhiQEAAAAAAA+A7hAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALufTcGD58uVq2rSp8uTJI4/Ho+nTp3utNzMNGjRIuXPnVsaMGVW/fn3t3LnTq82xY8fUvn17hYSEKCwsTJ07d9bJkye92mzcuFG1a9dWcHCw8ufPrxEjRlxQy5dffqkSJUooODhYZcuW1dy5c6+4FgAAAAAA0iOfhgOnTp1S+fLlNXbs2IuuHzFihEaPHq0JEyZozZo1ypw5s6Kjo5WQkOC0ad++vbZs2aJFixZp9uzZWr58uR577DFnfXx8vBo2bKiCBQtq3bp1GjlypAYPHqx33nnHabNq1Sq1a9dOnTt31k8//aTmzZurefPm2rx58xXVAgAAAABAeuQxM/N1EZLk8Xj09ddfq3nz5pLO/VKfJ08ePfXUU+rTp48kKS4uThEREZo4caLatm2rbdu2qVSpUlq7dq2qVKkiSZo/f77uvvtu/f7778qTJ4/Gjx+vgQMHKiYmRoGBgZKk/v37a/r06dq+fbskqU2bNjp16pRmz57t1FOjRg1VqFBBEyZMuKxaLiYxMVGJiYnO7fj4eOXPn19xcXEKCQm5uhvwKivUf46vS7jh7H25sa9LAAAAAIArEh8fr9DQ0Eueh96wYw7s2bNHMTExql+/vrMsNDRU1atX1+rVqyVJq1evVlhYmBMMSFL9+vXl5+enNWvWOG3q1KnjBAOSFB0drR07duj48eNOm/OfJ61N2vNcTi0XM3z4cIWGhjp/+fPn/7ebAwAAAACAa+aGDQdiYmIkSREREV7LIyIinHUxMTHKlSuX1/qAgABly5bNq83FHuP85/i7Nuevv1QtFzNgwADFxcU5f/v377/EqwYAAAAA4PoL8HUBN7OgoCAFBQX5ugwAAAAAAP7RDdtzIDIyUpJ06NAhr+WHDh1y1kVGRurw4cNe65OTk3Xs2DGvNhd7jPOf4+/anL/+UrUAAAAAAJBe3bDhQOHChRUZGanFixc7y+Lj47VmzRpFRUVJkqKiohQbG6t169Y5bZYsWaLU1FRVr17dabN8+XKdPXvWabNo0SIVL15c4eHhTpvznyetTdrzXE4tAAAAAACkVz4NB06ePKkNGzZow4YNks4N/Ldhwwbt27dPHo9HPXv21LBhwzRz5kxt2rRJHTp0UJ48eZwZDUqWLKm77rpLjz76qH744QetXLlS3bp1U9u2bZUnTx5J0v3336/AwEB17txZW7Zs0eTJk/Xmm2+qd+/eTh09evTQ/PnzNWrUKG3fvl2DBw/Wjz/+qG7duknSZdUCAAAAAEB65dMxB3788UfVq1fPuZ12wt6xY0dNnDhRffv21alTp/TYY48pNjZWt912m+bPn6/g4GDnPp999pm6deumO++8U35+fmrZsqVGjx7trA8NDdXChQvVtWtXVa5cWTly5NCgQYP02GOPOW1q1qypSZMm6dlnn9UzzzyjW265RdOnT1eZMmWcNpdTCwAAAAAA6ZHHzMzXRbjF5c4veSMo1H+Or0u44ex9ubGvSwAAAACAK3K556E37JgDAAAAAADg+iAcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcLsDXBQBuUqj/HF+XcMPZ+3JjX5cAAAAAuB49BwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHC5AF8XkN6MHTtWI0eOVExMjMqXL6+33npL1apV83VZgOsV6j/H1yXccPa+3NjXJQAAACCdIBy4ApMnT1bv3r01YcIEVa9eXW+88Yaio6O1Y8cO5cqVy9flAcBVR+hyIUIXAABwMyIcuAKvvfaaHn30UXXq1EmSNGHCBM2ZM0cffPCB+vfvf0H7xMREJSYmOrfj4uIkSfHx8den4P8gNfG0r0u44VyNfze264Wu1ueBbXsh3rPXxtXYrmWeX3AVKrm5bB4S7esSAAC4KaUdu5jZP7bz2KVaQJKUlJSkTJkyaerUqWrevLmzvGPHjoqNjdWMGTMuuM/gwYM1ZMiQ61glAAAAAAAX2r9/v/Lly/e36+k5cJmOHj2qlJQURUREeC2PiIjQ9u3bL3qfAQMGqHfv3s7t1NRUHTt2TNmzZ5fH47mm9d4s4uPjlT9/fu3fv18hISG+LuemwXa9Ntiu1wbb9dph214bbNdrg+167bBtrw2267XBdr1yZqYTJ04oT548/9iOcOAaCgoKUlBQkNeysLAw3xSTzoWEhPDhvwbYrtcG2/XaYLteO2zba4Ptem2wXa8dtu21wXa9NtiuVyY0NPSSbZjK8DLlyJFD/v7+OnTokNfyQ4cOKTIy0kdVAQAAAADw3xEOXKbAwEBVrlxZixcvdpalpqZq8eLFioqK8mFlAAAAAAD8N1xWcAV69+6tjh07qkqVKqpWrZreeOMNnTp1ypm9AFdfUFCQnn/++Qsuz8B/w3a9Ntiu1wbb9dph214bbNdrg+167bBtrw2267XBdr12mK3gCo0ZM0YjR45UTEyMKlSooNGjR6t69eq+LgsAAAAAgH+NcAAAAAAAAJdjzAEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQD/yeLFi3XmzBlfl4F/wLizuNbGjRunxYsXKzU11delAMBNZ+TIkXrwwQd9XcZN7ZtvvvF1CTcEwgEA/9qKFSvUtWtXDRgwQAkJCb4uBxdhZvJ4PJKkAwcO+Lga3KzGjRunhx56SCtXriQguEYI+W5cF3vP8++Fqylv3ryaPHmyunXr5utSbko//fSTGjZsqCeffNLXpfgc4QCAf61y5cpq3bq11qxZowEDBtCD4AaTkpLiBAOvvvqqnnnmGUnuO2hNe72//fab/vjjDx9Xc3NJ27abN29W0aJF1aFDB61YsULJyck+riz9S9u2f/75p06dOuV8lnFjSU1NlZ/fucPp3377TUePHnX2vSkpKT6uDjeL++67T1988YU+/vhjPf74474u56ZTqFAhjR07VpMnT1aPHj18XY5PEQ7gpnCx1J5fr66t5ORkZcqUSUOHDtVdd92ljRs36vnnn1diYqKvS3O9Tp06aeXKlfL393dO0jZt2qQiRYpIclc4kNZzYvr06WrTpo1mz56t2NhYX5d10/B4PEpKSpJ0rktmWFiY+vbtq++++44To/8o7X17zz33qHz58nruuee0bt06X5eFv0gLBp577jnVq1dP9erVU5s2bZSYmCh/f/+b+nOQ9l2yZcsWzZkzR7t37+ZHgqvMzGRmCggIUNmyZfXSSy/p7bffdsJ+/HdmpvDwcP3vf//T8OHDNXnyZD377LO+LstnCAeQ7p2f2n/zzTeaOXOmNm/e7CzDteHv7y9J+vHHH5WQkKD9+/fr7bff1uDBg7nEwId+//13/f7772rVqpXWrl2rgIAASdLBgwcVFBQkSa76bHg8Hs2cOVP333+/7rvvPjVp0kRhYWG+LuumYWYKDAzU5MmT9dBDDylXrlxau3atunTpwiUG/9FPP/2khx9+WHfffbeaN2+uuXPn6sUXX9SyZct8XRrk/QPEV199pXfeeUfDhw/XAw88oN9++00VK1ZUQkLCTR0QeDweTZs2TbfffrseffRR3XHHHRo+fDg9tK4ij8cjj8ejr776So0aNdL69etVoEABvfzyy+ratauvy7sppIVcK1eu1I4dO5Q1a1a99NJL6t+/v48r8w33HCHippV2otOvXz+1aNFCvXv3VsWKFTV27FhOUq8hj8ejOXPmqEaNGsqSJYt69uyp2267TTNnztTAgQPZ9j6SL18+vfnmm7r99tvVpEkTrVmzRtK5SwzSwoG0X3qlm68XwYYNG7xuHzp0SEOHDtVLL72k3r17K1u2bDp69KimT5+ulStX+qbIm4jH49HKlSvVqVMn3XHHHRo5cqTWrVunkJAQPfTQQ/Qg+Jd+/fVXzZkzR71799bAgQP16quv6sUXX1R8fLxee+01AoIbQNqxxxdffKHjx4/rlVdeUZs2bdS3b1+NHz9egYGBqlSp0k0ZEKR9b+zdu1djx47Viy++qHXr1unBBx/UwoULNWzYMB08eNDHVd48fvnlF3Xu3Fm9evXS22+/rdWrV2vChAn68MMPGYPgKvDz89OsWbPUoEEDhYeHq0ePHnrggQc0fvx49erVy9flXX8GpFOpqanO/2/YsMEqVKhga9assb1799obb7xhHo/Hhg8fbqdPn/ZhlTen1NRUO336tDVp0sR69OjhLE9MTLQBAwZY8eLFrX///paQkOC7Il0oOTnZ+f9t27ZZq1atLGfOnLZ161Z78sknbdSoUXb69Gn7/fffLT4+3pKTk23jxo0+rPjqmj59umXLls1iY2OdZfHx8RYVFWVjx461Y8eO2cCBA6127doWERFhmTNntk8++cSHFd8cxo8fb5UqVfLa1yYnJ1uVKlWsZMmStmzZMjt79qwPK0xffv/9d6tSpYrlzJnTnn76aa918+bNszvuuMNatGhhixYt8lGFSPPrr79a/vz5zePx2Ntvv+0sT01NtR9//NEqVKhgZcqUuSmPQ3788Ufr06ePtW/f3k6cOOEsHzFihFWvXt2eeOIJO3DggA8rvHmsWrXKChUqZPv373eWnT592saNG2cej8eee+45H1aX/iUkJFjr1q2te/fuzrIjR47Ym2++aVmzZrX+/fv7sLrrj3AA6d4rr7xivXv3tieffNJredpOk4Dg2mnUqJE99NBDXsuSk5Otfv36liNHDnv88cftzJkzPqrOXVJSUpz/P3bsmJmZ7dy501q1amVhYWGWIUMGK1GihBUsWNCyZ89u+fLlszx58tjdd9/tq5KvibSD0YMHD5qZWWxsrLVo0cJq1aplwcHBdu+999q4ceNs9+7d1rx5c+vatasvy70pvPLKK1awYEHndtr+dvny5ebxeKxw4cK2cuVKH1WXPn300UdWokQJi4qKsp9//tlr3fz5861SpUp2//33893mYwkJCTZjxgwrV66cVa9e3WtdamqqrVu3zvLkyWP333+/jyq8drp3726hoaF2yy23eAWyZucCglq1almHDh3sjz/+8FGFN49ff/3VgoODberUqV7L9+zZY5GRkebxeKxXr14+qi79S05OtqioKHvwwQe9lh89etRatWplHo/ngnOMm1mAr3suAFfKzpuaTTp3LfXo0aN1++23KyEhQcHBwZLkjOb65JNP6sSJE3r++ecVGBjok5pvFmnbPjU1VampqSpUqJC2bt2qP/74Q5GRkfJ4PPL391e9evX022+/KSYmRnFxcc6/Ca6N88fdeOmll7R//3516NBBUVFRev755xUeHq7PPvtMXbt2VevWrXXw4EGlpqYqISFBNWrU8HH1V0faezNPnjzavXu3ihUrpokTJ6pDhw567bXXtH79ep04cUKtW7dWxowZJZ3rEp8lSxYfV57+tW3bViNGjFDfvn01YsQIZ/tmyJBBrVq10tGjR5UrVy4fV5m+dOjQQf7+/ho1apRGjx6tJ598UuXKlZMkRUdHKyAgQMWKFXO2Na698/ezaYKCgtSgQQP5+/urZ8+eql+/vjNXusfjUcWKFbVkyRIVK1bMFyVfU6NHj1ZoaKg+/vhjjRw5Uk899ZTCw8MlSU8//bTOnDmjFStW+LjK9Oevx7jSuWkMmzVrpg8++EARERG67bbbJEnZs2dXw4YN1aBBA1WrVs0X5d4U/P391bRpUy1cuFA//fSTKlasKOnc9q1cubK2bt2qhQsXKiYmRpGRkT6u9jrwbTYB/Ht//vmn8//Dhg0zPz8/+/DDDy9oN3LkSKtVq5bXZQi4Mmnb7ujRo3bq1Ck7evSomZnt3bvXsmXLZm3atLHff//dad+zZ08bNmyYHTlyxCf1ulW/fv0sR44c9sUXX3h15/z555+tffv2ljt3blu3bt0F9zv/coT0Ku09umrVKtu7d6/17t3bMmfObJMmTbqg7bFjx6x///6WI0cO27Zt2/UuNd1K28bbtm2zBQsWOJdxmZm98cYbVrRoUXvqqafMzJxLOB5++GEuKfgHadt07dq19sEHH9g777xjmzZtctZ/8MEHVqlSJXv44YdvqkuA0pvze2Z9/vnn9vzzz9uQIUOcXh1nzpyx2bNnW4kSJaxBgwYXfYz0vJ9Ne58mJiZaUlKS17qePXtalSpVbOjQoRf0IDj/OA2Xlradv/vuOxs9erT16dPH1q5da2fOnLE1a9ZYnTp1rGHDhvbpp5/ali1b7Omnn7aSJUtyrHUF0rbx8ePH7fjx487yNWvWWOnSpa1Lly5ex0m9evWyIUOGWHx8/PUu1WcIB5BunP/l/Prrr1udOnVsy5YtzrL+/ftbhgwZLnoNcdrOgIDgyqVtsxkzZliNGjWsdOnSVrZsWXvvvffMzOynn36y7NmzW61atezee++1tm3bWnBwsP3yyy++LNt1li1bdkH37fPf71u3brU2bdqYx+OxrVu3+qLEa27+/PmWLVs2mzVrlpmZPfXUUxYYGGhffPGF0+aLL76w+++/3woVKmTr16/3Vanp1tSpUy1XrlxWvHhxy549u1WtWtWmT59uZmZjxoyxHDlyWGRkpJUoUcLCw8MvGkbhnLTP57Rp0yxbtmx25513WsGCBa1hw4Y2fvx4p92HH35o1atXt9atW3t95+H669u3rxUoUMAaNmxozZo1s9DQUFu2bJmZ/V9AULp0aatQoYKPK7160t6n8+bNsw4dOljlypXt1VdftdWrVzttevToYZUrV7YXX3zRuawN/87UqVMtc+bM1qBBAytatKjlz5/fHn/8cTt27Jj98MMP1rFjRwsODraiRYtanjx5+B67Aucfz1arVs2KFy9uJUqUsPfee8+Sk5Nt4cKFVrZsWYuKirJmzZpZ69atLSQkxLZv3+7jyq8vwgGkC+cHAytXrrQRI0aYx+Oxtm3b2o4dO5x1/fr1s8DAQPvss88ueAyCgX9v/vz5FhgYaCNGjLDx48fbgAEDzOPx2IABA8zMbN++fda3b19r06aNPfDAA/zC5QMzZsywYsWK2YEDBy4Iw9I+P1u3brVnn302Xf+C9XdiYmLs8ccft1GjRnktTwsIJk+ebGbn3qtjx4613bt3+6LMdO3HH3+0kJAQGzt2rB09etSWLVtmjz/+uOXOndtmzJhhZmaHDh2yd955xz7//HPbtWuXjyu+8S1btswiIiLsnXfeMbNzPV8yZ85s5cqVs9dee81pN378eLv99tudsTRw/U2YMMHy5ctna9euNTOzzz77zDwejwUFBdns2bPN7FxAMHXqVGvXrp3XcUt6N336dMuUKZP16dPHnnnmGatdu7ZFR0d7DYrZu3dvK1KkiI0cOZLjrX9p586dVrhwYXv33Xed7+nRo0db3bp1rWvXrpaYmGjJycm2f/9+27Rpkx06dMjHFac/CxYssMDAQBs6dKhNnjzZ/ve//1nRokVtwIABlpKSYj/++KONHj3a7r77bnv00UddeTxLOIB0pW/fvpYnTx4bOnSodezY0bJmzWp33XWXV0CQduK6YMECH1Z680hNTbUOHTpY586dvZZPmjTJPB6PTZw40cz+r8vkX7sc4vp4//33LSQkxE6dOmVm3v8OixYtumBAuJspIPjhhx+sWrVqVrZsWecg/fwD86eeesoyZ87sXHbEgeu/8+6771rNmjW93ju7du2yxx57zGrXrs2J6xVKTk62F154wZ544gkzM9u9e7cVKVLE7rvvPrvvvvuscOHCNm7cOKf9X7ts4/qJjY21Pn362AcffGBmZrNmzbKsWbPaqFGjrEOHDpYxY0ZbsmSJmZ3rep/mZtjPbty40YoXL+4EWCdPnrRs2bJZsWLFrF69erZ48WKnbf/+/Qle/4P169db3rx5L+hx9cYbb1i+fPm4DO4/SE1NtbNnz1rbtm3tscce81o3YsQIK1SokH366adey2+Gz++/QTiAG9ZfR7n/4YcfLHv27M4XsNm5KQzDw8OtUaNGXt1+xo0bx3WuV8nZs2etdu3azhQvycnJzrbt2bOnRUVFWVxcnLMT5cTr2vq7X6P+/PNPK1GihDVr1sxr+cmTJy06OtpeffXV61CdbyQkJFiDBg2cKZ3S3p/nb6suXbpYrly5LC4uzldlpnsfffSR5cmTx3777Tev5XPnzrXQ0FDbvHmzjypLP9L2j2n7y99//902bNhgp06dsqioKOvUqZOZmW3ZssXCwsKsYMGC9sYbb3jdF9fexfaz69ats127dtn27dutWLFi9tZbb5mZ2ddff20ej8c8Ho99991317vUa+7nn3+27t272+nTp+23336zIkWK2OOPP25z5861iIgIq1evnhPK4sqd/7les2aN5cuXz3kfnR805cmTx4YPH37d67vZNG3a1B5//HEzM6/ptjt06GAVK1Y0M/a1fpceshC4/tq1a6cFCxZ4LUtOTlZwcLAKFCggSTp79qzKly+vuXPnasmSJRo6dKh27Ngh6dxMBQEBAUpOTr7utd9sAgICVLt2bc2ePVu7d++Wv7+/M5JuRESEUlNTlSVLFvn7+0vSBaPs4uo5f7Ts5cuXa/bs2Vq9erVSU1OVLVs2DRw4ULt371bdunW1fPlyTZkyRa1bt1ZMTIx69Ojh4+qvnaCgIM2aNUuNGjXStGnTNH36dJ09e1Z+fn5KTU2VJI0fP16bNm1SSEiIj6tNvwoXLqyMGTNq5syZiouLc5aXKlVKuXPn1qlTp3xY3Y3P/v8o5CtXrtTnn3+u33//XXnz5lX58uWd2TT69esn6dz3W5UqVdSiRQvde++9kti3Xi/n72ffe+89vfbaa5KkSpUqqUiRItqyZYty5cql9u3bS5LCw8P12GOPaezYsapevbrP6r5azEySFBcXp6SkJJUrV079+vVTxowZ9cwzz6hWrVoaNWqUGjVqpAoVKmj79u368MMPderUKee+uLS0bXX+57patWrKmzevnnzySZ08edKZYevUqVMqUKCA8uXL55NabwZp2zt37tzOjCJBQUFKSkqSJNWoUUMZMmRQUlKS6/e1hAO4IRUuXFiNGjWSdO4gSZIiIyN19OhRLVu2TNK5k1YzU7FixVS4cGFNnjxZAwcO9PpyCghgts4rkbbt4uPjdeTIEWd5mzZtVLBgQfXr10979uxxgoA//vhDYWFhSkhI8Em9bmJmzgHrM888o3bt2mnAgAG6/fbb9dRTT2n37t26//779frrr8vM1KpVKw0bNkwBAQFau3atAgIClJKS4uNX8d+lvUc3bdqkKVOmaP78+fr5558VFBSkadOmKU+ePBo+fLhmzpzpBARp92E6vcuTtr22bt2qFStWaM6cOZKk2rVrq23btnr++ec1ceJE7dixQydPntS4ceOUmJioggUL+rLsG1paMDBt2jQ1atRIu3bt0okTJ7zWx8XF6aeffpIkTZs2TZGRkRo0aJATiOP6SNvPPv300xoyZIhSU1O1b98+Z/2pU6e0evVqHThwQH/++adGjRqllJSUm+JHibT36ezZs9WtWzctWrRIycnJyps3rxITE7V9+3aVLVtWGTNm1NmzZ5UnTx499dRTeuutt5Q5c2bXn1RdrrTtvHr1ar388ssaNWqUpk6dKkmaMmWKTp8+rdq1a2v+/Plavny5hg8frp07dyoqKsrHlacfad9jx44d0/HjxxUfHy9JGjZsmFJTU3XHHXcoJSXFCWB+/vlnhYSE3BTHSf/Z9e6qAPyTv3blGzdunI0dO9a51nLAgAGWP39++/LLL502J06csG7dutnChQstKCjIa5RnXL7zR3G97bbbLH/+/NawYUMbNWqUpaam2qxZs6xu3bqWN29ea9++vTVt2tSyZs1qGzZs8HHl7vLyyy9b3rx5nTEEnn/+ecuQIYM99NBDXjNE/PLLL3bkyBHn3/Vmusxm6tSpliNHDitTpozlz5/f8uXL51wPe/r0aatfv75Vr17dPvvsM8bAuEJp75cvv/zScufObcWKFbPQ0FArV66cMyr7s88+ayVKlLCwsDCrXLmyRUREMGL2ZVi7dq3lzJnT3n///Qs+j7/99pvdc889VrRoUStVqpSFh4fbTz/95JtCYZ999plFRETY999/f8G6Y8eOWbNmzczj8dgtt9xiZcqUcfYzN0N35K+//tqCg4PtxRdf9PpOiY2NtSZNmli7du1s5syZNnDgQCtatKjFxMT4sNr0a9q0aZYlSxa74447rGLFihYYGGhdunSx1NRUO3DggNWpU8cKFSpkBQsWtDJlyrCPvQJpn8Pp06dbnTp1nFlgXnzxRTMzW7FihRUrVswKFy5sbdq0sXvvvdeyZMniTE3qdoQDuKE1bdrUihYtahMnTrTExET77bffrEuXLhYeHm79+vWzt956y+644w6rUqWKJScnW+3ata1bt26+LjtduNhBzPz58y0oKMgGDx5sn376qXXo0MEqVapkXbt2tdTUVNu2bZu9+OKL1qJFC+vRowfTal0H5wdm+/fvt9atW9ukSZPMzOyrr76ysLAw69Kli2XJksXat29/0ROK9D5q9vn1p40zMn78eDtx4oRt3LjRnn32WfPz87N3333XzM6NV1K9enW7/fbbXTU38dWyZs0aCw0NtYkTJ9quXbvs4MGDdvvtt1vx4sWdUOrHH3+0r7/+2qZNm3bBGATwlravfeeddywqKspOnDjhrDv/vb1792775JNP7NVXX2UqWB9JGwuiX79+1rZtWzO7cNYXs3PXKk+bNs2+/PJL5z43QwC7f/9+K1eunDOewl999tlnVrNmTcuXL58VK1aMqUr/pV27dlm+fPlszJgxZmYWFxdns2bNspCQEOd6eLNzMwzt2LHDDh8+7KtS06158+ZZUFCQvfLKKzZ27FgbMGCAZcmSxXr27GlmZsePH7fevXtbp06d7Iknnrhpp3j+NwgHcMP4uxOYBx54wG699Vb78MMPLTk52Q4fPmyjR4+2okWLWvXq1a1JkyZOal+3bl0bNmzY9Sw73Ur7sklJSbGUlBRLSEiw+++/33r16uW0SUhIsDFjxljFihVt7NixvirVtf4aDJiZzZ492+Li4uyHH36wAgUK2JtvvmlmZi+88IJlyZLF7rvvPtu5c6dP6r3avvrqK+f/07bFtGnTrHLlys6sDGbnftEaMGCAFStWzBnNOSEhgZPWy/Ddd9/Z77//7rXsww8/tMqVK9vJkye93oO1a9e2ypUrX+8S06UjR47Y1q1bvQbW7du3rzPglZn353vt2rWcAPjIzz//fEEPgf/9739Wv379C45LEhISbO7cuRc8Rnod1fyvr2/Pnj1WsGBBW758ubPsrz8k/PHHH/bLL7/QY+Ayvf322xeceP74449WtGjRC2Z2+Prrry1TpkwM8HiF0gZuTHs/nz171jp16uQMpG127keDKVOmWNasWW3kyJFe978ZevxcTYw5gBvC+QMAbdiwQb/++qsOHDggSfrkk09UuXJlDR8+XJ988omyZMmi7t27a8OGDVq1apVmzZqlDBkyqF+/fvr111/Vpk0bX76UdGHKlCmqVauWNm3aJD8/P/n5+SkoKEjHjh3T0aNHnXZBQUH63//+p6JFi14wQCSurWnTpunrr7+WJD311FPq3LmzUlJSVK9ePYWEhGjWrFmqUKGCHnnkEUnnxteoWrWqUlNTVaRIEV+WflXs3btXLVu2VMuWLSX933XA/v7+2rZtm/bv3y/p3HWFoaGhatasmU6cOKE///xT0rn3Ltdq/7NVq1apQYMGev/99xUTE+MsP3TokP78809lzpxZfn5+On36tCTp/fff16+//qoVK1b4quR0YevWrWrevLnGjh2rbdu2OcvvuOMObdq0SdOmTZP0f+/phIQEffbZZ1q2bJkzgCauj0mTJunhhx/W22+/rV27djnLb731Vm3cuFE//PCD1zhGp06d0tixYzVz5kyvx0kbhyc9+e233/TRRx9pw4YNzrIjR47ojz/+UKZMmSSdG/MpbRyBn376SXPnzlW2bNl0yy23KCIiwhdlpytnzpzRq6++qmbNmmnnzp3O8qxZs2r//v3avHmzV/uaNWsqb968OnTo0PUuNd16//33VbRoUcXFxXmNMbR9+3bFxsY67YKDg9WkSRN16tRJq1at0pkzZxhA828QDuCGkHaQ1K9fPzVv3lxVq1ZVz5499dVXX0k69wVeuXJlvfLKK5o8ebLi4uKUJUsW+fn5af369erVq5c+/fRTzZo1S8WKFfPlS0kXMmfOrEKFCqlLly7Ol1NSUpIKFSqkAwcO6NChQ85BakBAgOrWrau9e/d6DaCFa8fMtHTpUrVu3VrNmjXTu+++q5EjR8rf31/BwcGSzh3EJSUlOf8ma9as0ZNPPqkvv/zSa5T+9KpgwYKaP3++Vq5c6RX4FS9eXKVLl9ZHH32kAwcOOAeuRYoUUbZs2Rgx/zKkHRDVrFlTffr00Ycffqj3339ff/zxhySpVatWio2N1XPPPSdJzonCmTNnlCNHDoWGhvqm8HRg06ZNuu2221SlShW1adNGFStWdNZVqVJFHTp0UN++fTVlyhRJ0tGjR/XSSy9p0qRJqlixovNdiGvvww8/VJcuXfToo49q4MCBKlq0qLOud+/eKlGihNq2bat58+Zp9+7d2r17t9q3b68///xTjRs39mHl/92mTZsUHR2tWbNmOZ97SapataruvPNOPfLIIzp06JAyZMjgrPvwww81Y8aMdP/dcj2kbaOMGTNqzZo1yp49u5o1a6ZffvlFkpQvXz7nu/3777937pc9e3Zlz57dGYgbl1atWjVlzZpV9erVU3x8vDwejwICAtS4cWPt27dPGzdudNpmzJhRuXPndoKatOMHBtL8C192WwDO78qzePFiK1KkiC1dutQmTpxo9913n1WtWtU+/fRTp80DDzxg4eHhXl2u4uPjbc6cObZ3797rWnt6k9bdKq371eLFi61x48ZWrVo1ZxCWbdu2WdasWa1jx4528OBB576PPPKI3X333V5zwuLaOL976q233moBAQE2atSoC9pNmzbNgoODLSoqyooXL26lSpVyrnlN713kzp8LfuHChRYWFmatW7d21g8dOtRKlixpTz/9tG3YsMEOHz5s/fr1s3z58tmBAwd8VXa6kLYfOL8767Bhwyxfvnw2bNgwZ/u9+uqrVrRoUXvmmWfMzOzo0aP2/PPPW7FixeyPP/64/oWnAzExMVa+fHkbMGDABevS3tO//fabde3a1fz9/a1EiRJWrlw5y5MnD4ONXWdr1661/PnzO+O3nO/48eNmdu6zcu+991rBggUtJCTEKlSoYNWrV3cuY0yvlxJs3brVwsLCrH///rZv374L1i9cuNBq1qxppUuXtqVLl9rMmTOtT58+FhYWZhs3bvRBxelL2j52y5YtNnnyZDM7t/+sVq2alSxZ0hlPZM6cOVa3bl2766677IsvvrCffvrJ+vTpYzly5LjgcgN4S9vGJ0+eNLNzx67ly5e3smXLWlxcnJmdex+XKVPGnnzySa+Bs7t162ZNmjTxujQR3ggHcEP46quvrEuXLjZ8+HBn2bp166xDhw5WpUoVr4Bg8ODBzpdyej8Jul7SdqTr16+3u+++2zkgWLBggd19991WrVo15+D0u+++s5CQEKtdu7Y1bdrU2rdvb1myZGFWguvg/PDl119/tejoaGvTpo0FBwfblClTnHXnj8T73HPP2aBBg5xgIL0esJ4v7fUdPXrUzM69T7Nly2YtWrRw2rz44osWFRVl/v7+Vr58eU6wLkPafmDDhg3m8Xjsiy++cNalBQRDhw6148ePW2xsrL3++usWHh5uuXPnttKlS1tkZCQDkP2DlStXWoUKFZxxL8zMfvrpJ3v33XftrrvuskcffdQ56F++fLm98cYb9vnnnxNs+8Ann3xiNWvWtNOnTzvL5s6daz169LBbb73V7r//fvv111/NzGzVqlU2c+ZMW7x4cboffPDUqVN27733el2LbXbue+PAgQPO2DabNm2yZs2aWVhYmN16661WvXp1Zs+4DGn72J9++skyZszodW370aNHrWrVqla8eHFnXKB58+ZZ+/btLSgoyEqUKGElSpTge+wSzv8eq1u3ru3YscPMzoUx5cuXtzJlyjgBwaeffmply5a16tWrW9OmTa1169bMsnUZCAfgc7t27bI6depYWFiY9enTx2vdunXrrGPHjla9enVnqrI0N8NJ0PVw/o40MDDwgm08b948JyBI22H+8ssv1r9/f2vXrp117dqVWQmug0WLFlmXLl3MzKxLly7WtGlTJ9nu0aOHBQUFeU3haWYXDCSXXg9YL2br1q1WuXJlW7t2rZmd+xXgrwHBb7/9ZosXL7YlS5ZcsC3g7fyD1ixZsjg9As4fkGzIkCGWN29eJyAwMztw4IC9++67Nn36dE5iLyFt+se0A/8PPvjA6tataxUrVrQ777zTKlWqZIUKFWKgzBvARx99ZLfeequtXr3azMy6d+9ut912m9WsWdOeeeYZy58/v912220XvW96PvZISEiwmjVr2ttvv+0sW7hwodMzoEiRItayZUtn3bZt2+zQoUN27NgxX5Sbrpx/rJUpUybr37//BW3+/PNPq1atmt16663OfiI5Odn27t1rO3fudAJxXNz52zhDhgw2cOBAr/VpAUGpUqWcgODbb7+1N99805o2bWq9e/fmePYyEA7gurvYr/0LFiyw+vXrW9GiRW3RokVe69avX29Nmza1hx9++G/vj4u7nC8rs3NTGP61B0F67zqZniQnJ9uQIUOsatWqVrVqVQsPD7ft27d7tenZs6dlzJjRPv30Uztw4IA1b97c7rvvPjO7OT8TP/zwg9WtW9deffVVMzsXfCxcuNCyZ8/udfCKS0t7f2zatMkyZsxoQ4YM8Vp//kjaQ4cOdQICApcrc/r0abvlllssb968VqVKFQsODrbBgwc7+9QVK1ZYZGSkff3112Z2c35u04t169ZZ7dq1rVixYpY3b14rWLCgvffee85lNevWrTOPx+NM3XmzOHr0qBUpUsR69uxpu3fvtldeecVKlixp9957r40cOdLGjh1r+fPnv2h4iEvbuHGjhYaGOtsvzffff2+HDh0ys/+7xKB48eJMWXoF0t6LP//8s2XMmPGCYCBNWkBQunRpJyAwO7e/ZZ97eQgHcF2d/0Vz+PBhr+vdVq5caY0aNbIGDRrY4sWLve63Y8cOvqT+pX379llAQIATDKSd7A8dOtRGjx7ttEu7xKBmzZpe3drYmV4/0dHR5vF4rF27ds6y88OZp59+2jwej5UuXdpKly7tBDg3g7T32fnTY40cOdJCQ0Od7r1JSUm2cOFCi4yMtLvuussndaZXR44cscKFC1u1atW83lPDhw+3Jk2aeI0jMHToUCtcuLA988wzTFd2mdK2aXx8vD3zzDP2zDPP2M8//+zVm2fbtm1WqlQpW7p0qa/KxHlWrlxpn3zyib366qsWGxvrtW7BggVWsWJF27Vrl4+qu/rS9rEzZswwj8djBQsWtMyZM9u4ceOck9QzZ87Y7bffbo899pgvS013UlNTLTk52cqXL29BQUFex7aDBw+2fPnyefW8Onr0qNWsWdMiIyOd7zdc2u7du83j8dhTTz3ltXzEiBH2ySefOLfTAoIKFSo4veBw+QgHcN2cf5L5wgsvWNWqVa1w4cJWtWpVmzFjhpn93yB5DRo0sCVLllzwGAQEV27RokVWtGhRa9CggfNv8NJLL1lISIjNmzfPq+3ChQvttttuszvvvNMZuBDXXkJCgsXHx9ugQYOsR48edtttt1nXrl0tPj7ezMwrBPj2229txowZ6f7a14tZuHCh5c6d2/r16+csu++++6xGjRp24sQJMzt3EjZ79mwrUqQIv2xfgZSUFHv44YetZs2a9vLLL5uZ2euvv25Zs2a1BQsWOG3SDBgwwEqXLk031ytwqV5WzzzzjFWoUIEBHX3sUoH3mTNn7J577rF77733pjvmSHvtO3futFWrVtnhw4e91icnJ9u9997r9C7ix4Ers2vXLouIiLC77rrLYmNjbfjw4ZYzZ06bM2fOBW2PHDlid955J+HAFdi4caMFBwfb/fff7/QKeOWVVywgIOCCXsdbt261AgUKWK1atXgfXyHCAVx3gwcPtoiICJsyZYodPXrUSpcubaVKlXIGalq0aJE1bdrUKlasyOBXV0FSUpItWLDAypQpYw0bNrQXX3zRcubM6RUMnL/jXLJkyUVHMMbV9f3339uKFSsuum7o0KFWo0YN69q1q3NSnJqaesG1cjfbJR+zZ882j8djfn5+Fh0dbV999ZVNnTrV2rRpY6NHj/YaiJSRhi9f2glOcnKyPfHEE1ajRg2Ljo62sLCwC96D558MHTly5LrWmZ5cSSj366+/2lNPPWXh4eEMhHWdXc7Jfdr334kTJ2zp0qXWqFEjK1OmjBPK3qwBwV8lJSXZs88+a3nz5nWuh8flS9sn7Nq1y8LDwy1v3ryWI0cOJ3y92Ha/2d5b18PatWste/bs1qFDBxsyZIhly5btgmAgzfbt22+q3j/Xi8fs/094DFxjKSkp+vPPP9WsWTP16dNHLVu21OLFi3Xvvffq1Vdf1WOPPea0nT17tpYtW6ZXXnmFeZ//AzOTx+NRcnKyFi9erIEDB2r9+vWaO3eu7rrrLiUnJysgIMCrLa69NWvWKCoqSqGhoWrTpo0aN26s6OhoBQYGSpKSkpL0yiuvaP78+SpVqpQGDBig//3vf8qUKZNmzJjh4+qvnr++5xISEvTiiy8qODhYv//+uxISEvTHH38oLi5ORYsW1ZgxYxQWFua7gtOx1NRU+fn5KSUlRb1799akSZPUrFkzTZgwQQEBAV7/Fmlt2Sdc6MiRIwoLC1OGDBm0ePFihYeHq1KlSn/b/tVXX9WUKVMkSe+9957KlSt3vUrFeWbPnq2KFSsqT548F31PJyUlqX///tq2bZsyZsyoKVOmKCAgwOs7Mj05dOiQDh06pKJFiypz5syXbD958mStXr1an3/+uebPn6+KFStehypvPikpKfL399fevXtVp04dhYeHa9asWSpQoIAkjrOulrVr1+ree+/VwYMH9dVXX6l58+a+Lunm4rtcAm6QmJjo9Qvf3r177ZZbbrGEhASbP3++ZcmSxcaPH29m5+YrHT9+/AXX/pGsXh1JSUk2d+5cq1Chgt1+++03Zbf09GLdunXWuHFj++abb6xLly7WqFEjK126tC1atMgZiDAxMdFef/11K1++vOXOnduqV69+U17q8e2331qjRo1s69atlpKSYnPnzrUGDRrY9u3bbefOnTZ06FDz9/c3j8dzwUB6uNA/dZ9M+8ynpKRY9+7drVq1avbyyy87vVPY1/6zw4cPW4MGDezZZ5+1zz//3Dwez0W7C5/vyJEj9vnnn3MJjI+kpKTYzp07zePx2OzZs/+x7bp16+zbb791Pgfp9btxy5YtVq1aNXvggQcuq6fKxo0b7bbbbrNmzZoxkvtVkLaf3b17t2XLls2io6MZePAaWL9+vUVERNh99913wXkD/hvCAVwzU6dOtRYtWljFihVt6NChzvJq1apZy5YtLWvWrPbuu+86y3fu3Gm33XabzZo1yxflpmtpBzOXOrg/e/aszZ8/38qUKWN16tTx6m6M6+uOO+6wxx9/3MzODcL33HPPWZ06daxUqVI2duxYZyC4gwcP2rfffnvThTnnj6BfvHhxq169ug0YMMBOnTplAwcOtAoVKjjdeufNm2f33nsvB66X6Z+mHUt7H6VdYlClShUbMWKEM74F/l5cXJw988wzdsstt1iGDBns/fffN7O/339yneuN49FHH7U777zT/vzzz8tqn16Dsk2bNjnTQq9ateqy73fgwAEGbrsMae+LhIQES0xM9Arsz/+8p+0Tdu3aZdmzZ7fGjRvbtm3brm+x6dTfffYutj/94YcfnBmMCAiuHsIBXBMTJkywkJAQ69Wrl/Xs2dP8/f1tzJgxZmY2evRoy507tzVv3txpf/r0aWcgQk5Ur0zajvS3336zjz/+2H7++ed/bJ8WEFSoUMHKlSuXbg+C0qu07b1p0ya7/fbbbfny5c66yMhIq1atmkVGRlqdOnWsadOmlpCQ4Ky/GT4bf3fC9PLLL1v9+vWtWLFiNmPGDKtXr569+uqrXgdjuLTjx49bzpw5/7GXxfkBwZNPPmnFihWzN954g5PZf5AWyi1ZssTCw8OtQIECNnjwYKZ8vcH89T2c9u82depUK1OmjPNL+s3473X48GGrXLmyDRgw4IJ1iYmJXsEyn/Url/ZdtG3bNmvfvr1Vq1bNOnbs+Le9h87vQeDxeKxVq1Y31QxD10LaNo6JibElS5bYN9984zWA698FBJGRkdagQQOvqQvx76W/C6lww3vvvffUvXt3TZkyxbkO6NChQ0pJSdGJEyfUvHlzbdu2TStWrNDdd9+t/Pnza9u2bYqNjdW6devk7+/vXPOKf5a2nTZv3qzWrVurYsWKCgsL+8frWgMCAnTnnXfqhRde0Msvv6z9+/erYMGC17Fqd0t7X+fMmVMpKSnaunWrateurfLly6to0aL67rvvtHv3bs2cOVPLly/3ut7V39/fV2VfFfb/r7f87rvvtGjRIiUnJ6tEiRJ68MEH1a9fP7Vr106jRo3SAw88oMyZM+v48eNq2bKlChUqpKCgIF+Xny6EhYXp6aef1nPPPadMmTKpT58+F7Tx9/d3ro197bXXFBgYqHvuuYdrYf9BQECAPv30U7322muaMmWKvvvuO82dO1cJCQkaOnSoAgICnG0K30l7Dy9cuFDFixd3vttatmypkSNH6vnnn9f06dNvyn+nQ4cOKTU1VW3atHGWrV27Vj/88IM+/vhjlSxZUs2aNdO9997LZ/0KpR1r/fzzz7r99tvVoEEDlSpVSkuWLNHPP/+sTJky6fbbb/e6T9p+tnDhwtq9e7cSExOVIUMG37yAdCBtG2/atEmtWrVSSkqKdu/erfr166tv376qX7/+Rd+3VatW1VdffaUHHnhA8fHxCgkJ8UH1NxlfpxO4uXz77bcXvTa4fPnyVrZsWcuSJYvdfffdNmTIEJsyZYrdc8899tBDD9mgQYOcVPtm6TZ9raUlqFu2bLGwsDDr27ev7dmz56JtL9Y74OzZs3by5MlrWSIuYerUqZYtWzbLkyeP1a5d2w4dOuSsO/+XrZvpV65p06ZZ5syZrWHDhlanTh3z8/OzBx980Ou1z50715o0aWI5c+a0AwcO+LDaG9/FfklJTU21t956y/z8/GzkyJF/e9+b6X11raRt36NHj1qJEiXs9ddfN7Nzlxj079/fqlWrZgMHDnS25Ycffmjr16/3VbmwczMeValSxUJDQ+311193pkWeO3euRUVF2erVq31c4bWxcOFCCwwMtK1bt5qZ2XvvvWe1atWyqlWrWosWLezOO++0kiVL2g8//ODjStOnrVu3WsaMGb0uk125cqWFhITYc88997f3Yz97aWnHqD///LNlypTJBgwYYD///LPNmDHDsmXLZi1btrzkpW9nzpy5HqW6AuEArqpffvnFateubffcc4+tXbvWzMxatGhhxYoVs8mTJ9u8efOsVKlSVqFChYsO0MRO9MqcPHnSmjVrZr169fJanpycbEeOHPGaP5duhDeeo0eP2h133GF169b9x+vEbxZ79+61QoUK2dixY51lK1assLCwMOvUqZNX24MHDzKV3iWkHVD9+eefXl0vzc593t944w3zeDz/GBDg0r755ht76qmn7NFHH7WTJ0862z0+Pt6eeeYZq1GjhrVu3dr69OljHo/HduzY4eOK3WXZsmXOWALDhw+3zz77zPbu3Wuvvfaa3XbbbVakSBF77LHH7IsvvrDChQvbW2+95eOKr67zv9sbNGhgGTJksEqVKllgYKANHTrUmRJ6zZo1FhERYZ9//rmvSk23Tp06ZbVr17YCBQrYxo0bzez/fshq0KCBPfbYY74s76awc+dOy5Ili3Xu3Nlr+ciRIy0kJORvf/zC1cdlBbiqbrnlFr3//vt68sknNXjwYMXGxurMmTNatGiRChUqJEnKlSuXqlSporVr1ypv3rxe978Zu/pdSx6PRwcOHFDTpk2dZYsXL9aiRYv0wQcfKDg4WI0bN9b48ePl8XiYRuc6+uulMRfrcpw9e3bVqVNH7777rjPd1M1ySc348eNVsmRJ1alTx3k9Z86ckZ+fn2677TZJ517rbbfdpunTp6t+/fpq1qyZmjVrJknKnTu3z2pPL/z8/LRr1y7dcccdSk1N1RNPPKGcOXPqwQcfVEBAgHr06CF/f3/17NlTqamp6tu3r69LTneSkpK0dOlSvfnmmypevLjzOU1KSlLWrFk1YMAA5ciRQ4sXL9bq1av1008/6dZbb/Vx1e6xZ88ePf300woLC1ORIkX09ttva8uWLSpYsKB69eqlVq1aac+ePerTp49iY2O1d+9evfjii6pfv75KlCjh6/L/k7T96aFDh5QjRw5lypRJCxcu1Ouvv66kpCR99tlnXq8xb968yps3r7JkyeLDqtOnTJkyqWfPnho1apSGDx+url27qlatWtq7d6+WLVumdu3a+brEdG/Xrl1KTExUSEiItm/f7rx3c+TIobCwMKWkpPi4QhfxdTqBm9Mvv/xi9evXt9DQUJsyZYqZnfuVKzU11datW2elSpWy7777zsdVpj9/vTxgz549VqpUKRsyZIjt3r3bXnvtNStTpow1a9bMhgwZYmPGjLHg4GB+OfSh995776KD5KT92pOYmGjlypWzp5566nqXdk2kva7ixYtbgQIFbOXKlc779tdff7WAgACbNm2amZ17P6ekpNjp06etYsWKNmrUKJ/VnZ6cvx+YOHGi5cyZ0/z9/a1Ro0ZWvHhxK1asmNWvX9+++OIL+/HHH+3DDz80j8djb7/9tg+rTr92795tQ4YMMY/HY6NHj3aWnz8YYWpqqjMlJK69+fPnO/8/a9Ysi4iIsIwZM9rSpUvN7MIBTE+ePGmrVq2yvn37WrZs2WzixIlmln57K27dutVatGhhZcqUsYCAACtfvrz169fPWX+xSwmfeeYZK1WqFJdqXaa077LzL3WdNm2aVa1a1R5++GH76quvrECBAta1a1dflZiupb1Hz5w542zryZMnW758+ex///ufHT161A4fPmw5cuSwgQMH+rJU1yEcwDXz66+/WnR0tDVq1MhrRPYmTZrY7bffzij5/9LevXtt0KBBzu3XXnvNMmbMaAULFrTMmTPbmDFjnG6tCQkJVq9ePevSpYuvynW1ffv2WbFixZwTiotd2nH27Fm799577eGHH77e5V11f/1M161b14oUKWIrVqxwTqQ6d+5s1apVs2XLlnm1rVmzpnM9Ny5tx44dNnHiREtISLC33nrL7rzzTnvggQcsNjbWvvzyS+vUqZPdcsstlitXLmvYsKHlzJnTPB6PffTRR74u/YaW9hk9efKk18n+sWPHrF+/fpYxY0abMGGCszy9nlymZ2+99ZZFRUU5J23fffedFStWzMqXL29NmjRxxi9JW//X/W737t2tZMmS6fZSu40bN1poaKh17drV3nvvPfvqq6+sWbNmFhgYaHfffbfX9Hpm567j7tOnj4WHhzuzNeDvpX2PJSUlWWpqqv3yyy9e4zN9+eWXVqVKFcuSJYvXrFvsC67ctm3b7MEHH7TFixc7n8cvvvjC8uXLZ+3bt7fcuXN7hS+cN1wfhAO4pn755Re766677O6777YVK1ZYixYt7NZbb3VOFPigX5nU1FQbOXKkFSlSxOuX5lWrVtny5csvuO44ISHBGjVqZMOHD7/epcLOHZy2adPGmjZt+o/tDh065BxYpNcD1rTP8p49e+ytt95yxruoXr26FS1a1OkptHLlSmvevLlVrFjRPv30U1u6dKk9/fTTli1bNq8xMnBxqamplpycbA899JC1bdvWzM5NX/jmm29a6dKlrVu3bk7bXbt22Y8//mhPPPGERUdHW0BAgG3ZssVXpd/w0j57s2bNsrp161qZMmWsVq1aNm3aNDt58qTFx8fbgAEDLGvWrPbOO+/4uFr3OnDggLO/THs/Hz582KZNm2a1atWyu+66y2uAU7Nz14yn+f77761ixYq2b9++61f0VXL48GGrWLGi9e/f/4LlY8aMscyZM1ubNm2c5R999JFVr17doqKinGvl8ffO7+XWvXt3K1u2rGXIkMHKlStnvXv3dtrNnDnTKlasaO3atbPvv//eV+WmW6mpqXb69GkrWbKkeTweu//++23FihVePQhy5sxpJUuW9PrOSq/HR+kN4QCuuV9++cUaN25sGTJksOLFizvBALMS/Dt//vmnDRs2zCpXrmw9evRwlv81aDl79qwNHDjQ8ufPb7t27brOVbrP3wVdW7dutWzZstmnn356yful118e0l7Dxo0b7dZbb7V7773Xvv76a2d99erVrXDhwrZq1SozM1u9erU9/vjjFhwcbCVLlrSyZcsywvsVGjVqlJUpU8a5ZCU+Pt5Gjx5t5cqVu2Bwx7QDKjcMevlfzZs3zwIDA23gwIH27rvvWrNmzaxEiRI2fPhwO336tB05csSee+4583g89uGHH/q6XFd5/vnnvW4vWrTIPB6P1yUCn332md12223WuHFjO3z4sJmZPfLII86lTGZmTz31lIWHh9vRo0evW+1Xy/r1661MmTK2adMm5/sibf8bGxtrw4YNs0yZMjn734MHD9q8efPs4MGDvio53Th/xPwCBQpY586dbfjw4TZv3jy75557LFu2bFavXj2n/dSpU61q1ar2wAMP2IoVK3xVdro2YsQIy5cvn+XMmdPq169vK1eudL6vvvrqK8uXL589/vjjtn37dh9X6i6EA7gutm3bZt27d2e6wiv0dyecx44dsyFDhlilSpW80uw0s2bNsu7du1vOnDk56boOzk+z586da/v373eWnThxwjp06GCPPvqomd28vWW2bdtm4eHh1r9//4te01qzZk3Lnz+/ExCYmf3+++924MABTlqvQNr7Z+bMmVa4cGE7ffq0sy4tIChfvrzXiM9p3Yz51eWfnTx50u65554LZn/p16+f3XrrrTZnzhwzO3dp17BhwzhgvY62b99uAQEB1rBhQ2fZrl27rGfPnhYeHu4VEEyaNMlq165thQoVsttvv93y5s3rdczxyiuvpNvp/D788EMLDg52bv/1M717924LDQ21ESNGXO/S0rW0/eqGDRssc+bM1q9fP6+p8WJjY+3111+3sLAwr0sJZsyYYbfccos98sgjTKV3BdKCrZ9++skeeeQRmzlzppUpU8Zq165tq1at8rrEoFChQvbggw/aL7/84suSXYVwANcdwcDlSds5bt++3d58802bO3eunT171hlo6ejRozZs2DArX76818Hs4sWLrVKlSnbPPffQhfg6OP9k/7vvvjOPx2O1a9e2du3aOd1WlyxZYoGBgTdtt84zZ85Y69atLxiYKSkpyXbv3u38gnfXXXdZ/vz5beXKlU4PIvyztPfX6dOnvQ4+T506ZbfeeqstXbrUudTA7P8CgsqVK9t9993nk5rTi+PHj9uuXbu8elbVqVPHGdjt/EHtoqOjrX79+s7t9NrLJz1btWqVFSxY0OvfYe/evfbUU09Z1qxZnYAgJSXFli9fbs8995z16tXrpvpRYsWKFRYcHGxTp0792zYVK1a0nj17Xseqbg579+614OBg69Onj5nZBe+b+Ph4e/bZZy1nzpxePVHmzp1ru3fvvv4FpyPnj+Pw1x9I7rzzTuvWrZudOnXKSpUqZXXr1vXqQfDxxx9b6dKlL7hsFtdO+p8vC+lOQAAzaF4Oj8ej2NhY1ahRQz179lS7du1UuXJlderUSVOnTtWZM2c0cOBAtWzZUuvXr1fPnj0lSXfccYc+++wzTZw4UaVKlfLti7jJmZkzTV/Xrl31wQcfaOPGjXrooYd08OBBRUVFqWPHjjpz5oyaN2+ucePGKSkpycdVX30BAQGKiYnxmjZrwYIF6tu3rypUqKBKlSqpdevWmjdvnkqXLq27775b69at82HF6Yefn5/27NmjWrVqqW7duho8eLDGjx+vlStXKjExUYcPH5bH45G/v79SU1OVNWtWderUSffdd5/++OMP/fHHH75+CTekzZs3q2nTpqpbt67q16+v7t27S5KKFCmib7/9VpIUFBTkfF5vv/12JSYmKjk5WRLT7l4v9erV05IlSyRJUVFR+vzzz7V9+3Y1aNBAklSwYEF1795djz32mLp3766PP/5Yfn5+ql27tl544QW99tprCggIUEpKyk1x7FGoUCGFhITo448/1m+//eYsT01NlSQdP35cGTNmVOXKlX1VYrqTtu2+++475cmTRzExMUpISPB635iZsmbNqq5du8rMtGXLFuf+jRo1UuHChX1Vfrrg5+enrVu3qmPHjnr99dd19OhRZ93YsWO1evVq7du3T998840OHjyogQMH6vvvv5eZ6cEHH9Tq1asVGRnpw1fgLoQDwA0sLCxM/fr1U44cOdSpUyfVq1dP4eHh6tKli2rVqqV27drp1KlTKlKkiBYvXqxevXpJkkqUKKHw8HAfV3/z83g8kqTff/9d33//vTp06KAyZcro4Ycf1tKlSzV8+HCFh4erefPmmj17tr755hudOnVK0v8dkNwMTp8+rSNHjmjjxo3asWOHhg8frh49emj//v0aOnSohgwZorVr12rYsGGaN2+eqlSpohw5cvi67Bta2vvDzBQeHq5HHnlE0dHR2rx5s1566SW9+OKL2rdvn6ZOnaqdO3dKOncAlpqaqixZsuiJJ57QjBkzlDt3bl++jBvSzz//rKioKJUrV04jRoxQnTp1NHXqVL300kvq27ev9u7dq/bt20uSAgMDJUk7duxQeHj4TfW5TQ+io6NVq1Yt53ZUVJSmTJly0YDgf//7n3r06KG33377gse5WcKcfPnyafz48Zo/f76ee+455yQ1LaR+7bXXdPDgQdWuXduXZaYLZiZJOnPmjCTp3nvv1bPPPqsdO3bowQcf1JkzZ+Tv76+UlBTnuz4yMlKRkZGKi4vzWd3pjZnpzJkzatmypb744gu99957qlSpkt566y0tWbJExYsXV968eTV//nzlzp1bS5Ys0ZEjR/TEE09o7dq1kqQsWbL4+FW4jA97LQC4iPO7X6UZNGiQ3XLLLfbyyy9bYmKi7du3z5YuXWqtWrWyBg0amMfjMY/HYxEREU4XblwfL730krVo0cIeeOABp9v3X7sc//TTT/b8889bvnz5vGaZuJksXrzYAgICrGDBgpY1a1abMGGC7dy508zOvZcbNmxo7dq183GV6cP5Mz+MGzfOfv75Z6/1iYmJFhMTY2+++abVqFHDHnvsMdu2bdsF98eFdu7cacHBwfbcc885y06fPm316tWzWrVqWUJCgn311VcWERFhVapUsUceecTuv/9+y5w58017WVB6MHz4cPv888+d26tWrbJ8+fJdcInBI488Yg0aNPBFiddNcnKyTZgwwQICAqx48eL28MMP28CBA+3++++38PBwxhm6AjExMVakSBH76quvzOzcvuC9996zqlWrWqtWrZzv9LRLC7Zu3Wo1atSw2bNnmxnjuPyTv26bGTNmWKFChaxbt27WrVs369q1q+XLl8+GDBlinTp1svDwcGccl99//92qVq1qe/fu9UXprpf++1gBN4nU1FT5+fk5CfXp06cVGhoqSRoyZIhSU1P11ltvKTk5WY888ojq1q2r2rVry+Px6Ntvv9X27dt15513KmfOnL58Ga6SmpqqoKAgzZ07V7fccovz603af6VzqXmFChVUokQJZcmSRQsWLNCJEyeUNWtWX5V9Tdxxxx3avXu3Dh8+rIIFC3r1DPD391doaKiKFi3q/PJ6/jbC/0nbD2zatEmtWrVS6dKlVaBAAZUrV06SlJycrMDAQEVEROjJJ59UUFCQ3n77bb311lt64oknVLp0abbt30hNTdUHH3ygrFmzer0/M2bMqHr16mn27NlKTU1V06ZNVa5cOQ0bNkyxsf+vvbsPq/F+/AD+PqfSKaEtKUSYvhghLSIu8w1tZDJdmMlKS+VXHsaUp4yKZNWUNmm1JEbI81Ni8hSmxQh5mGHI8pAilTqf3x+u7nVkG/ua0+m8X9fVdek+9333OV353J/z/jwVon79+jh27Bg6duyoxtJrt7y8PMyePRsKhQIuLi7SCIIRI0Zg4MCBSE9Ph6WlJYKDg2FmZqbu4v6rdHR04O3tja5duyI8PBzHjh2DsbExunTpgiNHjqhM76K/9vjxY3Tv3h3e3t6oV68eBg8ejNGjRwMA4uLi4ObmhuTkZBgYGAAAvvvuO8hkMmnaRlV7jVRVPceKi4tx584dmJub44MPPoBSqcTkyZPx4Ycf4qOPPoKPjw/mzp2LoqIiFBYWoqSkBEqlEs2bN0dWVladGfGjcdSdThCRak9hcHCw6N27t7C0tBSjR48WK1eulM6bM2eOsLCwEKGhoc9dEZ7+Xc/rJSgqKhLffvut0NXVFUFBQX953fHjx4WpqanUo64NysrKxOzZs0WzZs242vAL+rudH4T4YwcCIYSIj48XrVu3FlOmTOFCj3/jxo0bYtKkSaJHjx4iNDRUCCFEQUGBMDIyEmFhYc+9hosPvl5/NvLF399fKBQKqZdXiD8WKezatavKudrSo1tRUSG9V44Y+mcuX74svLy8hLGxsTQi4NkRBEIIERYWJho2bFhjJBepqvo7PHfunBg0aJDo1auXmDBhgsoWhS1atBAeHh7i999/F0+ePBH5+fnihx9+ULmPtvwfro0YDhCpWfU94q2srMRHH30kxo8fL0JCQkTr1q1Fs2bNxPTp06Xzg4KChIWFhQgLC2NA8BpVb3gVFhaKwsJC6fuSkhKxdOlSIZfLxYIFC6Tjzz7cYmJihKmpqdasurty5UoxceJEYWZmxqGuL+ivdn64fv26yvZ51VfTT0pK4orZL+jWrVvCz89P9OrVS3z++efCwsJC+Pv7S68rlUqV/7tspKrHtWvXagSpPj4+NQKCH374Qbi4uGjlh2P+nb64Z/8+qu9ecenSJeHl5SUaNWpUIyDo1auXMDMzE/r6+uLEiROvtcyapnp7tnHjxiIwMFBkZ2erhNlCCLFp0yZhYWEhPD09VXbV4t9w7cBwgEiNqu+ta2RkJKZPny7u378vvZ6Xlyfc3NyEmZmZCAkJkY4HBwcLQ0NDERERwV6t16B6o2LRokXCwcFBdOvWTQwbNkyak1hWViZiYmKEjo7Oc3sgy8rKRFBQkNb0Opw/f168++67YtiwYeLs2bPqLo7GePLkiejTp4+IiYmRju3atUtMnjxZNGzYULRu3Vo4OjpKjai6sD2bOty8eVP4+fmJpk2binfeeUc6zt+nekRHR6vML54+fbpo3769UCgU4r333hPh4eHSa76+vsLQ0FBs3Lixxn34PKS/cu3aNZVtIKv/vVQFBGZmZiIjI0MI8TSAjY2NFX379tWaZ/f/6tatW8La2rrGdprPhq6bN28WFhYWwsfHh7/bWobhAJGaVS2QNXv2bCHEHw+rqkbqpUuXxHvvvSesra3FmTNnpOvCw8M5TPs1mzlzpmjatKmIiYkRO3fuFKampmLAgAHi0qVLQoinvbuxsbFCJpOJ5OTkGtdrWyp++/ZtlREW9PcePHgg2rdvL7y8vMT58+fFggULRLt27cTw4cPFkiVLREJCgmjbtq347LPP1F1UjZefny/8/f1Fjx49VAI9beyBVqdz584JmUwmPvnkE3H79m2RmJgomjdvLlJTU8XWrVuFh4eHsLW1FVOmTJGumThxopDJZGL//v1qLDlpkidPnoiPPvpI2NjYqCxuWT0gOHv2rBg5cqTo16+ftLhzWVkZn2MvYceOHcLa2lqcO3fuuW2e6r/vjRs3CkNDQzFp0qQaowtIfRgOEKlRZWWlmDFjhjA1NRVLliyRjldVnlUV64EDB4RcLn9uTwm9Hrt37xbW1tbiwIEDQgghdu7cKRo0aCBMTU1F586dxeXLl4UQTxsS69evZw8k/WMvsvPDJ598ot5C1hFVUwwcHBz+dM0Q+vdUPeMOHTokFAqF8PX1FV988YWIjY2Vzrl7964ICwsTNjY2IjU1VToeFRXFepZeysWLF8XQoUNFv379xKpVq6Tj1T+wrlu3TpiZmUmhP72cOXPmiJYtW0rfP2/qy8OHD0VJSYkQQojt27ezo6uW4ZLGRGokl8vh5+eH0aNHY/Xq1QgLCwPwdDXi6vtp29rawsTEBDdv3gTwx/689Pro6OjAw8MDffr0we7duzFmzBgsXrwYx44dw40bN+Dj44O8vDzUq1cPw4cPh66uLioqKtRdbNJAVTs/bNiwAb/88gu8vb3Rtm1bAH/s/NCiRQuIpwG/mkur2czNzTFr1ixYWVnhyJEjuHv3rrqLpFVkMhmUSiUcHByQnp6OhIQEzJs3T3rWAcCbb76J//u//4O+vj72798vHZ88eTLrWXopbdu2RVRUFAwNDfHtt9/i+++/B/C0Xn3y5AkA4D//+Q+aNGnCuvUFVG+nVrGwsEBRURHOnTsHQHVHh6p/z5o1C1OmTIEQAoMGDYKVldXrKTC9EIYDRGrWrFkzBAYGws7ODps2bcKiRYsAPA0OqirenJwcNGvWDPb29gC4fc6/7XkPPEdHR7i6uqK0tBRhYWGYMGECvL29YWxsjFatWiEjIwMhISEq1+jqcrdY+mdatGgBW1tblS33ysvLMXfuXBw+fBhjx46FTCZjXfAKmJubIywsDCkpKTAxMVF3cbSOXC5HZWUl+vTpg8OHD8PAwAA//PADLly4IJ1jZGSEnj174sqVKygvL1e5nvUsvYzWrVsjJiYGhoaGiI+Px4oVKwAAenp6AIBVq1bB0NBQpe6l55PL5bh27Rqio6OlY82aNUNRURE2bdqEhw8f1rimvLwcT548QZcuXfj8qqUYDhDVAlW9V3Z2dti4caMUEFTt8bphwwaYmZmhVatWaiyldqjanxcATp8+jatXr6KgoADA0w9sBQUF+O2339CzZ08ATxsUnTp1wtmzZ5GUlKSuYlMdl5KSgs8//xzx8fHYtm0be1peMTMzM5iZmam7GFrj2QC26ln3zjvvYM+ePThx4gTmzp2Ln3/+GQBQXFyMQ4cOoXnz5qhXr95rLy/VLVUBgbGxMb7++mtMmjQJa9euhZ+fH5KSkrB8+XIYGxuru5i1XmVlJb7++mvExsYiPDwcAODs7IxPP/0UwcHBWLlyJe7cuaNyfnBwMPbu3QsnJyd1FZv+hkxw3AxRrZGfn4/Q0FD8+OOPGDZsGAICAhASEoLIyEgcOHAAnTp1UncRtUZgYCBSU1NRVFSEgQMHwsPDAwMGDIBSqUT79u3RsmVLeHp6Ij4+HiUlJThy5IjUA1bV0CV6FfLy8uDj44M33ngDoaGh6NChg7qLRPSPVQ9gU1JScP36dRQWFmLChAkwMzODQqHAwYMHMWDAAJiamsLGxgY6Ojq4fv06srKyoKenByEEex3pf/bbb78hISEBaWlp0NHRQYsWLbBgwQJ07NhR3UXTGDdu3MDixYtx9OhRfPDBB5g5cyYePXoET09PpKam4sMPP4SzszPu3r2L06dPY8uWLdi3bx+6du2q7qLTn2A4QFTLVAUEp06dQllZGX7++WccPnwY3bp1U3fR6rTqjc09e/bAy8sLCQkJuHDhAvbs2YNbt24hICAALi4uyMnJwccffwx9fX00btwYO3bsgJ6enkqjl+hV+v3336Gvr49GjRqpuyhEr0RgYCC+++479OnTB+fOnYOenh5mzJiBwYMHw8jICEePHoWTkxMMDAywYsUK9O/fHzo6OqioqOBUAnqllEolHj9+DB0dHSgUCnUXR+NUtVuPHz+O4cOHY/r06QCAkJAQrF27Fr/88gtatWoFW1tbzJgxgwF3LcdwgKgWys/Px8yZM3Hw4EGsW7eOCetrtHnzZuzZswetW7fG1KlTAQBZWVmIjo7GL7/8gqCgIAwePBgVFRW4ffs2mjVrBplMxgYrEdEL+vrrrxEWFoYtW7aga9euyMjIwMCBA9GpUycphK1fvz7279+PuXPnYv/+/ZDJZByZRa8cR6G8GtUDgmHDhiEwMBAAcP/+fZSXl8PExARKpZLTgjQAwwGiWqqgoABKpZLzYF+jCxcuYNy4ccjNzYW/vz/mz58vvZaVlYWYmBhcuXIFkyZNwqhRo6TXOGKAiOjPVf9QX1paisWLF8PU1BQ+Pj7YsGEDPv30UyxcuBAbN27EuXPnsHDhQjg7O6uMlGE9S1S7VZ8aWzXFAPjj/z+DGM3AcICItFbVg6r6A2vr1q348ssvcfv2bSQkJMDBwUE6/+jRo/jiiy/QokULxMfHq6vYREQaKS4uDkOHDsXNmzdhYWGB+/fvw8XFBd7e3pg8eTJ++ukn9OrVC02bNsWyZcvg5OTEDxREGqQqIMjJyYGjoyPmzZun7iLRS2IES0RaSalUSg3O8vJylJWVAQCGDBmCwMBAtGzZEqGhocjKypKusbe3R0REBOLi4tRSZiIiTVJ9V4KlS5fC19cX9+7dg42NDZo0aYLc3FwYGhrCxcUFAHDnzh2MHTsWI0aMQP/+/QFw614iTVK1+5aVlRWOHDmCu3fvqrtI9JI4QZaItE714akRERHYs2cPysvL0aZNG0REROD999+HEAJLlixBcHAwgoKCYG9vDwDSKsYc4kpE9Neq6sjMzEzI5XKkpaXh7bffRtWg1Tt37uDu3bu4evUq9PT0sHTpUnTs2BELFy4EAK4xQKSBzM3NERYWBgAwMTFRc2noZXFaARFprVmzZmH58uXw8/NDWVkZ1qxZA4VCgTVr1qBz587YvHkzli9fjoKCAiQmJnIrSSKil3T8+HH07NkTenp6WLNmDVxcXKQP/WVlZejVqxdu3LgBPT09NG7cGMePH4eenp66i01EpJUYDhCRVigrK4O+vr70/aVLl/D+++8jKioKzs7OAICSkhL069cPpaWlOHXqFAAgNTUVR48exZdffsmRAkRELyk/Px+rV69GSEgI3NzcsGTJEgB/1Mnl5eXYvn07ZDIZhgwZwu0KiYjUiC1dIqrz+vbti507d6ocKykpQWFhIVq3bg3g6boDhoaG2Lp1K27fvo2YmBgAwIgRIxAZGQm5XK4yf5aIiFQ9W0cqlUqYm5vD29sbgYGBWLZsmbRAmb6+PsrKylCvXj0MGzYMLi4u0NHRQWVlJYMBIiI1Ye1LRHXeBx98gPfffx8ApB4pKysr6OrqYt26dejYsSPq1auHyspKGBoawsLCAqWlpTXuw5EDRETPV30dliVLliA3NxenT5+Gt7c3+vbti2nTpkEulyM0NBQymQxBQUHQ19evsX4L1xggIlIfhgNEVGdVbYE1depUAMCCBQvQqFEjjB07Fg0aNICvry82b94MMzMz+Pr6QkdHBwqFAgBUpiAQEdFfq/qAHxgYiMTERAQEBMDY2BjBwcHYuXMnkpOT4e7uLgUExcXFWLx4MUNXIqJahOEAEdVZz26BlZ+fj9mzZ8PQ0BAeHh5wd3fH7du3ERERgYMHD6JTp07Ys2cPSktLMWHCBDWVmohIMx06dAhpaWnYvn077OzscODAAURFRWHevHnQ19eHvr4+xo8fj6KiImRlZUkBLhER1Q4MB4ioTsrKyoK9vT1kMhkWLVqELl26IDo6GgqFAt7e3lAqlfD09MTs2bNhb2+PpUuXorCwEJaWlkhPT4euri630SIiegllZWVo2LAh7OzssHbtWnh5eSE6OhpjxozBw4cPcfToUfTr1w9Tp06FkZERZDIZAwIiolqE4QAR1TmXLl3C+PHj0blzZzRu3BixsbHIyckBAISHh0OpVMLHxwcA4O7uDjc3N7i5uak0UrlaNhHRn6teX1b9+9GjR1Aqldi6dSu8vb2xcOFC+Pr6AgAyMzOxYcMGWFlZwdLSssY9iIhI/biVIRHVOWVlZVi3bh0mT56M0tJSZGZmwtbWFo8fP4aBgQEAYNq0aYiJicGyZcswfPhwNGzYULqeDVYioj9XfRHBZ+tLW1tb5OTkID4+Hp6engCA0tJSuLq6wsjICN9//z3rVyKiWordYkRUZ1Q1WPX19WFmZgaFQgETExNER0dj+fLlMDAwkPbW/vLLLyGTyeDp6QlTU1M4OztL92HDlYjo+YQQUjAQGxuLw4cPo23btujbty8cHR2xdOlSeHh4YPny5TA1NcXdu3exZs0a3Lx5Ezk5OZDJZDV2KCAiotqBIweIqE6o3tg8e/YslEolTExMkJGRga+++grt2rVDUlIS6tWrp3JuXFwcPD09OYWAiOhvVB8lEBwcjKioKAwaNAgnT56EsbExfHx8MGbMGOTk5GDq1Km4evUqzMzM8NZbbyExMRF6enpcy4WIqBZja5iINF71nqxZs2YhPT0ds2bNQqdOneDq6orS0lLExcVh3LhxSEpKgq6uLiZMmIDhw4fD29sbANcYICL6K9XryOzsbBQUFGDz5s3o06cPzpw5g6+++goRERFQKpUYO3Ys9u3bh+vXr8PExAQGBgaQyWSsZ4mIajmOHCCiOiM4OBhLly5FcnIy7Ozs8OabbwJ4Ot81JSUF33zzDSorK9GkSRPk5ubi6tWrbKgSEf2Fb775RlpUEADS0tIwf/58AMD27dvRvHlzAEBubi6++uor/PTTT5gwYYK03kAVruVCRFT7ccIXEWmk8vJyle9v3bqFjRs3IjIyEk5OTlIwUFlZCYVCgbFjxyIsLAwODg5o27atFAxUVlaqo/hERLXejh07MH/+fIwfP146Vr9+fTRr1gyXL19GVlaWdLxjx46YMmUK7Ozs8MUXX2DHjh0q92IwQERU+3HkABFpnH79+mHatGkYPHiwdOzy5cuwt7fH1q1bYW9vr7KuQGlpKR49egQTExOV+3CIKxHRnysqKkJycjISExNhY2ODhIQEAEBWVhYWLFiAwsJCBAQEqCzoeurUKezatQvTpk3j2gJERBqGIweISOMMGDAA/fv3BwCp59/U1BRyuRwZGRkAALlcLr124sQJpKWl4eHDhyr3YTBARPR8SqUSDRs2hLu7Ozw8PJCdnY1x48YBAHr27Ilp06ahcePGiIiIwLZt26TrunTpgoCAAOjo6HBkFhGRhuHIASLSGM/OWQ0LC0Pjxo0xatQoGBkZYebMmdixYwf8/f2l+a6VlZUYNGgQTE1NsXLlSg5tJSL6G8/Wtffv38fKlSuRmJiIbt26ITExEQCwf/9+REdHo6ioCD4+PnB1dVVXkYmI6BVgtxkRaYTq0wSqGq5nzpzB2rVrYWBggI8//hgeHh4oKChAaGgo9u7diyZNmiA7OxuFhYXYtm0bZDIZF8UiIvobVXXkokWL0KNHD7z77rtwc3MDACQmJmLcuHFITEzEu+++C5lMhqCgIGRmZjIcICLScBw5QEQa4cmTJ6ioqMC9e/fQpEkT6OnpAQB8fX3x3XffIT4+Hm5ubrh58yb27t2L+Ph4mJqaonnz5oiMjISuri7XGCAiekHFxcUYM2YMtm3bhgMHDsDBwUFlBIGtra20BkFOTg66dOkiBbhERKSZGA4QUa2Xnp6OTZs2Ydu2bSguLoaDgwOGDBkCb29vAIC3tzdWrFiB+Ph4jB49+rmLYDEYICL6c1Wjs6qPrrp+/Tpmz56NNWvWYO/evejduzfu37+PlJQUJCUlwdLSEmlpaTXuQUREmoktZSKq1RITExEUFISRI0fCz88PxsbGiImJwbx583D58mWEh4cjLi4OMpkM3t7ekMvlGDp0KIyMjFTuw2CAiOj5zpw5g06dOgEA7t27BxMTEwgh0KJFC4SGhkKpVMLR0RH79u2Dg4MD3Nzc8PDhQ+Tl5akEAgwGiIg0G0cOEFGtFRcXh4kTJ2LFihUYPny4NJXg4sWLCA0Nxa5du/DZZ59h+vTpAAB/f3/ExsZi586dcHJyUmfRiYg0wsWLF9GuXTvs3LkTurq6GDJkCH766Se0b99eGkVw7do1TJw4ERkZGcjMzIStrS2Ki4thZGQEmUzGEQNERHUEa3IiqpU2bdoEX19frF+/HqNGjZKGuVZWVsLKygpz5sxBhw4dsH79ely9ehUAEBMTg8WLF8PR0VGdRSci0hjm5uYYMGAA0tLSoKenBwcHBwwaNAh5eXnSB/+WLVvi448/RklJCezs7HDq1Ck0aNBAWuSVwQARUd3A2pyIap2ysjLs3r0bbdq0kT746+rqorKyEjo6OhBC4K233sKMGTOQnZ2N69evS9dOnTpVWnyQiIj+WoMGDdC3b19s2bIFHTp0QFxcHNq1a4cBAwbg/Pnz0gf/pk2bwsvLCxEREejYsaN0PXd/ISKqOxgOEFGto6+vj6CgIDg7OyMlJQWLFi0CAOjo6ECpVErntWrVCvXq1cOjR49q3INrDBAR1VQ1m1QIIf07MDAQb7zxBubNm4c2bdogLCwMnTt3xn//+1/s27cPZ8+eRWRkJHR0dDBlyhQGsEREdRTDASKqlZo2bYrAwEDY2dlh48aNUkAgl8tRWVkJADh9+jRsbW3x9ttvq7OoREQa48GDBwCe9vjLZDJUVFRACAEXFxf8+OOPuHfvHrp06YKFCxeiX79+6N+/P4YOHYorV65gyZIlAJ4GCwxgiYjqHoYDRFRrmZubY9asWTUCAl1dXRQXFyMxMRHt27eHhYWFmktKRFT77dq1C/3790dsbCx+//13AE/rUx0dHXh6euLMmTNISEgAAFhbW2PVqlU4cuQIkpOTceLECejp6aGiooJTCYiI6ijuVkBEtV5+fj5CQ0Px448/wtXVFdOmTYOLiwt+/fVXnDhxArq6uip7cxMRUU25ubmIiorCqlWrYG1tDTs7O8yZMwdGRkYwMjJCQEAADh06hNWrV6Nly5Y16tSqdV+IiKhuYjhARBohPz8fCxYsQHZ2Ni5dugRjY2OcOXMGenp6bLASEb2ECxcuICkpCWlpaXj06BEGDhwIPz8/FBQU4JNPPsG6devQu3dvblFIRKRlGA4QkcbIz89HQEAACgoKsHnzZmmIK+e+EhG9nMrKSlRUVGDx4sXIzMzEvn374O/vj+joaPTu3Ru7d++GgYGBuotJRESvEcMBItIo9+/fR6NGjSCXyxkMEBH9Q9WnYpWVlWHLli1YvXo1du7cie7duyMzM5NTtYiItAzDASLSSBzuSkT0v3l2rZYHDx7g1q1bsLKykraOZT1LRKQ9GA4QERERkQqu5UJEpH0YDhARERERERFpOY4VIyIiIiIiItJyDAeIiIiIiIiItBzDASIiIiIiIiItx3CAiIiIiIiISMsxHCAiIiIiIiLScgwHiIiIiIiIiLQcwwEiIiIiIiIiLcdwgIiIiIiIiEjLMRwgIiKiWiUpKQnGxsb/831kMhk2bdr0P9+HiIhIGzAcICIiolfO3d0dLi4u6i4GERERvSCGA0RERERERERajuEAERERvVaRkZGwtrZG/fr10aJFC0yYMAEPHz6scd6mTZtgZWUFhUIBJycnXL9+XeX1zZs3o1u3blAoFGjTpg3mzZuHioqK5/7M8vJy+Pn5oWnTplAoFLC0tMTChQv/lfdHRESkiRgOEBER0Wsll8sRHR2N3NxcrFixAvv27cP06dNVzikpKUFoaCiSk5Nx+PBhFBYWYtSoUdLrBw8exNixYzFp0iScPXsWcXFxSEpKQmho6HN/ZnR0NLZs2YLU1FTk5eVh1apVaNWq1b/5NomIiDSKTAgh1F0IIiIiqlvc3d1RWFj4QgsCrl+/Hj4+Prhz5w6ApwsSenh44OjRo+jRowcA4Pz58+jQoQOOHTuG7t27o3///nB0dMSMGTOk+6SkpGD69Om4efMmgKcLEm7cuBEuLi6YOHEicnNzkZGRAZlM9urfMBERkYbjyAEiIiJ6rTIyMuDo6IjmzZujQYMGcHNzw927d1FSUiKdo6urCzs7O+n79u3bw9jYGOfOnQMAnDp1CvPnz4eRkZH05eXlhVu3bqncp4q7uztOnjyJdu3aYeLEiUhPT//33ygREZEGYThAREREr82vv/4KZ2dndO7cGRs2bEB2djZiY2MBPF0X4EU9fPgQ8+bNw8mTJ6Wv06dP4+LFi1AoFDXO79atG65cuYLg4GA8fvwYI0aMgKur6yt7X0RERJpOV90FICIiIu2RnZ0NpVKJiIgIyOVP+yhSU1NrnFdRUYETJ06ge/fuAIC8vDwUFhaiQ4cOAJ5+2M/Ly0Pbtm1f+Gc3bNgQI0eOxMiRI+Hq6or33nsP9+7dw5tvvvkK3hkREZFmYzhARERE/4oHDx7g5MmTKscaN26MJ0+eICYmBkOGDMHhw4exbNmyGtfq6enB398f0dHR0NXVhZ+fH+zt7aWwICgoCM7OzmjZsiVcXV0hl8tx6tQpnDlzBiEhITXuFxkZiaZNm8LGxgZyuRzr1q2Dubk5jI2N/423TkREpHE4rYCIiIj+Ffv374eNjY3K18qVKxEZGYlFixahU6dOWLVq1XO3FDQ0NERAQABGjx4NBwcHGBkZYe3atdLrTk5O2LZtG9LT02FnZwd7e3tERUXB0tLyuWVp0KABwsPD8c4778DOzg6//vorduzYIY1eICIi0nbcrYCIiIiIiIhIyzEuJyIiIiIiItJyDAeIiIiIiIiItBzDASIiIiIiIiItx3CAiIiIiIiISMsxHCAiIiIiIiLScgwHiIiIiIiIiLQcwwEiIiIiIiIiLcdwgIiIiIiIiEjLMRwgIiIiIiIi0nIMB4iIiIiIiIi0HMMBIiIiIiIiIi33/zcnunQplIbhAAAAAElFTkSuQmCC",
-      "text/plain": [
-       "<Figure size 1200x600 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "plt.figure(figsize=(12, 6))\n",
-    "plt.bar(labels, sizes)\n",
-    "plt.title('Bar Graph')\n",
-    "plt.xlabel('Labels')\n",
-    "plt.ylabel('Count')\n",
-    "plt.xticks(rotation=45)\n",
-    "plt.show()\n"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {
-    "id": "YtSxaBSZ5C_h"
-   },
-   "outputs": [
-    {
-     "data": {
-      "image/png": "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",
-      "text/plain": [
-       "<Figure size 1400x1000 with 1 Axes>"
-      ]
-     },
-     "metadata": {},
-     "output_type": "display_data"
-    }
-   ],
-   "source": [
-    "fig, ax = plt.subplots(figsize=(14, 10))\n",
-    "wedges, texts, autotexts = ax.pie(sizes, autopct='%1.1f%%', startangle=140)\n",
-    "\n",
-    "ax.axis('equal')\n",
-    "plt.legend(wedges, labels, title=\"Activities\", loc=\"center left\", bbox_to_anchor=(1, 0, 0.5, 1))\n",
-    "\n",
-    "plt.title('Distribution of Network Activities')\n",
-    "plt.show()"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "KObpx4wfj3aQ"
-   },
-   "source": [
-    "## Data Preprocessing"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "id": "LuWeKTG2j0hF"
-   },
-   "outputs": [],
-   "source": [
-    "from sklearn.model_selection import train_test_split\n",
-    "from sklearn.preprocessing import LabelEncoder\n",
-    "from sklearn.preprocessing import StandardScaler"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 8,
-   "metadata": {
-    "id": "x0UovuBRjmE0"
-   },
-   "outputs": [],
-   "source": [
-    "X = df.drop('label', axis=1)\n",
-    "y = df['label']"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 9,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "from scipy import sparse\n",
-    "from sklearn.preprocessing import OneHotEncoder\n",
-    "\n",
-    "encoder = OneHotEncoder(sparse_output=True, dtype=np.float32)\n",
-    "\n",
-    "X_sparse = encoder.fit_transform(X)\n",
-    "\n",
-    "y_encoded = encoder.fit_transform(np.array(y).reshape(-1, 1))\n",
-    "y_train_dense = y_encoded.toarray()"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 10,
-   "metadata": {
-    "id": "pbRTAjhy6Yb3"
-   },
-   "outputs": [],
-   "source": [
-    "X_train, X_test, y_train, y_test = train_test_split(X_sparse, y_train_dense, test_size=0.2, random_state=42)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 11,
-   "metadata": {
-    "id": "FBpz07hL_cxj"
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "((505188, 646287), (126298, 646287))"
-      ]
-     },
-     "execution_count": 11,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "X_train.shape, X_test.shape"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 12,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/plain": [
-       "((505188, 10), (126298, 10))"
-      ]
-     },
-     "execution_count": 12,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "y_train.shape, y_test.shape"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "jNDgEG-88ff9"
-   },
-   "source": [
-    "## Model Training"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "lxFMcxYX-wMg"
-   },
-   "source": [
-    "### Model 1: Random Forest Classifier"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 19,
-   "metadata": {
-    "id": "2IhE9rN0_ZSE"
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<style>#sk-container-id-1 {\n",
-       "  /* Definition of color scheme common for light and dark mode */\n",
-       "  --sklearn-color-text: black;\n",
-       "  --sklearn-color-line: gray;\n",
-       "  /* Definition of color scheme for unfitted estimators */\n",
-       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
-       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
-       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
-       "  --sklearn-color-unfitted-level-3: chocolate;\n",
-       "  /* Definition of color scheme for fitted estimators */\n",
-       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
-       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
-       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
-       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
-       "\n",
-       "  /* Specific color for light theme */\n",
-       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
-       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
-       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
-       "  --sklearn-color-icon: #696969;\n",
-       "\n",
-       "  @media (prefers-color-scheme: dark) {\n",
-       "    /* Redefinition of color scheme for dark theme */\n",
-       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
-       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
-       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
-       "    --sklearn-color-icon: #878787;\n",
-       "  }\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 pre {\n",
-       "  padding: 0;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 input.sk-hidden--visually {\n",
-       "  border: 0;\n",
-       "  clip: rect(1px 1px 1px 1px);\n",
-       "  clip: rect(1px, 1px, 1px, 1px);\n",
-       "  height: 1px;\n",
-       "  margin: -1px;\n",
-       "  overflow: hidden;\n",
-       "  padding: 0;\n",
-       "  position: absolute;\n",
-       "  width: 1px;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
-       "  border: 1px dashed var(--sklearn-color-line);\n",
-       "  margin: 0 0.4em 0.5em 0.4em;\n",
-       "  box-sizing: border-box;\n",
-       "  padding-bottom: 0.4em;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-container {\n",
-       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
-       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
-       "     so we also need the `!important` here to be able to override the\n",
-       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
-       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
-       "  display: inline-block !important;\n",
-       "  position: relative;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       "div.sk-parallel-item,\n",
-       "div.sk-serial,\n",
-       "div.sk-item {\n",
-       "  /* draw centered vertical line to link estimators */\n",
-       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
-       "  background-size: 2px 100%;\n",
-       "  background-repeat: no-repeat;\n",
-       "  background-position: center center;\n",
-       "}\n",
-       "\n",
-       "/* Parallel-specific style estimator block */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item::after {\n",
-       "  content: \"\";\n",
-       "  width: 100%;\n",
-       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
-       "  flex-grow: 1;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel {\n",
-       "  display: flex;\n",
-       "  align-items: stretch;\n",
-       "  justify-content: center;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  position: relative;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item {\n",
-       "  display: flex;\n",
-       "  flex-direction: column;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
-       "  align-self: flex-end;\n",
-       "  width: 50%;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
-       "  align-self: flex-start;\n",
-       "  width: 50%;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
-       "  width: 0;\n",
-       "}\n",
-       "\n",
-       "/* Serial-specific style estimator block */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-serial {\n",
-       "  display: flex;\n",
-       "  flex-direction: column;\n",
-       "  align-items: center;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  padding-right: 1em;\n",
-       "  padding-left: 1em;\n",
-       "}\n",
-       "\n",
-       "\n",
-       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
-       "clickable and can be expanded/collapsed.\n",
-       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
-       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
-       "*/\n",
-       "\n",
-       "/* Pipeline and ColumnTransformer style (default) */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable {\n",
-       "  /* Default theme specific background. It is overwritten whether we have a\n",
-       "  specific estimator or a Pipeline/ColumnTransformer */\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "}\n",
-       "\n",
-       "/* Toggleable label */\n",
-       "#sk-container-id-1 label.sk-toggleable__label {\n",
-       "  cursor: pointer;\n",
-       "  display: block;\n",
-       "  width: 100%;\n",
-       "  margin-bottom: 0;\n",
-       "  padding: 0.5em;\n",
-       "  box-sizing: border-box;\n",
-       "  text-align: center;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
-       "  /* Arrow on the left of the label */\n",
-       "  content: \"▸\";\n",
-       "  float: left;\n",
-       "  margin-right: 0.25em;\n",
-       "  color: var(--sklearn-color-icon);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "}\n",
-       "\n",
-       "/* Toggleable content - dropdown */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content {\n",
-       "  max-height: 0;\n",
-       "  max-width: 0;\n",
-       "  overflow: hidden;\n",
-       "  text-align: left;\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
-       "  margin: 0.2em;\n",
-       "  border-radius: 0.25em;\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
-       "  /* Expand drop-down */\n",
-       "  max-height: 200px;\n",
-       "  max-width: 100%;\n",
-       "  overflow: auto;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
-       "  content: \"▾\";\n",
-       "}\n",
-       "\n",
-       "/* Pipeline/ColumnTransformer-specific style */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Estimator-specific style */\n",
-       "\n",
-       "/* Colorize estimator box */\n",
-       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
-       "#sk-container-id-1 div.sk-label label {\n",
-       "  /* The background is the default theme color */\n",
-       "  color: var(--sklearn-color-text-on-default-background);\n",
-       "}\n",
-       "\n",
-       "/* On hover, darken the color of the background */\n",
-       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Label box, darken color on hover, fitted */\n",
-       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Estimator label */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label label {\n",
-       "  font-family: monospace;\n",
-       "  font-weight: bold;\n",
-       "  display: inline-block;\n",
-       "  line-height: 1.2em;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label-container {\n",
-       "  text-align: center;\n",
-       "}\n",
-       "\n",
-       "/* Estimator-specific */\n",
-       "#sk-container-id-1 div.sk-estimator {\n",
-       "  font-family: monospace;\n",
-       "  border: 1px dotted var(--sklearn-color-border-box);\n",
-       "  border-radius: 0.25em;\n",
-       "  box-sizing: border-box;\n",
-       "  margin-bottom: 0.5em;\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "/* on hover */\n",
-       "#sk-container-id-1 div.sk-estimator:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
-       "\n",
-       "/* Common style for \"i\" and \"?\" */\n",
-       "\n",
-       ".sk-estimator-doc-link,\n",
-       "a:link.sk-estimator-doc-link,\n",
-       "a:visited.sk-estimator-doc-link {\n",
-       "  float: right;\n",
-       "  font-size: smaller;\n",
-       "  line-height: 1em;\n",
-       "  font-family: monospace;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  border-radius: 1em;\n",
-       "  height: 1em;\n",
-       "  width: 1em;\n",
-       "  text-decoration: none !important;\n",
-       "  margin-left: 1ex;\n",
-       "  /* unfitted */\n",
-       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-unfitted-level-1);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link.fitted,\n",
-       "a:link.sk-estimator-doc-link.fitted,\n",
-       "a:visited.sk-estimator-doc-link.fitted {\n",
-       "  /* fitted */\n",
-       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-fitted-level-1);\n",
-       "}\n",
-       "\n",
-       "/* On hover */\n",
-       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
-       ".sk-estimator-doc-link:hover,\n",
-       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
-       ".sk-estimator-doc-link:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
-       ".sk-estimator-doc-link.fitted:hover,\n",
-       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
-       ".sk-estimator-doc-link.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "/* Span, style for the box shown on hovering the info icon */\n",
-       ".sk-estimator-doc-link span {\n",
-       "  display: none;\n",
-       "  z-index: 9999;\n",
-       "  position: relative;\n",
-       "  font-weight: normal;\n",
-       "  right: .2ex;\n",
-       "  padding: .5ex;\n",
-       "  margin: .5ex;\n",
-       "  width: min-content;\n",
-       "  min-width: 20ex;\n",
-       "  max-width: 50ex;\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  box-shadow: 2pt 2pt 4pt #999;\n",
-       "  /* unfitted */\n",
-       "  background: var(--sklearn-color-unfitted-level-0);\n",
-       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link.fitted span {\n",
-       "  /* fitted */\n",
-       "  background: var(--sklearn-color-fitted-level-0);\n",
-       "  border: var(--sklearn-color-fitted-level-3);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link:hover span {\n",
-       "  display: block;\n",
-       "}\n",
-       "\n",
-       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
-       "\n",
-       "#sk-container-id-1 a.estimator_doc_link {\n",
-       "  float: right;\n",
-       "  font-size: 1rem;\n",
-       "  line-height: 1em;\n",
-       "  font-family: monospace;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  border-radius: 1rem;\n",
-       "  height: 1rem;\n",
-       "  width: 1rem;\n",
-       "  text-decoration: none;\n",
-       "  /* unfitted */\n",
-       "  color: var(--sklearn-color-unfitted-level-1);\n",
-       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
-       "  /* fitted */\n",
-       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-fitted-level-1);\n",
-       "}\n",
-       "\n",
-       "/* On hover */\n",
-       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-3);\n",
-       "}\n",
-       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(n_estimators=10, random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;RandomForestClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.ensemble.RandomForestClassifier.html\">?<span>Documentation for RandomForestClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestClassifier(n_estimators=10, random_state=42)</pre></div> </div></div></div></div>"
-      ],
-      "text/plain": [
-       "RandomForestClassifier(n_estimators=10, random_state=42)"
-      ]
-     },
-     "execution_count": 19,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from sklearn.ensemble import RandomForestClassifier\n",
-    "\n",
-    "model_1 = RandomForestClassifier(n_estimators=10, random_state=42)\n",
-    "model_1.fit(X_train, y_train)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 37,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "y_pred = model_1.predict(X_test)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 38,
-   "metadata": {
-    "id": "m76sl7hf_mMY"
-   },
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Accuracy: 0.9977196788547721\n",
-      "              precision    recall  f1-score   support\n",
-      "\n",
-      "           0       1.00      1.00      1.00    126154\n",
-      "           1       1.00      1.00      1.00    126186\n",
-      "\n",
-      "   micro avg       1.00      1.00      1.00    252340\n",
-      "   macro avg       1.00      1.00      1.00    252340\n",
-      "weighted avg       1.00      1.00      1.00    252340\n",
-      " samples avg       1.00      1.00      1.00    252340\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "from sklearn.preprocessing import MultiLabelBinarizer\n",
-    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
-    "\n",
-    "# Assuming y_test and y_pred are in multi-label format\n",
-    "mlb = MultiLabelBinarizer()\n",
-    "y_test_binary = mlb.fit_transform(y_test)\n",
-    "y_pred_binary = mlb.transform(y_pred)\n",
-    "\n",
-    "# Compute and print accuracy\n",
-    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
-    "print(f\"Accuracy: {accuracy}\")\n",
-    "\n",
-    "# Print classification report\n",
-    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {
-    "id": "FsWqdWgf_PCW"
-   },
-   "source": [
-    "### Model 2: XGBClassifier"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 35,
-   "metadata": {
-    "id": "uPcz1c688h5U"
-   },
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<style>#sk-container-id-2 {\n",
-       "  /* Definition of color scheme common for light and dark mode */\n",
-       "  --sklearn-color-text: black;\n",
-       "  --sklearn-color-line: gray;\n",
-       "  /* Definition of color scheme for unfitted estimators */\n",
-       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
-       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
-       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
-       "  --sklearn-color-unfitted-level-3: chocolate;\n",
-       "  /* Definition of color scheme for fitted estimators */\n",
-       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
-       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
-       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
-       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
-       "\n",
-       "  /* Specific color for light theme */\n",
-       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
-       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
-       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
-       "  --sklearn-color-icon: #696969;\n",
-       "\n",
-       "  @media (prefers-color-scheme: dark) {\n",
-       "    /* Redefinition of color scheme for dark theme */\n",
-       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
-       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
-       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
-       "    --sklearn-color-icon: #878787;\n",
-       "  }\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 pre {\n",
-       "  padding: 0;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 input.sk-hidden--visually {\n",
-       "  border: 0;\n",
-       "  clip: rect(1px 1px 1px 1px);\n",
-       "  clip: rect(1px, 1px, 1px, 1px);\n",
-       "  height: 1px;\n",
-       "  margin: -1px;\n",
-       "  overflow: hidden;\n",
-       "  padding: 0;\n",
-       "  position: absolute;\n",
-       "  width: 1px;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-dashed-wrapped {\n",
-       "  border: 1px dashed var(--sklearn-color-line);\n",
-       "  margin: 0 0.4em 0.5em 0.4em;\n",
-       "  box-sizing: border-box;\n",
-       "  padding-bottom: 0.4em;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-container {\n",
-       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
-       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
-       "     so we also need the `!important` here to be able to override the\n",
-       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
-       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
-       "  display: inline-block !important;\n",
-       "  position: relative;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-text-repr-fallback {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       "div.sk-parallel-item,\n",
-       "div.sk-serial,\n",
-       "div.sk-item {\n",
-       "  /* draw centered vertical line to link estimators */\n",
-       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
-       "  background-size: 2px 100%;\n",
-       "  background-repeat: no-repeat;\n",
-       "  background-position: center center;\n",
-       "}\n",
-       "\n",
-       "/* Parallel-specific style estimator block */\n",
-       "\n",
-       "#sk-container-id-2 div.sk-parallel-item::after {\n",
-       "  content: \"\";\n",
-       "  width: 100%;\n",
-       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
-       "  flex-grow: 1;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-parallel {\n",
-       "  display: flex;\n",
-       "  align-items: stretch;\n",
-       "  justify-content: center;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  position: relative;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-parallel-item {\n",
-       "  display: flex;\n",
-       "  flex-direction: column;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
-       "  align-self: flex-end;\n",
-       "  width: 50%;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
-       "  align-self: flex-start;\n",
-       "  width: 50%;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
-       "  width: 0;\n",
-       "}\n",
-       "\n",
-       "/* Serial-specific style estimator block */\n",
-       "\n",
-       "#sk-container-id-2 div.sk-serial {\n",
-       "  display: flex;\n",
-       "  flex-direction: column;\n",
-       "  align-items: center;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  padding-right: 1em;\n",
-       "  padding-left: 1em;\n",
-       "}\n",
-       "\n",
-       "\n",
-       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
-       "clickable and can be expanded/collapsed.\n",
-       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
-       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
-       "*/\n",
-       "\n",
-       "/* Pipeline and ColumnTransformer style (default) */\n",
-       "\n",
-       "#sk-container-id-2 div.sk-toggleable {\n",
-       "  /* Default theme specific background. It is overwritten whether we have a\n",
-       "  specific estimator or a Pipeline/ColumnTransformer */\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "}\n",
-       "\n",
-       "/* Toggleable label */\n",
-       "#sk-container-id-2 label.sk-toggleable__label {\n",
-       "  cursor: pointer;\n",
-       "  display: block;\n",
-       "  width: 100%;\n",
-       "  margin-bottom: 0;\n",
-       "  padding: 0.5em;\n",
-       "  box-sizing: border-box;\n",
-       "  text-align: center;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
-       "  /* Arrow on the left of the label */\n",
-       "  content: \"▸\";\n",
-       "  float: left;\n",
-       "  margin-right: 0.25em;\n",
-       "  color: var(--sklearn-color-icon);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "}\n",
-       "\n",
-       "/* Toggleable content - dropdown */\n",
-       "\n",
-       "#sk-container-id-2 div.sk-toggleable__content {\n",
-       "  max-height: 0;\n",
-       "  max-width: 0;\n",
-       "  overflow: hidden;\n",
-       "  text-align: left;\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-toggleable__content pre {\n",
-       "  margin: 0.2em;\n",
-       "  border-radius: 0.25em;\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
-       "  /* Expand drop-down */\n",
-       "  max-height: 200px;\n",
-       "  max-width: 100%;\n",
-       "  overflow: auto;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
-       "  content: \"▾\";\n",
-       "}\n",
-       "\n",
-       "/* Pipeline/ColumnTransformer-specific style */\n",
-       "\n",
-       "#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Estimator-specific style */\n",
-       "\n",
-       "/* Colorize estimator box */\n",
-       "#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
-       "#sk-container-id-2 div.sk-label label {\n",
-       "  /* The background is the default theme color */\n",
-       "  color: var(--sklearn-color-text-on-default-background);\n",
-       "}\n",
-       "\n",
-       "/* On hover, darken the color of the background */\n",
-       "#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Label box, darken color on hover, fitted */\n",
-       "#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Estimator label */\n",
-       "\n",
-       "#sk-container-id-2 div.sk-label label {\n",
-       "  font-family: monospace;\n",
-       "  font-weight: bold;\n",
-       "  display: inline-block;\n",
-       "  line-height: 1.2em;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-label-container {\n",
-       "  text-align: center;\n",
-       "}\n",
-       "\n",
-       "/* Estimator-specific */\n",
-       "#sk-container-id-2 div.sk-estimator {\n",
-       "  font-family: monospace;\n",
-       "  border: 1px dotted var(--sklearn-color-border-box);\n",
-       "  border-radius: 0.25em;\n",
-       "  box-sizing: border-box;\n",
-       "  margin-bottom: 0.5em;\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-estimator.fitted {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "/* on hover */\n",
-       "#sk-container-id-2 div.sk-estimator:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
-       "\n",
-       "/* Common style for \"i\" and \"?\" */\n",
-       "\n",
-       ".sk-estimator-doc-link,\n",
-       "a:link.sk-estimator-doc-link,\n",
-       "a:visited.sk-estimator-doc-link {\n",
-       "  float: right;\n",
-       "  font-size: smaller;\n",
-       "  line-height: 1em;\n",
-       "  font-family: monospace;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  border-radius: 1em;\n",
-       "  height: 1em;\n",
-       "  width: 1em;\n",
-       "  text-decoration: none !important;\n",
-       "  margin-left: 1ex;\n",
-       "  /* unfitted */\n",
-       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-unfitted-level-1);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link.fitted,\n",
-       "a:link.sk-estimator-doc-link.fitted,\n",
-       "a:visited.sk-estimator-doc-link.fitted {\n",
-       "  /* fitted */\n",
-       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-fitted-level-1);\n",
-       "}\n",
-       "\n",
-       "/* On hover */\n",
-       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
-       ".sk-estimator-doc-link:hover,\n",
-       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
-       ".sk-estimator-doc-link:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
-       ".sk-estimator-doc-link.fitted:hover,\n",
-       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
-       ".sk-estimator-doc-link.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "/* Span, style for the box shown on hovering the info icon */\n",
-       ".sk-estimator-doc-link span {\n",
-       "  display: none;\n",
-       "  z-index: 9999;\n",
-       "  position: relative;\n",
-       "  font-weight: normal;\n",
-       "  right: .2ex;\n",
-       "  padding: .5ex;\n",
-       "  margin: .5ex;\n",
-       "  width: min-content;\n",
-       "  min-width: 20ex;\n",
-       "  max-width: 50ex;\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  box-shadow: 2pt 2pt 4pt #999;\n",
-       "  /* unfitted */\n",
-       "  background: var(--sklearn-color-unfitted-level-0);\n",
-       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link.fitted span {\n",
-       "  /* fitted */\n",
-       "  background: var(--sklearn-color-fitted-level-0);\n",
-       "  border: var(--sklearn-color-fitted-level-3);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link:hover span {\n",
-       "  display: block;\n",
-       "}\n",
-       "\n",
-       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
-       "\n",
-       "#sk-container-id-2 a.estimator_doc_link {\n",
-       "  float: right;\n",
-       "  font-size: 1rem;\n",
-       "  line-height: 1em;\n",
-       "  font-family: monospace;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  border-radius: 1rem;\n",
-       "  height: 1rem;\n",
-       "  width: 1rem;\n",
-       "  text-decoration: none;\n",
-       "  /* unfitted */\n",
-       "  color: var(--sklearn-color-unfitted-level-1);\n",
-       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 a.estimator_doc_link.fitted {\n",
-       "  /* fitted */\n",
-       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-fitted-level-1);\n",
-       "}\n",
-       "\n",
-       "/* On hover */\n",
-       "#sk-container-id-2 a.estimator_doc_link:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-3);\n",
-       "}\n",
-       "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
-       "              colsample_bylevel=None, colsample_bynode=None,\n",
-       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
-       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
-       "              gamma=None, grow_policy=None, importance_type=None,\n",
-       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
-       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
-       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
-       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
-       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
-       "              num_parallel_tree=None, random_state=None, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;XGBClassifier<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
-       "              colsample_bylevel=None, colsample_bynode=None,\n",
-       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
-       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
-       "              gamma=None, grow_policy=None, importance_type=None,\n",
-       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
-       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
-       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
-       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
-       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
-       "              num_parallel_tree=None, random_state=None, ...)</pre></div> </div></div></div></div>"
-      ],
-      "text/plain": [
-       "XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
-       "              colsample_bylevel=None, colsample_bynode=None,\n",
-       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
-       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
-       "              gamma=None, grow_policy=None, importance_type=None,\n",
-       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
-       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
-       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
-       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
-       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
-       "              num_parallel_tree=None, random_state=None, ...)"
-      ]
-     },
-     "execution_count": 35,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from xgboost import XGBClassifier\n",
-    "\n",
-    "model_2 = XGBClassifier()\n",
-    "model_2.fit(X_train, y_train)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 39,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "y_pred = model_2.predict(X_test)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 40,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Accuracy: 0.9979176233986287\n",
-      "              precision    recall  f1-score   support\n",
-      "\n",
-      "           0       1.00      1.00      1.00    126154\n",
-      "           1       1.00      1.00      1.00    126186\n",
-      "\n",
-      "   micro avg       1.00      1.00      1.00    252340\n",
-      "   macro avg       1.00      1.00      1.00    252340\n",
-      "weighted avg       1.00      1.00      1.00    252340\n",
-      " samples avg       1.00      1.00      1.00    252340\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "from sklearn.preprocessing import MultiLabelBinarizer\n",
-    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
-    "\n",
-    "# Assuming y_test and y_pred are in multi-label format\n",
-    "mlb = MultiLabelBinarizer()\n",
-    "y_test_binary = mlb.fit_transform(y_test)\n",
-    "y_pred_binary = mlb.transform(y_pred)\n",
-    "\n",
-    "# Compute and print accuracy\n",
-    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
-    "print(f\"Accuracy: {accuracy}\")\n",
-    "\n",
-    "# Print classification report\n",
-    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "### Model 3: SVM"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 13,
-   "metadata": {},
-   "outputs": [
-    {
-     "data": {
-      "text/html": [
-       "<style>#sk-container-id-1 {\n",
-       "  /* Definition of color scheme common for light and dark mode */\n",
-       "  --sklearn-color-text: black;\n",
-       "  --sklearn-color-line: gray;\n",
-       "  /* Definition of color scheme for unfitted estimators */\n",
-       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
-       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
-       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
-       "  --sklearn-color-unfitted-level-3: chocolate;\n",
-       "  /* Definition of color scheme for fitted estimators */\n",
-       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
-       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
-       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
-       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
-       "\n",
-       "  /* Specific color for light theme */\n",
-       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
-       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
-       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
-       "  --sklearn-color-icon: #696969;\n",
-       "\n",
-       "  @media (prefers-color-scheme: dark) {\n",
-       "    /* Redefinition of color scheme for dark theme */\n",
-       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
-       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
-       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
-       "    --sklearn-color-icon: #878787;\n",
-       "  }\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 pre {\n",
-       "  padding: 0;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 input.sk-hidden--visually {\n",
-       "  border: 0;\n",
-       "  clip: rect(1px 1px 1px 1px);\n",
-       "  clip: rect(1px, 1px, 1px, 1px);\n",
-       "  height: 1px;\n",
-       "  margin: -1px;\n",
-       "  overflow: hidden;\n",
-       "  padding: 0;\n",
-       "  position: absolute;\n",
-       "  width: 1px;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
-       "  border: 1px dashed var(--sklearn-color-line);\n",
-       "  margin: 0 0.4em 0.5em 0.4em;\n",
-       "  box-sizing: border-box;\n",
-       "  padding-bottom: 0.4em;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-container {\n",
-       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
-       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
-       "     so we also need the `!important` here to be able to override the\n",
-       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
-       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
-       "  display: inline-block !important;\n",
-       "  position: relative;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
-       "  display: none;\n",
-       "}\n",
-       "\n",
-       "div.sk-parallel-item,\n",
-       "div.sk-serial,\n",
-       "div.sk-item {\n",
-       "  /* draw centered vertical line to link estimators */\n",
-       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
-       "  background-size: 2px 100%;\n",
-       "  background-repeat: no-repeat;\n",
-       "  background-position: center center;\n",
-       "}\n",
-       "\n",
-       "/* Parallel-specific style estimator block */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item::after {\n",
-       "  content: \"\";\n",
-       "  width: 100%;\n",
-       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
-       "  flex-grow: 1;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel {\n",
-       "  display: flex;\n",
-       "  align-items: stretch;\n",
-       "  justify-content: center;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  position: relative;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item {\n",
-       "  display: flex;\n",
-       "  flex-direction: column;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
-       "  align-self: flex-end;\n",
-       "  width: 50%;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
-       "  align-self: flex-start;\n",
-       "  width: 50%;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
-       "  width: 0;\n",
-       "}\n",
-       "\n",
-       "/* Serial-specific style estimator block */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-serial {\n",
-       "  display: flex;\n",
-       "  flex-direction: column;\n",
-       "  align-items: center;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  padding-right: 1em;\n",
-       "  padding-left: 1em;\n",
-       "}\n",
-       "\n",
-       "\n",
-       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
-       "clickable and can be expanded/collapsed.\n",
-       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
-       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
-       "*/\n",
-       "\n",
-       "/* Pipeline and ColumnTransformer style (default) */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable {\n",
-       "  /* Default theme specific background. It is overwritten whether we have a\n",
-       "  specific estimator or a Pipeline/ColumnTransformer */\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "}\n",
-       "\n",
-       "/* Toggleable label */\n",
-       "#sk-container-id-1 label.sk-toggleable__label {\n",
-       "  cursor: pointer;\n",
-       "  display: block;\n",
-       "  width: 100%;\n",
-       "  margin-bottom: 0;\n",
-       "  padding: 0.5em;\n",
-       "  box-sizing: border-box;\n",
-       "  text-align: center;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
-       "  /* Arrow on the left of the label */\n",
-       "  content: \"▸\";\n",
-       "  float: left;\n",
-       "  margin-right: 0.25em;\n",
-       "  color: var(--sklearn-color-icon);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "}\n",
-       "\n",
-       "/* Toggleable content - dropdown */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content {\n",
-       "  max-height: 0;\n",
-       "  max-width: 0;\n",
-       "  overflow: hidden;\n",
-       "  text-align: left;\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
-       "  margin: 0.2em;\n",
-       "  border-radius: 0.25em;\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
-       "  /* Expand drop-down */\n",
-       "  max-height: 200px;\n",
-       "  max-width: 100%;\n",
-       "  overflow: auto;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
-       "  content: \"▾\";\n",
-       "}\n",
-       "\n",
-       "/* Pipeline/ColumnTransformer-specific style */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Estimator-specific style */\n",
-       "\n",
-       "/* Colorize estimator box */\n",
-       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
-       "#sk-container-id-1 div.sk-label label {\n",
-       "  /* The background is the default theme color */\n",
-       "  color: var(--sklearn-color-text-on-default-background);\n",
-       "}\n",
-       "\n",
-       "/* On hover, darken the color of the background */\n",
-       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Label box, darken color on hover, fitted */\n",
-       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Estimator label */\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label label {\n",
-       "  font-family: monospace;\n",
-       "  font-weight: bold;\n",
-       "  display: inline-block;\n",
-       "  line-height: 1.2em;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-label-container {\n",
-       "  text-align: center;\n",
-       "}\n",
-       "\n",
-       "/* Estimator-specific */\n",
-       "#sk-container-id-1 div.sk-estimator {\n",
-       "  font-family: monospace;\n",
-       "  border: 1px dotted var(--sklearn-color-border-box);\n",
-       "  border-radius: 0.25em;\n",
-       "  box-sizing: border-box;\n",
-       "  margin-bottom: 0.5em;\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-0);\n",
-       "}\n",
-       "\n",
-       "/* on hover */\n",
-       "#sk-container-id-1 div.sk-estimator:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-2);\n",
-       "}\n",
-       "\n",
-       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
-       "\n",
-       "/* Common style for \"i\" and \"?\" */\n",
-       "\n",
-       ".sk-estimator-doc-link,\n",
-       "a:link.sk-estimator-doc-link,\n",
-       "a:visited.sk-estimator-doc-link {\n",
-       "  float: right;\n",
-       "  font-size: smaller;\n",
-       "  line-height: 1em;\n",
-       "  font-family: monospace;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  border-radius: 1em;\n",
-       "  height: 1em;\n",
-       "  width: 1em;\n",
-       "  text-decoration: none !important;\n",
-       "  margin-left: 1ex;\n",
-       "  /* unfitted */\n",
-       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-unfitted-level-1);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link.fitted,\n",
-       "a:link.sk-estimator-doc-link.fitted,\n",
-       "a:visited.sk-estimator-doc-link.fitted {\n",
-       "  /* fitted */\n",
-       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-fitted-level-1);\n",
-       "}\n",
-       "\n",
-       "/* On hover */\n",
-       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
-       ".sk-estimator-doc-link:hover,\n",
-       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
-       ".sk-estimator-doc-link:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
-       ".sk-estimator-doc-link.fitted:hover,\n",
-       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
-       ".sk-estimator-doc-link.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "/* Span, style for the box shown on hovering the info icon */\n",
-       ".sk-estimator-doc-link span {\n",
-       "  display: none;\n",
-       "  z-index: 9999;\n",
-       "  position: relative;\n",
-       "  font-weight: normal;\n",
-       "  right: .2ex;\n",
-       "  padding: .5ex;\n",
-       "  margin: .5ex;\n",
-       "  width: min-content;\n",
-       "  min-width: 20ex;\n",
-       "  max-width: 50ex;\n",
-       "  color: var(--sklearn-color-text);\n",
-       "  box-shadow: 2pt 2pt 4pt #999;\n",
-       "  /* unfitted */\n",
-       "  background: var(--sklearn-color-unfitted-level-0);\n",
-       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link.fitted span {\n",
-       "  /* fitted */\n",
-       "  background: var(--sklearn-color-fitted-level-0);\n",
-       "  border: var(--sklearn-color-fitted-level-3);\n",
-       "}\n",
-       "\n",
-       ".sk-estimator-doc-link:hover span {\n",
-       "  display: block;\n",
-       "}\n",
-       "\n",
-       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
-       "\n",
-       "#sk-container-id-1 a.estimator_doc_link {\n",
-       "  float: right;\n",
-       "  font-size: 1rem;\n",
-       "  line-height: 1em;\n",
-       "  font-family: monospace;\n",
-       "  background-color: var(--sklearn-color-background);\n",
-       "  border-radius: 1rem;\n",
-       "  height: 1rem;\n",
-       "  width: 1rem;\n",
-       "  text-decoration: none;\n",
-       "  /* unfitted */\n",
-       "  color: var(--sklearn-color-unfitted-level-1);\n",
-       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
-       "  /* fitted */\n",
-       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
-       "  color: var(--sklearn-color-fitted-level-1);\n",
-       "}\n",
-       "\n",
-       "/* On hover */\n",
-       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
-       "  /* unfitted */\n",
-       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
-       "  color: var(--sklearn-color-background);\n",
-       "  text-decoration: none;\n",
-       "}\n",
-       "\n",
-       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
-       "  /* fitted */\n",
-       "  background-color: var(--sklearn-color-fitted-level-3);\n",
-       "}\n",
-       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MultiOutputClassifier(estimator=SVC(), n_jobs=-1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;MultiOutputClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.multioutput.MultiOutputClassifier.html\">?<span>Documentation for MultiOutputClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>MultiOutputClassifier(estimator=SVC(), n_jobs=-1)</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">estimator: SVC</label><div class=\"sk-toggleable__content fitted\"><pre>SVC()</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;SVC<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.svm.SVC.html\">?<span>Documentation for SVC</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>SVC()</pre></div> </div></div></div></div></div></div></div></div></div>"
-      ],
-      "text/plain": [
-       "MultiOutputClassifier(estimator=SVC(), n_jobs=-1)"
-      ]
-     },
-     "execution_count": 13,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
-   "source": [
-    "from sklearn.multioutput import MultiOutputClassifier\n",
-    "from sklearn.svm import SVC\n",
-    "\n",
-    "svm = SVC(kernel='rbf', gamma='scale', C=1.0)\n",
-    "\n",
-    "model_3 = MultiOutputClassifier(svm, n_jobs=-1)\n",
-    "\n",
-    "model_3.fit(X_train, y_train)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 14,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "y_pred = model_3.predict(X_test)"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 15,
-   "metadata": {},
-   "outputs": [
-    {
-     "name": "stdout",
-     "output_type": "stream",
-     "text": [
-      "Accuracy: 0.9999287399642116\n",
-      "              precision    recall  f1-score   support\n",
-      "\n",
-      "           0       1.00      1.00      1.00    126298\n",
-      "           1       1.00      1.00      1.00    126298\n",
-      "\n",
-      "   micro avg       1.00      1.00      1.00    252596\n",
-      "   macro avg       1.00      1.00      1.00    252596\n",
-      "weighted avg       1.00      1.00      1.00    252596\n",
-      " samples avg       1.00      1.00      1.00    252596\n",
-      "\n"
-     ]
-    }
-   ],
-   "source": [
-    "from sklearn.preprocessing import MultiLabelBinarizer\n",
-    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
-    "\n",
-    "# Assuming y_test and y_pred are in multi-label format\n",
-    "mlb = MultiLabelBinarizer()\n",
-    "y_test_binary = mlb.fit_transform(y_test)\n",
-    "y_pred_binary = mlb.transform(y_pred)\n",
-    "\n",
-    "# Compute and print accuracy\n",
-    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
-    "print(f\"Accuracy: {accuracy}\")\n",
-    "\n",
-    "# Print classification report\n",
-    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
-   ]
-  }
- ],
- "metadata": {
-  "accelerator": "GPU",
-  "colab": {
-   "gpuType": "T4",
-   "provenance": [],
-   "toc_visible": true
-  },
-  "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
-   "language": "python",
-   "name": "python3"
-  },
-  "language_info": {
-   "codemirror_mode": {
-    "name": "ipython",
-    "version": 3
-   },
-   "file_extension": ".py",
-   "mimetype": "text/x-python",
-   "name": "python",
-   "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython3",
-   "version": "3.11.0"
-  }
- },
- "nbformat": 4,
- "nbformat_minor": 4
-}

From 57edf11c1eb5aa5f054ad29a513d3f7cbb37b9d2 Mon Sep 17 00:00:00 2001
From: Aditi Kala <130339327+why-aditi@users.noreply.github.com>
Date: Sat, 22 Jun 2024 17:37:18 +0530
Subject: [PATCH 09/10] Add files via upload

---
 ...IoT_Network_Traffic_Dataset_Analysis.ipynb | 3194 +++++++++++++++++
 1 file changed, 3194 insertions(+)
 create mode 100644 ACI IoT Network Traffic Dataset Analysis/Model/ACI_IoT_Network_Traffic_Dataset_Analysis.ipynb

diff --git a/ACI IoT Network Traffic Dataset Analysis/Model/ACI_IoT_Network_Traffic_Dataset_Analysis.ipynb b/ACI IoT Network Traffic Dataset Analysis/Model/ACI_IoT_Network_Traffic_Dataset_Analysis.ipynb
new file mode 100644
index 000000000..66c7e6e01
--- /dev/null
+++ b/ACI IoT Network Traffic Dataset Analysis/Model/ACI_IoT_Network_Traffic_Dataset_Analysis.ipynb	
@@ -0,0 +1,3194 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "YwuxWrIj26L7"
+   },
+   "source": [
+    "# ACI IoT Network Traffic"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "eA-t2jeQ2_Ay"
+   },
+   "source": [
+    "## Get dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "id": "f2-gDXPihjaF"
+   },
+   "outputs": [],
+   "source": [
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import tensorflow as tf\n",
+    "import matplotlib.pyplot as plt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "D:\\ML\\ACI IoT Network Traffic Dataset Analysis\\Model\n"
+     ]
+    }
+   ],
+   "source": [
+    "import os\n",
+    "print(os.getcwd())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<div>\n",
+       "<style scoped>\n",
+       "    .dataframe tbody tr th:only-of-type {\n",
+       "        vertical-align: middle;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe tbody tr th {\n",
+       "        vertical-align: top;\n",
+       "    }\n",
+       "\n",
+       "    .dataframe thead th {\n",
+       "        text-align: right;\n",
+       "    }\n",
+       "</style>\n",
+       "<table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       "    <tr style=\"text-align: right;\">\n",
+       "      <th></th>\n",
+       "      <th>srcip</th>\n",
+       "      <th>sport</th>\n",
+       "      <th>dstip</th>\n",
+       "      <th>dsport</th>\n",
+       "      <th>protocol_m</th>\n",
+       "      <th>sttl</th>\n",
+       "      <th>total_len</th>\n",
+       "      <th>payload</th>\n",
+       "      <th>stime</th>\n",
+       "      <th>label</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>192.168.1.81</td>\n",
+       "      <td>60683</td>\n",
+       "      <td>239.255.255.250</td>\n",
+       "      <td>1900</td>\n",
+       "      <td>udp</td>\n",
+       "      <td>2</td>\n",
+       "      <td>362</td>\n",
+       "      <td>4e4f54494659202a20485454502f312e310d0a4e54533a...</td>\n",
+       "      <td>1698670981</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>192.168.1.9</td>\n",
+       "      <td>53160</td>\n",
+       "      <td>239.255.255.250</td>\n",
+       "      <td>1900</td>\n",
+       "      <td>udp</td>\n",
+       "      <td>1</td>\n",
+       "      <td>204</td>\n",
+       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
+       "      <td>1698670984</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>192.168.1.9</td>\n",
+       "      <td>53160</td>\n",
+       "      <td>239.255.255.250</td>\n",
+       "      <td>1900</td>\n",
+       "      <td>udp</td>\n",
+       "      <td>1</td>\n",
+       "      <td>204</td>\n",
+       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
+       "      <td>1698670985</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>192.168.1.9</td>\n",
+       "      <td>53160</td>\n",
+       "      <td>239.255.255.250</td>\n",
+       "      <td>1900</td>\n",
+       "      <td>udp</td>\n",
+       "      <td>1</td>\n",
+       "      <td>204</td>\n",
+       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
+       "      <td>1698670986</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>192.168.1.9</td>\n",
+       "      <td>53160</td>\n",
+       "      <td>239.255.255.250</td>\n",
+       "      <td>1900</td>\n",
+       "      <td>udp</td>\n",
+       "      <td>1</td>\n",
+       "      <td>204</td>\n",
+       "      <td>4d2d534541524348202a20485454502f312e310d0a484f...</td>\n",
+       "      <td>1698670987</td>\n",
+       "      <td>Benign</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "          srcip  sport            dstip  dsport protocol_m  sttl  total_len  \\\n",
+       "0  192.168.1.81  60683  239.255.255.250    1900        udp     2        362   \n",
+       "1   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
+       "2   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
+       "3   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
+       "4   192.168.1.9  53160  239.255.255.250    1900        udp     1        204   \n",
+       "\n",
+       "                                             payload       stime   label  \n",
+       "0  4e4f54494659202a20485454502f312e310d0a4e54533a...  1698670981  Benign  \n",
+       "1  4d2d534541524348202a20485454502f312e310d0a484f...  1698670984  Benign  \n",
+       "2  4d2d534541524348202a20485454502f312e310d0a484f...  1698670985  Benign  \n",
+       "3  4d2d534541524348202a20485454502f312e310d0a484f...  1698670986  Benign  \n",
+       "4  4d2d534541524348202a20485454502f312e310d0a484f...  1698670987  Benign  "
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df = pd.read_csv('D:\\ML\\ACI IoT Network Traffic Dataset Analysis\\Dataset\\ACI-IoT-2023-Payload.csv')\n",
+    "pd.set_option('display.max_columns', None)\n",
+    "df.head()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "dW7fRPpahgGd"
+   },
+   "source": [
+    "## EDA"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "id": "t4ChRqiXsIZZ"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "srcip         0\n",
+       "sport         0\n",
+       "dstip         0\n",
+       "dsport        0\n",
+       "protocol_m    0\n",
+       "sttl          0\n",
+       "total_len     0\n",
+       "payload       0\n",
+       "stime         0\n",
+       "label         0\n",
+       "dtype: int64"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isnull().sum()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "id": "CxOR0kJM3SWR"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "label\n",
+       "Benign                601868\n",
+       "DNS Flood              18577\n",
+       "Dictionary Attack       4645\n",
+       "Slowloris               2974\n",
+       "SYN Flood               2113\n",
+       "Port Scan                582\n",
+       "Vulnerability Scan       445\n",
+       "OS Scan                  156\n",
+       "UDP Flood                 68\n",
+       "ICMP Flood                58\n",
+       "Name: count, dtype: int64"
+      ]
+     },
+     "execution_count": 5,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.label.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "id": "mrlQp4My4faj"
+   },
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "labels = ['Benign', 'DNS Flood', 'Dictionary Attack', 'Slowloris', 'SYN Flood',\n",
+    "          'Port Scan', 'Vulnerability Scan', 'OS Scan', 'UDP Flood', 'ICMP Flood']\n",
+    "sizes = [601868, 18577, 4645, 2974, 2113, 582, 445, 156, 68, 58]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "id": "Actc2Dc-4l4W"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABAcAAAJ3CAYAAADoNji5AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy80BEi2AAAACXBIWXMAAA9hAAAPYQGoP6dpAACcM0lEQVR4nOzdeZyN9f//8eeZGTNjm8U2Y1/Lvq9DSGESIktIkVQfhSzJkhJRirTI1q5NEWVfI0tIItklS0RjiZmxzYyZef3+8Jvr60ShcIzrcb/d5lbnut7nnNe5nHOd63qe9/V+e8zMBAAAAAAAXMvP1wUAAAAAAADfIhwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAuEyDBw+Wx+PR0aNHfV0KAABXFeEAAADQxIkT5fF4vP5y5cqlevXqad68ede9nlmzZqlp06aKiIhQYGCgsmXLpjp16mjUqFGKj4+/7vUAAHCzC/B1AQAA4MbxwgsvqHDhwjIzHTp0SBMnTtTdd9+tWbNmqUmTJtf8+VNTU9W5c2dNnDhRZcuW1RNPPKH8+fPrxIkTWr16tZ599lnNnTtXixcvvua1AADgJoQDAADA0ahRI1WpUsW53blzZ0VEROjzzz+/KuFAamqqkpKSFBwcfNH1I0aM0MSJE9WrVy+NGjVKHo/HWdejRw/98ccf+vjjj//TcwAAgAtxWQEAAPhbYWFhypgxowICvH9PePXVV1WzZk1lz55dGTNmVOXKlTV16tQL7u/xeNStWzd99tlnKl26tIKCgjR//vyLPtfp06f1yiuvqHTp0ho5cqRXMJAmd+7c6tev32U/x7+ps3jx4goODlblypW1fPnyi9YaGxurhx56SGFhYQoNDVWnTp10+vTpi29EAADSAXoOAAAAR1xcnI4ePSoz0+HDh/XWW2/p5MmTeuCBB7zavfnmm7rnnnvUvn17JSUl6YsvvlDr1q01e/ZsNW7c2KvtkiVLNGXKFHXr1k05cuRQoUKFLvrc3333nWJjY9WnTx/5+/tfUd1/9xxXUueyZcs0efJkPfnkkwoKCtK4ceN011136YcfflCZMmW82t53330qXLiwhg8frvXr1+u9995Trly59Morr1xR3QAA3Cg8Zma+LgIAAPjWxIkT1alTpwuWBwUF6e2331bHjh29lp85c0YZM2Z0bp89e1aVKlVSrly5vMYD8Hg88vPz06ZNm1SqVKl/rGH06NHq0aOHpk+frmbNmjnLU1JSdPz4ca+22bNnd3oW/NNzXEmdkvTjjz+qcuXKkqR9+/apePHiatSokb766itJ52YrGDJkiB5++GG9//77zv1btGih5cuXM4sBACDdoucAAABwjB07Vrfeeqsk6dChQ/r000/1yCOPKGvWrGrRooXT7vwT7uPHjyslJUW1a9fW559/fsFj1q1b95LBgCRnFoIsWbJ4Ld+0aZMqVqzotezIkSPKkSPHJZ/jSuqMiopyggFJKlCggJo1a6ZZs2YpJSXFqzdDly5dvO5bu3Ztff3114qPj1dISMglXysAADcawgEAAOCoVq2a14CE7dq1U8WKFdWtWzc1adJEgYGBkqTZs2dr2LBh2rBhgxITE532FxsnoHDhwpf13FmzZpUknTx50mt5sWLFtGjRIknSxx9/rE8++eSyn+NK6rzlllsuWHbrrbfq9OnTOnLkiCIjI53lBQoU8GoXHh4u6VwAQTgAAEiPGJAQAAD8LT8/P9WrV09//PGHdu7cKUlasWKF7rnnHgUHB2vcuHGaO3euFi1apPvvv18Xu1rx/F/v/0mJEiUkSZs3b/ZaniVLFtWvX1/169dXkSJFLnrfiz3HldZ5Jf5uTASu1gQApFf0HAAAAP8oOTlZ0v/9oj9t2jQFBwdrwYIFCgoKctp9+OGH/+l5ateurdDQUH3xxRcaMGCA/Pz+228YV1pnWvhxvl9++UWZMmVSzpw5/1MtAADc6Og5AAAA/tbZs2e1cOFCBQYGqmTJkpLO/Wru8XiUkpLitNu7d6+mT5/+n54rU6ZM6tu3rzZv3qz+/ftf9Ff4K/ll/krrXL16tdavX+/c3r9/v2bMmKGGDRte8ewJAACkN/QcAAAAjnnz5mn79u2SpMOHD2vSpEnauXOn+vfv71xL37hxY7322mu66667dP/99+vw4cMaO3asihUrpo0bN/6n5+/fv7+2bdumkSNHauHChWrZsqXy5cun48ePa/369fryyy+VK1cuBQcHX/KxrrTOMmXKKDo62msqQ0kaMmTIf3pNAACkB4QDAADAMWjQIOf/g4ODVaJECY0fP17/+9//nOV33HGH3n//fb388svq2bOnChcurFdeeUV79+79z+GAn5+fPvnkE7Vs2VLvvvuu3nrrLR0/flxZsmRRmTJl9OKLL+rRRx+9YEaDi7nSOuvWrauoqCgNGTJE+/btU6lSpTRx4kSVK1fuP70mAADSA48xcg4AAHA5j8ejrl27asyYMb4uBQAAn2DMAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5RiQEAAAuB5DMAEA3I6eAwAAAAAAuBw9B66j1NRUHTx4UFmzZpXH4/F1OQAAAACAm5yZ6cSJE8qTJ4/8/P6+fwDhwHV08OBB5c+f39dlAAAAAABcZv/+/cqXL9/friccuI6yZs0q6dw/SkhIiI+rAQAAAADc7OLj45U/f37nfPTvEA5cR2mXEoSEhBAOAAAAAACum0td2s6AhAAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4nM/DgQMHDuiBBx5Q9uzZlTFjRpUtW1Y//vijs97MNGjQIOXOnVsZM2ZU/fr1tXPnTq/HOHbsmNq3b6+QkBCFhYWpc+fOOnnypFebjRs3qnbt2goODlb+/Pk1YsSIC2r58ssvVaJECQUHB6ts2bKaO3eu1/rLqQUAAAAAgPTGp+HA8ePHVatWLWXIkEHz5s3T1q1bNWrUKIWHhzttRowYodGjR2vChAlas2aNMmfOrOjoaCUkJDht2rdvry1btmjRokWaPXu2li9frscee8xZHx8fr4YNG6pgwYJat26dRo4cqcGDB+udd95x2qxatUrt2rVT586d9dNPP6l58+Zq3ry5Nm/efEW1AAAAAACQ3njMzHz15P3799fKlSu1YsWKi643M+XJk0dPPfWU+vTpI0mKi4tTRESEJk6cqLZt22rbtm0qVaqU1q5dqypVqkiS5s+fr7vvvlu///678uTJo/Hjx2vgwIGKiYlRYGCg89zTp0/X9u3bJUlt2rTRqVOnNHv2bOf5a9SooQoVKmjChAmXVculxMfHKzQ0VHFxcQoJCfn3G+46KNR/jq9LuOHsfbmxr0sAAAAAgCtyueehPu05MHPmTFWpUkWtW7dWrly5VLFiRb377rvO+j179igmJkb169d3loWGhqp69epavXq1JGn16tUKCwtzggFJql+/vvz8/LRmzRqnTZ06dZxgQJKio6O1Y8cOHT9+3Glz/vOktUl7nsup5a8SExMVHx/v9QcAAAAAwI3Gp+HA7t27NX78eN1yyy1asGCBHn/8cT355JP66KOPJEkxMTGSpIiICK/7RUREOOtiYmKUK1cur/UBAQHKli2bV5uLPcb5z/F3bc5ff6la/mr48OEKDQ11/vLnz3+pTQIAAAAAwHXn03AgNTVVlSpV0ksvvaSKFSvqscce06OPPqoJEyb4sqyrZsCAAYqLi3P+9u/f7+uSAAAAAAC4gE/Dgdy5c6tUqVJey0qWLKl9+/ZJkiIjIyVJhw4d8mpz6NAhZ11kZKQOHz7stT45OVnHjh3zanOxxzj/Of6uzfnrL1XLXwUFBSkkJMTrDwAAAACAG41Pw4FatWppx44dXst++eUXFSxYUJJUuHBhRUZGavHixc76+Ph4rVmzRlFRUZKkqKgoxcbGat26dU6bJUuWKDU1VdWrV3faLF++XGfPnnXaLFq0SMWLF3dmRoiKivJ6nrQ2ac9zObUAAAAAAJAe+TQc6NWrl77//nu99NJL+vXXXzVp0iS988476tq1qyTJ4/GoZ8+eGjZsmGbOnKlNmzapQ4cOypMnj5o3by7pXE+Du+66S48++qh++OEHrVy5Ut26dVPbtm2VJ08eSdL999+vwMBAde7cWVu2bNHkyZP15ptvqnfv3k4tPXr00Pz58zVq1Cht375dgwcP1o8//qhu3bpddi0AAAAAAKRHAb588qpVq+rrr7/WgAED9MILL6hw4cJ644031L59e6dN3759derUKT322GOKjY3Vbbfdpvnz5ys4ONhp89lnn6lbt26688475efnp5YtW2r06NHO+tDQUC1cuFBdu3ZV5cqVlSNHDg0aNEiPPfaY06ZmzZqaNGmSnn32WT3zzDO65ZZbNH36dJUpU+aKagEAAAAAIL3xmJn5ugi3uNz5JW8EhfrP8XUJN5y9Lzf2dQkAAAAAcEUu9zzUp5cVAAAAAAAA3yMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5XwaDgwePFgej8frr0SJEs76hIQEde3aVdmzZ1eWLFnUsmVLHTp0yOsx9u3bp8aNGytTpkzKlSuXnn76aSUnJ3u1Wbp0qSpVqqSgoCAVK1ZMEydOvKCWsWPHqlChQgoODlb16tX1ww8/eK2/nFoAAAAAAEiPfN5zoHTp0vrjjz+cv++++85Z16tXL82aNUtffvmlli1bpoMHD6pFixbO+pSUFDVu3FhJSUlatWqVPvroI02cOFGDBg1y2uzZs0eNGzdWvXr1tGHDBvXs2VOPPPKIFixY4LSZPHmyevfureeff17r169X+fLlFR0drcOHD192LQAAAAAApFceMzNfPfngwYM1ffp0bdiw4YJ1cXFxypkzpyZNmqRWrVpJkrZv366SJUtq9erVqlGjhubNm6cmTZro4MGDioiIkCRNmDBB/fr105EjRxQYGKh+/fppzpw52rx5s/PYbdu2VWxsrObPny9Jql69uqpWraoxY8ZIklJTU5U/f351795d/fv3v6xaLkd8fLxCQ0MVFxenkJCQf73drodC/ef4uoQbzt6XG/u6BAAAAAC4Ipd7HurzngM7d+5Unjx5VKRIEbVv31779u2TJK1bt05nz55V/fr1nbYlSpRQgQIFtHr1aknS6tWrVbZsWScYkKTo6GjFx8dry5YtTpvzHyOtTdpjJCUlad26dV5t/Pz8VL9+fafN5dRyMYmJiYqPj/f6AwAAAADgRuPTcKB69eqaOHGi5s+fr/Hjx2vPnj2qXbu2Tpw4oZiYGAUGBiosLMzrPhEREYqJiZEkxcTEeAUDaevT1v1Tm/j4eJ05c0ZHjx5VSkrKRduc/xiXquVihg8frtDQUOcvf/78l7dhAAAAAAC4jgJ8+eSNGjVy/r9cuXKqXr26ChYsqClTpihjxow+rOzqGDBggHr37u3cjo+PJyAAAAAAANxwfH5ZwfnCwsJ066236tdff1VkZKSSkpIUGxvr1ebQoUOKjIyUJEVGRl4wY0Da7Uu1CQkJUcaMGZUjRw75+/tftM35j3GpWi4mKChIISEhXn8AAAAAANxobqhw4OTJk9q1a5dy586typUrK0OGDFq8eLGzfseOHdq3b5+ioqIkSVFRUdq0aZPXrAKLFi1SSEiISpUq5bQ5/zHS2qQ9RmBgoCpXruzVJjU1VYsXL3baXE4tAAAAAACkVz69rKBPnz5q2rSpChYsqIMHD+r555+Xv7+/2rVrp9DQUHXu3Fm9e/dWtmzZFBISou7duysqKsqZHaBhw4YqVaqUHnzwQY0YMUIxMTF69tln1bVrVwUFBUmSunTpojFjxqhv3756+OGHtWTJEk2ZMkVz5vzfaPy9e/dWx44dVaVKFVWrVk1vvPGGTp06pU6dOknSZdUCAAAAAEB65dNw4Pfff1e7du30559/KmfOnLrtttv0/fffK2fOnJKk119/XX5+fmrZsqUSExMVHR2tcePGOff39/fX7Nmz9fjjjysqKkqZM2dWx44d9cILLzhtChcurDlz5qhXr1568803lS9fPr333nuKjo522rRp00ZHjhzRoEGDFBMTowoVKmj+/PlegxReqhYAAAAAANIrj5mZr4twi8udX/JGUKj/nEs3cpm9Lzf2dQkAAAAAcEUu9zz0hhpzAAAAAAAAXH+EAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuNwNEw68/PLL8ng86tmzp7MsISFBXbt2Vfbs2ZUlSxa1bNlShw4d8rrfvn371LhxY2XKlEm5cuXS008/reTkZK82S5cuVaVKlRQUFKRixYpp4sSJFzz/2LFjVahQIQUHB6t69er64YcfvNZfTi0AAAAAAKRHN0Q4sHbtWr399tsqV66c1/JevXpp1qxZ+vLLL7Vs2TIdPHhQLVq0cNanpKSocePGSkpK0qpVq/TRRx9p4sSJGjRokNNmz549aty4serVq6cNGzaoZ8+eeuSRR7RgwQKnzeTJk9W7d289//zzWr9+vcqXL6/o6GgdPnz4smsBAAAAACC98piZ+bKAkydPqlKlSho3bpyGDRumChUq6I033lBcXJxy5sypSZMmqVWrVpKk7du3q2TJklq9erVq1KihefPmqUmTJjp48KAiIiIkSRMmTFC/fv105MgRBQYGql+/fpozZ442b97sPGfbtm0VGxur+fPnS5KqV6+uqlWrasyYMZKk1NRU5c+fX927d1f//v0vq5bLER8fr9DQUMXFxSkkJOSqbcNroVD/Ob4u4Yaz9+XGvi4BAAAAAK7I5Z6H+rznQNeuXdW4cWPVr1/fa/m6det09uxZr+UlSpRQgQIFtHr1aknS6tWrVbZsWScYkKTo6GjFx8dry5YtTpu/PnZ0dLTzGElJSVq3bp1XGz8/P9WvX99pczm1XExiYqLi4+O9/gAAAAAAuNEE+PLJv/jiC61fv15r1669YF1MTIwCAwMVFhbmtTwiIkIxMTFOm/ODgbT1aev+qU18fLzOnDmj48ePKyUl5aJttm/fftm1XMzw4cM1ZMiQv10PAAAAAMCNwGc9B/bv368ePXros88+U3BwsK/KuKYGDBiguLg452///v2+LgkAAAAAgAv4LBxYt26dDh8+rEqVKikgIEABAQFatmyZRo8erYCAAEVERCgpKUmxsbFe9zt06JAiIyMlSZGRkRfMGJB2+1JtQkJClDFjRuXIkUP+/v4XbXP+Y1yqlosJCgpSSEiI1x8AAAAAADcan4UDd955pzZt2qQNGzY4f1WqVFH79u2d/8+QIYMWL17s3GfHjh3at2+foqKiJElRUVHatGmT16wCixYtUkhIiEqVKuW0Of8x0tqkPUZgYKAqV67s1SY1NVWLFy922lSuXPmStQAAAAAAkF75bMyBrFmzqkyZMl7LMmfOrOzZszvLO3furN69eytbtmwKCQlR9+7dFRUV5cwO0LBhQ5UqVUoPPvigRowYoZiYGD377LPq2rWrgoKCJEldunTRmDFj1LdvXz388MNasmSJpkyZojlz/m80/t69e6tjx46qUqWKqlWrpjfeeEOnTp1Sp06dJEmhoaGXrAUAAAAAgPTKpwMSXsrrr78uPz8/tWzZUomJiYqOjta4ceOc9f7+/po9e7Yef/xxRUVFKXPmzOrYsaNeeOEFp03hwoU1Z84c9erVS2+++aby5cun9957T9HR0U6bNm3a6MiRIxo0aJBiYmJUoUIFzZ8/32uQwkvVAgAAAABAeuUxM/N1EW5xufNL3ggK9Z9z6UYus/flxr4uAQAAAACuyOWeh/pszAEAAAAAAHBjIBwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACX+1fhQJEiRfTnn39esDw2NlZFihT5z0UBAAAAAIDr51+FA3v37lVKSsoFyxMTE3XgwIH/XBQAAAAAALh+Aq6k8cyZM53/X7BggUJDQ53bKSkpWrx4sQoVKnTVigMAAAAAANfeFYUDzZs3lyR5PB517NjRa12GDBlUqFAhjRo16qoVBwAAAAAArr0rCgdSU1MlSYULF9batWuVI0eOa1IUAAAAAAC4fq4oHEizZ8+eq10HAAAAAADwkX8VDkjS4sWLtXjxYh0+fNjpUZDmgw8++M+FAQAAAACA6+NfhQNDhgzRCy+8oCpVqih37tzyeDxXuy4AAAAAAHCd/KtwYMKECZo4caIefPDBq10PAAAAAAC4zvz+zZ2SkpJUs2bNq10LAAAAAADwgX8VDjzyyCOaNGnS1a4FAAAAAAD4wL+6rCAhIUHvvPOOvvnmG5UrV04ZMmTwWv/aa69dleIAAAAAAMC196/CgY0bN6pChQqSpM2bN3utY3BCAAAAAADSl38VDnz77bdXuw4AAAAAAOAj/2rMAQAAAAAAcPP4Vz0H6tWr94+XDyxZsuRfFwQAAAAAAK6vfxUOpI03kObs2bPasGGDNm/erI4dO16NugAAAAAAwHXyr8KB119//aLLBw8erJMnT/6nggAAAAAAwPV1VccceOCBB/TBBx9czYcEAAAAAADX2FUNB1avXq3g4OCr+ZAAAAAAAOAa+1eXFbRo0cLrtpnpjz/+0I8//qjnnnvuqhQGAAAAAACuj38VDoSGhnrd9vPzU/HixfXCCy+oYcOGV6UwAAAAAABwffyrcODDDz+82nUAAAAAAAAf+VfhQJp169Zp27ZtkqTSpUurYsWKV6UoAAAAAABw/fyrcODw4cNq27atli5dqrCwMElSbGys6tWrpy+++EI5c+a8mjUCAAAAAIBr6F/NVtC9e3edOHFCW7Zs0bFjx3Ts2DFt3rxZ8fHxevLJJ692jQAAAAAA4Br6V+HA/PnzNW7cOJUsWdJZVqpUKY0dO1bz5s277McZP368ypUrp5CQEIWEhCgqKsrr/gkJCeratauyZ8+uLFmyqGXLljp06JDXY+zbt0+NGzdWpkyZlCtXLj399NNKTk72arN06VJVqlRJQUFBKlasmCZOnHhBLWPHjlWhQoUUHBys6tWr64cffvBafzm1AAAAAACQHv2rcCA1NVUZMmS4YHmGDBmUmpp62Y+TL18+vfzyy1q3bp1+/PFH3XHHHWrWrJm2bNkiSerVq5dmzZqlL7/8UsuWLdPBgwe9plFMSUlR48aNlZSUpFWrVumjjz7SxIkTNWjQIKfNnj171LhxY9WrV08bNmxQz5499cgjj2jBggVOm8mTJ6t37956/vnntX79epUvX17R0dE6fPiw0+ZStQAAAAAAkF55zMyu9E7NmjVTbGysPv/8c+XJk0eSdODAAbVv317h4eH6+uuv/3VB2bJl08iRI9WqVSvlzJlTkyZNUqtWrSRJ27dvV8mSJbV69WrVqFFD8+bNU5MmTXTw4EFFRERIkiZMmKB+/frpyJEjCgwMVL9+/TRnzhxt3rzZeY62bdsqNjZW8+fPlyRVr15dVatW1ZgxYySdCz/y58+v7t27q3///oqLi7tkLReTmJioxMRE53Z8fLzy58+vuLg4hYSE/OttdD0U6j/H1yXccPa+3NjXJQAAAADAFYmPj1doaOglz0P/Vc+BMWPGKD4+XoUKFVLRokVVtGhRFS5cWPHx8Xrrrbf+VcEpKSn64osvdOrUKUVFRWndunU6e/as6tev77QpUaKEChQooNWrV0uSVq9erbJlyzrBgCRFR0crPj7e6X2wevVqr8dIa5P2GElJSVq3bp1XGz8/P9WvX99pczm1XMzw4cMVGhrq/OXPn/9fbRsAAAAAAK6lfzVbQf78+bV+/Xp988032r59uySpZMmSF5yEX45NmzYpKipKCQkJypIli77++muVKlVKGzZsUGBgoDMbQpqIiAjFxMRIkmJiYryCgbT1aev+qU18fLzOnDmj48ePKyUl5aJt0l5bTEzMJWu5mAEDBqh3797O7bSeAwAAAAAA3EiuKBxYsmSJunXrpu+//14hISFq0KCBGjRoIEmKi4tT6dKlNWHCBNWuXfuyH7N48eLasGGD4uLiNHXqVHXs2FHLli27sldxgwoKClJQUJCvywAAAAAA4B9d0WUFb7zxhh599NGLXqcQGhqq//3vf3rttdeuqIDAwEAVK1ZMlStX1vDhw1W+fHm9+eabioyMVFJSkmJjY73aHzp0SJGRkZKkyMjIC2YMSLt9qTYhISHKmDGjcuTIIX9//4u2Of8xLlULAAAAAADp1RWFAz///LPuuuuuv13fsGFDrVu37j8VlJqaqsTERFWuXFkZMmTQ4sWLnXU7duzQvn37FBUVJUmKiorSpk2bvGYVWLRokUJCQlSqVCmnzfmPkdYm7TECAwNVuXJlrzapqalavHix0+ZyagEAAAAAIL26ossKDh06dNEpDJ0HCwjQkSNHLvvxBgwYoEaNGqlAgQI6ceKEJk2apKVLl2rBggUKDQ1V586d1bt3b2XLlk0hISHq3r27oqKinNkBGjZsqFKlSunBBx/UiBEjFBMTo2effVZdu3Z1uvN36dJFY8aMUd++ffXwww9ryZIlmjJliubM+b/R+Hv37q2OHTuqSpUqqlatmt544w2dOnVKnTp1kqTLqgUAAAAAgPTqisKBvHnzavPmzSpWrNhF12/cuFG5c+e+7Mc7fPiwOnTooD/++EOhoaEqV66cFixY4Ixj8Prrr8vPz08tW7ZUYmKioqOjNW7cOOf+/v7+mj17th5//HFFRUUpc+bM6tixo1544QWnTeHChTVnzhz16tVLb775pvLly6f33ntP0dHRTps2bdroyJEjGjRokGJiYlShQgXNnz/fa5DCS9UCAAAAAEB65TEzu9zG3bt319KlS7V27VoFBwd7rTtz5oyqVaumevXqafTo0Ve90JvB5c4veSMo1H/OpRu5zN6XG/u6BAAAAAC4Ipd7HnpFPQeeffZZffXVV7r11lvVrVs3FS9eXJK0fft2jR07VikpKRo4cOB/qxwAAAAAAFxXVxQOREREaNWqVXr88cc1YMAApXU68Hg8io6O1tixY7264gMAAAAAgBvfFYUDklSwYEHNnTtXx48f16+//ioz0y233KLw8PBrUR8AAAAAALjGrjgcSBMeHq6qVatezVoAAAAAAIAP+Pm6AAAAAAAA4FuEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALicT8OB4cOHq2rVqsqaNaty5cql5s2ba8eOHV5tEhIS1LVrV2XPnl1ZsmRRy5YtdejQIa82+/btU+PGjZUpUyblypVLTz/9tJKTk73aLF26VJUqVVJQUJCKFSumiRMnXlDP2LFjVahQIQUHB6t69er64YcfrrgWAAAAAADSG5+GA8uWLVPXrl31/fffa9GiRTp79qwaNmyoU6dOOW169eqlWbNm6csvv9SyZct08OBBtWjRwlmfkpKixo0bKykpSatWrdJHH32kiRMnatCgQU6bPXv2qHHjxqpXr542bNignj176pFHHtGCBQucNpMnT1bv3r31/PPPa/369Spfvryio6N1+PDhy64FAAAAAID0yGNm5usi0hw5ckS5cuXSsmXLVKdOHcXFxSlnzpyaNGmSWrVqJUnavn27SpYsqdWrV6tGjRqaN2+emjRpooMHDyoiIkKSNGHCBPXr109HjhxRYGCg+vXrpzlz5mjz5s3Oc7Vt21axsbGaP3++JKl69eqqWrWqxowZI0lKTU1V/vz51b17d/Xv3/+yavmrxMREJSYmOrfj4+OVP39+xcXFKSQk5NpsxKukUP85vi7hhrP35ca+LgEAAAAArkh8fLxCQ0MveR56Q405EBcXJ0nKli2bJGndunU6e/as6tev77QpUaKEChQooNWrV0uSVq9erbJlyzrBgCRFR0crPj5eW7Zscdqc/xhpbdIeIykpSevWrfNq4+fnp/r16zttLqeWvxo+fLhCQ0Odv/z58/+7DQMAAAAAwDV0w4QDqamp6tmzp2rVqqUyZcpIkmJiYhQYGKiwsDCvthEREYqJiXHanB8MpK1PW/dPbeLj43XmzBkdPXpUKSkpF21z/mNcqpa/GjBggOLi4py//fv3X+bWAAAAAADg+gnwdQFpunbtqs2bN+u7777zdSlXTVBQkIKCgnxdBgAAAAAA/+iG6DnQrVs3zZ49W99++63y5cvnLI+MjFRSUpJiY2O92h86dEiRkZFOm7/OGJB2+1JtQkJClDFjRuXIkUP+/v4XbXP+Y1yqFgAAAAAA0iOfhgNmpm7duunrr7/WkiVLVLhwYa/1lStXVoYMGbR48WJn2Y4dO7Rv3z5FRUVJkqKiorRp0yavWQUWLVqkkJAQlSpVymlz/mOktUl7jMDAQFWuXNmrTWpqqhYvXuy0uZxaAAAAAABIj3x6WUHXrl01adIkzZgxQ1mzZnWu3Q8NDVXGjBkVGhqqzp07q3fv3sqWLZtCQkLUvXt3RUVFObMDNGzYUKVKldKDDz6oESNGKCYmRs8++6y6du3qdOnv0qWLxowZo759++rhhx/WkiVLNGXKFM2Z838j8vfu3VsdO3ZUlSpVVK1aNb3xxhs6deqUOnXq5NR0qVoAAAAAAEiPfBoOjB8/XpJ0++23ey3/8MMP9dBDD0mSXn/9dfn5+ally5ZKTExUdHS0xo0b57T19/fX7Nmz9fjjjysqKkqZM2dWx44d9cILLzhtChcurDlz5qhXr1568803lS9fPr333nuKjo522rRp00ZHjhzRoEGDFBMTowoVKmj+/PlegxReqhYAAAAAANIjj5mZr4twi8udX/JGUKj/nEs3cpm9Lzf2dQkAAAAAcEUu9zz0hhiQEAAAAAAA+A7hAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALkc4AAAAAACAyxEOAAAAAADgcoQDAAAAAAC4HOEAAAAAAAAuRzgAAAAAAIDLEQ4AAAAAAOByhAMAAAAAALgc4QAAAAAAAC5HOAAAAAAAgMsRDgAAAAAA4HKEAwAAAAAAuBzhAAAAAAAALufTcGD58uVq2rSp8uTJI4/Ho+nTp3utNzMNGjRIuXPnVsaMGVW/fn3t3LnTq82xY8fUvn17hYSEKCwsTJ07d9bJkye92mzcuFG1a9dWcHCw8ufPrxEjRlxQy5dffqkSJUooODhYZcuW1dy5c6+4FgAAAAAA0iOfhgOnTp1S+fLlNXbs2IuuHzFihEaPHq0JEyZozZo1ypw5s6Kjo5WQkOC0ad++vbZs2aJFixZp9uzZWr58uR577DFnfXx8vBo2bKiCBQtq3bp1GjlypAYPHqx33nnHabNq1Sq1a9dOnTt31k8//aTmzZurefPm2rx58xXVAgAAAABAeuQxM/N1EZLk8Xj09ddfq3nz5pLO/VKfJ08ePfXUU+rTp48kKS4uThEREZo4caLatm2rbdu2qVSpUlq7dq2qVKkiSZo/f77uvvtu/f7778qTJ4/Gjx+vgQMHKiYmRoGBgZKk/v37a/r06dq+fbskqU2bNjp16pRmz57t1FOjRg1VqFBBEyZMuKxaLiYxMVGJiYnO7fj4eOXPn19xcXEKCQm5uhvwKivUf46vS7jh7H25sa9LAAAAAIArEh8fr9DQ0Eueh96wYw7s2bNHMTExql+/vrMsNDRU1atX1+rVqyVJq1evVlhYmBMMSFL9+vXl5+enNWvWOG3q1KnjBAOSFB0drR07duj48eNOm/OfJ61N2vNcTi0XM3z4cIWGhjp/+fPn/7ebAwAAAACAa+aGDQdiYmIkSREREV7LIyIinHUxMTHKlSuX1/qAgABly5bNq83FHuP85/i7Nuevv1QtFzNgwADFxcU5f/v377/EqwYAAAAA4PoL8HUBN7OgoCAFBQX5ugwAAAAAAP7RDdtzIDIyUpJ06NAhr+WHDh1y1kVGRurw4cNe65OTk3Xs2DGvNhd7jPOf4+/anL/+UrUAAAAAAJBe3bDhQOHChRUZGanFixc7y+Lj47VmzRpFRUVJkqKiohQbG6t169Y5bZYsWaLU1FRVr17dabN8+XKdPXvWabNo0SIVL15c4eHhTpvznyetTdrzXE4tAAAAAACkVz4NB06ePKkNGzZow4YNks4N/Ldhwwbt27dPHo9HPXv21LBhwzRz5kxt2rRJHTp0UJ48eZwZDUqWLKm77rpLjz76qH744QetXLlS3bp1U9u2bZUnTx5J0v3336/AwEB17txZW7Zs0eTJk/Xmm2+qd+/eTh09evTQ/PnzNWrUKG3fvl2DBw/Wjz/+qG7duknSZdUCAAAAAEB65dMxB3788UfVq1fPuZ12wt6xY0dNnDhRffv21alTp/TYY48pNjZWt912m+bPn6/g4GDnPp999pm6deumO++8U35+fmrZsqVGjx7trA8NDdXChQvVtWtXVa5cWTly5NCgQYP02GOPOW1q1qypSZMm6dlnn9UzzzyjW265RdOnT1eZMmWcNpdTCwAAAAAA6ZHHzMzXRbjF5c4veSMo1H+Or0u44ex9ubGvSwAAAACAK3K556E37JgDAAAAAADg+iAcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHA5wgEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcLsDXBQBuUqj/HF+XcMPZ+3JjX5cAAAAAuB49BwAAAAAAcDnCAQAAAAAAXI5wAAAAAAAAlyMcAAAAAADA5QgHAAAAAABwOcIBAAAAAABcjnAAAAAAAACXIxwAAAAAAMDlCAcAAAAAAHC5AF8XkN6MHTtWI0eOVExMjMqXL6+33npL1apV83VZgOsV6j/H1yXccPa+3NjXJQAAACCdIBy4ApMnT1bv3r01YcIEVa9eXW+88Yaio6O1Y8cO5cqVy9flAcBVR+hyIUIXAABwMyIcuAKvvfaaHn30UXXq1EmSNGHCBM2ZM0cffPCB+vfvf0H7xMREJSYmOrfj4uIkSfHx8den4P8gNfG0r0u44VyNfze264Wu1ueBbXsh3rPXxtXYrmWeX3AVKrm5bB4S7esSAAC4KaUdu5jZP7bz2KVaQJKUlJSkTJkyaerUqWrevLmzvGPHjoqNjdWMGTMuuM/gwYM1ZMiQ61glAAAAAAAX2r9/v/Lly/e36+k5cJmOHj2qlJQURUREeC2PiIjQ9u3bL3qfAQMGqHfv3s7t1NRUHTt2TNmzZ5fH47mm9d4s4uPjlT9/fu3fv18hISG+LuemwXa9Ntiu1wbb9dph214bbNdrg+167bBtrw2267XBdr1yZqYTJ04oT548/9iOcOAaCgoKUlBQkNeysLAw3xSTzoWEhPDhvwbYrtcG2/XaYLteO2zba4Ptem2wXa8dtu21wXa9NtiuVyY0NPSSbZjK8DLlyJFD/v7+OnTokNfyQ4cOKTIy0kdVAQAAAADw3xEOXKbAwEBVrlxZixcvdpalpqZq8eLFioqK8mFlAAAAAAD8N1xWcAV69+6tjh07qkqVKqpWrZreeOMNnTp1ypm9AFdfUFCQnn/++Qsuz8B/w3a9Ntiu1wbb9dph214bbNdrg+167bBtrw2267XBdr12mK3gCo0ZM0YjR45UTEyMKlSooNGjR6t69eq+LgsAAAAAgH+NcAAAAAAAAJdjzAEAAAAAAFyOcAAAAAAAAJcjHAAAAAAAwOUIBwAAAAAAcDnCAQD/yeLFi3XmzBlfl4F/wLizuNbGjRunxYsXKzU11delAMBNZ+TIkXrwwQd9XcZN7ZtvvvF1CTcEwgEA/9qKFSvUtWtXDRgwQAkJCb4uBxdhZvJ4PJKkAwcO+Lga3KzGjRunhx56SCtXriQguEYI+W5cF3vP8++Fqylv3ryaPHmyunXr5utSbko//fSTGjZsqCeffNLXpfgc4QCAf61y5cpq3bq11qxZowEDBtCD4AaTkpLiBAOvvvqqnnnmGUnuO2hNe72//fab/vjjDx9Xc3NJ27abN29W0aJF1aFDB61YsULJyck+riz9S9u2f/75p06dOuV8lnFjSU1NlZ/fucPp3377TUePHnX2vSkpKT6uDjeL++67T1988YU+/vhjPf74474u56ZTqFAhjR07VpMnT1aPHj18XY5PEQ7gpnCx1J5fr66t5ORkZcqUSUOHDtVdd92ljRs36vnnn1diYqKvS3O9Tp06aeXKlfL393dO0jZt2qQiRYpIclc4kNZzYvr06WrTpo1mz56t2NhYX5d10/B4PEpKSpJ0rktmWFiY+vbtq++++44To/8o7X17zz33qHz58nruuee0bt06X5eFv0gLBp577jnVq1dP9erVU5s2bZSYmCh/f/+b+nOQ9l2yZcsWzZkzR7t37+ZHgqvMzGRmCggIUNmyZfXSSy/p7bffdsJ+/HdmpvDwcP3vf//T8OHDNXnyZD377LO+LstnCAeQ7p2f2n/zzTeaOXOmNm/e7CzDteHv7y9J+vHHH5WQkKD9+/fr7bff1uDBg7nEwId+//13/f7772rVqpXWrl2rgIAASdLBgwcVFBQkSa76bHg8Hs2cOVP333+/7rvvPjVp0kRhYWG+LuumYWYKDAzU5MmT9dBDDylXrlxau3atunTpwiUG/9FPP/2khx9+WHfffbeaN2+uuXPn6sUXX9SyZct8XRrk/QPEV199pXfeeUfDhw/XAw88oN9++00VK1ZUQkLCTR0QeDweTZs2TbfffrseffRR3XHHHRo+fDg9tK4ij8cjj8ejr776So0aNdL69etVoEABvfzyy+ratauvy7sppIVcK1eu1I4dO5Q1a1a99NJL6t+/v48r8w33HCHippV2otOvXz+1aNFCvXv3VsWKFTV27FhOUq8hj8ejOXPmqEaNGsqSJYt69uyp2267TTNnztTAgQPZ9j6SL18+vfnmm7r99tvVpEkTrVmzRtK5SwzSwoG0X3qlm68XwYYNG7xuHzp0SEOHDtVLL72k3r17K1u2bDp69KimT5+ulStX+qbIm4jH49HKlSvVqVMn3XHHHRo5cqTWrVunkJAQPfTQQ/Qg+Jd+/fVXzZkzR71799bAgQP16quv6sUXX1R8fLxee+01AoIbQNqxxxdffKHjx4/rlVdeUZs2bdS3b1+NHz9egYGBqlSp0k0ZEKR9b+zdu1djx47Viy++qHXr1unBBx/UwoULNWzYMB08eNDHVd48fvnlF3Xu3Fm9evXS22+/rdWrV2vChAn68MMPGYPgKvDz89OsWbPUoEEDhYeHq0ePHnrggQc0fvx49erVy9flXX8GpFOpqanO/2/YsMEqVKhga9assb1799obb7xhHo/Hhg8fbqdPn/ZhlTen1NRUO336tDVp0sR69OjhLE9MTLQBAwZY8eLFrX///paQkOC7Il0oOTnZ+f9t27ZZq1atLGfOnLZ161Z78sknbdSoUXb69Gn7/fffLT4+3pKTk23jxo0+rPjqmj59umXLls1iY2OdZfHx8RYVFWVjx461Y8eO2cCBA6127doWERFhmTNntk8++cSHFd8cxo8fb5UqVfLa1yYnJ1uVKlWsZMmStmzZMjt79qwPK0xffv/9d6tSpYrlzJnTnn76aa918+bNszvuuMNatGhhixYt8lGFSPPrr79a/vz5zePx2Ntvv+0sT01NtR9//NEqVKhgZcqUuSmPQ3788Ufr06ePtW/f3k6cOOEsHzFihFWvXt2eeOIJO3DggA8rvHmsWrXKChUqZPv373eWnT592saNG2cej8eee+45H1aX/iUkJFjr1q2te/fuzrIjR47Ym2++aVmzZrX+/fv7sLrrj3AA6d4rr7xivXv3tieffNJredpOk4Dg2mnUqJE99NBDXsuSk5Otfv36liNHDnv88cftzJkzPqrOXVJSUpz/P3bsmJmZ7dy501q1amVhYWGWIUMGK1GihBUsWNCyZ89u+fLlszx58tjdd9/tq5KvibSD0YMHD5qZWWxsrLVo0cJq1aplwcHBdu+999q4ceNs9+7d1rx5c+vatasvy70pvPLKK1awYEHndtr+dvny5ebxeKxw4cK2cuVKH1WXPn300UdWokQJi4qKsp9//tlr3fz5861SpUp2//33893mYwkJCTZjxgwrV66cVa9e3WtdamqqrVu3zvLkyWP333+/jyq8drp3726hoaF2yy23eAWyZucCglq1almHDh3sjz/+8FGFN49ff/3VgoODberUqV7L9+zZY5GRkebxeKxXr14+qi79S05OtqioKHvwwQe9lh89etRatWplHo/ngnOMm1mAr3suAFfKzpuaTTp3LfXo0aN1++23KyEhQcHBwZLkjOb65JNP6sSJE3r++ecVGBjok5pvFmnbPjU1VampqSpUqJC2bt2qP/74Q5GRkfJ4PPL391e9evX022+/KSYmRnFxcc6/Ca6N88fdeOmll7R//3516NBBUVFRev755xUeHq7PPvtMXbt2VevWrXXw4EGlpqYqISFBNWrU8HH1V0faezNPnjzavXu3ihUrpokTJ6pDhw567bXXtH79ep04cUKtW7dWxowZJZ3rEp8lSxYfV57+tW3bViNGjFDfvn01YsQIZ/tmyJBBrVq10tGjR5UrVy4fV5m+dOjQQf7+/ho1apRGjx6tJ598UuXKlZMkRUdHKyAgQMWKFXO2Na698/ezaYKCgtSgQQP5+/urZ8+eql+/vjNXusfjUcWKFbVkyRIVK1bMFyVfU6NHj1ZoaKg+/vhjjRw5Uk899ZTCw8MlSU8//bTOnDmjFStW+LjK9Oevx7jSuWkMmzVrpg8++EARERG67bbbJEnZs2dXw4YN1aBBA1WrVs0X5d4U/P391bRpUy1cuFA//fSTKlasKOnc9q1cubK2bt2qhQsXKiYmRpGRkT6u9jrwbTYB/Ht//vmn8//Dhg0zPz8/+/DDDy9oN3LkSKtVq5bXZQi4Mmnb7ujRo3bq1Ck7evSomZnt3bvXsmXLZm3atLHff//dad+zZ08bNmyYHTlyxCf1ulW/fv0sR44c9sUXX3h15/z555+tffv2ljt3blu3bt0F9zv/coT0Ku09umrVKtu7d6/17t3bMmfObJMmTbqg7bFjx6x///6WI0cO27Zt2/UuNd1K28bbtm2zBQsWOJdxmZm98cYbVrRoUXvqqafMzJxLOB5++GEuKfgHadt07dq19sEHH9g777xjmzZtctZ/8MEHVqlSJXv44YdvqkuA0pvze2Z9/vnn9vzzz9uQIUOcXh1nzpyx2bNnW4kSJaxBgwYXfYz0vJ9Ne58mJiZaUlKS17qePXtalSpVbOjQoRf0IDj/OA2Xlradv/vuOxs9erT16dPH1q5da2fOnLE1a9ZYnTp1rGHDhvbpp5/ali1b7Omnn7aSJUtyrHUF0rbx8ePH7fjx487yNWvWWOnSpa1Lly5ex0m9evWyIUOGWHx8/PUu1WcIB5BunP/l/Prrr1udOnVsy5YtzrL+/ftbhgwZLnoNcdrOgIDgyqVtsxkzZliNGjWsdOnSVrZsWXvvvffMzOynn36y7NmzW61atezee++1tm3bWnBwsP3yyy++LNt1li1bdkH37fPf71u3brU2bdqYx+OxrVu3+qLEa27+/PmWLVs2mzVrlpmZPfXUUxYYGGhffPGF0+aLL76w+++/3woVKmTr16/3Vanp1tSpUy1XrlxWvHhxy549u1WtWtWmT59uZmZjxoyxHDlyWGRkpJUoUcLCw8MvGkbhnLTP57Rp0yxbtmx25513WsGCBa1hw4Y2fvx4p92HH35o1atXt9atW3t95+H669u3rxUoUMAaNmxozZo1s9DQUFu2bJmZ/V9AULp0aatQoYKPK7160t6n8+bNsw4dOljlypXt1VdftdWrVzttevToYZUrV7YXX3zRuawN/87UqVMtc+bM1qBBAytatKjlz5/fHn/8cTt27Jj98MMP1rFjRwsODraiRYtanjx5+B67Aucfz1arVs2KFy9uJUqUsPfee8+Sk5Nt4cKFVrZsWYuKirJmzZpZ69atLSQkxLZv3+7jyq8vwgGkC+cHAytXrrQRI0aYx+Oxtm3b2o4dO5x1/fr1s8DAQPvss88ueAyCgX9v/vz5FhgYaCNGjLDx48fbgAEDzOPx2IABA8zMbN++fda3b19r06aNPfDAA/zC5QMzZsywYsWK2YEDBy4Iw9I+P1u3brVnn302Xf+C9XdiYmLs8ccft1GjRnktTwsIJk+ebGbn3qtjx4613bt3+6LMdO3HH3+0kJAQGzt2rB09etSWLVtmjz/+uOXOndtmzJhhZmaHDh2yd955xz7//HPbtWuXjyu+8S1btswiIiLsnXfeMbNzPV8yZ85s5cqVs9dee81pN378eLv99tudsTRw/U2YMMHy5ctna9euNTOzzz77zDwejwUFBdns2bPN7FxAMHXqVGvXrp3XcUt6N336dMuUKZP16dPHnnnmGatdu7ZFR0d7DYrZu3dvK1KkiI0cOZLjrX9p586dVrhwYXv33Xed7+nRo0db3bp1rWvXrpaYmGjJycm2f/9+27Rpkx06dMjHFac/CxYssMDAQBs6dKhNnjzZ/ve//1nRokVtwIABlpKSYj/++KONHj3a7r77bnv00UddeTxLOIB0pW/fvpYnTx4bOnSodezY0bJmzWp33XWXV0CQduK6YMECH1Z680hNTbUOHTpY586dvZZPmjTJPB6PTZw40cz+r8vkX7sc4vp4//33LSQkxE6dOmVm3v8OixYtumBAuJspIPjhhx+sWrVqVrZsWecg/fwD86eeesoyZ87sXHbEgeu/8+6771rNmjW93ju7du2yxx57zGrXrs2J6xVKTk62F154wZ544gkzM9u9e7cVKVLE7rvvPrvvvvuscOHCNm7cOKf9X7ts4/qJjY21Pn362AcffGBmZrNmzbKsWbPaqFGjrEOHDpYxY0ZbsmSJmZ3rep/mZtjPbty40YoXL+4EWCdPnrRs2bJZsWLFrF69erZ48WKnbf/+/Qle/4P169db3rx5L+hx9cYbb1i+fPm4DO4/SE1NtbNnz1rbtm3tscce81o3YsQIK1SokH366adey2+Gz++/QTiAG9ZfR7n/4YcfLHv27M4XsNm5KQzDw8OtUaNGXt1+xo0bx3WuV8nZs2etdu3azhQvycnJzrbt2bOnRUVFWVxcnLMT5cTr2vq7X6P+/PNPK1GihDVr1sxr+cmTJy06OtpeffXV61CdbyQkJFiDBg2cKZ3S3p/nb6suXbpYrly5LC4uzldlpnsfffSR5cmTx3777Tev5XPnzrXQ0FDbvHmzjypLP9L2j2n7y99//902bNhgp06dsqioKOvUqZOZmW3ZssXCwsKsYMGC9sYbb3jdF9fexfaz69ats127dtn27dutWLFi9tZbb5mZ2ddff20ej8c8Ho99991317vUa+7nn3+27t272+nTp+23336zIkWK2OOPP25z5861iIgIq1evnhPK4sqd/7les2aN5cuXz3kfnR805cmTx4YPH37d67vZNG3a1B5//HEzM6/ptjt06GAVK1Y0M/a1fpceshC4/tq1a6cFCxZ4LUtOTlZwcLAKFCggSTp79qzKly+vuXPnasmSJRo6dKh27Ngh6dxMBQEBAUpOTr7utd9sAgICVLt2bc2ePVu7d++Wv7+/M5JuRESEUlNTlSVLFvn7+0vSBaPs4uo5f7Ts5cuXa/bs2Vq9erVSU1OVLVs2DRw4ULt371bdunW1fPlyTZkyRa1bt1ZMTIx69Ojh4+qvnaCgIM2aNUuNGjXStGnTNH36dJ09e1Z+fn5KTU2VJI0fP16bNm1SSEiIj6tNvwoXLqyMGTNq5syZiouLc5aXKlVKuXPn1qlTp3xY3Y3P/v8o5CtXrtTnn3+u33//XXnz5lX58uWd2TT69esn6dz3W5UqVdSiRQvde++9kti3Xi/n72ffe+89vfbaa5KkSpUqqUiRItqyZYty5cql9u3bS5LCw8P12GOPaezYsapevbrP6r5azEySFBcXp6SkJJUrV079+vVTxowZ9cwzz6hWrVoaNWqUGjVqpAoVKmj79u368MMPderUKee+uLS0bXX+57patWrKmzevnnzySZ08edKZYevUqVMqUKCA8uXL55NabwZp2zt37tzOjCJBQUFKSkqSJNWoUUMZMmRQUlKS6/e1hAO4IRUuXFiNGjWSdO4gSZIiIyN19OhRLVu2TNK5k1YzU7FixVS4cGFNnjxZAwcO9PpyCghgts4rkbbt4uPjdeTIEWd5mzZtVLBgQfXr10979uxxgoA//vhDYWFhSkhI8Em9bmJmzgHrM888o3bt2mnAgAG6/fbb9dRTT2n37t26//779frrr8vM1KpVKw0bNkwBAQFau3atAgIClJKS4uNX8d+lvUc3bdqkKVOmaP78+fr5558VFBSkadOmKU+ePBo+fLhmzpzpBARp92E6vcuTtr22bt2qFStWaM6cOZKk2rVrq23btnr++ec1ceJE7dixQydPntS4ceOUmJioggUL+rLsG1paMDBt2jQ1atRIu3bt0okTJ7zWx8XF6aeffpIkTZs2TZGRkRo0aJATiOP6SNvPPv300xoyZIhSU1O1b98+Z/2pU6e0evVqHThwQH/++adGjRqllJSUm+JHibT36ezZs9WtWzctWrRIycnJyps3rxITE7V9+3aVLVtWGTNm1NmzZ5UnTx499dRTeuutt5Q5c2bXn1RdrrTtvHr1ar388ssaNWqUpk6dKkmaMmWKTp8+rdq1a2v+/Plavny5hg8frp07dyoqKsrHlacfad9jx44d0/HjxxUfHy9JGjZsmFJTU3XHHXcoJSXFCWB+/vlnhYSE3BTHSf/Z9e6qAPyTv3blGzdunI0dO9a51nLAgAGWP39++/LLL502J06csG7dutnChQstKCjIa5RnXL7zR3G97bbbLH/+/NawYUMbNWqUpaam2qxZs6xu3bqWN29ea9++vTVt2tSyZs1qGzZs8HHl7vLyyy9b3rx5nTEEnn/+ecuQIYM99NBDXjNE/PLLL3bkyBHn3/Vmusxm6tSpliNHDitTpozlz5/f8uXL51wPe/r0aatfv75Vr17dPvvsM8bAuEJp75cvv/zScufObcWKFbPQ0FArV66cMyr7s88+ayVKlLCwsDCrXLmyRUREMGL2ZVi7dq3lzJnT3n///Qs+j7/99pvdc889VrRoUStVqpSFh4fbTz/95JtCYZ999plFRETY999/f8G6Y8eOWbNmzczj8dgtt9xiZcqUcfYzN0N35K+//tqCg4PtxRdf9PpOiY2NtSZNmli7du1s5syZNnDgQCtatKjFxMT4sNr0a9q0aZYlSxa74447rGLFihYYGGhdunSx1NRUO3DggNWpU8cKFSpkBQsWtDJlyrCPvQJpn8Pp06dbnTp1nFlgXnzxRTMzW7FihRUrVswKFy5sbdq0sXvvvdeyZMniTE3qdoQDuKE1bdrUihYtahMnTrTExET77bffrEuXLhYeHm79+vWzt956y+644w6rUqWKJScnW+3ata1bt26+LjtduNhBzPz58y0oKMgGDx5sn376qXXo0MEqVapkXbt2tdTUVNu2bZu9+OKL1qJFC+vRowfTal0H5wdm+/fvt9atW9ukSZPMzOyrr76ysLAw69Kli2XJksXat29/0ROK9D5q9vn1p40zMn78eDtx4oRt3LjRnn32WfPz87N3333XzM6NV1K9enW7/fbbXTU38dWyZs0aCw0NtYkTJ9quXbvs4MGDdvvtt1vx4sWdUOrHH3+0r7/+2qZNm3bBGATwlravfeeddywqKspOnDjhrDv/vb1792775JNP7NVXX2UqWB9JGwuiX79+1rZtWzO7cNYXs3PXKk+bNs2+/PJL5z43QwC7f/9+K1eunDOewl999tlnVrNmTcuXL58VK1aMqUr/pV27dlm+fPlszJgxZmYWFxdns2bNspCQEOd6eLNzMwzt2LHDDh8+7KtS06158+ZZUFCQvfLKKzZ27FgbMGCAZcmSxXr27GlmZsePH7fevXtbp06d7Iknnrhpp3j+NwgHcMP4uxOYBx54wG699Vb78MMPLTk52Q4fPmyjR4+2okWLWvXq1a1JkyZOal+3bl0bNmzY9Sw73Ur7sklJSbGUlBRLSEiw+++/33r16uW0SUhIsDFjxljFihVt7NixvirVtf4aDJiZzZ492+Li4uyHH36wAgUK2JtvvmlmZi+88IJlyZLF7rvvPtu5c6dP6r3avvrqK+f/07bFtGnTrHLlys6sDGbnftEaMGCAFStWzBnNOSEhgZPWy/Ddd9/Z77//7rXsww8/tMqVK9vJkye93oO1a9e2ypUrX+8S06UjR47Y1q1bvQbW7du3rzPglZn353vt2rWcAPjIzz//fEEPgf/9739Wv379C45LEhISbO7cuRc8Rnod1fyvr2/Pnj1WsGBBW758ubPsrz8k/PHHH/bLL7/QY+Ayvf322xeceP74449WtGjRC2Z2+Prrry1TpkwM8HiF0gZuTHs/nz171jp16uQMpG127keDKVOmWNasWW3kyJFe978ZevxcTYw5gBvC+QMAbdiwQb/++qsOHDggSfrkk09UuXJlDR8+XJ988omyZMmi7t27a8OGDVq1apVmzZqlDBkyqF+/fvr111/Vpk0bX76UdGHKlCmqVauWNm3aJD8/P/n5+SkoKEjHjh3T0aNHnXZBQUH63//+p6JFi14wQCSurWnTpunrr7+WJD311FPq3LmzUlJSVK9ePYWEhGjWrFmqUKGCHnnkEUnnxteoWrWqUlNTVaRIEV+WflXs3btXLVu2VMuWLSX933XA/v7+2rZtm/bv3y/p3HWFoaGhatasmU6cOKE///xT0rn3Ltdq/7NVq1apQYMGev/99xUTE+MsP3TokP78809lzpxZfn5+On36tCTp/fff16+//qoVK1b4quR0YevWrWrevLnGjh2rbdu2OcvvuOMObdq0SdOmTZP0f+/phIQEffbZZ1q2bJkzgCauj0mTJunhhx/W22+/rV27djnLb731Vm3cuFE//PCD1zhGp06d0tixYzVz5kyvx0kbhyc9+e233/TRRx9pw4YNzrIjR47ojz/+UKZMmSSdG/MpbRyBn376SXPnzlW2bNl0yy23KCIiwhdlpytnzpzRq6++qmbNmmnnzp3O8qxZs2r//v3avHmzV/uaNWsqb968OnTo0PUuNd16//33VbRoUcXFxXmNMbR9+3bFxsY67YKDg9WkSRN16tRJq1at0pkzZxhA828QDuCGkHaQ1K9fPzVv3lxVq1ZVz5499dVXX0k69wVeuXJlvfLKK5o8ebLi4uKUJUsW+fn5af369erVq5c+/fRTzZo1S8WKFfPlS0kXMmfOrEKFCqlLly7Ol1NSUpIKFSqkAwcO6NChQ85BakBAgOrWrau9e/d6DaCFa8fMtHTpUrVu3VrNmjXTu+++q5EjR8rf31/BwcGSzh3EJSUlOf8ma9as0ZNPPqkvv/zSa5T+9KpgwYKaP3++Vq5c6RX4FS9eXKVLl9ZHH32kAwcOOAeuRYoUUbZs2Rgx/zKkHRDVrFlTffr00Ycffqj3339ff/zxhySpVatWio2N1XPPPSdJzonCmTNnlCNHDoWGhvqm8HRg06ZNuu2221SlShW1adNGFStWdNZVqVJFHTp0UN++fTVlyhRJ0tGjR/XSSy9p0qRJqlixovNdiGvvww8/VJcuXfToo49q4MCBKlq0qLOud+/eKlGihNq2bat58+Zp9+7d2r17t9q3b68///xTjRs39mHl/92mTZsUHR2tWbNmOZ97SapataruvPNOPfLIIzp06JAyZMjgrPvwww81Y8aMdP/dcj2kbaOMGTNqzZo1yp49u5o1a6ZffvlFkpQvXz7nu/3777937pc9e3Zlz57dGYgbl1atWjVlzZpV9erVU3x8vDwejwICAtS4cWPt27dPGzdudNpmzJhRuXPndoKatOMHBtL8C192WwDO78qzePFiK1KkiC1dutQmTpxo9913n1WtWtU+/fRTp80DDzxg4eHhXl2u4uPjbc6cObZ3797rWnt6k9bdKq371eLFi61x48ZWrVo1ZxCWbdu2WdasWa1jx4528OBB576PPPKI3X333V5zwuLaOL976q233moBAQE2atSoC9pNmzbNgoODLSoqyooXL26lSpVyrnlN713kzp8LfuHChRYWFmatW7d21g8dOtRKlixpTz/9tG3YsMEOHz5s/fr1s3z58tmBAwd8VXa6kLYfOL8767Bhwyxfvnw2bNgwZ/u9+uqrVrRoUXvmmWfMzOzo0aP2/PPPW7FixeyPP/64/oWnAzExMVa+fHkbMGDABevS3tO//fabde3a1fz9/a1EiRJWrlw5y5MnD4ONXWdr1661/PnzO+O3nO/48eNmdu6zcu+991rBggUtJCTEKlSoYNWrV3cuY0yvlxJs3brVwsLCrH///rZv374L1i9cuNBq1qxppUuXtqVLl9rMmTOtT58+FhYWZhs3bvRBxelL2j52y5YtNnnyZDM7t/+sVq2alSxZ0hlPZM6cOVa3bl2766677IsvvrCffvrJ+vTpYzly5LjgcgN4S9vGJ0+eNLNzx67ly5e3smXLWlxcnJmdex+XKVPGnnzySa+Bs7t162ZNmjTxujQR3ggHcEP46quvrEuXLjZ8+HBn2bp166xDhw5WpUoVr4Bg8ODBzpdyej8Jul7SdqTr16+3u+++2zkgWLBggd19991WrVo15+D0u+++s5CQEKtdu7Y1bdrU2rdvb1myZGFWguvg/PDl119/tejoaGvTpo0FBwfblClTnHXnj8T73HPP2aBBg5xgIL0esJ4v7fUdPXrUzM69T7Nly2YtWrRw2rz44osWFRVl/v7+Vr58eU6wLkPafmDDhg3m8Xjsiy++cNalBQRDhw6148ePW2xsrL3++usWHh5uuXPnttKlS1tkZCQDkP2DlStXWoUKFZxxL8zMfvrpJ3v33XftrrvuskcffdQ56F++fLm98cYb9vnnnxNs+8Ann3xiNWvWtNOnTzvL5s6daz169LBbb73V7r//fvv111/NzGzVqlU2c+ZMW7x4cboffPDUqVN27733el2LbXbue+PAgQPO2DabNm2yZs2aWVhYmN16661WvXp1Zs+4DGn72J9++skyZszodW370aNHrWrVqla8eHFnXKB58+ZZ+/btLSgoyEqUKGElSpTge+wSzv8eq1u3ru3YscPMzoUx5cuXtzJlyjgBwaeffmply5a16tWrW9OmTa1169bMsnUZCAfgc7t27bI6depYWFiY9enTx2vdunXrrGPHjla9enVnqrI0N8NJ0PVw/o40MDDwgm08b948JyBI22H+8ssv1r9/f2vXrp117dqVWQmug0WLFlmXLl3MzKxLly7WtGlTJ9nu0aOHBQUFeU3haWYXDCSXXg9YL2br1q1WuXJlW7t2rZmd+xXgrwHBb7/9ZosXL7YlS5ZcsC3g7fyD1ixZsjg9As4fkGzIkCGWN29eJyAwMztw4IC9++67Nn36dE5iLyFt+se0A/8PPvjA6tataxUrVrQ777zTKlWqZIUKFWKgzBvARx99ZLfeequtXr3azMy6d+9ut912m9WsWdOeeeYZy58/v912220XvW96PvZISEiwmjVr2ttvv+0sW7hwodMzoEiRItayZUtn3bZt2+zQoUN27NgxX5Sbrpx/rJUpUybr37//BW3+/PNPq1atmt16663OfiI5Odn27t1rO3fudAJxXNz52zhDhgw2cOBAr/VpAUGpUqWcgODbb7+1N99805o2bWq9e/fmePYyEA7gurvYr/0LFiyw+vXrW9GiRW3RokVe69avX29Nmza1hx9++G/vj4u7nC8rs3NTGP61B0F67zqZniQnJ9uQIUOsatWqVrVqVQsPD7ft27d7tenZs6dlzJjRPv30Uztw4IA1b97c7rvvPjO7OT8TP/zwg9WtW9deffVVMzsXfCxcuNCyZ8/udfCKS0t7f2zatMkyZsxoQ4YM8Vp//kjaQ4cOdQICApcrc/r0abvlllssb968VqVKFQsODrbBgwc7+9QVK1ZYZGSkff3112Z2c35u04t169ZZ7dq1rVixYpY3b14rWLCgvffee85lNevWrTOPx+NM3XmzOHr0qBUpUsR69uxpu3fvtldeecVKlixp9957r40cOdLGjh1r+fPnv2h4iEvbuHGjhYaGOtsvzffff2+HDh0ys/+7xKB48eJMWXoF0t6LP//8s2XMmPGCYCBNWkBQunRpJyAwO7e/ZZ97eQgHcF2d/0Vz+PBhr+vdVq5caY0aNbIGDRrY4sWLve63Y8cOvqT+pX379llAQIATDKSd7A8dOtRGjx7ttEu7xKBmzZpe3drYmV4/0dHR5vF4rF27ds6y88OZp59+2jwej5UuXdpKly7tBDg3g7T32fnTY40cOdJCQ0Od7r1JSUm2cOFCi4yMtLvuussndaZXR44cscKFC1u1atW83lPDhw+3Jk2aeI0jMHToUCtcuLA988wzTFd2mdK2aXx8vD3zzDP2zDPP2M8//+zVm2fbtm1WqlQpW7p0qa/KxHlWrlxpn3zyib366qsWGxvrtW7BggVWsWJF27Vrl4+qu/rS9rEzZswwj8djBQsWtMyZM9u4ceOck9QzZ87Y7bffbo899pgvS013UlNTLTk52cqXL29BQUFex7aDBw+2fPnyefW8Onr0qNWsWdMiIyOd7zdc2u7du83j8dhTTz3ltXzEiBH2ySefOLfTAoIKFSo4veBw+QgHcN2cf5L5wgsvWNWqVa1w4cJWtWpVmzFjhpn93yB5DRo0sCVLllzwGAQEV27RokVWtGhRa9CggfNv8NJLL1lISIjNmzfPq+3ChQvttttuszvvvNMZuBDXXkJCgsXHx9ugQYOsR48edtttt1nXrl0tPj7ezMwrBPj2229txowZ6f7a14tZuHCh5c6d2/r16+csu++++6xGjRp24sQJMzt3EjZ79mwrUqQIv2xfgZSUFHv44YetZs2a9vLLL5uZ2euvv25Zs2a1BQsWOG3SDBgwwEqXLk031ytwqV5WzzzzjFWoUIEBHX3sUoH3mTNn7J577rF77733pjvmSHvtO3futFWrVtnhw4e91icnJ9u9997r9C7ix4Ers2vXLouIiLC77rrLYmNjbfjw4ZYzZ06bM2fOBW2PHDlid955J+HAFdi4caMFBwfb/fff7/QKeOWVVywgIOCCXsdbt261AgUKWK1atXgfXyHCAVx3gwcPtoiICJsyZYodPXrUSpcubaVKlXIGalq0aJE1bdrUKlasyOBXV0FSUpItWLDAypQpYw0bNrQXX3zRcubM6RUMnL/jXLJkyUVHMMbV9f3339uKFSsuum7o0KFWo0YN69q1q3NSnJqaesG1cjfbJR+zZ882j8djfn5+Fh0dbV999ZVNnTrV2rRpY6NHj/YaiJSRhi9f2glOcnKyPfHEE1ajRg2Ljo62sLCwC96D558MHTly5LrWmZ5cSSj366+/2lNPPWXh4eEMhHWdXc7Jfdr334kTJ2zp0qXWqFEjK1OmjBPK3qwBwV8lJSXZs88+a3nz5nWuh8flS9sn7Nq1y8LDwy1v3ryWI0cOJ3y92Ha/2d5b18PatWste/bs1qFDBxsyZIhly5btgmAgzfbt22+q3j/Xi8fs/094DFxjKSkp+vPPP9WsWTP16dNHLVu21OLFi3Xvvffq1Vdf1WOPPea0nT17tpYtW6ZXXnmFeZ//AzOTx+NRcnKyFi9erIEDB2r9+vWaO3eu7rrrLiUnJysgIMCrLa69NWvWKCoqSqGhoWrTpo0aN26s6OhoBQYGSpKSkpL0yiuvaP78+SpVqpQGDBig//3vf8qUKZNmzJjh4+qvnr++5xISEvTiiy8qODhYv//+uxISEvTHH38oLi5ORYsW1ZgxYxQWFua7gtOx1NRU+fn5KSUlRb1799akSZPUrFkzTZgwQQEBAV7/Fmlt2Sdc6MiRIwoLC1OGDBm0ePFihYeHq1KlSn/b/tVXX9WUKVMkSe+9957KlSt3vUrFeWbPnq2KFSsqT548F31PJyUlqX///tq2bZsyZsyoKVOmKCAgwOs7Mj05dOiQDh06pKJFiypz5syXbD958mStXr1an3/+uebPn6+KFStehypvPikpKfL399fevXtVp04dhYeHa9asWSpQoIAkjrOulrVr1+ree+/VwYMH9dVXX6l58+a+Lunm4rtcAm6QmJjo9Qvf3r177ZZbbrGEhASbP3++ZcmSxcaPH29m5+YrHT9+/AXX/pGsXh1JSUk2d+5cq1Chgt1+++03Zbf09GLdunXWuHFj++abb6xLly7WqFEjK126tC1atMgZiDAxMdFef/11K1++vOXOnduqV69+U17q8e2331qjRo1s69atlpKSYnPnzrUGDRrY9u3bbefOnTZ06FDz9/c3j8dzwUB6uNA/dZ9M+8ynpKRY9+7drVq1avbyyy87vVPY1/6zw4cPW4MGDezZZ5+1zz//3Dwez0W7C5/vyJEj9vnnn3MJjI+kpKTYzp07zePx2OzZs/+x7bp16+zbb791Pgfp9btxy5YtVq1aNXvggQcuq6fKxo0b7bbbbrNmzZoxkvtVkLaf3b17t2XLls2io6MZePAaWL9+vUVERNh99913wXkD/hvCAVwzU6dOtRYtWljFihVt6NChzvJq1apZy5YtLWvWrPbuu+86y3fu3Gm33XabzZo1yxflpmtpBzOXOrg/e/aszZ8/38qUKWN16tTx6m6M6+uOO+6wxx9/3MzODcL33HPPWZ06daxUqVI2duxYZyC4gwcP2rfffnvThTnnj6BfvHhxq169ug0YMMBOnTplAwcOtAoVKjjdeufNm2f33nsvB66X6Z+mHUt7H6VdYlClShUbMWKEM74F/l5cXJw988wzdsstt1iGDBns/fffN7O/339yneuN49FHH7U777zT/vzzz8tqn16Dsk2bNjnTQq9ateqy73fgwAEGbrsMae+LhIQES0xM9Arsz/+8p+0Tdu3aZdmzZ7fGjRvbtm3brm+x6dTfffYutj/94YcfnBmMCAiuHsIBXBMTJkywkJAQ69Wrl/Xs2dP8/f1tzJgxZmY2evRoy507tzVv3txpf/r0aWcgQk5Ur0zajvS3336zjz/+2H7++ed/bJ8WEFSoUMHKlSuXbg+C0qu07b1p0ya7/fbbbfny5c66yMhIq1atmkVGRlqdOnWsadOmlpCQ4Ky/GT4bf3fC9PLLL1v9+vWtWLFiNmPGDKtXr569+uqrXgdjuLTjx49bzpw5/7GXxfkBwZNPPmnFihWzN954g5PZf5AWyi1ZssTCw8OtQIECNnjwYKZ8vcH89T2c9u82depUK1OmjPNL+s3473X48GGrXLmyDRgw4IJ1iYmJXsEyn/Url/ZdtG3bNmvfvr1Vq1bNOnbs+Le9h87vQeDxeKxVq1Y31QxD10LaNo6JibElS5bYN9984zWA698FBJGRkdagQQOvqQvx76W/C6lww3vvvffUvXt3TZkyxbkO6NChQ0pJSdGJEyfUvHlzbdu2TStWrNDdd9+t/Pnza9u2bYqNjdW6devk7+/vXPOKf5a2nTZv3qzWrVurYsWKCgsL+8frWgMCAnTnnXfqhRde0Msvv6z9+/erYMGC17Fqd0t7X+fMmVMpKSnaunWrateurfLly6to0aL67rvvtHv3bs2cOVPLly/3ut7V39/fV2VfFfb/r7f87rvvtGjRIiUnJ6tEiRJ68MEH1a9fP7Vr106jRo3SAw88oMyZM+v48eNq2bKlChUqpKCgIF+Xny6EhYXp6aef1nPPPadMmTKpT58+F7Tx9/d3ro197bXXFBgYqHvuuYdrYf9BQECAPv30U7322muaMmWKvvvuO82dO1cJCQkaOnSoAgICnG0K30l7Dy9cuFDFixd3vttatmypkSNH6vnnn9f06dNvyn+nQ4cOKTU1VW3atHGWrV27Vj/88IM+/vhjlSxZUs2aNdO9997LZ/0KpR1r/fzzz7r99tvVoEEDlSpVSkuWLNHPP/+sTJky6fbbb/e6T9p+tnDhwtq9e7cSExOVIUMG37yAdCBtG2/atEmtWrVSSkqKdu/erfr166tv376qX7/+Rd+3VatW1VdffaUHHnhA8fHxCgkJ8UH1NxlfpxO4uXz77bcXvTa4fPnyVrZsWcuSJYvdfffdNmTIEJsyZYrdc8899tBDD9mgQYOcVPtm6TZ9raUlqFu2bLGwsDDr27ev7dmz56JtL9Y74OzZs3by5MlrWSIuYerUqZYtWzbLkyeP1a5d2w4dOuSsO/+XrZvpV65p06ZZ5syZrWHDhlanTh3z8/OzBx980Ou1z50715o0aWI5c+a0AwcO+LDaG9/FfklJTU21t956y/z8/GzkyJF/e9+b6X11raRt36NHj1qJEiXs9ddfN7Nzlxj079/fqlWrZgMHDnS25Ycffmjr16/3VbmwczMeValSxUJDQ+311193pkWeO3euRUVF2erVq31c4bWxcOFCCwwMtK1bt5qZ2XvvvWe1atWyqlWrWosWLezOO++0kiVL2g8//ODjStOnrVu3WsaMGb0uk125cqWFhITYc88997f3Yz97aWnHqD///LNlypTJBgwYYD///LPNmDHDsmXLZi1btrzkpW9nzpy5HqW6AuEArqpffvnFateubffcc4+tXbvWzMxatGhhxYoVs8mTJ9u8efOsVKlSVqFChYsO0MRO9MqcPHnSmjVrZr169fJanpycbEeOHPGaP5duhDeeo0eP2h133GF169b9x+vEbxZ79+61QoUK2dixY51lK1assLCwMOvUqZNX24MHDzKV3iWkHVD9+eefXl0vzc593t944w3zeDz/GBDg0r755ht76qmn7NFHH7WTJ0862z0+Pt6eeeYZq1GjhrVu3dr69OljHo/HduzY4eOK3WXZsmXOWALDhw+3zz77zPbu3Wuvvfaa3XbbbVakSBF77LHH7IsvvrDChQvbW2+95eOKr67zv9sbNGhgGTJksEqVKllgYKANHTrUmRJ6zZo1FhERYZ9//rmvSk23Tp06ZbVr17YCBQrYxo0bzez/fshq0KCBPfbYY74s76awc+dOy5Ili3Xu3Nlr+ciRIy0kJORvf/zC1cdlBbiqbrnlFr3//vt68sknNXjwYMXGxurMmTNatGiRChUqJEnKlSuXqlSporVr1ypv3rxe978Zu/pdSx6PRwcOHFDTpk2dZYsXL9aiRYv0wQcfKDg4WI0bN9b48ePl8XiYRuc6+uulMRfrcpw9e3bVqVNH7777rjPd1M1ySc348eNVsmRJ1alTx3k9Z86ckZ+fn2677TZJ517rbbfdpunTp6t+/fpq1qyZmjVrJknKnTu3z2pPL/z8/LRr1y7dcccdSk1N1RNPPKGcOXPqwQcfVEBAgHr06CF/f3/17NlTqamp6tu3r69LTneSkpK0dOlSvfnmmypevLjzOU1KSlLWrFk1YMAA5ciRQ4sXL9bq1av1008/6dZbb/Vx1e6xZ88ePf300woLC1ORIkX09ttva8uWLSpYsKB69eqlVq1aac+ePerTp49iY2O1d+9evfjii6pfv75KlCjh6/L/k7T96aFDh5QjRw5lypRJCxcu1Ouvv66kpCR99tlnXq8xb968yps3r7JkyeLDqtOnTJkyqWfPnho1apSGDx+url27qlatWtq7d6+WLVumdu3a+brEdG/Xrl1KTExUSEiItm/f7rx3c+TIobCwMKWkpPi4QhfxdTqBm9Mvv/xi9evXt9DQUJsyZYqZnfuVKzU11datW2elSpWy7777zsdVpj9/vTxgz549VqpUKRsyZIjt3r3bXnvtNStTpow1a9bMhgwZYmPGjLHg4GB+OfSh995776KD5KT92pOYmGjlypWzp5566nqXdk2kva7ixYtbgQIFbOXKlc779tdff7WAgACbNm2amZ17P6ekpNjp06etYsWKNmrUKJ/VnZ6cvx+YOHGi5cyZ0/z9/a1Ro0ZWvHhxK1asmNWvX9+++OIL+/HHH+3DDz80j8djb7/9tg+rTr92795tQ4YMMY/HY6NHj3aWnz8YYWpqqjMlJK69+fPnO/8/a9Ysi4iIsIwZM9rSpUvN7MIBTE+ePGmrVq2yvn37WrZs2WzixIlmln57K27dutVatGhhZcqUsYCAACtfvrz169fPWX+xSwmfeeYZK1WqFJdqXaa077LzL3WdNm2aVa1a1R5++GH76quvrECBAta1a1dflZiupb1Hz5w542zryZMnW758+ex///ufHT161A4fPmw5cuSwgQMH+rJU1yEcwDXz66+/WnR0tDVq1MhrRPYmTZrY7bffzij5/9LevXtt0KBBzu3XXnvNMmbMaAULFrTMmTPbmDFjnG6tCQkJVq9ePevSpYuvynW1ffv2WbFixZwTiotd2nH27Fm799577eGHH77e5V11f/1M161b14oUKWIrVqxwTqQ6d+5s1apVs2XLlnm1rVmzpnM9Ny5tx44dNnHiREtISLC33nrL7rzzTnvggQcsNjbWvvzyS+vUqZPdcsstlitXLmvYsKHlzJnTPB6PffTRR74u/YaW9hk9efKk18n+sWPHrF+/fpYxY0abMGGCszy9nlymZ2+99ZZFRUU5J23fffedFStWzMqXL29NmjRxxi9JW//X/W737t2tZMmS6fZSu40bN1poaKh17drV3nvvPfvqq6+sWbNmFhgYaHfffbfX9Hpm567j7tOnj4WHhzuzNeDvpX2PJSUlWWpqqv3yyy9e4zN9+eWXVqVKFcuSJYvXrFvsC67ctm3b7MEHH7TFixc7n8cvvvjC8uXLZ+3bt7fcuXN7hS+cN1wfhAO4pn755Re766677O6777YVK1ZYixYt7NZbb3VOFPigX5nU1FQbOXKkFSlSxOuX5lWrVtny5csvuO44ISHBGjVqZMOHD7/epcLOHZy2adPGmjZt+o/tDh065BxYpNcD1rTP8p49e+ytt95yxruoXr26FS1a1OkptHLlSmvevLlVrFjRPv30U1u6dKk9/fTTli1bNq8xMnBxqamplpycbA899JC1bdvWzM5NX/jmm29a6dKlrVu3bk7bXbt22Y8//mhPPPGERUdHW0BAgG3ZssVXpd/w0j57s2bNsrp161qZMmWsVq1aNm3aNDt58qTFx8fbgAEDLGvWrPbOO+/4uFr3OnDggLO/THs/Hz582KZNm2a1atWyu+66y2uAU7Nz14yn+f77761ixYq2b9++61f0VXL48GGrWLGi9e/f/4LlY8aMscyZM1ubNm2c5R999JFVr17doqKinGvl8ffO7+XWvXt3K1u2rGXIkMHKlStnvXv3dtrNnDnTKlasaO3atbPvv//eV+WmW6mpqXb69GkrWbKkeTweu//++23FihVePQhy5sxpJUuW9PrOSq/HR+kN4QCuuV9++cUaN25sGTJksOLFizvBALMS/Dt//vmnDRs2zCpXrmw9evRwlv81aDl79qwNHDjQ8ufPb7t27brOVbrP3wVdW7dutWzZstmnn356yful118e0l7Dxo0b7dZbb7V7773Xvv76a2d99erVrXDhwrZq1SozM1u9erU9/vjjFhwcbCVLlrSyZcsywvsVGjVqlJUpU8a5ZCU+Pt5Gjx5t5cqVu2Bwx7QDKjcMevlfzZs3zwIDA23gwIH27rvvWrNmzaxEiRI2fPhwO336tB05csSee+4583g89uGHH/q6XFd5/vnnvW4vWrTIPB6P1yUCn332md12223WuHFjO3z4sJmZPfLII86lTGZmTz31lIWHh9vRo0evW+1Xy/r1661MmTK2adMm5/sibf8bGxtrw4YNs0yZMjn734MHD9q8efPs4MGDvio53Th/xPwCBQpY586dbfjw4TZv3jy75557LFu2bFavXj2n/dSpU61q1ar2wAMP2IoVK3xVdro2YsQIy5cvn+XMmdPq169vK1eudL6vvvrqK8uXL589/vjjtn37dh9X6i6EA7gutm3bZt27d2e6wiv0dyecx44dsyFDhlilSpW80uw0s2bNsu7du1vOnDk56boOzk+z586da/v373eWnThxwjp06GCPPvqomd28vWW2bdtm4eHh1r9//4te01qzZk3Lnz+/ExCYmf3+++924MABTlqvQNr7Z+bMmVa4cGE7ffq0sy4tIChfvrzXiM9p3Yz51eWfnTx50u65554LZn/p16+f3XrrrTZnzhwzO3dp17BhwzhgvY62b99uAQEB1rBhQ2fZrl27rGfPnhYeHu4VEEyaNMlq165thQoVsttvv93y5s3rdczxyiuvpNvp/D788EMLDg52bv/1M717924LDQ21ESNGXO/S0rW0/eqGDRssc+bM1q9fP6+p8WJjY+3111+3sLAwr0sJZsyYYbfccos98sgjTKV3BdKCrZ9++skeeeQRmzlzppUpU8Zq165tq1at8rrEoFChQvbggw/aL7/84suSXYVwANcdwcDlSds5bt++3d58802bO3eunT171hlo6ejRozZs2DArX76818Hs4sWLrVKlSnbPPffQhfg6OP9k/7vvvjOPx2O1a9e2du3aOd1WlyxZYoGBgTdtt84zZ85Y69atLxiYKSkpyXbv3u38gnfXXXdZ/vz5beXKlU4PIvyztPfX6dOnvQ4+T506ZbfeeqstXbrUudTA7P8CgsqVK9t9993nk5rTi+PHj9uuXbu8elbVqVPHGdjt/EHtoqOjrX79+s7t9NrLJz1btWqVFSxY0OvfYe/evfbUU09Z1qxZnYAgJSXFli9fbs8995z16tXrpvpRYsWKFRYcHGxTp0792zYVK1a0nj17Xseqbg579+614OBg69Onj5nZBe+b+Ph4e/bZZy1nzpxePVHmzp1ru3fvvv4FpyPnj+Pw1x9I7rzzTuvWrZudOnXKSpUqZXXr1vXqQfDxxx9b6dKlL7hsFtdO+p8vC+lOQAAzaF4Oj8ej2NhY1ahRQz179lS7du1UuXJlderUSVOnTtWZM2c0cOBAtWzZUuvXr1fPnj0lSXfccYc+++wzTZw4UaVKlfLti7jJmZkzTV/Xrl31wQcfaOPGjXrooYd08OBBRUVFqWPHjjpz5oyaN2+ucePGKSkpycdVX30BAQGKiYnxmjZrwYIF6tu3rypUqKBKlSqpdevWmjdvnkqXLq27775b69at82HF6Yefn5/27NmjWrVqqW7duho8eLDGjx+vlStXKjExUYcPH5bH45G/v79SU1OVNWtWderUSffdd5/++OMP/fHHH75+CTekzZs3q2nTpqpbt67q16+v7t27S5KKFCmib7/9VpIUFBTkfF5vv/12JSYmKjk5WRLT7l4v9erV05IlSyRJUVFR+vzzz7V9+3Y1aNBAklSwYEF1795djz32mLp3766PP/5Yfn5+ql27tl544QW99tprCggIUEpKyk1x7FGoUCGFhITo448/1m+//eYsT01NlSQdP35cGTNmVOXKlX1VYrqTtu2+++475cmTRzExMUpISPB635iZsmbNqq5du8rMtGXLFuf+jRo1UuHChX1Vfrrg5+enrVu3qmPHjnr99dd19OhRZ93YsWO1evVq7du3T998840OHjyogQMH6vvvv5eZ6cEHH9Tq1asVGRnpw1fgLoQDwA0sLCxM/fr1U44cOdSpUyfVq1dP4eHh6tKli2rVqqV27drp1KlTKlKkiBYvXqxevXpJkkqUKKHw8HAfV3/z83g8kqTff/9d33//vTp06KAyZcro4Ycf1tKlSzV8+HCFh4erefPmmj17tr755hudOnVK0v8dkNwMTp8+rSNHjmjjxo3asWOHhg8frh49emj//v0aOnSohgwZorVr12rYsGGaN2+eqlSpohw5cvi67Bta2vvDzBQeHq5HHnlE0dHR2rx5s1566SW9+OKL2rdvn6ZOnaqdO3dKOncAlpqaqixZsuiJJ57QjBkzlDt3bl++jBvSzz//rKioKJUrV04jRoxQnTp1NHXqVL300kvq27ev9u7dq/bt20uSAgMDJUk7duxQeHj4TfW5TQ+io6NVq1Yt53ZUVJSmTJly0YDgf//7n3r06KG33377gse5WcKcfPnyafz48Zo/f76ee+455yQ1LaR+7bXXdPDgQdWuXduXZaYLZiZJOnPmjCTp3nvv1bPPPqsdO3bowQcf1JkzZ+Tv76+UlBTnuz4yMlKRkZGKi4vzWd3pjZnpzJkzatmypb744gu99957qlSpkt566y0tWbJExYsXV968eTV//nzlzp1bS5Ys0ZEjR/TEE09o7dq1kqQsWbL4+FW4jA97LQC4iPO7X6UZNGiQ3XLLLfbyyy9bYmKi7du3z5YuXWqtWrWyBg0amMfjMY/HYxEREU4XblwfL730krVo0cIeeOABp9v3X7sc//TTT/b8889bvnz5vGaZuJksXrzYAgICrGDBgpY1a1abMGGC7dy508zOvZcbNmxo7dq183GV6cP5Mz+MGzfOfv75Z6/1iYmJFhMTY2+++abVqFHDHnvsMdu2bdsF98eFdu7cacHBwfbcc885y06fPm316tWzWrVqWUJCgn311VcWERFhVapUsUceecTuv/9+y5w58017WVB6MHz4cPv888+d26tWrbJ8+fJdcInBI488Yg0aNPBFiddNcnKyTZgwwQICAqx48eL28MMP28CBA+3++++38PBwxhm6AjExMVakSBH76quvzOzcvuC9996zqlWrWqtWrZzv9LRLC7Zu3Wo1atSw2bNnmxnjuPyTv26bGTNmWKFChaxbt27WrVs369q1q+XLl8+GDBlinTp1svDwcGccl99//92qVq1qe/fu9UXprpf++1gBN4nU1FT5+fk5CfXp06cVGhoqSRoyZIhSU1P11ltvKTk5WY888ojq1q2r2rVry+Px6Ntvv9X27dt15513KmfOnL58Ga6SmpqqoKAgzZ07V7fccovz603af6VzqXmFChVUokQJZcmSRQsWLNCJEyeUNWtWX5V9Tdxxxx3avXu3Dh8+rIIFC3r1DPD391doaKiKFi3q/PJ6/jbC/0nbD2zatEmtWrVS6dKlVaBAAZUrV06SlJycrMDAQEVEROjJJ59UUFCQ3n77bb311lt64oknVLp0abbt30hNTdUHH3ygrFmzer0/M2bMqHr16mn27NlKTU1V06ZNVa5cOQ0bNkyxsf+vvbsPq/F+/AD+PqfSKaEtKUSYvhghLSIu8w1tZDJdmMlKS+VXHsaUp4yKZNWUNmm1JEbI81Ni8hSmxQh5mGHI8pAilTqf3x+u7nVkG/ua0+m8X9fVdek+9333OV353J/z/jwVon79+jh27Bg6duyoxtJrt7y8PMyePRsKhQIuLi7SCIIRI0Zg4MCBSE9Ph6WlJYKDg2FmZqbu4v6rdHR04O3tja5duyI8PBzHjh2DsbExunTpgiNHjqhM76K/9vjxY3Tv3h3e3t6oV68eBg8ejNGjRwMA4uLi4ObmhuTkZBgYGAAAvvvuO8hkMmnaRlV7jVRVPceKi4tx584dmJub44MPPoBSqcTkyZPx4Ycf4qOPPoKPjw/mzp2LoqIiFBYWoqSkBEqlEs2bN0dWVladGfGjcdSdThCRak9hcHCw6N27t7C0tBSjR48WK1eulM6bM2eOsLCwEKGhoc9dEZ7+Xc/rJSgqKhLffvut0NXVFUFBQX953fHjx4WpqanUo64NysrKxOzZs0WzZs242vAL+rudH4T4YwcCIYSIj48XrVu3FlOmTOFCj3/jxo0bYtKkSaJHjx4iNDRUCCFEQUGBMDIyEmFhYc+9hosPvl5/NvLF399fKBQKqZdXiD8WKezatavKudrSo1tRUSG9V44Y+mcuX74svLy8hLGxsTQi4NkRBEIIERYWJho2bFhjJBepqvo7PHfunBg0aJDo1auXmDBhgsoWhS1atBAeHh7i999/F0+ePBH5+fnihx9+ULmPtvwfro0YDhCpWfU94q2srMRHH30kxo8fL0JCQkTr1q1Fs2bNxPTp06Xzg4KChIWFhQgLC2NA8BpVb3gVFhaKwsJC6fuSkhKxdOlSIZfLxYIFC6Tjzz7cYmJihKmpqdasurty5UoxceJEYWZmxqGuL+ivdn64fv26yvZ51VfTT0pK4orZL+jWrVvCz89P9OrVS3z++efCwsJC+Pv7S68rlUqV/7tspKrHtWvXagSpPj4+NQKCH374Qbi4uGjlh2P+nb64Z/8+qu9ecenSJeHl5SUaNWpUIyDo1auXMDMzE/r6+uLEiROvtcyapnp7tnHjxiIwMFBkZ2erhNlCCLFp0yZhYWEhPD09VXbV4t9w7cBwgEiNqu+ta2RkJKZPny7u378vvZ6Xlyfc3NyEmZmZCAkJkY4HBwcLQ0NDERERwV6t16B6o2LRokXCwcFBdOvWTQwbNkyak1hWViZiYmKEjo7Oc3sgy8rKRFBQkNb0Opw/f168++67YtiwYeLs2bPqLo7GePLkiejTp4+IiYmRju3atUtMnjxZNGzYULRu3Vo4OjpKjai6sD2bOty8eVP4+fmJpk2binfeeUc6zt+nekRHR6vML54+fbpo3769UCgU4r333hPh4eHSa76+vsLQ0FBs3Lixxn34PKS/cu3aNZVtIKv/vVQFBGZmZiIjI0MI8TSAjY2NFX379tWaZ/f/6tatW8La2rrGdprPhq6bN28WFhYWwsfHh7/bWobhAJGaVS2QNXv2bCHEHw+rqkbqpUuXxHvvvSesra3FmTNnpOvCw8M5TPs1mzlzpmjatKmIiYkRO3fuFKampmLAgAHi0qVLQoinvbuxsbFCJpOJ5OTkGtdrWyp++/ZtlREW9PcePHgg2rdvL7y8vMT58+fFggULRLt27cTw4cPFkiVLREJCgmjbtq347LPP1F1UjZefny/8/f1Fjx49VAI9beyBVqdz584JmUwmPvnkE3H79m2RmJgomjdvLlJTU8XWrVuFh4eHsLW1FVOmTJGumThxopDJZGL//v1qLDlpkidPnoiPPvpI2NjYqCxuWT0gOHv2rBg5cqTo16+ftLhzWVkZn2MvYceOHcLa2lqcO3fuuW2e6r/vjRs3CkNDQzFp0qQaowtIfRgOEKlRZWWlmDFjhjA1NRVLliyRjldVnlUV64EDB4RcLn9uTwm9Hrt37xbW1tbiwIEDQgghdu7cKRo0aCBMTU1F586dxeXLl4UQTxsS69evZw8k/WMvsvPDJ598ot5C1hFVUwwcHBz+dM0Q+vdUPeMOHTokFAqF8PX1FV988YWIjY2Vzrl7964ICwsTNjY2IjU1VToeFRXFepZeysWLF8XQoUNFv379xKpVq6Tj1T+wrlu3TpiZmUmhP72cOXPmiJYtW0rfP2/qy8OHD0VJSYkQQojt27ezo6uW4ZLGRGokl8vh5+eH0aNHY/Xq1QgLCwPwdDXi6vtp29rawsTEBDdv3gTwx/689Pro6OjAw8MDffr0we7duzFmzBgsXrwYx44dw40bN+Dj44O8vDzUq1cPw4cPh66uLioqKtRdbNJAVTs/bNiwAb/88gu8vb3Rtm1bAH/s/NCiRQuIpwG/mkur2czNzTFr1ixYWVnhyJEjuHv3rrqLpFVkMhmUSiUcHByQnp6OhIQEzJs3T3rWAcCbb76J//u//4O+vj72798vHZ88eTLrWXopbdu2RVRUFAwNDfHtt9/i+++/B/C0Xn3y5AkA4D//+Q+aNGnCuvUFVG+nVrGwsEBRURHOnTsHQHVHh6p/z5o1C1OmTIEQAoMGDYKVldXrKTC9EIYDRGrWrFkzBAYGws7ODps2bcKiRYsAPA0OqirenJwcNGvWDPb29gC4fc6/7XkPPEdHR7i6uqK0tBRhYWGYMGECvL29YWxsjFatWiEjIwMhISEq1+jqcrdY+mdatGgBW1tblS33ysvLMXfuXBw+fBhjx46FTCZjXfAKmJubIywsDCkpKTAxMVF3cbSOXC5HZWUl+vTpg8OHD8PAwAA//PADLly4IJ1jZGSEnj174sqVKygvL1e5nvUsvYzWrVsjJiYGhoaGiI+Px4oVKwAAenp6AIBVq1bB0NBQpe6l55PL5bh27Rqio6OlY82aNUNRURE2bdqEhw8f1rimvLwcT548QZcuXfj8qqUYDhDVAlW9V3Z2dti4caMUEFTt8bphwwaYmZmhVatWaiyldqjanxcATp8+jatXr6KgoADA0w9sBQUF+O2339CzZ08ATxsUnTp1wtmzZ5GUlKSuYlMdl5KSgs8//xzx8fHYtm0be1peMTMzM5iZmam7GFrj2QC26ln3zjvvYM+ePThx4gTmzp2Ln3/+GQBQXFyMQ4cOoXnz5qhXr95rLy/VLVUBgbGxMb7++mtMmjQJa9euhZ+fH5KSkrB8+XIYGxuru5i1XmVlJb7++mvExsYiPDwcAODs7IxPP/0UwcHBWLlyJe7cuaNyfnBwMPbu3QsnJyd1FZv+hkxw3AxRrZGfn4/Q0FD8+OOPGDZsGAICAhASEoLIyEgcOHAAnTp1UncRtUZgYCBSU1NRVFSEgQMHwsPDAwMGDIBSqUT79u3RsmVLeHp6Ij4+HiUlJThy5IjUA1bV0CV6FfLy8uDj44M33ngDoaGh6NChg7qLRPSPVQ9gU1JScP36dRQWFmLChAkwMzODQqHAwYMHMWDAAJiamsLGxgY6Ojq4fv06srKyoKenByEEex3pf/bbb78hISEBaWlp0NHRQYsWLbBgwQJ07NhR3UXTGDdu3MDixYtx9OhRfPDBB5g5cyYePXoET09PpKam4sMPP4SzszPu3r2L06dPY8uWLdi3bx+6du2q7qLTn2A4QFTLVAUEp06dQllZGX7++WccPnwY3bp1U3fR6rTqjc09e/bAy8sLCQkJuHDhAvbs2YNbt24hICAALi4uyMnJwccffwx9fX00btwYO3bsgJ6enkqjl+hV+v3336Gvr49GjRqpuyhEr0RgYCC+++479OnTB+fOnYOenh5mzJiBwYMHw8jICEePHoWTkxMMDAywYsUK9O/fHzo6OqioqOBUAnqllEolHj9+DB0dHSgUCnUXR+NUtVuPHz+O4cOHY/r06QCAkJAQrF27Fr/88gtatWoFW1tbzJgxgwF3LcdwgKgWys/Px8yZM3Hw4EGsW7eOCetrtHnzZuzZswetW7fG1KlTAQBZWVmIjo7GL7/8gqCgIAwePBgVFRW4ffs2mjVrBplMxgYrEdEL+vrrrxEWFoYtW7aga9euyMjIwMCBA9GpUycphK1fvz7279+PuXPnYv/+/ZDJZByZRa8cR6G8GtUDgmHDhiEwMBAAcP/+fZSXl8PExARKpZLTgjQAwwGiWqqgoABKpZLzYF+jCxcuYNy4ccjNzYW/vz/mz58vvZaVlYWYmBhcuXIFkyZNwqhRo6TXOGKAiOjPVf9QX1paisWLF8PU1BQ+Pj7YsGEDPv30UyxcuBAbN27EuXPnsHDhQjg7O6uMlGE9S1S7VZ8aWzXFAPjj/z+DGM3AcICItFbVg6r6A2vr1q348ssvcfv2bSQkJMDBwUE6/+jRo/jiiy/QokULxMfHq6vYREQaKS4uDkOHDsXNmzdhYWGB+/fvw8XFBd7e3pg8eTJ++ukn9OrVC02bNsWyZcvg5OTEDxREGqQqIMjJyYGjoyPmzZun7iLRS2IES0RaSalUSg3O8vJylJWVAQCGDBmCwMBAtGzZEqGhocjKypKusbe3R0REBOLi4tRSZiIiTVJ9V4KlS5fC19cX9+7dg42NDZo0aYLc3FwYGhrCxcUFAHDnzh2MHTsWI0aMQP/+/QFw614iTVK1+5aVlRWOHDmCu3fvqrtI9JI4QZaItE714akRERHYs2cPysvL0aZNG0REROD999+HEAJLlixBcHAwgoKCYG9vDwDSKsYc4kpE9Neq6sjMzEzI5XKkpaXh7bffRtWg1Tt37uDu3bu4evUq9PT0sHTpUnTs2BELFy4EAK4xQKSBzM3NERYWBgAwMTFRc2noZXFaARFprVmzZmH58uXw8/NDWVkZ1qxZA4VCgTVr1qBz587YvHkzli9fjoKCAiQmJnIrSSKil3T8+HH07NkTenp6WLNmDVxcXKQP/WVlZejVqxdu3LgBPT09NG7cGMePH4eenp66i01EpJUYDhCRVigrK4O+vr70/aVLl/D+++8jKioKzs7OAICSkhL069cPpaWlOHXqFAAgNTUVR48exZdffsmRAkRELyk/Px+rV69GSEgI3NzcsGTJEgB/1Mnl5eXYvn07ZDIZhgwZwu0KiYjUiC1dIqrz+vbti507d6ocKykpQWFhIVq3bg3g6boDhoaG2Lp1K27fvo2YmBgAwIgRIxAZGQm5XK4yf5aIiFQ9W0cqlUqYm5vD29sbgYGBWLZsmbRAmb6+PsrKylCvXj0MGzYMLi4u0NHRQWVlJYMBIiI1Ye1LRHXeBx98gPfffx8ApB4pKysr6OrqYt26dejYsSPq1auHyspKGBoawsLCAqWlpTXuw5EDRETPV30dliVLliA3NxenT5+Gt7c3+vbti2nTpkEulyM0NBQymQxBQUHQ19evsX4L1xggIlIfhgNEVGdVbYE1depUAMCCBQvQqFEjjB07Fg0aNICvry82b94MMzMz+Pr6QkdHBwqFAgBUpiAQEdFfq/qAHxgYiMTERAQEBMDY2BjBwcHYuXMnkpOT4e7uLgUExcXFWLx4MUNXIqJahOEAEdVZz26BlZ+fj9mzZ8PQ0BAeHh5wd3fH7du3ERERgYMHD6JTp07Ys2cPSktLMWHCBDWVmohIMx06dAhpaWnYvn077OzscODAAURFRWHevHnQ19eHvr4+xo8fj6KiImRlZUkBLhER1Q4MB4ioTsrKyoK9vT1kMhkWLVqELl26IDo6GgqFAt7e3lAqlfD09MTs2bNhb2+PpUuXorCwEJaWlkhPT4euri630SIiegllZWVo2LAh7OzssHbtWnh5eSE6OhpjxozBw4cPcfToUfTr1w9Tp06FkZERZDIZAwIiolqE4QAR1TmXLl3C+PHj0blzZzRu3BixsbHIyckBAISHh0OpVMLHxwcA4O7uDjc3N7i5uak0UrlaNhHRn6teX1b9+9GjR1Aqldi6dSu8vb2xcOFC+Pr6AgAyMzOxYcMGWFlZwdLSssY9iIhI/biVIRHVOWVlZVi3bh0mT56M0tJSZGZmwtbWFo8fP4aBgQEAYNq0aYiJicGyZcswfPhwNGzYULqeDVYioj9XfRHBZ+tLW1tb5OTkID4+Hp6engCA0tJSuLq6wsjICN9//z3rVyKiWordYkRUZ1Q1WPX19WFmZgaFQgETExNER0dj+fLlMDAwkPbW/vLLLyGTyeDp6QlTU1M4OztL92HDlYjo+YQQUjAQGxuLw4cPo23btujbty8cHR2xdOlSeHh4YPny5TA1NcXdu3exZs0a3Lx5Ezk5OZDJZDV2KCAiotqBIweIqE6o3tg8e/YslEolTExMkJGRga+++grt2rVDUlIS6tWrp3JuXFwcPD09OYWAiOhvVB8lEBwcjKioKAwaNAgnT56EsbExfHx8MGbMGOTk5GDq1Km4evUqzMzM8NZbbyExMRF6enpcy4WIqBZja5iINF71nqxZs2YhPT0ds2bNQqdOneDq6orS0lLExcVh3LhxSEpKgq6uLiZMmIDhw4fD29sbANcYICL6K9XryOzsbBQUFGDz5s3o06cPzpw5g6+++goRERFQKpUYO3Ys9u3bh+vXr8PExAQGBgaQyWSsZ4mIajmOHCCiOiM4OBhLly5FcnIy7Ozs8OabbwJ4Ot81JSUF33zzDSorK9GkSRPk5ubi6tWrbKgSEf2Fb775RlpUEADS0tIwf/58AMD27dvRvHlzAEBubi6++uor/PTTT5gwYYK03kAVruVCRFT7ccIXEWmk8vJyle9v3bqFjRs3IjIyEk5OTlIwUFlZCYVCgbFjxyIsLAwODg5o27atFAxUVlaqo/hERLXejh07MH/+fIwfP146Vr9+fTRr1gyXL19GVlaWdLxjx46YMmUK7Ozs8MUXX2DHjh0q92IwQERU+3HkABFpnH79+mHatGkYPHiwdOzy5cuwt7fH1q1bYW9vr7KuQGlpKR49egQTExOV+3CIKxHRnysqKkJycjISExNhY2ODhIQEAEBWVhYWLFiAwsJCBAQEqCzoeurUKezatQvTpk3j2gJERBqGIweISOMMGDAA/fv3BwCp59/U1BRyuRwZGRkAALlcLr124sQJpKWl4eHDhyr3YTBARPR8SqUSDRs2hLu7Ozw8PJCdnY1x48YBAHr27Ilp06ahcePGiIiIwLZt26TrunTpgoCAAOjo6HBkFhGRhuHIASLSGM/OWQ0LC0Pjxo0xatQoGBkZYebMmdixYwf8/f2l+a6VlZUYNGgQTE1NsXLlSg5tJSL6G8/Wtffv38fKlSuRmJiIbt26ITExEQCwf/9+REdHo6ioCD4+PnB1dVVXkYmI6BVgtxkRaYTq0wSqGq5nzpzB2rVrYWBggI8//hgeHh4oKChAaGgo9u7diyZNmiA7OxuFhYXYtm0bZDIZF8UiIvobVXXkokWL0KNHD7z77rtwc3MDACQmJmLcuHFITEzEu+++C5lMhqCgIGRmZjIcICLScBw5QEQa4cmTJ6ioqMC9e/fQpEkT6OnpAQB8fX3x3XffIT4+Hm5ubrh58yb27t2L+Ph4mJqaonnz5oiMjISuri7XGCAiekHFxcUYM2YMtm3bhgMHDsDBwUFlBIGtra20BkFOTg66dOkiBbhERKSZGA4QUa2Xnp6OTZs2Ydu2bSguLoaDgwOGDBkCb29vAIC3tzdWrFiB+Ph4jB49+rmLYDEYICL6c1Wjs6qPrrp+/Tpmz56NNWvWYO/evejduzfu37+PlJQUJCUlwdLSEmlpaTXuQUREmoktZSKq1RITExEUFISRI0fCz88PxsbGiImJwbx583D58mWEh4cjLi4OMpkM3t7ekMvlGDp0KIyMjFTuw2CAiOj5zpw5g06dOgEA7t27BxMTEwgh0KJFC4SGhkKpVMLR0RH79u2Dg4MD3Nzc8PDhQ+Tl5akEAgwGiIg0G0cOEFGtFRcXh4kTJ2LFihUYPny4NJXg4sWLCA0Nxa5du/DZZ59h+vTpAAB/f3/ExsZi586dcHJyUmfRiYg0wsWLF9GuXTvs3LkTurq6GDJkCH766Se0b99eGkVw7do1TJw4ERkZGcjMzIStrS2Ki4thZGQEmUzGEQNERHUEa3IiqpU2bdoEX19frF+/HqNGjZKGuVZWVsLKygpz5sxBhw4dsH79ely9ehUAEBMTg8WLF8PR0VGdRSci0hjm5uYYMGAA0tLSoKenBwcHBwwaNAh5eXnSB/+WLVvi448/RklJCezs7HDq1Ck0aNBAWuSVwQARUd3A2pyIap2ysjLs3r0bbdq0kT746+rqorKyEjo6OhBC4K233sKMGTOQnZ2N69evS9dOnTpVWnyQiIj+WoMGDdC3b19s2bIFHTp0QFxcHNq1a4cBAwbg/Pnz0gf/pk2bwsvLCxEREejYsaN0PXd/ISKqOxgOEFGto6+vj6CgIDg7OyMlJQWLFi0CAOjo6ECpVErntWrVCvXq1cOjR49q3INrDBAR1VQ1m1QIIf07MDAQb7zxBubNm4c2bdogLCwMnTt3xn//+1/s27cPZ8+eRWRkJHR0dDBlyhQGsEREdRTDASKqlZo2bYrAwEDY2dlh48aNUkAgl8tRWVkJADh9+jRsbW3x9ttvq7OoREQa48GDBwCe9vjLZDJUVFRACAEXFxf8+OOPuHfvHrp06YKFCxeiX79+6N+/P4YOHYorV65gyZIlAJ4GCwxgiYjqHoYDRFRrmZubY9asWTUCAl1dXRQXFyMxMRHt27eHhYWFmktKRFT77dq1C/3790dsbCx+//13AE/rUx0dHXh6euLMmTNISEgAAFhbW2PVqlU4cuQIkpOTceLECejp6aGiooJTCYiI6ijuVkBEtV5+fj5CQ0Px448/wtXVFdOmTYOLiwt+/fVXnDhxArq6uip7cxMRUU25ubmIiorCqlWrYG1tDTs7O8yZMwdGRkYwMjJCQEAADh06hNWrV6Nly5Y16tSqdV+IiKhuYjhARBohPz8fCxYsQHZ2Ni5dugRjY2OcOXMGenp6bLASEb2ECxcuICkpCWlpaXj06BEGDhwIPz8/FBQU4JNPPsG6devQu3dvblFIRKRlGA4QkcbIz89HQEAACgoKsHnzZmmIK+e+EhG9nMrKSlRUVGDx4sXIzMzEvn374O/vj+joaPTu3Ru7d++GgYGBuotJRESvEcMBItIo9+/fR6NGjSCXyxkMEBH9Q9WnYpWVlWHLli1YvXo1du7cie7duyMzM5NTtYiItAzDASLSSBzuSkT0v3l2rZYHDx7g1q1bsLKykraOZT1LRKQ9GA4QERERkQqu5UJEpH0YDhARERERERFpOY4VIyIiIiIiItJyDAeIiIiIiIiItBzDASIiIiIiIiItx3CAiIiIiIiISMsxHCAiIiIiIiLScgwHiIiIiIiIiLQcwwEiIiIiIiIiLcdwgIiIiIiIiEjLMRwgIiKiWiUpKQnGxsb/831kMhk2bdr0P9+HiIhIGzAcICIiolfO3d0dLi4u6i4GERERvSCGA0RERERERERajuEAERERvVaRkZGwtrZG/fr10aJFC0yYMAEPHz6scd6mTZtgZWUFhUIBJycnXL9+XeX1zZs3o1u3blAoFGjTpg3mzZuHioqK5/7M8vJy+Pn5oWnTplAoFLC0tMTChQv/lfdHRESkiRgOEBER0Wsll8sRHR2N3NxcrFixAvv27cP06dNVzikpKUFoaCiSk5Nx+PBhFBYWYtSoUdLrBw8exNixYzFp0iScPXsWcXFxSEpKQmho6HN/ZnR0NLZs2YLU1FTk5eVh1apVaNWq1b/5NomIiDSKTAgh1F0IIiIiqlvc3d1RWFj4QgsCrl+/Hj4+Prhz5w6ApwsSenh44OjRo+jRowcA4Pz58+jQoQOOHTuG7t27o3///nB0dMSMGTOk+6SkpGD69Om4efMmgKcLEm7cuBEuLi6YOHEicnNzkZGRAZlM9urfMBERkYbjyAEiIiJ6rTIyMuDo6IjmzZujQYMGcHNzw927d1FSUiKdo6urCzs7O+n79u3bw9jYGOfOnQMAnDp1CvPnz4eRkZH05eXlhVu3bqncp4q7uztOnjyJdu3aYeLEiUhPT//33ygREZEGYThAREREr82vv/4KZ2dndO7cGRs2bEB2djZiY2MBPF0X4EU9fPgQ8+bNw8mTJ6Wv06dP4+LFi1AoFDXO79atG65cuYLg4GA8fvwYI0aMgKur6yt7X0RERJpOV90FICIiIu2RnZ0NpVKJiIgIyOVP+yhSU1NrnFdRUYETJ06ge/fuAIC8vDwUFhaiQ4cOAJ5+2M/Ly0Pbtm1f+Gc3bNgQI0eOxMiRI+Hq6or33nsP9+7dw5tvvvkK3hkREZFmYzhARERE/4oHDx7g5MmTKscaN26MJ0+eICYmBkOGDMHhw4exbNmyGtfq6enB398f0dHR0NXVhZ+fH+zt7aWwICgoCM7OzmjZsiVcXV0hl8tx6tQpnDlzBiEhITXuFxkZiaZNm8LGxgZyuRzr1q2Dubk5jI2N/423TkREpHE4rYCIiIj+Ffv374eNjY3K18qVKxEZGYlFixahU6dOWLVq1XO3FDQ0NERAQABGjx4NBwcHGBkZYe3atdLrTk5O2LZtG9LT02FnZwd7e3tERUXB0tLyuWVp0KABwsPD8c4778DOzg6//vorduzYIY1eICIi0nbcrYCIiIiIiIhIyzEuJyIiIiIiItJyDAeIiIiIiIiItBzDASIiIiIiIiItx3CAiIiIiIiISMsxHCAiIiIiIiLScgwHiIiIiIiIiLQcwwEiIiIiIiIiLcdwgIiIiIiIiEjLMRwgIiIiIiIi0nIMB4iIiIiIiIi0HMMBIiIiIiIiIi33/zcnunQplIbhAAAAAElFTkSuQmCC",
+      "text/plain": [
+       "<Figure size 1200x600 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "plt.figure(figsize=(12, 6))\n",
+    "plt.bar(labels, sizes)\n",
+    "plt.title('Bar Graph')\n",
+    "plt.xlabel('Labels')\n",
+    "plt.ylabel('Count')\n",
+    "plt.xticks(rotation=45)\n",
+    "plt.show()\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "id": "YtSxaBSZ5C_h"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABQcAAAMsCAYAAADphhT5AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjkuMCwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy80BEi2AAAACXBIWXMAAA9hAAAPYQGoP6dpAAD8MElEQVR4nOzddXhT598G8PskqbsLLS2U4s5g2LAxhk0ZA6awMXcX9pswd6ZsOAPGgAnD3bVFWrTQQt29TeM55/2Dl24d9aY9TXJ/rotra3Ke57lzCDR8+4ggSZIEIiIiIiIiIiIisjsKuQMQERERERERERGRPFgcJCIiIiIiIiIislMsDhIREREREREREdkpFgeJiIiIiIiIiIjsFIuDREREREREREREdorFQSIiIiIiIiIiIjvF4iAREREREREREZGdYnGQiIiIiIiIiIjITrE4SEREREREREREZKdYHCQiIqvx7rvvQhCEFhlrxIgRGDFiROXXe/bsgSAI+P3331tk/OnTpyMyMrJFxmostVqNmTNnIjg4GIIg4Pnnn5c7UquQkpICQRDwxRdfyB2lVlff03v27Glw2//++aiNNbyXiYiIiOwZi4NERCSLJUuWQBCEyl/Ozs4IDQ3FzTffjG+//Rbl5eUWGScrKwvvvvsu4uLiLNKfJbXmbPXx0UcfYcmSJXjiiSewbNky3H///TVeGxkZCUEQ8Mwzz1zzXFMKr9Z+D2tTUlICZ2dnCIKA8+fPN7qfH3/8EUuWLLFcsGrY8u8DERERka1jcZCIiGQ1e/ZsLFu2DHPnzq0sHD3//PPo0aMHTp06VeXat956C1qttkH9Z2Vl4b333mtw0WLbtm3Ytm1bg9o0VG3Z5s+fjwsXLjTr+E21a9cuDBw4EO+88w7uu+8+9OvXr8428+fPR1ZWlsUyNPb31xqsWbMGgiAgODgYK1asaHQ/NRUHhw0bBq1Wi2HDhjW4z//++bD29zIRERGRPWNxkIiIZDVu3Djcd999mDFjBt544w1s3boVO3bsQF5eHm699dYqxUCVSgVnZ+dmzaPRaAAAjo6OcHR0bNaxauPg4AAnJyfZxq+PvLw8eHt71/v6bt26wWw245NPPmm+UDISRRE6nc5i/S1fvhzjx4/HtGnT8Ouvv1qs36sUCgWcnZ2hUDT842BD/nxYw3uZiIiIyJ6xOEhERK3OqFGj8L///Q+pqalYvnx55ePV7Tm4fft2DB06FN7e3nB3d0enTp3w5ptvAriyXLV///4AgBkzZlQuYb46i2rEiBHo3r07jh8/jmHDhsHV1bWybU17qpnNZrz55psIDg6Gm5sbbr31VqSnp1e5JjIyEtOnT7+m7b/7rCtbdfu0VVRU4KWXXkJ4eDicnJzQqVMnfPHFF5Akqcp1giDg6aefxtq1a9G9e3c4OTmhW7du2LJlS/U3/D/y8vLw8MMPIygoCM7OzujVqxeWLl1a+fzVZcDJycnYuHFjZfaUlJRa+42MjMQDDzxQ79mDmZmZeOihhxAUFFT5GhYtWlQlR0338Ntvv4VSqURJSUnl9V9++SUEQcCLL75Y+ZjZbIaHhwdee+21yscaep9XrFiBbt26wcnJqcZ7LEkSHn30UTg6OuLPP/+s87WnpaVh//79mDp1KqZOnYrk5GQcOnSo2muXL1+OAQMGwNXVFT4+Phg2bFjlrL7IyEicPXsWe/furbw//34P/nvPwaeffhru7u6VBfJ/mzZtGoKDg2E2mwE0/b0siiLmzJmDbt26wdnZGUFBQXjsscdQXFxc5bpjx47h5ptvhr+/P1xcXNCuXTs89NBDdd4/IiIiIqo/ldwBiIiIqnP//ffjzTffxLZt2/DII49Ue83Zs2cxceJE9OzZE7Nnz4aTkxOSkpJw8OBBAECXLl0we/ZsvP3223j00Udxww03AAAGDx5c2UdhYSHGjRuHqVOn4r777kNQUFCtuT788EMIgoDXXnsNeXl5mDNnDkaPHo24uDi4uLjU+/XVJ9u/SZKEW2+9Fbt378bDDz+M3r17Y+vWrXjllVeQmZmJr7/+usr1Bw4cwJ9//oknn3wSHh4e+PbbbzFp0iSkpaXBz8+vxlxarRYjRoxAUlISnn76abRr1w5r1qzB9OnTUVJSgueeew5dunTBsmXL8MILLyAsLAwvvfQSACAgIKDO1z1r1iz88ssv+OSTT/Dtt9/WeF1ubi4GDhxYWYALCAjA5s2b8fDDD6OsrAzPP/98rfewtLQUoijiwIEDmDhxIgBg//79UCgU2L9/f+U4J0+ehFqtrlxa29D7vGvXLqxevRpPP/00/P39qz14w2w246GHHsKqVavw119/YcKECXXep5UrV8LNzQ0TJ06Ei4sLoqKisGLFimveH++99x7effddDB48GLNnz4ajoyOOHj2KXbt2YcyYMZgzZw6eeeYZuLu7Y9asWQBQ43t8ypQp+OGHH7Bx40ZMnjy58nGNRoP169dj+vTpUCqV17Rr6HsZAB577DEsWbIEM2bMwLPPPovk5GR8//33OHnyJA4ePAgHBwfk5eVhzJgxCAgIwOuvvw5vb2+kpKTUq7hKRERERA0gERERyWDx4sUSACk2NrbGa7y8vKQ+ffpUfv3OO+9I//7W9fXXX0sApPz8/Br7iI2NlQBIixcvvua54cOHSwCkn376qdrnhg8fXvn17t27JQBSmzZtpLKyssrHV69eLQGQvvnmm8rHIiIipAcffLDOPmvL9uCDD0oRERGVX69du1YCIH3wwQdVrrvrrrskQRCkpKSkyscASI6OjlUei4+PlwBI33333TVj/ducOXMkANLy5csrHzMYDNKgQYMkd3f3Kq89IiJCmjBhQq39VXftjBkzJGdnZykrK0uSpH/u7Zo1ayqvf/jhh6WQkBCpoKCgSj9Tp06VvLy8JI1GI0lSzffQbDZLnp6e0quvvipJkiSJoij5+flJkydPlpRKpVReXi5JkiR99dVXkkKhkIqLiyVJavh9VigU0tmzZ6tcm5ycLAGQPv/8c8loNEpTpkyRXFxcpK1bt9brXkmSJPXo0UO69957K79+8803JX9/f8loNFY+lpiYKCkUCumOO+6QzGZzlfaiKFb+f7du3aq87666et93795d2aZNmzbSpEmTqlx39T2+b9++ysea8l7ev3+/BEBasWJFleu2bNlS5fG//vqrzr8jiIiIiKjpuKyYiIhaLXd391pPLb66393ff/8NURQbNYaTkxNmzJhR7+sfeOABeHh4VH591113ISQkBJs2bWrU+PW1adMmKJVKPPvss1Uef+mllyBJEjZv3lzl8dGjRyMqKqry6549e8LT0xOXL1+uc5zg4GBMmzat8jEHBwc8++yzUKvV2Lt3b5Nfy1tvvQWTyVTj3oOSJOGPP/7ALbfcAkmSUFBQUPnr5ptvRmlpKU6cOFHrGAqFAoMHD8a+ffsAAOfPn0dhYSFef/11SJKEw4cPA7gym7B79+6V76WG3ufhw4eja9eu1WYwGAyYPHkyNmzYgE2bNmHMmDF13hsAOHXqFE6fPl3l92DatGkoKCjA1q1bKx9bu3YtRFHE22+/fc2+gf9dfl8fgiBg8uTJ2LRpE9RqdeXjq1atQps2bTB06NAG91mdNWvWwMvLCzfddFOV39t+/frB3d0du3fvBvDPn+8NGzbAaDRaZGwiIiIiuhaLg0RE1Gqp1eoqhbj/mjJlCoYMGYKZM2ciKCgIU6dOxerVqxtUKGzTpk2DDh6Jjo6u8rUgCOjQoUOd++01VWpqKkJDQ6+5H126dKl8/t/atm17TR8+Pj7X7OlW3TjR0dHXFJtqGqcx2rdvj/vvvx/z5s1Ddnb2Nc/n5+ejpKQE8+bNQ0BAQJVfVwu5eXl5dY5zww034Pjx49Bqtdi/fz9CQkLQt29f9OrVq3Jp8YEDByqXwV59fQ25z+3atatx/I8//hhr167F77//Xu3+lTVZvnw53Nzc0L59eyQlJSEpKQnOzs6IjIyscmrxpUuXoFAoaixONsaUKVOg1Wqxbt06AFf+DG7atAmTJ09uVMGxOomJiSgtLUVgYOA1v79qtbry93b48OGYNGkS3nvvPfj7++O2227D4sWLodfrLZKDiIiIiK7gnoNERNQqZWRkoLS0FB06dKjxGhcXF+zbtw+7d+/Gxo0bsWXLFqxatQqjRo3Ctm3bqt0frbo+LK2mIorZbK5XJkuoaRzpP4dqyGXWrFlYtmwZPv30U9x+++1Vnrta3L3vvvvw4IMPVtu+Z8+edY4xdOhQGI1GHD58GPv3768sAt5www3Yv38/EhISkJ+fX6U42FC1vX9uvvlmbNmyBZ999hlGjBhRr5O2JUnCypUrUVFRUW3RLy8vD2q1Gu7u7o3OXJuBAwciMjISq1evxj333IP169dDq9ViypQpFhtDFEUEBgZWKXT+29W9KwVBwO+//44jR45g/fr12Lp1Kx566CF8+eWXOHLkSLPdAyIiIiJ7w+IgERG1SsuWLQNwpcBSG4VCgRtvvBE33ngjvvrqK3z00UeYNWsWdu/ejdGjR1tsttNViYmJVb6WJAlJSUlVilU+Pj5VTsm9KjU1Fe3bt6/8uiHZIiIisGPHDpSXl1eZ1ZaQkFD5vCVERETg1KlTEEWxyuxBS48TFRWF++67Dz///DOuv/76Ks8FBATAw8MDZrMZo0ePrrWf2u7hgAED4OjoiP3792P//v145ZVXAADDhg3D/PnzsXPnzsqvr7LkfR44cCAef/xxTJw4EZMnT8Zff/0Flar2j1579+5FRkYGZs+eXTlb8ari4mI8+uijWLt2Le677z5ERUVBFEWcO3cOvXv3rrHPhv4ZuPvuu/HNN9+grKwMq1atQmRkJAYOHFhrm4aMERUVhR07dmDIkCH1Ks4PHDgQAwcOxIcffohff/0V9957L3777TfMnDmz3mMSERERUc24rJiIiFqdXbt24f3330e7du1w77331nhdUVHRNY9dLZJcXXro5uYGANUW6xrjl19+qbIP4u+//47s7GyMGzeu8rGoqCgcOXIEBoOh8rENGzYgPT29Sl8NyTZ+/HiYzWZ8//33VR7/+uuvIQhClfGbYvz48cjJycGqVasqHzOZTPjuu+/g7u6O4cOHW2Qc4Mreg0ajEZ999lmVx5VKJSZNmoQ//vgDZ86cuaZdfn5+5f/Xdg+dnZ3Rv39/rFy5EmlpaVVmDmq1Wnz77beIiopCSEhIZRtL3+fRo0fjt99+w5YtW3D//ffXueT96pLiV155BXfddVeVX4888giio6MrZ9zdfvvtUCgUmD179jX9/nuGqJubW4Pe/1OmTIFer8fSpUuxZcsW3H333XW2ach7+e6774bZbMb7779/zXMmk6myj+Li4mtmuv73zzcRERERNR1nDhIRkaw2b96MhIQEmEwm5ObmYteuXdi+fTsiIiKwbt26Wpdizp49G/v27cOECRMQERGBvLw8/PjjjwgLC6s8PCEqKgre3t746aef4OHhATc3N1x//fW17hVXG19fXwwdOhQzZsxAbm4u5syZgw4dOuCRRx6pvGbmzJn4/fffMXbsWNx99924dOkSli9fXuWAkIZmu+WWWzBy5EjMmjULKSkp6NWrF7Zt24a///4bzz///DV9N9ajjz6Kn3/+GdOnT8fx48cRGRmJ33//HQcPHsScOXNq3QOyoa7OHly6dOk1z33yySfYvXs3rr/+ejzyyCPo2rUrioqKcOLECezYsaOyMFzXPbzhhhvwySefwMvLCz169AAABAYGolOnTrhw4QKmT59eZdzmuM+33347Fi9ejAceeACenp74+eefq71Or9fjjz/+wE033VTj+/7WW2/FN998g7y8PHTo0AGzZs3C+++/jxtuuAF33nknnJycEBsbi9DQUHz88ccAgH79+mHu3Ln44IMP0KFDBwQGBmLUqFE15u3bt29l33q9vl5LihvyXh4+fDgee+wxfPzxx4iLi8OYMWPg4OCAxMRErFmzBt988w3uuusuLF26FD/++CPuuOMOREVFoby8HPPnz4enpyfGjx9fZyYiIiIiqie5jkkmIiL7tnjxYglA5S9HR0cpODhYuummm6RvvvlGKisru6bNO++8I/37W9fOnTul2267TQoNDZUcHR2l0NBQadq0adLFixertPv777+lrl27SiqVSgIgLV68WJIkSRo+fLjUrVu3avMNHz5cGj58eOXXu3fvlgBIK1eulN544w0pMDBQcnFxkSZMmCClpqZe0/7LL7+U2rRpIzk5OUlDhgyRjh07dk2ftWV78MEHpYiIiCrXlpeXSy+88IIUGhoqOTg4SNHR0dLnn38uiaJY5ToA0lNPPXVNpoiICOnBBx+s9vX+W25urjRjxgzJ399fcnR0lHr06FGZ67/9TZgwoc7+ars2MTFRUiqVEgBpzZo11+R46qmnpPDwcMnBwUEKDg6WbrzxRmnevHlVrqvpHkqSJG3cuFECII0bN65Km5kzZ0oApIULF16Tqan3OTk5WQIgff7551Ue//HHHyUA0ssvv1ztPfrjjz9qzHTVnj17JADSN998U/nYokWLpD59+khOTk6Sj4+PNHz4cGn79u2Vz+fk5EgTJkyQPDw8JACV78Gr7+ndu3dfM86sWbMkAFKHDh2qzdHU97IkSdK8efOkfv36SS4uLpKHh4fUo0cP6dVXX5WysrIkSZKkEydOSNOmTZPatm0rOTk5SYGBgdLEiROlY8eO1Xh/iIiIiKjhBElqJTuTExERERERERERUYvinoNERERERERERER2isVBIiIiIiIiIiIiO8XiIBERERERERERkZ1icZCIiIiIiIiIiMhOsThIRERERERERERkp1gcJCIiIiIiIiIislMsDhIREREREREREdkpFgeJiIiIiIiIiIjsFIuDREREREREREREdorFQSIiIiIiIiIiIjvF4iAREREREREREZGdYnGQiIiIiIiIiIjITrE4SEREREREREREZKdYHCQiIiIiIiIiIrJTLA4SERERERERERHZKRYHiYiIiIiIiIiI7BSLg0RERERERERERHaKxUEiIiIiIiIiIiI7xeIgERERERERERGRnWJxkIiIiIiIiIiIyE6xOEhERERERERERGSnWBwkIiIiIiIiIiKyUywOEhERERERERER2SkWB4mIiIiIiIiIiOwUi4NERERERERERER2isVBIiIiIiIiIiIiO8XiIBERERERERERkZ1icZCIiIiIiIiIiMhOsThIRERERERERERkp1gcJCIiIiIiIiIislMsDhIREREREREREdkpFgeJiIiIiIiIiIjsFIuDREREREREREREdorFQSIiIiIiIiIiIjvF4iAREREREREREZGdYnGQiIiIiIiIiIjITrE4SEREREREREREZKdYHCQiIiIiIiIiIrJTLA4SERERERERERHZKRYHiYiIiIiIiIiI7BSLg0RERERERERERHaKxUEiIiJqtUxmEZIkyR2DiIiIiMhmqeQOQERERNZDkiSo9SaUao0o05pQpjOiTGtEme7qY8b/f+zK12q9EUazBJNZhEmUYBYlmMRrvzaLEoxmscrXZvGfoqCDUoCTSgknlQKOKgWcVAo4qZT//L+DAo7KK485OSj+dZ0Sbo5KeLs6wsfNAT6ujvB1c4SPqyN83Bzh7sSPQkRERERk3wSJP44nIiKya5IkoUBtQE6pDtmlWmSX6pBdqkNOqRb5aj1KtcbKYqBab6pStLN2jioFfFyvFA0rC4duVb/2c3dEiJcLwnxc4OyglDsyEREREZFFsThIRERkwyRJQr5aj+ySfwp+/xT/dMgu0yK3VA+DWZQ7aqsnCICfmxPa+FwpFF755YowHxeE+7igjbcrXBxZPCQiIiIi68LiIBERkQ0o1RqRlKfGpXw1Ll39b34FMoo1MJr5rb6l+Lk5Vikahvm4IMzXFe383NDW1xUKhSB3RCIiIiKiKlgcJCIisiJZJdrKIuA//61AgVovdzSqg5NKgagAd0QHuSM60B0dAj0QHeSOSD83KFk0JCIiIiKZsDhIRETUCmWVaHEmsxQXc8v/vwhYgcv5alQYzHJHIwtzVCnQ3t8NXUI80TnY48p/QzwQ6OEsdzQiIiIisgMsDhIREcksvUiDs1mlOJ1ZitOZZTibWYrCCoPcsUhm/u6O6BTsgS7Bnujexgt92/qgrZ+r3LGIiIiIyMawOEhERNSCiioMiEsvRlxaCU6ml+BMZimKNUa5Y5GV8Hd3Qu9wb/SN8Ebftj7oFebNQ1CIiIiIqElYHCQiImomepMZZ7PKEJdWgrj0K7/SijRyxyIbolII6BTsgT5trxQL+7b1QaS/m9yxiIiIiMiKsDhIRERkIUaziPj0Ehy6VIjDlwpxIq0YepModyyyM75ujugT7l1ZMOwV7g03J5XcsYiIiIiolWJxkIiIqJHMooQzmaVXioGXC3EspQgaHhhCrYxSIaB7qCeGRvtjaIcA9IvwgaNKIXcsIiIiImolWBwkIiKqJ0mScD67HIcvF+LwpQIcTS5Cuc4kdyyiBnF1VOL6dr4YGh2AG6L90THIQ+5IRERERCQjFgeJiIhqkZSnxuFLBTh0qRBHk4tQxFOEycYEeTphaIcrhcIhHfwR4OEkdyQiIiIiakEsDhIREf2LwSTiyOVCbD+Xi53nc5FVqpM7ElGLEQSgU5AHboj2xw3RARjQzhfODjwNmYiIiMiWsThIRER2r1RjxO4Ledh+Phf7LuSjXM+lwkQA4KRSoH+kL27sEoix3YMR4uUidyQiIiIisjAWB4mIyC6lF2mw7VwudpzLRWxKEUwivx0S1UYQgJ5h3hjbLRjjugcj0t9N7khEREREZAEsDhIRkV2QJAnxGaXYcS4X28/l4kJuudyRiKxa52AP3NwtGON6BKNzsKfccYiIiIiokVgcJCIim2U0iziQWIBt53KxKyEXuWV6uSMR2aR2/m4Y0y0I47qHoFeYFwRBkDsSEREREdUTi4NERGRTJEnCsdRi/HUyE5tOZ6NEY5Q7EpFdCfVyxphuwRjbPRgDIn2hULBQSERERNSasThIREQ2ISlPjbUnM/F3fCbSi7RyxyEiAP7ujri5WzDu7BuGfhE+cschIiIiomqwOEhERFYrr1yHdXFZWBuXiTOZZXLHIaJatPd3w6R+YbizbxueekxERETUirA4SEREVqVCb8KWMzlYG5eJQ5cKYeYpw0RWRSEAQzr4Y1LfMIztHgxnB6XckYiIiIjsGouDRETU6pnMIvYl5uOvk1nYcS4XWqNZ7khEZAEeTiqM7xGCu64LQ/9IX7njEBEREdklFgeJiKjVupSvxoojafg7LhOFFQa54xBRM4r0c8WdfcMwqV8Y2nhz2TERERFRS2FxkIiIWhWTWcS2c7lYfiQVhy4Vyh2HiFqYIACD2vthUt8wjO8RAhdHLjsmIiIiak4sDhIRUauQU6rDrzFpWBWbhtwyvdxxiKgVcHdSYVLfNnhgcCSiAtzljkNERERkk1gcJCIi2UiShINJhVh2JAU7z+fBxMNFiKgaggDcEB2AGYMjMaJTAARBkDsSERERkc1gcZCIiFpcqcaINcfT8evRNFwuqJA7DhFZkXb+brh/YAQmXxcGD2cHueMQERERWT0WB4mIqMXEp5dg+ZFUrD+VBZ1RlDsOEVkxdycV7uzbBg9yyTERERFRk7A4SEREzcpoFrEuLgtLD6fgVEap3HGIyMZcXXI8fXAERnYK5JJjIiIiogZicZCIiJqFxmDCr0fTsOhAMrJKdXLHISI7EOnnivsHReJuLjkmIiIiqjcWB4mIyKKKKwxYfCgFvxxOQYnGKHccIrJDbo5KTOoXhkduaI9wX1e54xARERG1aiwOEhGRRWSWaDF/32Wsik2H1miWOw4REVQKAbf1boOnRkahPfclJCIiIqoWi4NERNQkF3PL8dOeS1gXnwWTyG8pRNT6KARgfI8QPDMqGp2CPeSOQ0RERNSqsDhIRESNcjy1CD/uvoRdF/LA7yREZA0EARjdJQjPjOqAnmHecschIiIiahVYHCQiogbZlZCLuXsuITalWO4oRESNNqxjAJ4d1QHXRfrKHYWIiIhIViwOEhFRnSRJwsbT2fh+VxIScsrljkNEZDED2/vimVHRGNLBX+4oRERERLJgcZCIiGq1+0Ievth6AWezyuSOQkTUbPq29cbTozpgVOcguaMQERERtSgWB4mIqFqxKUX4fMsFxKQUyR2FiKjFdAv1xDOjojG2e7DcUYiIiIhaBIuDRERUxdmsUny+9QL2XMiXOwoRkWz6tvXGG+O7oD/3JCQiIiIbx+IgEREBAJILKvDltgvYeDqbpw8TEf2/0V2C8Pq4TugQ6CF3FCIiIqJmweIgEZGdyy7V4psdifj9eAZMIr8lEBH9l1Ih4O7rwvDC6I4I9HSWOw4RERGRRbE4SERkp4oqDPhhdxKWH0mF3iTKHYeIqNVzcVDi4aHt8PiIKLg7qeSOQ0RERGQRLA4SEdkZtd6E+fsuY+GBZKj1JrnjEBFZHT83RzwzqgPuHRgBB6VC7jhERERETcLiIBGRnRBFCb/FpuPLbRdQWGGQOw4RkdWL8HPFy2M6YWLPEAiCIHccIiIiokZhcZCIyA4cTy3CO+vO4kxmmdxRiIhsTq8wL7w+rgsGRfnJHYWIiIiowVgcJCKyYXllOny8OQFr4zJ5AjERUTMb2SkAb03siqgAd7mjEBEREdUbi4NERDbIYBKx6GAyvtuZiAqDWe44RER2w0Ep4KGh7fDsqGi48dASIiIisgIsDhIR2ZjdF/Lw/vpzuFxQIXcUIiK7FezpjDcndMGtvULljkJERERUKxYHiYhsRGphBWavP4edCXlyRyEiov83sL0vZt/WHR2DPOSOQkRERFQtFgeJiKycxmDC97uSsOBAMgwmUe44RET0HyqFgAcGReKFm6Lh4ewgdxwiIiKiKlgcJCKyYn/HZeLjTQnIKdPJHYWIiOoQ5OmE/03siok9udSYiIiIWg8WB4mIrFBibjlm/XUGMSlFckchIqIGGt4xAO/f1h1t/VzljkJERETE4iARkTUxmET8uCcJP+6+BIOZS4iJiKyVs4MCT43ogMeGR8FRpZA7DhEREdkxFgeJiKzE8dRivPHnKVzMVcsdhYiILCQqwA3v394dg6P85Y5CREREdorFQSKiVq5Cb8JnWxKw7EgqRP6NTURkk6YNCMesCV3h7qSSOwoRERHZGRYHiYhasYMJWXjlr/PIKuWBI0REtq6Ntws+u6snhnTgLEIiIiJqOSwOEhG1RtpiYPPrKMzPRr/kx+ROQ0RELUQQgHuvb4s3x3eBqyNnERIREVHzY3GQiKi1SdgEbHgBUOcAAJaHzsJbl7vJHIqIiFpSuK8LPr+rFwa295M7ChEREdk4FgeJiFoLTRGw+VXg9JoqD4suvrjZ8DkSK1xkCkZERHIQBODBQZF4bWxnuDgq5Y5DRERENorFQSKi1uD8BmDji4A6t9qns9qMxeBLD7RwKCIiag0i/Vzx+eRe6B/pK3cUIiIiskEsDhIRyUlXBmx8CTi9us5L5wa9h09To1sgFBERtTYKAZgxpB1eubkTnB04i5CIiIgsh8VBIiK5pMcAf8wESlLrdbnZLRDDKz5Fhs6pmYMREVFr1T7ADV9M7oW+bX3kjkJEREQ2gsVBIqKWJorA/i+AvZ8CoqlBTZPDbsfIpLubKRgREVkDhQA8ckN7vDimI5xUnEVIRERETcPiIBFRSyrNAP58FEg92OguPg/4CD+kR1ouExERWaVOQR74/p4+iA7ykDsKERERWTEWB4mIWsq5v4F1zwK6kiZ1Y/IIw6DSD5FvcLBMLiIislouDkq8d2s33N0/XO4oREREZKVYHCQiam6GCmDza8DJZRbrMiF8CsYm3max/oiIyLrd0acNPri9O9ycVHJHISIiIivD4iARUXPKjgd+fxgoTLRotxIEvOP7OX7JCrVov0REZL3a+7vh+3v6omuop9xRiIiIyIqwOEhE1BwkCTj8A7DzPcBsaJYhDN7t0a/gXZSbOEuEiIiucFIp8NbErrh/YITcUYiIiMhKsDhIRGRp6jzgr8eBSzubfaiTbR/EHRdvbvZxiIjIukzoEYKPJ/WApzP3pyUiIqLasThIRGRJiduBtU8AFfktMpwkKPGS55f4MzewRcYjIiLr0dbXFd/f0wc9w7zljkJEREStGIuDRESWIIrAno+AfV8AaNm/VnW+XdAn901ozcoWHZeIiFo/R6UCr47thJk3tJc7ChEREbVSLA4SETWVpgj4Y2aLLCOuyaHwR3FP4gjZxiciotZtdJdAfDG5F7xdHeWOQkRERK0Mi4NERE2RdRJY9QBQmiZrDEnpiEddvsL2Al9ZcxARUesV6uWM7+7pg34R/F5BRERE/2BxkIiosY4vBTa9Apj1cicBAFQE9EbvzFdgFAW5oxARUSvloBTwzi3dcB9PMyYiIqL/x+IgEVFDmfTAppeBE7/IneQaO8KfwczEQXLHICKiVu7e69vi3Vu7wUGpkDsKERERyYzFQSKihijLAlbdB2QelztJtSSVC+5z+AoHi73kjkJERK3c9e18Mfe+fvB14z6ERERE9ozFQSKi+ko7Cqy+H1Dnyp2kVmVB16NX2rOQJC4vJiKi2oX5uGD+A9ehS4in3FGIiIhIJlxHQERUH8cWA0sntvrCIAB45h7FnPYn5Y5BRERWIKNYi0lzD2Hz6Wy5oxAREZFMOHOQiKg2ZuOVQ0eOL5Y7SYNIju64A18hrsxd7ihERGQFBAF4ZlQ0XhgdDUHgzHMiIiJ7wuIgEVFN1PlXlhGnHZY7SaMUhgxHv+TH5I5BRERWZGy3YHw1pRdcHVVyRyEiIqIWwmXFRETVyb8ILBhltYVBAPDL3osP2p+VOwYREVmRLWdzcOePh5BepJE7ChEREbUQzhwkIvqvlAPAb/cCuhK5kzSZ6OKLmw2fI7HCRe4oRERkRXzdHPHDPX0xKMpP7ihERETUzDhzkIjo306tBpbdYROFQQBQaIuwNHiN3DGIiMjKFFUYcP/Co1h2OEXuKERERNTMWBwkIrpq3+fAn48CZoPcSSwqNHMLXotIlDsGERFZGZMo4X9/n8Xbf5+BKHKxERERka3ismIiIrMJ2PgCcOIXuZM0G7NbIIZXfIoMnZPcUYiIyAqN6x6MOVN7w0mllDsKERERWRhnDhKRfdOXA7/ebdOFQQBQVuRhWdjfcscgIiIrtflMDh5YGIMynVHuKERERGRhLA4Skf0qywIWjQMu7ZQ7SYtol7EWT4WnyB2DiIis1NHkItz902HklOrkjkJEREQWxGXFRGSfcs5cmTFYlil3khZl8gjDoNIPkW9wkDsKERFZqTbeLlj6UH90CPSQOwoRERFZAGcOEpH9SdoJLB5nd4VBAFCVZ2BZxCa5YxARkRXLLNHirp8O43hqkdxRiIiIyAJYHCQi+3Ji2ZUZg/oyuZPIplP6ajwQmiV3DCIismIlGiPuXXAU28/lyh2FiIiImojFQSKyH7s/BtY9DYgmuZPISoCEt8Qf4aGy7/tARERNozOKeHz5cayMSZM7ChERETUBi4NEZPskCdj8GrD3E7mTtBqOJZfxS3v7OIiFiIiaj1mU8MafpzFnx0W5oxAREVEjsThIRLZNNAN/PwUc/UnuJK1O7/TluDMoT+4YRERkA+bsSMSbf52GWeRZh0RERNaGpxUTke0yGYA/HgbOr5M7Saul8+2CPrlvQmtWyh2FiIhswJiuQfh2Wh84O/D7ChERkbXgzEEisk0GDbByKguDdXAuOo+F7ffLHYOIiGzEtnO5eHBRDDQG7mtLRERkLVgcJCLboysFlt8JXOKeevUxKGsJbvIvkjsGERHZiKPJRXhwUQwq9CwQEhERWQMWB4nIppTqS/Hw7mdxxqyWO4rVEMwGzHFZAAcFd5kgIiLLiE0pxgOLYlCuM8odhYiIiOrA4iAR2YxCbSFmbJ2BmLwTeMxdxIXgLnJHshpu+XGYG3VE7hhERGRDjqeyQEhERGQNWBwkIpuQp8nDjK0zkFicCAAoM5TjUW9HJAdEyZzMetyYvQBDfErljkFERDbkZFoJ7lsYg1ItC4REREStFYuDRGT1cipyMGPLDCSXJld5vEhfjJn+XsjwbStTMusimLSY67kEgsDlxUREZDnx6SW4b8FRlGpYICQiImqNWBwkIquWU5GDh7Y+hLTytGqfz9MVYGZIEHK827RwMuvkmXsUc9qflDsGERHZmNOZpbhnwRGUaAxyRyEiIqL/YHGQiKzW1cJgenl6rddlanLxSFhbFLoHtFAy63Zr/k/o7ckDXYiIyLLOZpVh2vyjKKpggZCIiKg1YXGQiKxSfQuDV6VUZOLRdp1Q6urTzMmsn2BQY6HfCrljEBGRDTqfXYZ75h9BoVovdxQiIiL6fywOEpHVydPk4eGtD9e7MHjVRXUaHo/uCbWzZzMlsx1+2XvxYfszcscgIiIblJBTjmnzj6CABUIiIqJWgcVBIrIqBdoCPLz14Rr3GKzLmbJkPNX5OmgdXS2czPZMK5qLjm5auWMQEZENupirxtR5R5BXrpM7ChERkd1jcZCIrEaxrhgzt85ESllKk/o5UZqE57oNgUHpZJlgNkqhK8bS4NVyxyAiIhuVlMcCIRERUWvA4iARWYUyQxke3f4oLpVeskh/h0su4KWeI2FSqCzSn60KydyK1yMuyh2DiIhs1OX8CjywMAalWqPcUYiIiOwWi4NE1OqJFRXYuPJDJBQlWLTfPSXn8EbvmyAK/KuwNo+of0SYM/eFIiKi5pGQU46Hl8RCZzTLHYWIiMgu8V/ERNSqiTod0p94Er0/24jncntZvP8txWfxTp9xkCBYvG9boazIw/KwtXLHICIiG3YstRhPLD8Oo1mUOwoREZHdYXGQiFotyWhExnPPQRMTA5jNGLL4BN7I7GPxcdYWn8ZHfSdYvF9bEpnxN54OT5E7BhER2bDdF/Lx8pp4SJIkdxQiIiK7wuIgEbVKkigi67XXUbF3378elNDnl1i8l9LX4uP9VnwKX/VhgbA2z+t+QKAT94QiIqLm83dcFt5bf07uGERERHaFxUEiapVy3n8fZZs2Vftcl5Ux+Oyi5QuEi0tOY26v8Rbv11aoyjOxrG31vydERESWsuRQCubs4GFYRERELYXFQSJqdfK++QYlK3+r9ZrIP2LwzVnLFwh/LDuDpT3HWbxfW9ExfTUeDM2UOwYREdm4OTsSsfRQitwxiIiI7AKLg0TUqhQtX4HCuT/V69qQdTGYe7I3BAtvTfRF+Vms7j7Gsp3aCAES3jLPhZeDSe4oRERk495dfxZ/x/EHUkRERM2NxUEiajXKtmxB7kcfNaiN35ZjmB/bEyrJsn+dfVBxAeu63GjRPm2FQ+llLI3cIXcMIiKycZIEvLwmHrsv5MkdhYiIyKaxOEhErULmhWLsO+YA0cm1wW09d57AggNd4SQpLZZHgoS39ZexrdMwi/VpS3plrMCdQfzHGhERNS+jWcKTy0/gWEqR3FGIiIhsFouDRCS7wkw1Nv10GqkZAs7d+gXMvkEN7sP1QBwW7IqGu+RosVxmyYzXTBnYFzXYYn3aCkEy4yPlT3BRmuWOQkRENk5rNOOhJbFIyCmTOwoREZFNYnGQiGSlLtZh/XfxMGiv7GGXl2tG/Mj3YQrv1OC+nGLOYN7WCPiILhbLZxJNeFHIx9F2/S3Wp61wLkrAovb75Y5BRER2oExnwv0LY5BepJE7ChERkc1hcZCIZKPXmrD+u3hUlOirPF5SaMTxPi/C0OX6BvepOnkeczcEI1B0s1RM6M16PKMqQ1x4H4v1aSsGZi7GGH8u9SIiouaXX67HQ0tiUaYzyh2FiIjIprA4SESyMJtFbPn5NIqyKqp9vqLMhJjIGdAOGN/gvhVnE/H9X74IM3k1NWYlrUmLJ130OBva3WJ92gJBNGKO83w4KCx8ZDQREVE1EvPUePrXkzCL/L5DRERkKSwOEpEsjvx5GBkJxbVeY9CaEeN1C8pvfKDhA1xMxte/uyHa6NfIhNcqN6rxuIeAxKCGL3m2Za4F8fgp6ojcMYiIyE7su5iP9zeckzsGERGRzWBxkIha3NG/VuPoH58isO2lOq81G0UcE69H0a3PN3gcKTkNH/2mRDdDYCNSVq/EUIpHfVyQ6t/eYn3aglHZCzDUt1TuGEREZCeWHErBsiOpcscgIiKyCSwOElGL0pzKh3uaGyRJRFr83wgIPQ4ItS8NkiQgriwa2Xe/1+DxpIwsvLvchH6GkMZGvkaBvggzA32Q5dPWYn1aO8GkxY8eiyHU8XtJRERkKe+tO4sDiQVyxyAiIrJ6LA4SUYvJKUjGmaNx8Mr2xJ1DXoGDgzPSz+6Ft+9OqBzMdbY/n+eP1Hu+hKRUNWhcKTcPbyytwBBdeGOjXyNHm4+ZocHI87Jc0dHaeebG4JuoE3LHICIiO2ESJTy54jgu5avljkJERGTVWBwkohaRXarFc5vScSY6Exc6FsEhS4E7+74EL89A5CSdgoNqLZzdDXX2cynLGYlTvoHo4t6g8cWCIjy/qBCjNe0a+xKuka7JwSNt26HYzXL7Glq7W/J+Rl8v/iONiIhaRpnOhIeXxKJEU/dnCCIiIqoei4NE1Ox0RjMe/eU4jp4rx/dHQnE+Wo+T3VJhLjRiXPtHEdamK4qzUmEs/xWe/nUXljKygLO3fgGzX8Nm7UmlZXhsYRZuVUc39qVc47I6A49GdUWZi+VORrZmgkGN+b7L5Y5BRER2JKVQg8eXH4fRLModhYiIyCqxOEhEze6lNfE4nXnlsIqiEiO+2eaB0+HeONbjAvQGPYZ63o7uXUaioqQIxem/wC+07v2D8nPNiBv+HoxtG3ZysKSuwP0LknF3qeVOHE4oT8UTHftC49Sw2Yy2yi97Hz5qf1ruGEREZEeOXC7C/9aekTsGERGRVWJxkIia1bc7E7HxVHaVx4xGEfO2CDji1RYxPRNQ5mpAN8P1uKH/NBh1OmSdX47A8JQ6+y4tMuJ4rxdh6DqoQZkkrQ6TFyTiweJuDWpXm1Nll/BUl+uhc3CxWJ/WbGrRT+joppU7BhER2ZHfYtOxYP9luWMQERFZHUGSJB4tSUTNYsuZbDyx4gRq+1tmRB9HjPZMRtfL7RGY7gR1aAU2HvoBkCSEdx+F/MxeAIRax3F0VqJf8Qa4HN3QsIAqFXZP74m5Aaca1q4WQ7w747tTe+Bg5t5HOW3GYOCl6XLHICIiO6IQgPkPXIcbuwTJHYWIiMhqsDhIRM3iXFYZ7vrpEDSGuk8h7treCXdHp6P9pUC0T/KEORRYf/x76HUVCOnYF2UlN8BsVNbah1IloC9i4LFjScOCKhQ48mBffBUc17B2tbjRpyu+iNsBlWiyWJ/Wal7wu/gopaPcMYiIyI64O6nw+xOD0DnYU+4oREREVoHFQSKyuOIKAyZ+dwCZJfVfVhrg64iHBhagXYoCXRNCoPB1wPZLS1BUlAm/sPYwYQL0FQ619iEIQE/Py/D7+8uGBRYEnLr3OnwQfrJh7Woxwac7Pjq5BQrJvjdHF10DMEL7KdK0znJHISIiO9LG2wUbnhkKHzdHuaMQERG1etxzkIgsSpIkPL8qrkGFQQDILzJgzk5vxEe44Hj3RBjLjRgTNh2RbXuhMOMyzJrf4OFbUcfYQHxpe2Tf/X5DQ6Pn8lh8cLlvw9rVYmPxGczuM85i/VkrhSYfy9qslTsGERHZmcwSLZ5bFQdR5DwIIiKiurA4SEQW9cPuJOy9mN+otnq9iLlblIj1a4OYngmoUBgw0GU8+vQYC3VRPkqzlsE3uKjOfs7n+SLlnq8gqho2W6Djqhh8ccFyBcI/ik/j074TLdaftYrIWIdn2ibLHYOIiOzMvov5+GZnotwxiIiIWj0uKyYiizl0qQD3L4yB2QI/pR/T3wHDnVPQI6kDfHMdkOefg91Hl0KhVCGs2x3ISw+vs482oUD0329AUVHWoLFzJ/bHMz0st8T4Ea8eeDZuo8X6s0YmjzYYXPYR8vS1Lw0nIiKyJEEAFk3vj5GdAuWOQkRE1Gpx5iARWURemQ7ProyzSGEQALbFGrE6px1Odk9BWkQFAvOCcevQ5wFJQtqpNQgIOwMJtY+VmQWcnfA5zP5tGjR20IZY/HS8N5R1nJJcX/NLT2NBr/EW6ctaqcozsaztJrljEBGRnZEk4IVVcUgv0sgdhYiIqNVicZCImswsSnhm5UkUqPUW7Tc+0YCf49viTJdCJHTJg0umEyYNfBWurp5IP70N/kEHoVDWfuBHfp4JccPegSmia4PG9t12DPMOd4ejVPspyfX1TdkZLO8x1iJ9WauO6avxYGim3DGIiMjOlGiMeHLFCehNZrmjEBERtUosDhJRk32x7QKOJte9F2BjZOXpMWe3P+IjlTjRMxlivhm3dnkWAQGRyEyIgZvbJji6GGvto7TIiGM9n4O++9AGje2x5yTm7+sEZ0nVlJdQ6TP1efzRbbRF+rJGAiS8ZZ4LLweT3FGIiMjOnM4sxbvrzsodg4iIqFVicZCImmRXQi5+2nupWcfQaE34fosDjgX4I7bXRWj1etwYdC+io65HfupFwLgG7j61n46sKTchNuw+aAbd2qCxXQ6dwoKdUfAQnZryEgAAEiTM1iZhY+eRTe7LWjmUXsbSyB1yxyAiIju0MiYdf53MkDsGERFRq8MDSYio0TKKNZj43QGUaGqfuWdJE653wBBlKnondoBniSMuu5xFbPw6OLm5wzf8bhTnetfaXqEU0FcRC8/tixs0rrlXJzw9NhuFiqbvWaQSVPhC2QY3Ju5vcl/WSBKUeMnzS/yZy83hiYioZbk6KrHu6aHoEOgudxQiIqJWgzMHiahRDCYRT6040aKFQQDYeNSIP4sicLzHZeSEaNG+vAtuGjQT+go18pJ+QUBYVq3tRbOEY6brUHj7Kw0aVxl/AT+uC0Swuen/mDBJJrwiZuFA1KAm92WNBMmMj5Q/wUXJvZ+IiKhlaQxmPP3rCeiM/B5ERER0FYuDRNQoH248h/iMUlnGPpZgxLzzEYjrmo2kDsXwzfHD7UNfAiQF0k//hsDw87V3IAHxJZHImvIBJKH+JxIL55Pw7Z/eiDB5N+0FADCKRrwgFCA24rom92WNnIsSsKi9fc6cJCIieSXklOOdv7n/IBER0VUsDhJRg204lYWlh1NlzZCercec/UGIizbiTI8MOGQrMan/y/Bw90Paqc3wDz4MQVH7ScYJuT5ImfYVRJVj/QdOSsEXq50RbfJr4isAdGY9nnZU41RYryb3ZY0GZi7GGP/mOciGiIioNquOcf9BIiKiq7jnIBE1yOV8NW79/iDU+tZx4qxSKeCBUUDPghz0Ot8BTi6O2Je9GlnZFxHYrgt0uptg0NV+2nCbEAHR69+AQl3/mZBCaDBmT1PgtGNeU18CPBzcsagc6Jx9rsl9WRuNfy/0ynoVRrH+MziJiIgsgfsPEhERXcGZg0RUb3qTGU+uONFqCoMAYDZLWLxdwl7XNojpcxHl0GGYz13o0vEG5CWfhyD+DjcvXa19ZGZLODP+M5gDwuo9rpSVg7eXGTBA36apLwHlRjUe81LhcmB0k/uyNq4F8fgp6ojcMYiIyA5d3X9Qb+L+g0REZN9YHCSievty20Uk5JTLHaNaaw+a8Hd5WxzreQn5Plr0FIdgcN+7UJqbBU3hCngHltXaviDPhJND34Yxslu9x5TyCvDKkjIM10Y0NT6K9CV4xM8d6X6RTe7L2ozKXoChvvLsX0lERPYtIaccX227KHcMIiIiWXFZMRHVy9HLhZg2/wjEVv43RlS4I+7tmo1OSQGIuOSO0tAybDn0E1QODgjueBcKMoNrbe/irkKftOVwPlX/wzIET08snB6CLW6XmhofoS6BWJqVg+AS+9oHqSxoAHqlPQdJ4vJiIiJqWQoB+O3RQRjQzlfuKERERLLgzEEiqpNab8JLa+JbfWEQAC6lG/Dt4SCc6KhGQtcceGZ74M7Br0AhKZFxdiUCwxNrba9VmxAbcg80Q+6o95hSWRkeXpiBO8o7NjU+srR5mBkWhgKPoCb3ZU08c2PwTdQJuWMQEZEdEiXgpTVxrWrbFCIiopbE4iAR1em9dWeRUayVO0a9lZSZ8O12d8SEueBkr2Qo8oE7+r4IL89ApJ1aD//QWAhCzZVOo15EjPNNKLt5Zr3HlCoqcM+Cy5hW2qXJ+VMrsvBIZAeUuNrXDIZb8n5GXy+13DGIiMgOpRdp8f56+zsYjIiICGBxkIjqsO1sDtYct74lrkaTiHnbBOz3CMbRvknQaQ0Y124m2oZ1R8bZ/fD02QEHx5pnCIhmCccMfVBwx6v1HlPS6XDH/AQ8XNS9yfmT1Ol4rEN3lDt7NbkvayEY1Jjvu1zuGEREZKdWHUvH9nO5cscgIiJqcSwOElGNCtR6vPHnabljNMma/SZs1IUhpk8Sip11GOx+K3p0GYXcS6ehUqyFi4e+5sYScKo4AplTPoIk1HMvPKMRNy88g6fzejY5+7nyFDzVuR80jm5N7sta+GXvw0ftrfs9R0RE1uuNP0+hUF3LZwMiIiIbxOIgEdXojT9Po7DCIHeMJtsbb8TS1HAc75mKjBA1uhoGYFj/e1CcnQZ96a/w8q99KeuFXC8kT5sD0dGpfgOaTBi2OA6vZPVucvaTpUl4ttsg6FXOTe7LWkwt+gkd3axnGTsREdmOArXB6n8wSkRE1FAsDhJRtVbb2NKaC6lGfBPbBic6FyKxUz5CCsIxccgz0JaVoijtF/iF5tfaPiVLhQuTvobo7l2/AUUR/Zcew9upfZqc/WjJRbzYYziMCocm92UNFLpi/BK8Su4YRERkp7ady8WaY+lyxyAiImoxLA4S0TXSizSYbYObcheVGPD1Lm/EtFXidK80OOe6YNKgV6EUVMg6twKB4ZdrbZ+dLeH0uE9hDmxb7zG7/xqLj5P6NjU69pWcx2u9R8MsKJvclzUIztyGNyMvyh2DiIjs1Oz155BRrJE7BhERUYtgcZCIqhBFCS+tiYdaX/NhHdbMYBAxd6sS+7x9cbzvJZhLzLitx3Pw9QlF2qm1CGhzAkDNJxkX5ptwcshbMLav/56CUWti8NW5phcItxefxdt9xkJCPfc/tHIzy35AWxed3DGIiMgOletNeGl1PESx5s8EREREtoLFQSKqYsGBy4hJLpI7RrNbuVfEJnMbxPS7jHJRj5vaPIh2kX2QfmYPvP13Q+lgrrFtWbERx7o8BX2vEfUeL+zvGPwQ3wdCE/+Nsa74ND7sO75pnVgJhSYfy9qslTsGERHZqaPJRVh4IFnuGERERM2OxUEiqpSQU4YvttnPUs4dJ4z4NbsNYnunINdbg+sdx6JPj3HISYyDk8M6OLvVfBiLtsKEmOApqBg6qd7jBWyKxc/HekHZxJl/q4pP44s+E5vUh7WIyFiHZ9ryH2ZERCSPz7ddwIWccrljEBERNStBkiTOlSciGM0ibv3+IM5nl8kdpcUF+zng4esK0eWyOyKTvJEfkItdR5fAzccfbn53oqzQvca2CqWAPg5x8Noyr97jVQzrg8cHn4NeqHl2Yn087tUDT8VtbFIf1sDk0QaDyz5Cnt4+DmQhIqLWpWuIJ/5+eggclJxXQUREtonf4YgIAPDTnkt2WRgEgJxCI77c44Oj7c041z0L/vmBuHXoC9CVlaAkczl8QwprbCuaJRzX90L+nW/Uezy3fSexYE9HuIpNK3b9VHoai3uOa1If1kBVnollbW2/CEpERK3TuewyzNtX+6FlRERE1ozFQSJCSkEFvt+dJHcMWen0Zny3zQH7/T1wvG8KVAUOuHPAK1AJDsi5sByB4Wk1N5aA00VhyJz6MSShfkuGnY6cxvwd7eAlOjcp91flZ7Gy+81N6sMadExfg+mhGXLHICIiO/XdrkSkFlbIHYOIiKhZsDhIRPjf32egN4lyx5CfBCzbLWGrEIjYfpeg05pwa5dn4O/XFmmnfkdA2ClItZxkfCHHE8nT5kByrF/Bz+H4Ofy8KRT+oluTYn9ckYC1XUc3qY/WToCEWea58HKwzVO0iYioddMZRby19ozcMYiIiJoFi4NEdm7tyUzsTyyQO0arsvmYGb8VtEFMn2QUOmkwKvAedIwaiPTTO+AXuB8KVc2F1JQsFRImfQ3Rw7deYylOX8QPa/3QxuzZ6LwSJLyru4QtnYY3ug9r4FCajF/abZc7BhER2an9iQX4Oy5T7hhEREQWxwNJiOxYqcaIG7/agwJ1zafy2rOwQEfM6J2Lbkn+CEtzR7JbAmLi1sI/vAOM4ljoNY41tvULUKHbgY+hyk6p32DtI/D6JA0uq4obnVelUOFrIRQjkg40uo/WThKUeNnzC/yRGyR3FCIiskP+7k7Y+dJweLnwkCwiIrIdnDlIZMc+2XKehcFaZOQZ8NWBAByNrkBix1y0K+uEMYMeQUF6EkTdanj4aGpsW5hvwsnr34Qxqnf9Brucik9/c0Rno3+j85pEE16ScnC43YBG99HaCZIZHyl/gpuSy+CJiKjlFaj1+GRzgtwxiIiILIrFQSI7dSylCL/Fpssdo9Wr0JjwzXYX7At2RlzvNHgU+OCOoS9DW1qCstzl8A2ueaZfeYkRsZ2fgK73qHqNJaVn4v0VEvoYQhqd1yAa8JyyBCfa9m10H62dU9EFLGy/V+4YRERkp36LTcPx1CK5YxAREVkMi4NEdshoFvHmX6fBTQXqRxQlLN4FbHP0R+x1yRBLBNx53ctwVDgj5+IyBITXvP+QrsKEmMDJqLhhcr3GkrJzMWupBoN0YY3OqzXr8JSzFmfa9Gh0H63d9ZlLMDagUO4YRERkhyQJePPPMzCaOYudiIhsA4uDRHZo3r7LuJirljuG1Vl31ITfS4IRc10KykU9JnR4HCFBUUg/tQqB4edqbGcyiIh1GInScY/XaxyxoBAvLinBSG1ko7OqjRV43F3CxaDOje6jNRNEI75ymg8HBSvcRETU8i7klmPevstyxyAiIrIIFgeJ7ExaoQbf7UqUO4bVOppgwvzEUMT0zkC2Zxlu8J6Erp2GIe3UFvgFHYRQw154oijhuLYH8ifNqtc4UnEJnlyYg/EVUY3OWmoowyM+TkgOaHwfrZlrwSn8HHVY7hhERGSnvtuViLTCmvcfJiIishYsDhLZmbf+PgOdkctgmiI5y4CvDgfiSJdSJEfko4d5MIb0uxuZCUfh7rYZDi7GGtueLgxFxrRPIQlCneNI5WrMmJ+Gu8o6NTprkb4YjwR4IdO3baP7aM1GZi/EUN9SuWMQEZEd0hlF/O/vM3LHICIiajIWB4nsyLr4LOy7mC93DJtQpjbh6x1u2NdGgbPdMxBaEolxg59EftpFKEy/w9VLV2Pbi9nuuDztG0iOznWOI2m1mLIgCfeXdG101lxtAR4OCUKuV2ij+2itBJMWP7ovgiBweTEREbW8vRfzsS4+S+4YRERETcLiIJGdKNUa8f6GmvfFo4YzmyXM26nANjdvHLsuFS7Fbpg0+FVoi0ugKVgOn8CaZ7SlZilx/s6vIXr61TmOpNfjlvnn8GhB90ZnzdTkYmZ4BArdAxrdR2vlmReLb6NOyB2DiIjs1PsbzqFUW/OqASIiotaOxUEiO/HZlgTkl+vljmGT/jhkxlptAI72T4FOa8YdfV6Es8oVeZd/QUBYdo3tcnJEnBrzEcwh7eoexGTC6EWn8Vxur0bnTKnIxKPtOqHUxbvRfbRWE/N+Rl8vHrJDREQtL79cj8+2JMgdg4iIqNFYHCSyA+ezy7AyJk3uGDZt32kzFiUHI6ZPOgocKjA24mG0CeqE9DO/ITD8Qo3tigpMOD7gDRg79Kl7ELMZQxafwBuZ9bi2BhfVaXiiY29UOHk0uo/WSDCoscB3mdwxiIjITv0Wm46EnDK5YxARETUKi4NEduDDjechcku2Zncxw4Q5xwJxpHsh0gKLMdj9FvTsciPSTm2Ef0hMjfviqUuNiO30OHR9R9c9iCShzy+xeC+lb6Nzni67jCe79IfW0bXRfbRGvtn78XH703LHICIiO2QWJXy48bzcMYiIiBqFxUEiG7c7IQ8HkgrkjmE3ispM+HKXJ/ZFmpDQMRudDf0wfMC9yDh3AJ7e2+DgZK62na7ChBj/SVAPn1KvcbqsjMFnFxtfIDxRmoTnuw2BQenU6D5aoylFc9HZXSN3DCIiskP7Ewuw+0Ke3DGIiIgajMVBIhtmMov4cBN/it3SjCYRc3cosd3LFSf7pCGgpA0mDnkOecnnoZT+gKtH9Xs/mgwijimHo2TCU/UaJ/KPGHxztvEFwkMlF/BSz5EwKVSN7qO1UehKsCRoldwxiIjITn208TzMXK5BRERWhsVBIhu2MjYdSXk8pEEuvx2QsNboj6MDUqAod8SkQa9CV1oCbckKeAVUvy+RKEo4UdEVeXf9r15jhKyLwdyTvVHDiuU67Sk5hzd7j4Eo2M63g+DM7ZgVWfM+j0RERM0lMU/NfZ6JiMjq2M6/BomoinKdEXO2X5Q7ht3bFW/CkowgHL0uDeWiEbf1eB6uDh4oTFkG/9Calx6dKQhG+rTPICmUdY7ht+UY5sf2hEpq3F/pm4vP4N0+4yBBaFT71ujhsh/R1kUndwwiIrJDc3ZcRLnOKHcMIiKiemNxkMhG/bD7EgorDHLHIADnUk34Nj4Qh3vmItu9FDeFPoC2bboj89yvCGx7qcZ2idluuDR1DiQnlzrH8Nx5AgsOdIGTVHcxsTp/FZ/Gx30mNKpta6TQ5GNZm7VyxyAiIjtUoDbgxz01f38nIiJqbVgcJLJB6UUaLDqYLHcM+pe8IhO+2OeFfR00SGqbgwEOY9C3xzikxf+NgNDjqGldcFqWAufu+Aqil3+dY7geiMeCXdFwlxwblXFlySl8bUMFwoiMdXimLf8cEBFRy1t0IBkZxTwgi4iIrAOLg0Q26LOtF2AwiXLHoP/Q60V8t9MRO/ydEN8jDe213XHjwBlIP7sX3r47oXKo/iTj3BwR8Td9BFNo+zrHcIo5g3lbI+Aj1j3bsDqLSk7j517jG9UWAD7er0f/+Wp4fFyGwM/LcftvGlwoqP51XWU0S5i9V4+ob8vh/EEZev2kxpYkU5VrVpwyIvzrcvh8WoYXt1ZdLpxSIqLjd2qU6a8tsD6n/RGBTlzaRURELUtvEvHZFu5/S0RE1oHFQSIbcyKtGOvjs+SOQTWRgGX7JKyDL2KvS4VnmT9uG/oi8pPPwUG1Fs7u1S8FLy4w4kT/12DoeF2dQ6hOnsfcDcEIFN0aFfH7sjP4pcfYRrXdm2rCU/0dceRhN2y/3xVGERizXIMKQ80npry1S4+fjxvw3ThnnHvKHY/3c8QdqzQ4mX2lqFigETFzvRZf3OSMbfe5YfkpIzZc/Kfg9+RGHT4Z7QRPp2v3TFSVZ2J52w2Nei1ERERNsf5UFk6mFcsdg4iIqE4sDhLZmA82nJM7AtXDlhMm/JIfgCMD0mDSKXDngFdhKC2DsfxXePpXf8K0utSE2A4zoes3ps7+FWcT8f1fvggzeTUq3+fqc1jd7aYGt9tynxum93ZEt0AlegUrseQ2Z6SVSjieXfPswWWnjHhzqBPGRzugvY8CT/R3xPhoFb48fKVQerlYgpeTgCndHdC/jRIj2ylxPv/KzNiVp41wUAJ3dnGosf/o9N8xPTSjwa+FiIioKSQJ+GDjebljEBER1YnFQSIbsuFUFk6klcgdg+op/pIJP5wNwKE+2ShUaXBL56fg4eSD4vRf4BdaUG0bvcaMGN87oB5xT90DXEzG12tcEW30a1S+DzQXsb7LqEa1vapUf+W/vi41n4SsNwPOqqqPuagEHEi7srQ42lcBjVHCyWwzirQSYjPN6BmkRLFWwv926/D9OOdaMwiQMMs8F14OplqvIyIisrTjqcXYeCpb7hhERES1YnGQyEboTWZ8uiVB7hjUQJkFZnx+wBv7OpchLSAfI/ynol1YH2SdX47A8JRq25iMImIVQ1A88ek6+5dS0vHRb0p0MwQ2OJsECf/TJ2N7x2ENbgsAoiTh+S06DAlXontgzaco3xylxFdHDEgsNEOUJGy/ZMKf543IVl9ZiuzjImDp7S54YK0WA+ar8UAvB9zcQYWXt+nw9ABHJJeI6POzGt1/VOP3c9XvL+hQmoxlkdsb9TqIiIia4tMtCdCbat9/l4iISE6CJEk1bwRFRFbj572X8PFmFgetlSAA04cDg0o06HouBCmuF3D05F8I7z4K+Zm9AFQ/866bfy6Cfp9dd/9Bgfj0Xmccc2r4fpQqhQrfIBjDLh1qULsnNmixOcmEAw+5Icyz5p9F5VeIeGS9DusvmiAAiPJVYHQ7JRbFGaGd5Vltm70pJry8XYe9093Q4Vs1Vk5yQbC7gAELKpD4jDsC3a4dTxKUeMXrC/yeE9Sg10FERNRUb47vjEeHRckdg4iIqFqcOUhkA8p1Rvy455LcMagJJAlYvAdY7+CO433SEKaNxs2DH0P6mV3wCdgLZQ0nGZ8tCEL6PZ9DUtQ8Mw8ApNw8vLZUjaG68AZnM4kmvCjkIyayf73bPL1Jiw2JJux+sPbCIAAEuCmwdqorKt70QOrz7kh4yg3ujgLa+1TfTm+S8OQmHX6e6IKkIhEmERgeqUInfyU6+ilwNKP6eyVIZnwo/AQ3JU/yJiKilvXjnktQ67m9BRERtU4sDhLZgMUHU1CqrX45JVmX9bEiVhT74+iAdDhqPHHH0FeQf/kMnB3Xw8mt+t/jxCxXJE39BqJz7acTS4VFeG5RIUZr2jU4l96sxzMO5YgL7137GJKEpzdp8VeCCbsecEW7Ggp81XFWCWjjqYBJBP44b8RtnVTVXvfBPj3GRqnQN0QJswiYxH8mwBvNgLmW+fBOxRewqP3eemciIiKyhBKNEUsOJssdg4iIqFosDhJZuTKdEQsP8MOmLYm5aMSPif440i8LarMZk/q9AkNZOcya3+DhW1Ftm/QsAedv+xJm39qXzEqlZXhsYRZuVUc3OJfGpMGTLgacC+1W4zVPbdJh+Skjfr3TBR5OAnLUInLUIrTGfyp2D/ylxRs7dJVfH824ssfg5WIR+1NNGLtCA1ECXh3idE3/5/LNWHXWhNkjrzzX2V8BhSBg4QkDNl40IqFARP/Q2mdRDshcgrEBhQ19+URERE2y4EAyynX8YS4REbU+LA4SWbnFBzhr0Bal5pjw2REfHOhejGyPYkyIegxeLv4ozVoG3+Ciatvk5ppxauRsmMJqL/xJ6grcvyAZd5d2anCucqMaj3kokBRUfdu5x4wo1QMjlmoQ8qW68teqs/+8R9NKxcrDRgBAZwLe2qVH1x/UuGOVFm08FDjwkBu8navusyhJEh5dr8NXNzvBzfHKcy4OApbc7ozZ+/R4eJ0O3493Rps6ljELohFfOc2Hg4Jb7hIRUcu5MnswRe4YRERE1+CBJERWrExnxA2f7mZx0IYpFAJmDjNhUKEZHZOCcFo8hPOJBxDW7Q7kpVe/f6Cbpwp9Li6AY0JsrX0Ljo7Y+FAXLPE52+Bc/k6+WFpQirYF1jtrdVf403gocbDcMYiIyI54uzpg/6sj4eHsIHcUIiKiSpw5SGTFOGvQ9omihHl7lFjv6owT3dPRFQMxqM8kpJ1ag4CwM5Bw7c93KspMiG33MLT9x9bat2QwYPyCs3gyv2eDcxXoizAz0BfZPg0/4KS1GJm9EEN9S+WOQUREdoSzB4mIqDVicZDISpXpjFjEja3txp9HRfym9kZM/3QE6Npi/JCnkH5mO/yDDkJRzem7eq0ZMd63oXzUfbV3bDJhxKI4vJTdu8GZsrX5mBkainzP4Aa3bQ0EkxY/ui+CIHACPRERtRzuPUhERK0Ni4NEVoqzBu3PwfMmzL3sg8P9MyEZnDFp8KvIv3wGbm6b4Ohy7XvBbBRxDINQdMvztXcsirh+6XG8ld6nwZnSNNl4JKI9it38Gty2NfDMi8W3USfkjkFERHakVGvEYs4eJCKiVoTFQSIrdOWE4styxyAZXMoy44vjvtjfKx9FKg3u6P0CzGVqwLgG7j7aa66XRCCuPBo5k9+tvWNJQs/lsfjgct+GZ1Jn4LGorihz8Wpw29ZgYt7P6OulljsGERHZkYWcPUhERK0Ii4NEVmjRgWSU6UxyxyCZlJSb8fled2zvoEeKfx7GhM+Aj3MgynOXwSeopNo25/IDkHbPF5CUqlr77rgqBl8kNLxAeL48FU927AuNk3uD28pNMKixwHeZ3DGIiMiOcPYgERG1JjytmMjKlOmMGPrJLhYHCQAwZRAwSq9B13MhuKA4gTMXdiG0y13Izwit9vrwUAlRf70Ohbb6mXK/FhdjUVEh8iURqggnhNwXAtf2rtVee/njy9Bc0Fzz+NiOjtg8zRkA8MUhPT47aAAAvDbEES8Ndqq87miGCU9u0uHoTDeoFEKDXndzWBn6Bt643EPuGEREZCe8XByw/7WR8OTJxUREJDMWB4mszJwdFzFnR6LcMagVGdldgds8S9D7ZBsUemRjz9FlaNtzHPLSu1R7fWCQEl22vwNlUW6VxzeXleH1nGy8ExSEns4uWOCmxMbky4j+pCNUntfOODSpTZBM/3wLMVeYkfS/JIx46jpsC0jB+SwtBi6owIZ7XCFJwMSVGsTMdEOPICVMooT+8yswb6IL+rdRWvaGNJLo7I3xpi+QoK6+GEpERGRpL4zuiOdGR8sdg4iI7ByXFRNZkVKtEYsO8IRiqmr3GRE/p/vi8IAsuBuCccvQ55B+eiv8gw9DUFx7knFerhnxI9+HKbxTlceXFBdhspcX7vTyRgcnJ3xkVMIXTijbV1LtuCp3FRy8HSp/qc+ooXBUIK+7Bq/2uhHnCoCeQUqMaqfCje1V6BmkQELBlTyfHzRgWFtVqykMAoBCV4IlQavkjkFERHZk0cFklHHvQSIikhmLg0RWhHsNUk3Op5vwVbw3DvTNhVYSMGnQayhIOQsPz61wdL72PVNSaMTxPi/C0GUgAMAgSTin02Ggq1vlNQpBwGCVA6KPKuAs1b5XIQAU7y+G1/VeUDgpsKP4LHaMGIaLhSLSSkWkloi4WCiie6ACl4pELI4z4oNRTnX22dKCM7djVuQFuWMQEZGdKNUasfhAitwxiIjIzrE4SGQlynVGLDrIWYNUs/wSMz7Z74FdndXI9SjB7d2ehVSuhSD+Djcv3TXXV5SZEBM5HdoB41FiNsEMwF9VtQjop1ShKL8IC3ZGwUOsuZinuayBPkMPn+E+lY8ddU/H4On9cNMyDcYs1+DjG53RJUCJxzZo8dlNTth6yYTuP6rR52c19qW2nqL3w2U/oq3LtfeLiIioOSw8cBlqfev5PkhERPaHxUEiK/FbTDrKOWuQ6mA0ivhmlwPWBQIXwrMxKvge+LuGQlO4At6BZddcb9CaEeN1C9RDJ9far2PsWczbEgY/sfr9+Ir3FcMpzOmaw0tSB+rw0MKpuPC0Ox6/zhFL4wzwcBIwKEyJmeu0+GuKC74a44ypv2uhN7WOLXAVmnwsa7NW7hhERGQnynQm/BaTJncMIiKyY3WvEyMi2ZlFCUsOpcgdg6zI8gNAXi9n3NIjA33iR8OnXTDiEn5BcMe7UJAZDADYe2YtdsavRpm2CG1820MBAQWmqgXoQrMJ/ioV/iotwazVfwOr/3lOUAnotqAbRL2I0qOlcOvshvPPnAcABIwPgP84/ytZSk4h1/V67PxqJ8p0IvY/5I6jmWZ09FMg2k+JaD/AKAIXC0X0CGodexBGZKzDM22vx3dp7eSOQkREdmDJoRTMGNIOSoUgdxQiIrJDnDlIZAU2n8lGZolW7hhkZbbFi1iQ64mj12WiDbpgRN/7kXF2JQLDE3E8aTf+OvwTxvV7AK9N+glt/DoAgoDNgR0r24uShCMaDXo7uwAA3BUK7I3qgL03jsSNXw5Apy+vHGhSGlMK0SBCfUaN8CfCEf5EOHL/zIUu/crSXMksYe4P+yGGBuLFQc4I81TALF4pCF5lEiWYW8fEwUrPaX9EoBM3iSciouaXUazF1rM5cscgIiI7xeIgkRVYsJ97DVLjxCeb8dVZLxy8LhdKyQu3DXkRmWc3Y1/CUgzuMh6DOo9FiE8kpg57Hs6ObtgavxcLuo5DksmE93JzoRVF3OHlBQDQiSKWFRchICMb32/1RBe3IABXDiJxiXSBc7gz3Lu6w72rO5zDnaHP1gMACjYXwMHfAZdKS+H90C0AgP5tlEgoELE50Yh5xw1QCgI6+bWub0mq8kwsb7tB7hhERGQnFuy/LHcEIiKyU63rX2JEdI3jqcWISy+ROwZZsZwiMz465I7d3UpR5qjHLX1fQHJWBvp0VsLB8coyYoWgQPeIgQj2icDi7StwZ0oqEoxG/BwWXnlIiQnAiuJijLqUhCcPHcGMeRpEprlDc1EDn2E+MOQaYCg0wFBggD5HD6cwJ+jz9CjeVwxdhg6hD4bic00C/uw6GmGeCnw3zhkz/tbhw/16LL3dGS4OrW8pVXT675gemiF3DCIisgMn0kpwMq1Y7hhERGSHBEmSWtlCLiL6tydXHMem01xmQk1XfmIDzPF/QlNUBKPJhJk33ohB3TsCDrdAW+6EtUd+RmL2Kbxyxw+Iu7wfu878ivy8yzCJZgSqVBjg6oqp3j5QiyIWFxXikEYDV6USOhcFvMf7QuGkQMG2AgCAZx9PqM+poXBVwH+0PyRRQt7aPAhKAaH3huK7nj0wPmG3zHekfoxe7XBd0XsoNXKbXiIial4Teobgh3v6yh2DiIjsDGcOErVi6UUabD2bK3cMsgEV5/ehaNcCqPpNw/g33wcArNx/GE6CD/Slv8LLX13leldnD9zY417MemgRfh88Gvf4+ODP0lIUmk3o7+qKp/z9YZQk3ODqih/DopD/Zx5co13R8ZOOiP4wGuqzanj09oDSRQnXDq7IXJSJts+0RfC0YKTNTcMbFcnYGX2DHLeiwRxKk7EscrvcMYiIyA5sOZODjGKN3DGIiMjOsDhI1IotOZQCs8jJvdQ05Sc2oGDjV4AoojxuM45cUgCCAMFRgfizBejZfiSK0n6BHjlwVDpj/rZ3sXz3Z5i/7R3EnjmC3EFv4e6hE9HRyQkntFqsLyvFzPR0SABOa7UYKEro5uiCLineMOQbkPBcApzDnVFyqASh94VCc1kDp2AnOAU7wb2LOySzBE22Bq+IWTjYfqDct6deemT8iruCWagnIqLmZRYlLD2UIncMIiKyMywOErVSar0Jq2PT5Y5BVi7jp4dQtP0nwGwCJBGGvBTkrX4HDgHtYHbxxs7yE/BTtseIPvfj1MUYFJQnIz55P4rUVwphO+JXo6LMiF+kbkg2i/izpASvZWejVLxy1HC60Yg/SkqQotXCZW0yLr5yEWa1GWadGf5j/OHg6wCIV04svkoyS5BECUbRiOcVhTgW0U+We9MQgmTGh8JPcFOKdV9MRETUBL/FpkOtN8kdg4iI7AiLg0St1G8xaSjnB0NqgtzVb8NcmvfPAyonwGyAZNRB5RUIbUEWTidk4FfvU5j9xzxoDCYUq0vh5uwCf48QAECppgDPzBuNb9a+grCAzsgzmwEAvoor3z7MAD7Jy8OTvr5YXVgIAUD33mHQp+tRtKcISW8nQRIl6LP1KD9VjqI9RRAUApxCnAAAOrMeTztW4FRYr5a8NY3iVHwBi9rvlTsGERHZuHKdCav4A2IiImpBLA4StUJmUcISLimhJtKlnAQAOLXtCQAImPx25XPGokw4te0BY1kB3n/iJRzNTwIEAQ5KB8y5byr8fRwqr3VycEW7oG5Iyj5d+VikoyMEXPkmMtbTA8tLSgEA3goFSs/mQigVK/cYzF6RjeBpwchckIn89fkImxkGheM/334qTBo84WbCheCuzXg3LGNA5hKMCyiQOwYREdm4JYeSubUMERG1GBYHiVqhrWdzkFGslTsGWTGztgz4/8PonSN6AoIC0GkgODhfeV5dBJWHH1za90PEy2uhvOMrGE1GtAkNwdj2j+DdSVOgEAQ4KB2hN2rxwm1zEBl4pXingAqXFY6QADgA8FQokGEyAgCe8Q+ABAAGM0acCarcY9At2g2dv+2MTl92gkdvj2vylhnK8ai3CpcDO7TA3Wk8QTTiS6cFcFDwH2xERNR80ou02HY2R+4YRERkJ1gcJGqFFh5IljsCWTl9dmLl/ytdveAY3AG61HgIji5XHhTN0KXEw6lN5yrtdB5+ON41EwP9bgUgQKmQgCvlPgT7tIWTygUiTCjRlEGlUOGhgEAsLS6GgCtLjWfn5SLDaIRBkrBsxUE8frFz5R6DdSnSl+ARPw+k+0VY6C40D9eCU/g56pDcMYiIyMYt4OdBIiJqISq5AxBRVSfTinE8tVjuGGRDRK0anv1vR8HGryEorywXlswmSEYd3HuMBgAUbPgSAFCiAb657I7AxB8BAAqFEoARh5OXICZxO6YOfQ6Du0yo7PuHzc9BRB5UAIr+/5CSwS6uOKTVQCdJ2Pn9NrjBoXKPwbrk6QrxSHAQlpjNCC7JsNAdsLyR2QsxzLcb9hV5yx2FiIhs1PHUYpxMK0aftj5yRyEiIhvHmYNErcyigylyRyAb4BQSXfn/uoyzcOsyDD4jH4Jk0Fx5UKFA4N2zoXS78g8OU1k+gCvLjS/nmrErWYQoidDodQCAgyc24NnJj1QpDCbnnMP5tDMAgC5uHhAACAAWtG1bec228nJ85hOAT9Ouq3f2TE0uHgkLQ4F7YGNeeosQTDp8774YgsDlxURE1HwW83MhERG1ABYHiVqRogoDtp7h/jLUdEoXT0C4Uq7TJZ+A+vROOIb9c+CHZ//b4RTaCQUbvkTx3iUIvucTCCpHGIsyYci9DFX7IVf2KQTg6uyCJY//gCinIgSEnYL0/8uMv93wMgRBgeHdbodjaG9cLZP9UVJSOc7rgUEY7u6OqDUx+Opc33rnT6nIwqPtOqLUtfXOlvDMi8V3UcfljkFERDZsy9kcFFcY5I5BREQ2jsVBolbkzxMZMJhFuWOQjXCO7ANAAiQRhdt+QO6S5648oXSEZ79bkPbVXag4uwfapFgAgHvfiYBoQvaSZ5G95FlAuvJe1Oi0eHzl27i95wuoyDwPv8D9WL73MxjNerg5euLW62fiuqibAQACBLybm/P//w8MdXOrzBP2dwx+iO+D+k62S1Sn4bHonlA7e1rkfjSHCXk/o69XudwxiIjIRhlMIv46mSl3DCIisnEsDhK1IquPpcsdgWxI0N2z4RDY/soXpiuzDhSuPgi+52Mo3XwgmQyAADgGXzkh2HfkQ3Bu27PavopVLoiPysLoiAdRnleIIwlb4esRgHtHvgwnBxf0iBiEyMAuECHBDMARwHtBwQhycKjST8CmWMw71gsqqX7ffs6WJePJztdB6+jaqHvQ3ARDBRb4LJM7BhER2TB+PiQiouYmSJLEDZOIWoETacW480eegEqtV6dQBWa2V6PfmWAkG+NwKfsknL3uRHlx1cKdQimgr/IYPLctqrGvimG98fjg89AL5nqNPdC7E344tQ+OZn2TXkNz+S30Dbx+uYfcMYiIyEb99eRgHkxCRETNhjMHiVqJ1bH8qTC1bheyRHx8yh17e+chxLUbruswDmW5y+EbXPV0bdEs4ZixHwpuf6XGvtz2xWHBno5wFR1qvObfjpRcwIs9R8CoqN/1Le3uorno7K6ROwYREdkozh4kIqLmxOIgUStQoTdhfXyW3DGI6lRUJuKjA67Y1lUNhasnbu4zE3mXfkVA+H/2Q5KAUyWRyJryASRBqLYvpyOnsWB7O3iJzvUae2/JebzRezTMgrKpL8PiFLoSLAlcJXcMIiKyUevjs6ExmOSOQURENorFQaJWYOOpbFQY6re8kkhuRpOIOXuVWBNsQq6PDndc9yIKk7YgMPzcNdcm5PogZdpXEFWO1falOnEOP28Khb/oVu3z/7W1+Cze7jMWEqovOMopOGs73oq8IHcMIiKyQWq9CRtOZcsdg4iIbBSLg0StwG+xaXJHIGqwFUeAJVDhfJt8TOz6NLTZCfALOghBWfXE7eQsRyROngPR3avafhSnL+KHtX5oY67fqcTrik/jw77jm5y/OTxU9gMiXXRyxyAiIhu0ilvQEBFRM2FxkEhmSXnlOJFWIncMokbZccaM73KdEdspG8PCp8LVIMHdbTMcXIxVrsvMlnBm/GcwB4RV249w4TK+/t0D7U3122x9VfFpfNlnYpPzW5pCU4Bf2vwldwwiIrJBx1OLkZRXLncMIiKyQSwOEsnstxj+FJis25l0Mz4554qDPXPRyW84Ir07QmH6Ha5eVWfQFeSZcHLo2zC26159R5dT8elvjuhqDKjXuEtKTmFu7wlNjW9xbTPW47m2l+WOQURENoizB4mIqDmwOEgkI6NZxF8nM+u+kKiVyysx471DLtjevQS+nlHoHzUBmoLl8AksrXJdWbERx7o9A13PG6rtR0rPxHvLzehjCKnXuD+WnsaSnuOanN/SntX8iGAng9wxiIjIxvx5IhNGs1j3hURERA3A4iCRjLafy0VhBQsIZBsMRglf7FHhz3AdtN6OGNv7ERSl/oaAsKobqGvVJsSG3APNkDuq7UfKycOspRoM0lW/BPm/viw/i9+6j2lyfktSqrOwrO1GuWMQEZGNKawwYPu5XLljEBGRjWFxkEhGXBpCtmjRYQG/OAKpQeW4tfezKEnZjsDwqqf4GvUiYpxvQunNj1Tbh1hQiBeXlGCUJrJeY35UcQF/d7mxqdEtqkP673ioDf+MExGRZfHzIxERWRqLg0QyySrRYn9ivtwxiJrFplMSvi9WIb5dHm7u/CiMeRfhHxIDQZAqrxHNEo4beqPgjteq7UMqLsETi3IwQd2hzvEkSHhHfxlbOg232GtoKgES3jDNhY+DSe4oRERkQ/Yn5iOrRCt3DCIisiEsDhLJZM2xDIhS3dcRWasTyRI+vuiMI12zMSD8TniYAE/vbXBwMv9zkQScKm6LzKkfQRKEa/qQytWYviAVd5V1qnM8s2TGG6Z07O0wxJIvo0kcSlPwS7ttcscgIiIbIkpXPkcSERFZCouDRDJZG8eDSMj2ZRWJePeoC3Z2K0KkX3+09+4CpfQHXD30Va67kOOF5GlzIDo6XdOHpNViyoIk3F/Stc7xTKIJL0q5ONJugMVeQ1N1T/8Vk4Nz5I5BREQ2ZF08P0cSEZHlCJIkce4SUQs7nVGKW74/IHcMopYjAI8OkjAmVwUXjRn7zq6ER9BdKM33rHJZSIiATuvfhEJdcm0fKhV2zOiOef5n6hzOReWCn3Wu6JN+0kIvoGn0Ph3RN+9tVJj5MzkiIrKMzc/dgC4hnnVfSEQWIUkSTCYTzGZz3RcTyUypVEKlUkGoZnVWdVgcJJLBR5vOY96+y3LHIGpxt/YG7pIkhBd4Ykvcz/CNuAUFWYFVrvELUKH73g+hzEu7tgOlEoce6I05wfF1juXu4IYFFSp0yzxtofRNczR8JqYkjpI7BhER2YinR3bAyzfXve0GETWdwWBAdnY2NBqN3FGI6s3V1RUhISFwdHSs81oWB4lamCRJGPrpbmRyI2myUwOiFJjuZ0D3VH9sT1gMz4jrkZcWVeUaTx8H9Dz1PRwvnbq2A0HAyfuvw8dt6p4V6OXoiUUlJnTMTbBU/EaTFA540u1LbM73lzsKERHZgPb+btj18gi5YxDZPFEUkZiYCKVSiYCAADg6OtZ7NhaRHCRJgsFgQH5+PsxmM6Kjo6FQ1L6CicVBohZ2LKUId/10WO4YRLKKDBTwTEc9+lwIwLHM9YC3P/Kz+wLSPx+0XNxU6JP5G5zjdlfbR8LUAXi73Yk6x/Jz8sGSQjUi8y9ZLH9jafx7oFfW6zCK/EBJRERNt/HZoegW6iV3DCKbptPpkJycjIiICLi6usodh6jeNBoNUlNT0a5dOzg7O9d6LTc/Imph6+Oz5I5AJLuUPAnvHXfC3i6F6Bk+Dt6iEt6+O6Fy+GcPF22FCbFBd6Ni6KRq++j8Www+u9i3zrEK9cWYGeCFTN+2FsvfWK4FpzEv6pDcMYiIyEZsPJUtdwQiu1HXzCui1qYh71m+u4lakFmUsPE0Ty0lAoAyrYT3DzhgQ5QaQUE9EO3TDQ6qtXB2N1ReY9SLiHW6EaVjH622j8g/YvDN2boLhLnaAswMCUaeV4jF8jfWiOyFGOZbIncMIiKyAZtOszhIRERNx+IgUQs6crkQBWq93DGIWg1RlPD9IQHLfY0wB/lgcLtbYVL/Bk9/9T/XmCUc1/dC/p1vVNtHyLoYzD3ZG0Idm2RkaHLwSNt2KHKTd88/waTDD+6LINQVmIiIqA4phRqcySyVOwYREVk5FgeJWtBG/nSXqFprTkr4wQBkhBpwc5eHoc37E36hBf9cIAGni8KQOfVjSNVsAO235Rjmx/SESqr929pldQYejeqCUhdvC7+ChvHIO4bvo47JmoGIiGzDBi4tJqJWasmSJfD29q739Xv27IEgCCgpKan1usjISMyZM6dJ2agqFgeJWogoSth2lkuKiWpyIFHCJxkqnIwsxJiuj0CfuweB4SlVrrmQ44nL0+ZAcrx2Q13PXSew4EAXOEuqWse5UJ6KJzv2RoWThyXjN9j4vHno61UuawYiIrJ+XFpMRJZ0+PBhKJVKTJgwoUHtqivYTZkyBRcvXqx3H4MHD0Z2dja8vK4ctFRTcTE2NhaPPlr9tkPUOCwOErWQmJQiFKgNdV9IZMeSckS8d9oJ+6MLMDh6KpRlyQhoEwfgnyW4qVkqJEz6GqKH7zXtXQ/EY8GuDnCXHGsd51TZZTzVZQB0Di4WfgX1JxgqsNDnF9nGJyIi25BWpMGpjBK5YxCRjVi4cCGeeeYZ7Nu3D1lZTTtM08XFBYGBgfW+3tHREcHBwRCqWSn0bwEBATw52sJYHCRqIZv5U12ieilRi3j3kAM2R5WhU9sR8IcjfAL2Qvmvk4yzs0WcHvsxTCGR17R3jDmDeVsj4CPWXvg7XpqI57vfAKOy9kJic/LJOYhP25+SbXwiIrINPLWYiCxBrVZj1apVeOKJJzBhwgQsWbKkyvPr169H//794ezsDH9/f9xxxx0AgBEjRiA1NRUvvPACBEGoLO79e+bfxYsXIQgCEhISqvT59ddfIyoqCkDVZcV79uzBjBkzUFpaWtnnu+++C+DaWYolJSWYOXMmAgIC4OnpiVGjRiE+Pr7y+fj4eIwcORIeHh7w9PREv379cOwYt/j5NxYHiVqAJEnYwiXFRPVmNkv46qCAX4P08AiNRhffnnB2XA8nN2PlNYX5Jpy8/k0Yo3pf01518jzmbghGoOhW6zgHSxLwUq9RMClqX4rcnCYX/YTO7hrZxiciIuvHfa2JyBJWr16Nzp07o1OnTrjvvvuwaNEiSNKVFTwbN27EHXfcgfHjx+PkyZPYuXMnBgwYAAD4888/ERYWhtmzZyM7OxvZ2df+ndSxY0dcd911WLFiRZXHV6xYgXvuueea6wcPHow5c+bA09Ozss+XX3652tyTJ09GXl4eNm/ejOPHj6Nv37648cYbUVRUBAC49957ERYWhtjYWBw/fhyvv/46HBwcmnSvbA2Lg0Qt4ERaMXLLeEoxUUOtOCZhrtKEklAXDIm8DZJ+DTx8KyqfLy8xIrbzE9D1ufGatoqzifj+T1+0NXvXOsbu4nN4s/cYiII83xIVuhIsCVwly9hERGQbMoq1iEsvkTsGEVm5hQsX4r777gMAjB07FqWlpdi7dy8A4MMPP8TUqVPx3nvvoUuXLujVqxfeeOMNAICvry+USiU8PDwQHByM4ODgavu/9957sXLlysqvL168iOPHj+Pee++95lpHR0d4eXlBEITKPt3d3a+57sCBA4iJicGaNWtw3XXXITo6Gl988QW8vb3x+++/AwDS0tIwevRodO7cGdHR0Zg8eTJ69erVtJtlY1gcJGoBm05z1iBRY+1KAD7PE3AxrAKjO06HsXgdfIOLKp/XVZgQE3AX1MPuvrZxYjK+XO2CaKNfrWNsLj6D9/qMg4Ta9zdpLsFZ2/FW5AVZxiYiItuw8VTT9gYjIvt24cIFxMTEYNq0aQAAlUqFKVOmYOHChQCAuLg43HjjtT+Qb4ipU6ciJSUFR44cAXBl1mDfvn3RuXPnRvcZHx8PtVoNPz8/uLu7V/5KTk7GpUuXAAAvvvgiZs6cidGjR+OTTz6pfJz+weIgUQvYyiXFRE1yLlPCO+dUONq+CCM7Pwix+AACw9MrnzcZRBxTjUDJ+CeuaSulpOOjlQp0NwbVOsafxafxSd+GncpmSQ+V/YBIF51s4xMRkXXbfIafN4mo8RYuXAiTyYTQ0FCoVCqoVCrMnTsXf/zxB0pLS+Hi0vSD/IKDgzFq1Cj8+uuvAIBff/212lmDDaFWqxESEoK4uLgqvy5cuIBXXnkFAPDuu+/i7NmzmDBhAnbt2oWuXbvir7/+avLrsSUsDhI1s6S8cmQUa+WOQWT1Csol/O+ICtuiStAv+lY4V6QjIOwMpP8/yVgUJZzQdEf+pFnXtJUys/HOMiOu04fWOsavxacwp488BUKFpgC/tOGHFCIiapyMYi0Sc8vljkFEVshkMuGXX37Bl19+WaXAFh8fj9DQUKxcuRI9e/bEzp07a+zD0dERZrO5xuevuvfee7Fq1SocPnwYly9fxtSpU5vUZ9++fZGTkwOVSoUOHTpU+eXv7195XceOHfHCCy9g27ZtuPPOO7F48eI6s9oTFgeJmtmeC/lyRyCyGUaThE8OCFgVqkVY5PUIUbrCP+ggFEqx8prThaHImPYpJIWySlspNw+vLVVjqC681jEWlpzGvF7jmyV/XdpmrMdzbS/LMjYREVm/XQl5ckcgIiu0YcMGFBcX4+GHH0b37t2r/Jo0aRIWLlyId955BytXrsQ777yD8+fP4/Tp0/j0008r+4iMjMS+ffuQmZmJgoKCGse68847UV5ejieeeAIjR45EaGjNP7yPjIyEWq3Gzp07UVBQAI3m2kP8Ro8ejUGDBuH222/Htm3bkJKSgkOHDmHWrFk4duwYtFotnn76aezZswepqak4ePAgYmNj0aVLl6bdNBvD4iBRM2NxkMjyFscAPzsboYgIQzffXnBz2wRHl39OMr6Y7Y7LU7+G5FR1+YNUWITnFhVitKZdrf1/V3YGy3qMbZbsdXlW8yOCnQyyjE1ERNZtJ4uDRNQICxcuxOjRo+Hl5XXNc5MmTcKxY8fg6+uLNWvWYN26dejduzdGjRqFmJiYyutmz56NlJQUREVFISAgoMaxPDw8cMsttyA+Pr7OJcWDBw/G448/jilTpiAgIACfffbZNdcIgoBNmzZh2LBhmDFjBjp27IipU6ciNTUVQUFBUCqVKCwsxAMPPICOHTvi7rvvxrhx4/Dee+814A7ZPkG6ei41EVmcxmBC7/e2w2AW676YiBqsV5iAJ4MltM92xf6kNVC6ToC6+J+CYHCwAp03vQVFWWGVdoK7G5ZNb4t1Hom19v+OayfcdXZ7s2SvTWL4ZNyUeEeLj0tERNZNpRBw/H83wcvFQe4oRDZDp9MhOTkZ7dq1g7Ozs9xxiOqtIe9dzhwkakaHkgpZGCRqRvEZEt5JEnAqohzDo6YB6k3wCSqpfD4nR8SpMR/BHFJ1pqCkrsD9C5MxpbT2k9He1yZiQ+dRzRG9Vh3Sf8dDbdLrvpCIiOhfTKKEfRe5aoWIiBqGxUGiZrSXH86Iml1OiYRZx5TY264MAzveDaX6CALCsiqfLyow4fiAN2Ds0KdKO0mrw10LLmJ6cbca+xYlEW8ZkrGj4w3Nlr86AiS8YZoLHwdTi45LRETWbzeXFhMRUQOxOEjUjPZc5IczopagMwCzDwF/talAl45j4GHIQmD4+crn1aVGxHZ6HLq+o6u0kwwGjF9wFk/m96yxb7NkxqvmLOyPGtRs+avjUJqCX9pta9ExiYjI+u25mA9R5M5RRERUfywOEjWTS/lqpBdp5Y5BZD8k4KcYCQvdDPCN6okwB3f4Bx+GoLiytF9XYUKM/yRUDJ9atZ3JhBGL4vBSdu8auzaKRrwoFCA2sn8zvoBrdU//FZODc1p0TCIism5FFQbEZ5TIHYOIiKwIi4NEzYSnFBPJ4+8zEj7XiNBGBqK7Ty94eG6Do/OV5bkmg4hY5TCUTHiqaiNRxPVLj+Ot9D7V9HiFzqzH0w7liAvv3YzpqxIkER8IP8FNyb1LiYio/vZdLJA7AhERWREWB4mayZ4LXFJMJJdjqRLeSZGQFAEMDBsPJ+UGuHnpAACiKOFERVfk3fW/qo0kCT2Xx+LDy31r7Fdj0uBJFwPOh3RtzvhVOBVfxKL2e1psPCIisn77E/lDaiIiqj8WB4magc5oRkxykdwxiOxaepGEWXECjkSoMbD9nVAZt8M7sKzy+TMFwUif9hkkhbJKu+hVMfgyoeYCYblRjcc8lbgU2LHZsv/XgMylGBfAWSBERFQ/ceklKNMZ5Y5BRERWgsVBomZw+FIh9CYuAySSm1oHvH1IwIZQDfp0nAhnw3H4t/lnD7/EbDdcmjoHkpNLlXbhf8Xgu1N9INSwn3uxoRSP+Lkizb9dc8avJIhGfOk0Hw4KbjBPRER1M4kSDiXxh0pERFQ/LA4SNQMuKSZqPSQJ+PaohKWeBkR0ugF+Uh4CwxMrn0/LUuDcHV9B9PKv0i5oYyx+OtELSgjV9puvK8LMQF9k+4Q3a/6rXAtOY17UoRYZi4iIrN++RBYHiYioflgcJGoGey5ynxei1mb1KRFfGUxwiO6Mds6e8A+NhfD/UwNzc0TE3/QRTG06VGnjs+045h3uDkdJWV2XyNbmY2ZoKAo8gpo9PwCMyF6IYb4lLTIWERFZt338PEpELSQyMhJz5syROwY1gSBJEtcoEVlQckEFRn6xR+4YRFSD9gECXokEIrMUOJG9DxXqETAaVAAAdy8VeicsgOOF2CpttIN74okbEqFRVL9/Uwf3cCy6nACfisLmjo/ywOvQM/0FSFL1MxqJiIiu2vXScLQPcJc7BpFV0+l0SE5ORrt27eDs7FzlucjXN7ZYjpRPJjS4zfTp07F06dLKr319fdG/f3989tln6Nmzp8Wy5efnw83NDa6urhbrk5qutvfuf3HmIJGFHeD+LkSt2uV8Ca+dkRAfYUb/NmPg6rINLh56AIC61ITYqIeh6zemShuXQ6cwf2d7eIhO1faZpE7HY1HdUO7s1ez5PfKO4fuoY80+DhERWb9Dl5r/h1ZE1LqNHTsW2dnZyM7Oxs6dO6FSqTBx4kSLjhEQEMDCoJVjcZDIwmJ5SjFRq1emBd48ImB7qAb9IsfDVbEXXv5qAIBeY0aM7x1Qj7inShuHY2cxb0sY/MTqP/icL0/BE536QuPo1uz5x+fNQ1+v8mYfh4iIrNuxFH4uJbJ3Tk5OCA4ORnBwMHr37o3XX38d6enpyM+/svVAeno67r77bnh7e8PX1xe33XYbUlJSKttPnz4dt99+O7744guEhITAz88PTz31FIzGf1bU/HdZcUJCAoYOHQpnZ2d07doVO3bsgCAIWLt2LQAgJSUFgiDgzz//xMiRI+Hq6opevXrh8OHDLXFLqBosDhJZGD+EEVkHUZTw+VEJK3x16BQ9Gp44Db/QKx+STEYRsYohKJ74TJU2yvgL+HFdAILN1S/Rii+7hGe7DoJeVfu0/aYSDBVY6PNLs45BRETWLzalWO4IRNSKqNVqLF++HB06dICfnx+MRiNuvvlmeHh4YP/+/Th48CDc3d0xduxYGAyGyna7d+/GpUuXsHv3bixduhRLlizBkiVLqh3DbDbj9ttvh6urK44ePYp58+Zh1qxZ1V47a9YsvPzyy4iLi0PHjh0xbdo0mEym5njpVAcWB4ksKLNEi6xSndwxiKgBlp+U8C30COh0HYKVRQgMvwwAkETgpLozcie/XeV64fwlfPunNyJM3tX2d7T0Il7oMRxGpWOz5vbJOYhP259q1jGIiMi6ZZZokV2qlTsGEclow4YNcHd3h7u7Ozw8PLBu3TqsWrUKCoUCq1atgiiKWLBgAXr06IEuXbpg8eLFSEtLw549eyr78PHxwffff4/OnTtj4sSJmDBhAnbu3FnteNu3b8elS5fwyy+/oFevXhg6dCg+/PDDaq99+eWXMWHCBHTs2BHvvfceUlNTkZSU1By3gerA4iCRBXHWIJF12p0EvFtogqljO0S5eCOgzUkAV87rOpsfhLR7Poek+NeJxUkp+GK1MzoZ/avtb3/JebzW60aYhepPObaUuwvnoou7plnHICIi68bZg0T2beTIkYiLi0NcXBxiYmJw8803Y9y4cUhNTUV8fDySkpLg4eFRWUD09fWFTqfDpUuXKvvo1q0blMp/PteGhIQgLy+v2vEuXLiA8PBwBAcHVz42YMCAaq/996EoISEhAFBjv9S8WBwksqBYFgeJrNaFHODVBDNS2rmhh28P+Absh9LBDABIynJF0tRvIDr/s5+glJqBD34FehqCqu1ve/FZ/K/PWEhovlOFBX0plgT+1mz9ExGR9eN+2ET2zc3NDR06dECHDh3Qv39/LFiwABUVFZg/fz7UajX69etXWTy8+uvixYu4555/9t92cHCo0qcgCBBFscnZ/t2vIFz5zGyJfqnhWBwksqBj/MkskVUrqgBePS7iYKgZfUJvgLf7bji7XdlvJT1LwPnbvoTZ959ioJSVg/8t02OAvk21/a0vPo33+45v1sxBWTvwv3YJzToGERFZL/7wmoj+TRAEKBQKaLVa9O3bF4mJiQgMDKwsIF795eXl1aj+O3XqhPT0dOTm5lY+Fhsba6n41ExYHCSykFKtERdzeXookbUzmYAPjopY42dEt/Y3wtv5MDz9rpxknJtrxqmRs2EKi668XsorwCuLSzFcG1Ftf2uKT+OzPhObNfOM0h8R6cL9TomI6FoXc8tRpjPWfSER2SS9Xo+cnBzk5OTg/PnzeOaZZ6BWq3HLLbfg3nvvhb+/P2677Tbs378fycnJ2LNnD5599tn/Y+++o6MqEzeOP5OZ9F5JCIE00ugQQERaBCmCoCiICEQFG2ADxUZRdAV7wbI2gqioLIqsCioIqEEFgVBDDz20QIAQUmd+f/jbuFlaEpLcJPP9nJOzJzPvfe8zWSSX5977Xu3fv79C++vRo4eioqI0YsQIrV+/XqmpqXryyScl/X11IGoei9EBgLpizZ4TstqMTgGgsnywplj7Y2y6PeYqHc9YJ0tIIx3P9NeJrCKtbj1erTzel9OWv86C2k5ka8yHVrkmR2mR+85z5pqdvV5uLa/VmLRvqySrQ+4xzW7wpTrtuOXSgwEAdsVqk1bvOaFusUFGRwHqnN3TrjU6wiUtWrSoZD0/T09PxcXFae7cueratask6eeff9aECRN0ww036PTp0woNDdXVV18tLy+vCu3PbDZr/vz5GjlypNq2bavIyEi98MIL6tevn1xcXCrrY6GSmWw2G3UGUAmeX7RFby07txQAULs1rW/SuCCznPYc0MEiBx3Z11CS5OxqVuusBXJd+V3JWJObmz69PVxfeW4771wPeDbRHesXVlnWV4Oe0at7I6tsfgBA7TS6W5Qe7hlndAygVsrLy1NGRoYiIiIotyooNTVVV111lXbs2KGoqCij49iN8vzZ5bZioJKw3iBQN208aNOEXYXKahyiGA8fBTXYIJtsyj9brJXe/XQ66daSsbbcXN3y/i7dcjL+vHO9enqTPm3Ws8qyjs19S8HOBVU2PwCgduKJxQCq01dffaUff/xRu3fv1uLFi3XnnXeqY8eOFIM1GOUgUAkKiqxatz/b6BgAqsiRUyaNX2tVWkMXJfjHKSj4dzlYrCoutOpPddDxfg+UjLXl5WnAe1s0MqvpeeealrNFXyV0r5Kc5pyDmt3wmyqZGwBQe63fn62CIp4ACqB6nD59WqNHj1ZcXJySk5PVtm1bff3110bHwkVQDgKVYMOBbOVzwAXUaQWF0uQ/ivVdgBRfv50CfFPl7FYgm1VKO91Yh26a8vfgwkJd88EGjT3S4px5bLJpSt4OLYzrWiU5o/fN0x2h+6pkbgBA7ZRXaNWGAyeNjgHATgwfPlzbtm1TXl6e9u/fr5SUFPn7+xsdCxdBOQhUAm7VAOzHm6uL9L5TkSKjrlSg5xp5+uZKkjYfDdSeW16Szfz/z/oqLlanmWv1yMGW58xhtVn1eMFe/dS4U6XnM8mmRwvfkq9jUaXPDQCovf7cfdzoCACAGopyEKgEHGwB9uXrLVY9m1Mkv9i2qu+eIb/gv04Q7Dzoou2DX5PV1eOvgVarEmf9qcl7Wp8zR5GtSA9bM7Ui8opKz+d4ao8+Cv++0ucFANRenMwGAFwI5SBwmWw2m1bv4WALsDdr9lv16N4CFcXGKtw9V4FhByRJ+w9Km697UVa/4JKxTT5dqed2nFsQFlgL9IDDca1u2KbS8zXdP0eDQw5V+rwAgNpp9Z7jstlsRscAANRAlIPAZdqTlasTuYVGxwBggAPZ0oMbirQnOlCNvbxVLyxdknTkcLHSuj2torDYkrFRc1fqlc3nFoRni/M02vmMNjRoXqnZTDarntY7cjezHioAQDqRW6g9WblGxwAA1ECUg8Bl2px5yugIAAx0tsCmR1cW65dgF8UGRCs4dI1MZquyswq1utVDKoj/+7bh0K9X6s11rWT6nws3zhTl6m73Ym0Njq/UbM4ntmlm5NJKnRMAUHulc9wKADgPykHgMm0+yEEWYPds0surC/WRmxTVoLlC6q2So2uhzpwq0srwZJ1td23J0MDvVundP1vIYiv9K/hUwWnd6eOkXUHRlRqt7YFZ6hN4rFLnBADUTpzUBlDTTJkyRS1btqzy/SQnJ2vAgAFVvp/aymJ0AKC24wwsgP+Yu6lIBxo5aGxkopwzNuhwTpxyT7popXdftb7aX55LPpIkeS9erfcKWuruK9OVbyou2f54/gmN8g9QSnEjhWXtqZRMJmuRXnJ+V0scHlW+lXOCAGDPOG4FKtkU72rc18lyDU9OTtasWbMkSRaLRX5+fmrevLmGDBmi5ORkOTj8fVwYHh6uPXv26LffftMVV/x918sDDzygtLQ0LVu2TJKUm5urqVOn6osvvtCBAwfk6emphIQEPfTQQ+rfv/95c6SkpOi222475/X33ntPI0eOLNdnQtXhXwnAZeIMLID/tmKPVY8eLJRzbFOF++yTb9BJFRda9ae1vY5f92DJOPef0/T+shi5WR1LbX8k75hGBQfpkE9opWVyPbZR/4xaUWnzAQBqJ+54AexLr169lJmZqd27d2vhwoXq1q2b7r//fvXt21dFRUWlxrq4uGjChAkXne/uu+/Wl19+qTfeeENbtmzRokWLdOONNyorK+ui23l5eSkzM7PU19ChQy/786HyUA4ClyE7t0CZJ/OMjgGghtlz3KYHNhfqREyEon3zFdggUzablHYqWocGPV0yzvn3DXr/xwh5W11KbX8g97BGNWioLI/ASsvUJfNDdfHnyeoAYM8OnszTSR6kB9gNZ2dnBQcHKzQ0VK1bt9bjjz+ur7/+WgsXLlRKSkqpsXfeead+//13fffddxecb8GCBXr88cfVp08fhYeHq02bNho7dqxuv/32i+YwmUwKDg4u9eXq6nresVarVU8//bQaNGggZ2dntWzZUosWLSo1ZsOGDUpKSpKrq6v8/f115513Kicnp+T94uJiPfTQQ/Lx8ZG/v78eeeQRntZ+CZSDwGXg7CuACzmdJ437s1BrG/ipsb+HgsK2S5I2H/HXnlteks3818oeljWb9c/v6iuo2KPU9rvPHNCoiFiddPOtlDymojzNcJ8ps4mnFwOAPduUWb5bEwHULUlJSWrRooW+/PLLUq9HRETo7rvv1mOPPSar9fzHi8HBwfruu+90+vTpKsv32muv6aWXXtKLL76o9evXq2fPnrruuuu0fftfx9JnzpxRz5495evrq1WrVmnu3LlavHixxowZUzLHSy+9pJSUFH344Yf69ddfdfz4cX311VdVlrkuoBwELgO3FAO4GJtNem51ob7ydFV0cCOFNNwgk8mmnQddtH3wa7K6e0mSHDZs0xtf+ym02KvU9ttz9uquxs2V4+J1vunLzfPIn3ojanWlzAUAqJ3SM6vuH/UAaoe4uDjt3r37nNeffPJJZWRk6JNPPjnvdu+++65WrFghf39/tW3bVg8++KBSU1Mvub+TJ0/Kw8Oj5Cs4OPiCY1988UVNmDBBN998s2JjYzV9+nS1bNlSr776qiTp008/VV5enj766CM1bdpUSUlJmjFjhmbPnq3Dhw9Lkl599VU99thjuuGGGxQfH6933nlH3t7VuD5kLUQ5CFwGykEAZfHRxkK9UWRTWIN4hTVYL0fnYu0/KG3q+7yK/UMkSaatu/TKvzwUWVT6SsFNpzI0Oi5RZ53cKiVL78PvKtGbfxgCgL3izhcANptNJpPpnNcDAwM1fvx4TZo0SQUFBee837lzZ+3atUtLlizRjTfeqE2bNqlTp06aOnXqRffn6emptLS0kq8VK86/FvapU6d08OBBdezYsdTrHTt2VHp6uiQpPT1dLVq0kLu7e6n3rVartm7dqpMnTyozM1Pt27cved9isSgxMfGiGe0d5SBwGTjzCqCsfsqw6okjRfKMbKrw4G1y88zX0cPFSuvylIoaxv01aNdeTf/MUQmFpdcaXHNyh+5rcqUKzM6XncNUeEbv+X502fMAAGonnlgMID09XREREed976GHHtLZs2f11ltvnfd9R0dHderUSRMmTNAPP/ygp59+WlOnTj1vmfgfDg4Oio6OLvmKjIyslM+BykM5CFRQQZFVO45QDgIou23HbHpge4Hyo2MUVe+wvANP6eTxQv3Z4kHlN7lSkmTbd1BPfVysVgUhpbb9PXubxrXoqkIHx/NNXS6+h1L1fNS6y54HAFD77DiSo8Ji1p8F7NVPP/2kDRs2aODAged938PDQxMnTtSzzz5bprUFExISVFRUpLy8y39Qp5eXl+rXr3/OrcqpqalKSEiQJMXHx2vdunU6c+ZMqfcdHBwUGxsrb29vhYSE6I8//ih5v6ioSKtXs7TOxVAOAhX014EVTzwCUD7ZudIDawu0s1GoGgcVKqD+EeWeLtKqsOHKvaKfJMl26IiemJWrK/PCSm277ES6HmvZXVbT5f/6vunYO4r3yL3seQAAtUtBsVU7juRceiCAWi8/P1+HDh3SgQMHtGbNGv3jH/9Q//791bdvXw0fPvyC2915553y9vbWp59+Wur1rl276p///KdWr16t3bt367vvvtPjjz+ubt26ycurctbIfvjhhzV9+nR9/vnn2rp1qx599FGlpaXp/vvvlyQNHTpULi4uGjFihDZu3KilS5dq7NixGjZsmOrVqydJuv/++zVt2jTNnz9fW7Zs0b333qvs7OxKyVdXUQ4CFcR6gwAqqtgqPbW6QD/5+ii6nrvqNcxQQV6xVnn01qket0mSrMey9GDKCSXlhpfa9vsTmzSpVW/ZdO46MeVhyj+pWUFzLmsOAEDtxLqDgH1YtGiRQkJCFB4erl69emnp0qV6/fXX9fXXX8tsNl9wO0dHR02dOvWcqwF79uypWbNm6ZprrlF8fLzGjh2rnj176osvvqi0zPfdd58eeughjRs3Ts2aNdOiRYu0YMECNW7cWJLk5uam77//XsePH1fbtm1144036uqrr9aMGTNK5hg3bpyGDRumESNGqEOHDvL09NT1119faRnrIpPNZuPSJ6ACpn6zWR/8mmF0DAC1XK8oR91usSrz0C7t3xsrk0xq7rVL/l+/JEkyeXooJbmBvvXYUWq7wb7N9OSaby97/x+GTNTTGfGXPQ8AoPYYeVWEnuybYHQMoFbIy8tTRkaGIiIi5OLiYnQcoMzK82eXKweBCuKMK4DKsGhnoZ46YZN/wyhFNNois6VY605GKnPwM5Ik2+kcJb+/Rzeeii213ecnNujlVtde9v6Ts99WpNvlrxEDAKg9uAMGAPDfKAeBCko/xEEVgMqx6YhVD2YUyRQRq+iwDLl4FCj9sK923/KKrBYn2c6e1eD3d2hYdumrPGZmb9DbLS+vIHQ4e0yz6s+7rDkAALULTywGAPw3ykGgAo6czlN2bqHRMQDUIUdzpPvX5+tweIRiGxyTV0COdh100vZBr8jq7iVbfr76vbdZdx1rVmq7t05u0KzmvS5r32H7v9WDDXdd1hwAgNrjRG6hjp7ONzoGAKCGoBwEKmBPFk/4BFD5Coqlx9cU6I+gEMXUL5R//WM6cFDaeO0LKg4IlYqKdPWH6/XAoRaltnvx9GZ93vSay9r3mNw3FeJScFlzAABqjz1ZZ4yOAACoISgHgQrYfYyDKQBV5431eZrj6KXI+m4Kbrhfx44UKa3zZBWGN5GKi3Vlyho9tr9VqW2ePbNVC+KvrvA+zTmZmh3278uNDgCoJTjZDQD4D8pBoAL2HudgCkDVmr+zQNNyzApuEKhGkRk6ebxAq5vep/xmnSSbTa1mr9LTGa1Lxttk06T8Xfo+tkuF9xm170vdEbqvMuIDAGq4PRzPAgD+H+UgUAGcaQVQHdYcsmrcXqucwhqocfRu5efna1XoUOVeOUCSFPfZSj2/7e+CsNhWrEeL9unnqCsrtD+TbHq08C35OhZVRnwAQA3GbcUAgP+gHAQqgDOtAKrLoRxp7KZCnQxrqLiIgzKZ87TS9RqduuZ2SVL4vJV6bePftxgXWYv0kOmofo9oV6H9OZ7ao4/Cv6+U7ACAmouT3QCA/6AcBCpgL2daAVSj/CKTHl5boI3BDRQbflzu3jn6s7CNjg14WJIU8u9VentNS5ls/z++OF/3WU5qbViri8x6YU33z9HgkEOVFR8AUAOxTA4A4D8oB4FyOnm2UCdyC42OAcAOvbg+T9+5BSimUbH86p3Q+uxwHRz8rGwmk/y//1PvrWwui+2vX+1ni85qtGu+NtVvWu79mGxWPa135G62VvZHAADUEMfPFOhUHse0ACSTyaT58+cbPgf+lpKSIh8fn2rbn6Xa9gTUEXu5BQOAgeZsL9Du+s4aG26Vs/NhbdlTT/lDXlGjf02Q109r9EF+C93VaavyTEU6XZijuz299WG9WDU+vLVc+3E+sU0zI5dq0PaKPwEZAFCz7c3KVdNQb6NjALVWs1nNqm1fG0ZsKNf45ORkzZo1S5JksVjk5+en5s2ba8iQIUpOTpaDw9/XimVmZsrX17dM806ZMkXz589XWlpaqdfLM0dNNmfOHN166626++679eabb5Z6Lzk5WdnZ2aVK0N27dysiIkJr165Vy5YtqzdsJeLKQaCc9hznlmIAxvrtoFWPZZrk3dBX4VEHtOugRdsGviKrh7dcU9fp/Z+i5WFzkiRlF5zUnb6u2hMQWe79tD0wS30Cj1V2fABADcG6g0Dd1qtXL2VmZmr37t1auHChunXrpvvvv199+/ZVUdHfD6ALDg6Ws7PzZe2rMua4XDabrdTnqogPPvhAjzzyiObMmaO8vLxKSlbzUQ4C5cRBFICaYM9Jm+7bVqzCBsGKizmoQ0eKtbHP8yoObCCnlRv17qJG8rW6SpKO5R/XyCBfHfRtWK59mKxFesn5XTk7cHsxANRFnPQG6jZnZ2cFBwcrNDRUrVu31uOPP66vv/5aCxcuVEpKSsm4/70leP/+/RoyZIj8/Pzk7u6uxMRE/fHHH0pJSdFTTz2ldevWyWQyyWQylczzv3Ns2LBBSUlJcnV1lb+/v+68807l5OSUvJ+cnKwBAwboxRdfVEhIiPz9/TV69GgVFv693MHs2bOVmJgoT09PBQcH65ZbbtGRI0dK3l+2bJlMJpMWLlyoNm3ayNnZWR9//LEcHBz0559/lvpZvPrqq2rUqJGs1gsf12ZkZGjFihV69NFHFRMToy+//LLkvSlTpmjWrFn6+uuvSz77smXLFBERIUlq1aqVTCaTunbtKklatWqVevTooYCAAHl7e6tLly5as2ZNqf1lZ2frrrvuUr169eTi4qKmTZvqm2++OW+2o0ePKjExUddff73y8/Mv+BkqinIQKCduKwZQU5zJlx5YX6BdwfUVH3dYp06f1dqrJqkwoqksael6+5tgBVndJUmHzh7VyPrBOuIdUq59uB7bqH9GraiK+AAAg+05xnEtYG+SkpLUokWLUsXXf8vJyVGXLl104MABLViwQOvWrdMjjzwiq9WqwYMHa9y4cWrSpIkyMzOVmZmpwYMHnzPHmTNn1LNnT/n6+mrVqlWaO3euFi9erDFjxpQat3TpUu3cuVNLly7VrFmzlJKSUqq0LCws1NSpU7Vu3TrNnz9fu3fvVnJy8jn7e/TRRzVt2jSlp6fruuuuU/fu3TVz5sxSY2bOnHnO7dT/a+bMmbr22mvl7e2tW2+9VR988EHJe+PHj9egQYNKrsbMzMzUlVdeqZUrV0qSFi9erMzMzJKf6+nTpzVixAj9+uuv+v3339W4cWP16dNHp0+fliRZrVb17t1bqamp+vjjj7V582ZNmzZNZrP5nFz79u1Tp06d1LRpU/3rX/+qkis0WXMQKKfdPKkYQE1ik/6xPk/JsUG6OiZbu/YW6c8mY9Xa8xM5r/9ZMwoiNP56R+01Z2tf7iGNahihmbsK5Xem7LcLd8n8UF38m2h5Vu1fRwYA8DeuHATsU1xcnNavX3/e9z799FMdPXpUq1atkp+fnyQpOjq65H0PDw9ZLBYFBwdfcP5PP/1UeXl5+uijj+Tu/teJ6hkzZqhfv36aPn266tWrJ0ny9fXVjBkzZDabFRcXp2uvvVZLlizRqFGjJEm33357yZyRkZF6/fXX1bZtW+Xk5MjDw6Pkvaefflo9evQo+X7kyJG6++679fLLL8vZ2Vlr1qzRhg0b9PXXX18ws9VqVUpKit544w1J0s0336xx48YpIyNDERER8vDwkKurq/Lz80t99sDAQEmSv79/qdeTkpJKzf/uu+/Kx8dHy5cvV9++fbV48WKtXLlS6enpiomJKfmM/2vr1q3q0aOHrr/+er366qsymUwX/AyXgysHgXLae5wzrABqnpStBZpZ7K3I6EK5uGVpZcgQ5Xa8XtqeoZe+cFXjQn9J0q6c/borKl4nXX3KPLepKE8z3GfKbOL2YgCoS7gjBrBPNpvtgiVTWlqaWrVqVVIMVkR6erpatGhRUgxKUseOHWW1WrV1698PyWvSpEmpK+VCQkJK3Ta8evVq9evXTw0bNpSnp6e6dOkiSdq7d2+p/SUmJpb6fsCAATKbzfrqq68k/fXk327duik8PPyCmX/88UedOXNGffr0kSQFBASoR48e+vDDD8v56f9y+PBhjRo1So0bN5a3t7e8vLyUk5NTkj0tLU0NGjQoKQbP5+zZs+rUqZNuuOEGvfbaa1VWDEqUg0C55BUW69Ap+1mUFEDt8tP+Qk3JclZIlLMCgo9ppUsPnew5Srbd+/SPOQ5qWvjXWdotp/fo3piWynX2uMSMf/M88qfeiFpdVdEBAAbIPJWnvMJio2MAqGbp6ekla+X9L1dX12rL4ejoWOp7k8lUsibgf25N9vLy0ieffKJVq1aVlH0FBQWltvvvElKSnJycNHz4cM2cOVMFBQX69NNPS12FeD4ffPCBjh8/LldXV1ksFlksFn333XeaNWvWRdcpvJARI0YoLS1Nr732mlasWKG0tDT5+/uXZC/Lz9nZ2Vndu3fXN998owMHDpQ7Q3lQDgLlsP9Ermw2o1MAwIXtPG7VA7uscmrkrkYRR7SmoKWOXT9BtgOZmjy7QIn59SVJ60/t0uj49spzLPsBYO/D7yrR+3RVRQcAVDOb7a/jWwD246efftKGDRs0cODA877fvHlzpaWl6fjx4+d938nJScXFFz+pEB8fr3Xr1unMmb+XLkhNTZWDg4NiY2PLlHPLli3KysrStGnT1KlTJ8XFxZW6qvBSRo4cqcWLF+utt95SUVGRbrjhhguOzcrK0tdff63PPvtMaWlpJV9r167ViRMn9MMPP0g6/2d3cnKSpHNeT01N1X333ac+ffqoSZMmcnZ21rFjfy/r07x5c+3fv1/btm27YC4HBwfNnj1bbdq0Ubdu3XTw4MEyf/7yohwEymHf8bNGRwCASzqZb9J9G606Ut9XsXFHtOFkAx24+TlZjxzThFk5uiovTJL058nteqBpJxWanco0r6nwjN7z/agqowMAqhnHt0DdlZ+fr0OHDunAgQNas2aN/vGPf6h///7q27evhg8fft5thgwZouDgYA0YMECpqanatWuX5s2bp99++02SFB4eroyMDKWlpenYsWPnfXLu0KFD5eLiohEjRmjjxo1aunSpxo4dq2HDhpWsN3gpDRs2lJOTk9544w3t2rVLCxYs0NSpU8v82ePj43XFFVdowoQJGjJkyEWv1Js9e7b8/f01aNAgNW3atOSrRYsW6tOnT8mDScLDw7V+/Xpt3bpVx44dU2FhoYKCguTq6qpFixbp8OHDOnnypCSpcePGmj17ttLT0/XHH39o6NChpTJ06dJFnTt31sCBA/Xjjz8qIyNDCxcu1KJFi0plM5vN+uSTT9SiRQslJSXp0KFDZf4ZlAflIFAOR09X/iPDAaAqWK3SlPWF+sMrQHEJWcrIdlPGkFdVfPqM7v8wS9ec+WvB49TsLRrfIklFDmV7RpnvoVQ9H7WuKqMDAKrR0RyOb4G6atGiRQoJCVF4eLh69eqlpUuX6vXXX9fXX3993qfiSn9dCffDDz8oKChIffr0UbNmzUo9RXfgwIHq1auXunXrpsDAQM2ZM+ecOdzc3PT999/r+PHjatu2rW688UZdffXVmjFjRpmzBwYGKiUlRXPnzlVCQoKmTZumF198sVyf/4477lBBQcElbyn+8MMPdf311593Tb+BAwdqwYIFOnbsmEaNGqXY2FglJiYqMDBQqampslgsev311/XPf/5T9evXV//+/SX9dZvyiRMn1Lp1aw0bNkz33XefgoKCSs09b948tW3bVkOGDFFCQoIeeeSR816VabFYNGfOHDVp0kRJSUnluoKyrEw2GzdJAmX15tIdeuH7rZceCAA1SO+GThrimKNdO5zl5eaq2G+elNmWr9nJDbXAc7skqY9vUz23dpEcbJdeU8Xm7K0+xS8pPcetqqMDAKrYI71idW/X6EsPBOxUXl5eyRNrXVxcjI6Dcpg6darmzp17wScz13Xl+bPLlYNAORzjzCqAWmjh3gJNP+mqhnFW5RWf1oZez6nIzV/DPsjQ4JNxkqTvTmzU0616y6ZLPwXNlH9Ss4LOPUsMAKh9uDMGQF2Tk5OjjRs3asaMGRo7dqzRcWoFykGgHDh4AlBbbTpWrPF7TPKJtsjZ9bjWdnxS+fVjdOP723Tb8SaSpHknNuj51teWab6gg0s0KSK9KiMDAKrBsZyCSw8CgFpkzJgxatOmjbp27XrJW4rxF8pBoBy4chBAbXY8Txq7xaqzjVwVEHBUq+NG62xCR/X+YJPuPdpckvTxifV6vWXZCsLk7LcV6ZZXlZEBAFXsGCe/AdQxKSkpys/P1+eff37BtRVRGuUgUA6cWQVQ2xVbTXp8Q5E2+3uoYcQRrQq+SWc6DFDXD9M0PrOlJOm9kxv0Xos+l5zL4ewxzao/r4oTAwCqEie/AQCUg0A5cPAEoK54Y0uhvrF4Kyr2hNI8OuvkNSPVbtZqTdzXWpL0+qmN+rhZr0vOE7b/Wz3YcFdVxwUAVBGObwEAlINAGRUWW3XybKHRMQCg0szfXaC3ct0V0SRPm53idPT6R9Xs45V6dtdfBeHzOema16T7JecZk/umQly4shoAaqPss4UqKr70k+oBAHUX5SBQRlk5BbLZjE4BAJVr9dEiTTxgVv0m0n5zgA7c/Jyiv1ill9Jbyyabnj67Q9/EJV10DnNOpmaH/buaEgMAKpPNJmWd4QQPANgzykGgjLjlAkBddfCsTWO3WWVubNJpR0ftGvKqGny3Xm+sbyWb1aqJBbu1pHGni84RvW+eRjbYV02JAQCV6SgPJQEAu0Y5CJTRUcpBAHVYYbE0YbNV+0MtMrmf1ZaBryjw5516Z00L2WzFeth6UL9GdbjoHBMK3pKvY1E1JQYAVBaOcwHAvlEOAmV0jDOqAOzAS1uK9LO7i9wDTmpDr+fkuSFL761oKlOxVQ+ajmlVo8QLbut4ao9mh39fjWkBAJWB41zAPplMJs2fP79K5l62bJlMJpOys7Mva57du3fLZDIpLS2tUnLh/CxGBwBqi2M5rMUCwD58vrtIewJddXvYSa278mE1X/e+3l8eq7s7b9cYpxy9G9ZCLfatO++2TfbP0c0hrfVZZkg1pwYAVBTHuUDFpMfFV9u+4rekl3ubo0ePatKkSfr22291+PBh+fr6qkWLFpo0aZI6duxYBSkrX1hYmDIzMxUQEGB0lDqNKweBMmLNQQD25PejhZp62FH+kXla3yJZygvUe0si5Vho1T2uhdoSknDe7Uw2q57WO3K3FFdvYABAhXGcC9RNAwcO1Nq1azVr1ixt27ZNCxYsUNeuXZWVlWV0tDIpKCiQ2WxWcHCwLBaubatKlINAGXHQBMDe7DtTrIcyrHJtbNO2mH7Kd2uid74LlVO+VXd5W7QrqPF5t3M6sV0pEUurOS0AoKI4zgXqnuzsbP3yyy+aPn26unXrpkaNGqldu3Z67LHHdN111513mw0bNigpKUmurq7y9/fXnXfeqZycHEnSxo0b5eDgoKNHj0qSjh8/LgcHB918880l2z/zzDO66qqrLphp3rx5atKkiZydnRUeHq6XXnqp1Pvh4eGaOnWqhg8fLi8vL915553n3FZ84sQJDR06VIGBgXJ1dVXjxo01c+bMy/lRQZSDQJlx0ATAHp0tMmn81iKdaCQdaHSFTjdI0lsLAuWUW6RR/h7a5x9+3u0SD3ykvoHHqjcsAKBCOM4F6h4PDw95eHho/vz5ys+/9H/jZ86cUc+ePeXr66tVq1Zp7ty5Wrx4scaMGSNJatKkifz9/bV8+XJJ0i+//FLqe0lavny5unbtet75V69erUGDBunmm2/Whg0bNGXKFE2cOFEpKSmlxr344otq0aKF1q5dq4kTJ54zz8SJE7V582YtXLhQ6enpevvtt7nluBJQDgJllJPHEzgB2CebTZq2rUir/RyU1SBaRxNu1utf+sg1p1gj6wXokE+Dc7YxWYv0gtO7cnawGpAYAFAeOfksBQHUNRaLRSkpKZo1a5Z8fHzUsWNHPf7441q/fv15x3/66afKy8vTRx99pKZNmyopKUkzZszQ7NmzdfjwYZlMJnXu3FnLli2T9NcDR2677Tbl5+dry5YtKiws1IoVK9SlS5fzzv/yyy/r6quv1sSJExUTE6Pk5GSNGTNGL7zwQqlxSUlJGjdunKKiohQVFXXOPHv37lWrVq2UmJio8PBwde/eXf369bu8HxYoB4Gyyi3goAmAfZu9p0hfyKwzob7al3i3XpjrKs9TVo1s0EDHPOudM941a6PejUo1ICkAoDzOFnASHKiLBg4cqIMHD2rBggXq1auXli1bptatW59ztZ4kpaenq0WLFnJ3dy95rWPHjrJardq6daskqUuXLiXl4PLly5WUlFRSGK5atUqFhYUXfNBJenr6Oe917NhR27dvV3Hx3//WTkxMvOhnuueee/TZZ5+pZcuWeuSRR7RixYqy/ChwCZSDQBlRDgKA9PORIr103Kyi+s7a1fFBTZ3rIu8TxRoVHq1sN79zxnc++KG6+p0wICkAoKw4zgXqLhcXF/Xo0UMTJ07UihUrlJycrMmTJ1dorq5du2rz5s3avn27Nm/erKuuukpdu3bVsmXLtHz5ciUmJsrNze2y8v53OXk+vXv31p49e/Tggw/q4MGDuvrqqzV+/PjL2icoB4EyO1vIQRMASNLOnGJN2Fes/FCztl91v574yk3+WVbdGd1Up128S401FedrhseHMpu4vRgAaqqzlIOA3UhISNCZM2fOeT0+Pl7r1q0r9V5qaqocHBwUGxsrSWrWrJl8fX31zDPPqGXLlvLw8FDXrl21fPlyLVu27ILrDf5n/tTU0neUpKamKiYmRmazuVyfITAwUCNGjNDHH3+sV199Ve+++265tse5KAeBMsrldgsAKHG6UBq/vVCHQ83acdW9euA7HwUdsene2NbKdSp9xtfjyGrNiPrToKQAgEvhykGg7snKylJSUpI+/vhjrV+/XhkZGZo7d66ef/559e/f/5zxQ4cOlYuLi0aMGKGNGzdq6dKlGjt2rIYNG6Z69f5aPuY/6w5+8sknJUVg8+bNlZ+fryVLllxwvUFJGjdunJYsWaKpU6dq27ZtmjVrlmbMmFHuq/4mTZqkr7/+Wjt27NCmTZv0zTffKD4+vlxz4FyUg0AZWK025RVy1QsA/DerTXp2W4HW+Zi0+8rbNGpZiIIzpfsSOijf4lJqbK/D76mdzymDkgIALiavqFhWq83oGAAqkYeHh9q3b69XXnlFnTt3VtOmTTVx4kSNGjVKM2bMOGe8m5ubvv/+ex0/flxt27bVjTfeqKuvvvqcsV26dFFxcXFJOejg4KDOnTvLZDJdcL1BSWrdurW++OILffbZZ2ratKkmTZqkp59+WsnJyeX6XE5OTnrsscfUvHlzde7cWWazWZ999lm55sC5TDabjd8CwCXk5Bep6eTvjY4BADVWj3pm9TdJ9dcv1vzWGcoKM+vVdT/J0VpYMuZEcEe12j3awJQAgAvZ9FRPuTtbjI4B1Dh5eXnKyMhQRESEXFxcLr0BUEOU588uVw4CZcAtxQBwcT8eLtaMXJsOJl6jvltaKWy3NKFldxWb/l5DxvdQql6MXGdcSADABXFrMQDYL8pBoAxYpBkALm3LKauePFSk/c3bq/P+q9Roh0mTWvWSTaaSMQOz3lYTz3MXwQYAGIvjXQCwX5SDQBlwJhUAyia7wKaHdxdoS0wTtT5xjRptddAzrfuUvG/KP6WZgawLAwA1TW4hd8oAgL2iHATKgHIQAMqu2Co9vTNPv4Y2Ukx+XzXcZNELrfqWvB90cIkmR6QbmBAA8L843gUA+0U5CJQBt1kAQPn9c/dZzfXwV6jDAIVtctWbLa8teW9E9luKdMszMB0A4L9xvAsA9otyECiDMzyQBAAq5NtDBXq12EW+rn1Vf5OvPmzeW5LkcDZLH9WfZ3A6AMB/nMnneBcA7BXlIFAGnEkFgIrbeMqmJ7MdZfbqrcD0BprTtKckqcH+bzWu0U6D0wEAJOlsIce7AGCvKAeBMmANFgC4PEfzpfGZJp307S6vbY31dfzVkqR7c95UiEuBwekAABzvAoD9ohwEyiCX24oB4LIVWKUn9xZrq1cnWTJa6YfGXWQ+c0gfh/3b6GgAYPcoBwHAflEOAmVQWGwzOgIA1Bmv7y/WYscrVJTZSb9GXqWoffN0Z4O9RscCALtWVGw1OgIAOxIeHq5XX321yvdjMpk0f/78Kt9PbWcxOgBQG5hMRicAgLrlq6MF2uPdXMnHnbU6rFCPnHxL85ymKqvA0ehoAGCXON4Fyu/Nu3+qtn2NfiepXOOPHj2qSZMm6dtvv9Xhw4fl6+urFi1aaNKkSYqNjVXTpk1133336fHHHy+13aBBg7R3716lpqZq6tSpeuqpp3TXXXfpnXfeKRmTlpamVq1aKSMjQ+Hh4efdf9euXbV8+fJzXi8sLJTFQhVV03DlIFAGHCsBQOVbc7JI07JjtCv/Jm13C9BHjb43OhIA2C0TR7xAnTJw4ECtXbtWs2bN0rZt27RgwQJ17dpVWVlZCggI0LvvvqunnnpKGzZsKNlm7ty5+uabbzRr1iyZzWZJkouLiz744ANt37693BlGjRqlzMzMUl8UgzUT5SBQBpxJBYCqcTCvWE/uC9UqDZfL2U26JSTT6EgAYJc43gXqjuzsbP3yyy+aPn26unXrpkaNGqldu3Z67LHHdN1110mSrrvuOt1yyy0aMWKECgsLdfToUY0ePVrTpk1TbGxsyVyxsbHq1q2bnnjiiXLncHNzU3BwcKmvC9m7d6/69+8vDw8PeXl5adCgQTp8+HCpMW+//baioqLk5OSk2NhYzZ49u9T727dvV+fOneXi4qKEhAT9+OOP5c5srygHgTLgTCoAVJ18m02Tdgfpa4eRus31R7lbWBQfAACgojw8POTh4aH58+crPz//guNee+01ZWVlaerUqbr33nvVtGlTjR079pxx06ZN07x58/Tnn39WSV6r1ar+/fvr+PHjWr58uX788Uft2rVLgwcPLhnz1Vdf6f7779e4ceO0ceNG3XXXXbrtttu0dOnSkjluuOEGOTk56Y8//tA777yjCRMmVEneuohyECgDzqQCQNV7fa+/Psi7Tk9HbLj0YABApTJxwAvUGRaLRSkpKZo1a5Z8fHzUsWNHPf7441q/fn2pcV5eXpo5c6b+8Y9/6IcfftDMmTPP+3dB69atNWjQoHKXbW+99VZJUenh4aFx48add9ySJUu0YcMGffrpp2rTpo3at2+vjz76SMuXL9eqVaskSS+++KKSk5N17733KiYmRg899JBuuOEGvfjii5KkxYsXa8uWLfroo4/UokULde7cWf/4xz/KldeeUQ4CAIAa47ODPpp3NFINXfOMjgIAdoVqEKhbBg4cqIMHD2rBggXq1auXli1bptatWyslJaXUuKSkJF1xxRUaNmyYGjVqdMH5nnnmGf3yyy/64Ycfypxh6NChSktLK/l67LHHzjsuPT1dYWFhCgsLK3ktISFBPj4+Sk9PLxnTsWPHUtt17Nix1PthYWGqX79+yfsdOnQoc1Z7RzkIlAFnUgGg+qzI9tLesy5GxwAAAKjVXFxc1KNHD02cOFErVqxQcnKyJk+efM44i8VyyQeFREVFadSoUXr00Udls9nKtH9vb29FR0eXfAUEBFToc6DqUQ4CZUA1CAAAgLqMc+FA3ZeQkKAzZ85UePtJkyZp27Zt+uyzzyoxlRQfH699+/Zp3759Ja9t3rxZ2dnZSkhIKBmTmppaarvU1NRS7+/bt0+ZmX8/3O7333+v1Jx1Gc+QBsqAgyUAAADUZRzuAnVHVlaWbrrpJt1+++1q3ry5PD099eeff+r5559X//79KzxvvXr19NBDD+mFF16oxLRS9+7d1axZMw0dOlSvvvqqioqKdO+996pLly5KTEyUJD388MMaNGiQWrVqpe7du+vf//63vvzySy1evLhkjpiYGI0YMUIvvPCCTp06VaEnLNsrrhwEyoCDJQAAANRlLKMD1B0eHh5q3769XnnlFXXu3FlNmzbVxIkTNWrUKM2YMeOy5h4/frw8PDwqKelfTCaTvv76a/n6+qpz587q3r27IiMj9fnnn5eMGTBggF577TW9+OKLatKkif75z39q5syZ6tq1qyTJwcFBX331lc6ePat27dpp5MiRevbZZys1Z11mspX1ZnHAjqWkZmjKvzcbHQMAAACoEk/3b6LhHcKNjgHUOHl5ecrIyFBERIRcXFgTGbVHef7scuUgUAacSQUAAEBdxtEuANgvykGgDOgGAQAAUKdxwAsAdotyECgDDpUAAAAAAEBdRDkIlAVnUgEAAFCHcbQLAPaLchAoAzPlIAAAAOowiwPHuwBgrygHgTJwdeI/FQAAANRdbs4WoyMAAAxC4wGUgasjB0sAAACouzyczUZHAAAYhHIQKAM3Jw6WAAAAUHe5OXEyHADsFeUgUAaUgwAAAKjLPLitGADsFuUgUAYujpSDAAAAqLvcKQcBwG7xGwAoA64cBAAAQF3mzpqDQLm9NLhvte1r3OfflGt8cnKyZs2aJUlydHRUw4YNNXz4cD3++OOyWCpeBSUnJys7O1vz58+/6LijR49q0qRJ+vbbb3X48GH5+vqqRYsWmjRpkjp27Fjh/aNqUA4CZcAaLAAAAKjLuK0YqHt69eqlmTNnKj8/X999951Gjx4tR0dHPfbYY+Weq7i4WCaTqczjBw4cqIKCAs2aNUuRkZE6fPiwlixZoqysrHLvG1WP24qBMnDjTCoAAADqKAeT5MoyOkCd4+zsrODgYDVq1Ej33HOPunfvrgULFkiSTpw4oeHDh8vX11dubm7q3bu3tm/fXrJtSkqKfHx8tGDBAiUkJMjZ2Vm33367Zs2apa+//lomk0kmk0nLli07Z7/Z2dn65ZdfNH36dHXr1k2NGjVSu3bt9Nhjj+m6664rNe6uu+5SvXr15OLioqZNm+qbb/66QjIrK0tDhgxRaGio3Nzc1KxZM82ZM6fUfrp27ar77rtPjzzyiPz8/BQcHKwpU6ZU/g/SDnB6CCgDDyeLTCbJZjM6CQAAAFC53Jws5boiCEDt5OrqWnLlXnJysrZv364FCxbIy8tLEyZMUJ8+fbR582Y5OjpKknJzczV9+nS9//778vf3V0hIiM6ePatTp05p5syZkiQ/P79z9uPh4SEPDw/Nnz9fV1xxhZydnc8ZY7Va1bt3b50+fVoff/yxoqKitHnzZpnNf52oyMvLU5s2bTRhwgR5eXnp22+/1bBhwxQVFaV27dqVzDNr1iw99NBD+uOPP/Tbb78pOTlZHTt2VI8ePSr951eXUQ4CZeDgYJK7k0U5+UVGRwEAAAAqFesNAnWbzWbTkiVL9P3332vs2LElpWBqaqquvPJKSdInn3yisLAwzZ8/XzfddJMkqbCwUG+99ZZatGhRMperq6vy8/MVHBx8wf1ZLBalpKRo1KhReuedd9S6dWt16dJFN998s5o3by5JWrx4sVauXKn09HTFxMRIkiIjI0vmCA0N1fjx40u+Hzt2rL7//nt98cUXpcrB5s2ba/LkyZKkxo0ba8aMGVqyZAnlYDlxWzFQRqzDAgAAgLqIJxUDddM333wjDw8Pubi4qHfv3ho8eLCmTJmi9PR0WSwWtW/fvmSsv7+/YmNjlZ6eXvKak5NTSZlXXgMHDtTBgwe1YMEC9erVS8uWLVPr1q2VkpIiSUpLS1ODBg1KisH/VVxcrKlTp6pZs2by8/OTh4eHvv/+e+3du7fUuP/NFxISoiNHjlQosz2jHATKyNOFgyYAAADUPe48fA+ok7p166a0tDRt375dZ8+e1axZs+Tu7l7m7V1dXS9ryQEXFxf16NFDEydO1IoVK5ScnFxylZ+rq+tFt33hhRf02muvacKECVq6dKnS0tLUs2dPFRQUlBr3n1ug/8NkMslqtVY4s72iHATKiHIQAAAAdRG3FQN1k7u7u6Kjo9WwYUNZLH//ezY+Pl5FRUX6448/Sl7LysrS1q1blZCQcNE5nZycVFxcXKE8CQkJOnPmjKS/rvjbv3+/tm3bdt6xqamp6t+/v2699Va1aNFCkZGRFxyLy0c5CJSRp4vjpQcBAAAAtQzL5wD2pXHjxurfv79GjRqlX3/9VevWrdOtt96q0NBQ9e/f/6LbhoeHa/369dq6dauOHTumwsLCc8ZkZWUpKSlJH3/8sdavX6+MjAzNnTtXzz//fMn8Xbp0UefOnTVw4ED9+OOPysjI0MKFC7Vo0aKSjD/++KNWrFih9PR03XXXXTp8+HDl/zAgiXIQKDOuHAQAAEBdxJqDgP2ZOXOm2rRpo759+6pDhw6y2Wz67rvvzrlN93+NGjVKsbGxSkxMVGBgoFJTU88Z4+Hhofbt2+uVV15R586d1bRpU02cOFGjRo3SjBkzSsbNmzdPbdu21ZAhQ5SQkKBHHnmk5KrEJ598Uq1bt1bPnj3VtWtXBQcHa8CAAZX6M8DfTDabzWZ0CKA2eOzLDZqzcu+lBwIAAAC1yC3tG+of1zczOgZQI+Xl5SkjI0MRERFycXExOg5QZuX5s8uVg0AZBXg4GR0BAAAAqHR+bhznAoA9oxwEyijI09noCAAAAECl4yQ4ANg3ykGgjAI9uYQcAAAAdU8AJ8EBwK5RDgJlFOTFQRMAAADqngAPjnMBwJ5RDgJlxG3FAAAAqIsoBwHAvlEOAmUUSDkIAACAOiiQchAA7BrlIFBGzhazfNwcjY4BAAAAVBons4O8OcYFALtGOQiUA7cWAwAAoC7x50nFAGD3KAeBcgjiicUAAACoQzj5DQCgHATKgYMnAAAA1CX1vDj5DeD8pkyZopYtWxodo4TJZNL8+fMv+P7u3btlMpmUlpYmSVq2bJlMJpOys7MlSSkpKfLx8anynLWRxegAQG0S6EU5CAAAgLoj2JtyEKio/Y/+Um37ajCtU5nH9uvXT4WFhVq0aNE57/3yyy/q3Lmz1q1bp+bNm1dmRMOFhYUpMzNTAQEB531/8ODB6tOnT8n3U6ZM0fz580vKxMvx3nvvacaMGdq5c6csFosiIiI0aNAgPfbYY5c9d3WgHATKgduKAQAAUJdw5SBQ99xxxx0aOHCg9u/frwYNGpR6b+bMmUpMTKwxxWBxcbFMJpMcHC7/xlaz2azg4OALvu/q6ipXV9fL3s//+vDDD/XAAw/o9ddfV5cuXZSfn6/169dr48aNlb6vqsJtxUA5cFsxAAAA6pJgykGgzunbt68CAwOVkpJS6vWcnBzNnTtXd9xxx3lvsZ0/f75MJtMF501OTtaAAQP04osvKiQkRP7+/ho9erQKCwtLxuTn52v8+PEKDQ2Vu7u72rdvr2XLlpW8/5/9LliwQAkJCXJ2dtbevXu1atUq9ejRQwEBAfL29laXLl20Zs2aczJkZmaqd+/ecnV1VWRkpP71r3+VvPe/txX/r//+zCkpKXrqqae0bt06mUwmmUwmpaSk6Pbbb1ffvn1LbVdYWKigoCB98MEH5513wYIFGjRokO644w5FR0erSZMmGjJkiJ599tlS4z788EM1adJEzs7OCgkJ0ZgxY0ree/nll9WsWTO5u7srLCxM9957r3Jycs7J/v333ys+Pl4eHh7q1auXMjMzz5upvCgHgXKgHAQAAEBdwm3FQN1jsVg0fPhwpaSkyGazlbw+d+5cFRcXa8iQIRWee+nSpdq5c6eWLl2qWbNmKSUlpVQJOWbMGP3222/67LPPtH79et10003q1auXtm/fXjImNzdX06dP1/vvv69NmzYpKChIp0+f1ogRI/Trr7/q999/V+PGjdWnTx+dPn261P4nTpyogQMHat26dRo6dKhuvvlmpaenl/tzDB48WOPGjVOTJk2UmZmpzMxMDR48WCNHjtSiRYtKlW7ffPONcnNzNXjw4PPOFRwcrN9//1179uy54P7efvttjR49Wnfeeac2bNigBQsWKDo6uuR9BwcHvf7669q0aZNmzZqln376SY888kipOXJzc/Xiiy9q9uzZ+vnnn7V3716NHz++3J/9fCgHgXII4swqAAAA6hBuKwbqpttvv107d+7U8uXLS16bOXOmBg4cKG9v7wrP6+vrqxkzZiguLk59+/bVtddeqyVLlkiS9u7dq5kzZ2ru3Lnq1KmToqKiNH78eF111VWaOXNmyRyFhYV66623dOWVVyo2NlZubm5KSkrSrbfeqri4OMXHx+vdd99Vbm5uqfySdNNNN2nkyJGKiYnR1KlTlZiYqDfeeKPcn8PV1VUeHh6yWCwKDg5WcHCwXF1dSzLNnj27ZOzMmTN10003ycPD47xzTZ48WT4+PgoPD1dsbKySk5P1xRdfyGq1lox55plnNG7cON1///2KiYlR27Zt9cADD5S8/8ADD6hbt24KDw9XUlKSnnnmGX3xxRel9lNYWKh33nlHiYmJat26tcaMGVPys79clINAOXDlIAAAAOoSrhwE6qa4uDhdeeWV+vDDDyVJO3bs0C+//KI77rjjsuZt0qSJzGZzyfchISE6cuSIJGnDhg0qLi5WTEyMPDw8Sr6WL1+unTt3lmzj5OR0zpqHhw8f1qhRo9S4cWN5e3vLy8tLOTk52rt3b6lxHTp0OOf7ilw5eDEjR44sKTMPHz6shQsX6vbbb7/g+JCQEP3222/asGGD7r//fhUVFWnEiBHq1auXrFarjhw5ooMHD+rqq6++4ByLFy/W1VdfrdDQUHl6emrYsGHKyspSbm5uyRg3NzdFRUWV2u9/fvaXiweSAOXg7myRl4tFp/KKjI4CAAAAXBZvV0d5OPNPQqCuuuOOOzR27Fi9+eabmjlzpqKiotSlSxdJf93G+t+3HEsqtXbghTg6Opb63mQylVwhl5OTI7PZrNWrV5cqECWVuurO1dX1nLUNR4wYoaysLL322mtq1KiRnJ2d1aFDBxUUFJT9A1eS4cOH69FHH9Vvv/2mFStWKCIiQp06Xfpp0U2bNlXTpk1177336u6771anTp20fPlyJSYmXnS73bt3q2/fvrrnnnv07LPPys/PT7/++qvuuOMOFRQUyM3NTdL5f/b/+/9hRXHlIFBOEQHuRkcAAAAALls4x7VAnTZo0CA5ODjo008/1UcffaTbb7+9pJQLDAzU6dOndebMmZLxF3qQR1m1atVKxcXFOnLkiKKjo0t9XewpwpKUmpqq++67T3369Cl5aMexY8fOGff777+f8318fHyF8jo5Oam4uPic1/39/TVgwADNnDlTKSkpuu2228o9d0JCgiTpzJkz8vT0VHh4+AVvAV69erWsVqteeuklXXHFFYqJidHBgwfLvc/LwWkioJzCA9y1bv9Jo2MAAAAAlyXC383oCACqkIeHhwYPHqzHHntMp06dUnJycsl77du3l5ubmx5//HHdd999+uOPP855unF5xcTEaOjQoRo+fLheeukltWrVSkePHtWSJUvUvHlzXXvttRfctnHjxpo9e7YSExN16tQpPfzww3J1dT1n3Ny5c5WYmKirrrpKn3zyiVauXHnBpwhfSnh4uDIyMpSWlqYGDRrI09NTzs5/LSU2cuRI9e3bV8XFxRoxYsRF57nnnntUv359JSUlqUGDBsrMzNQzzzyjwMDAktugp0yZorvvvltBQUHq3bu3Tp8+rdTUVI0dO1bR0dEqLCzUG2+8oX79+ik1NVXvvPNOhT5TRXHlIFBO4f6cYQUAAEDtx5WDQN13xx136MSJE+rZs6fq169f8rqfn58+/vhjfffdd2rWrJnmzJmjKVOmXPb+Zs6cqeHDh2vcuHGKjY3VgAEDtGrVKjVs2PCi233wwQc6ceKEWrdurWHDhum+++5TUFDQOeOeeuopffbZZ2revLk++ugjzZkzp+QqvfIaOHCgevXqpW7duikwMFBz5swpea979+4KCQk55+d2Pt27d9fvv/+um266STExMRo4cKBcXFy0ZMkS+fv7S/rrtulXX31Vb731lpo0aaK+ffuWPMG5RYsWevnllzV9+nQ1bdpUn3zyiZ577rkKfaaKMtkq6wZlwE7MX3tAD3yeZnQMAAAA4LK8dnNL9W8ZanQMoEbLy8tTRkaGIiIi5OLCA3zsRU5OjkJDQzVz5kzdcMMNRsepkPL82eW2YqCcWHMQAAAAdQHHtQBQmtVq1bFjx/TSSy/Jx8dH1113ndGRqgXlIFBO3H4BAACAuoDjWgAobe/evYqIiFCDBg2UkpIii8U+ajP7+JRAJfJ2dZSfu5OOn6n+R6oDAAAAlcHf3UleLo5GxwCAGiU8PFz2uPoeDyQBKiCcJ7sBAACgFuOqQQDAf1AOAhXAwRQAAABqs3B/jmcBAH+hHAQqIIKDKQAAANRiEQHcCQMA+AvlIFABEYGUgwAAAKi9uBMGAPAflINABXAbBgAAAGozjmcBAP9BOQhUQARnWgEAAFCLcTwLAPgPykGgAtydLQr0dDY6BgAAAFBugZ7Ocne2GB0DAFBD8BsBqKAIf3cdPZ1vdAwAAACgXHi4HlA5pkyZUqP3tW/fPk2ePFmLFi3SsWPHFBISogEDBmjSpEny9/cvGZeRkaEnnnhCy5Yt0/HjxxUQEKA2bdpo+vTpiouLO+/cR48e1aRJk/Ttt9/q8OHD8vX1VYsWLTRp0iR17Nixoh8TBqEcBCooKshdK3cfNzoGAAAAUC5RQZSDQF23a9cudejQQTExMZozZ44iIiK0adMmPfzww1q4cKF+//13+fn5qbCwUD169FBsbKy+/PJLhYSEaP/+/Vq4cKGys7MvOP/AgQNVUFCgWbNmKTIyUocPH9aSJUuUlZVVfR8SlYZyEKighPrekvYZHQMAAAAol7+OYwHUZaNHj5aTk5N++OEHubq6SpIaNmyoVq1aKSoqSk888YTefvttbdq0STt37tSSJUvUqFEjSVKjRo0uevVfdna2fvnlFy1btkxdunQp2aZdu3bnjJswYYLmz5+vkydPKjo6WtOmTVPfvn2VlZWlMWPG6Oeff9aJEycUFRWlxx9/XEOGDCnZvmvXrmrevLlcXFz0/vvvy8nJSXfffXe1XrFpL1hzEKigJvW9jI4AAAAAlFtTjmOBOu348eP6/vvvde+995YUg/8RHBysoUOH6vPPP5fNZlNgYKAcHBz0r3/9S8XFxWWa38PDQx4eHpo/f77y88+/1JbValXv3r2Vmpqqjz/+WJs3b9a0adNkNpslSXl5eWrTpo2+/fZbbdy4UXfeeaeGDRumlStXlppn1qxZcnd31x9//KHnn39eTz/9tH788ccK/FRwMZSDQAXFB3vJ7GAyOgYAAABQZmYHk+JDKAeBumz79u2y2WyKj48/7/vx8fE6ceKEjh49qtDQUL3++uuaNGmSfH19lZSUpKlTp2rXrl0XnN9isSglJUWzZs2Sj4+POnbsqMcff1zr168vGbN48WKtXLlSX375pXr06KHIyEj17dtXvXv3liSFhoZq/PjxatmypSIjIzV27Fj16tVLX3zxRal9NW/eXJMnT1bjxo01fPhwJSYmasmSJZXwU8J/oxwEKsjVyazIANZrAQAAQO0RFeguF0ez0TEAVAObzVamcaNHj9ahQ4f0ySefqEOHDpo7d66aNGly0Sv0Bg4cqIMHD2rBggXq1auXli1bptatWyslJUWSlJaWpgYNGigmJua82xcXF2vq1Klq1qyZ/Pz85OHhoe+//1579+4tNa558+alvg8JCdGRI0fK9LlQdpSDwGXg1mIAAADUJk1YbxCo86Kjo2UymZSenn7e99PT0+Xr66vAwMCS1zw9PdWvXz89++yzWrdunTp16qRnnnnmovtxcXFRjx49NHHiRK1YsULJycmaPHmyJJ1zO/P/euGFF/Taa69pwoQJWrp0qdLS0tSzZ08VFBSUGufo6Fjqe5PJJKvVetG5UX6Ug8BlaBrKwRUAAABqD05uA3Wfv7+/evToobfeektnz54t9d5/rhAcPHiwTKbzL5NlMpkUFxenM2fOlGu/CQkJJds0b95c+/fv17Zt2847NjU1Vf3799ett96qFi1aKDIy8oJjUfUoB4HLkMDBFQAAAGoRrhwE7MOMGTOUn5+vnj176ueff9a+ffu0aNEi9ejRQ6GhoXr22Wcl/XX7b//+/fWvf/1Lmzdv1o4dO/TBBx/oww8/VP/+/c87d1ZWlpKSkvTxxx9r/fr1ysjI0Ny5c/X888+XbNOlSxd17txZAwcO1I8//qiMjAwtXLhQixYtkiQ1btxYP/74o1asWKH09HTdddddOnz4cPX8cHAOi9EBgNqMgysAAADUFiaT1CSUk9uAPWjcuLH+/PNPTZ48WYMGDdLx48cVHBysAQMGaPLkyfLz85MkNWjQQOHh4Xrqqae0e/dumUymku8ffPDB887t4eGh9u3b65VXXtHOnTtVWFiosLAwjRo1So8//njJuHnz5mn8+PEaMmSIzpw5o+joaE2bNk2S9OSTT2rXrl3q2bOn3NzcdOedd2rAgAE6efJk1f9wcA6TrawrVAI4r07P/6R9x89eeiAAAABgoIZ+bvr5kW5GxwBqlby8PGVkZCgiIkIuLi5GxwHKrDx/drmtGLhMTbl6EAAAALUA6w0CAM6HchC4TBxkAQAAoDbguBUAcD6Ug8BlYt1BAAAA1AZNQjluBQCci3IQuEws6gwAAIDagOVwAADnQzkIXKYgTxcFejobHQMAAAC4oCBPZ45ZAQDnRTkIVIKmrN8CAACAGoz1BgEAF0I5CFSCZg18jI4AAAAAXBDHqwCAC6EcBCpB23BfoyMAAAAAF9Qu3M/oCACAGopyEKgEbRr5yuJgMjoGAAAAcA5Hs0ltGnEyGwBwfpSDQCVwc7KoSShPfwMAAEDN06S+t1ydzEbHAIBSdu/eLZPJpLS0tCrdz7Jly2QymZSdnV2l+6nNLEYHAOqK9hF+Wrcv2+gYAAAAQCntI7ilGKgKS36KqrZ9XZ20s1zju3btqpYtW+rVV18t9XpKSooeeOCBkqJsypQpeuqppyRJZrNZPj4+SkhI0A033KB77rlHzs7OpeZcvny5JMnZ2VmRkZEaM2aM7r333gvmMJnOvcOuY8eO+vXXX8v1eVC1uHIQqCSs4wIAAICaqB3lIICLaNKkiTIzM7V3714tXbpUN910k5577jldeeWVOn36dKmxo0aNUmZmpjZv3qxBgwZp9OjRmjNnzkXnnzlzpjIzM0u+FixYUJUfBxVAOQhUkrYRfmLZQQAAANQkDiYpkZPYAC7CYrEoODhY9evXV7NmzTR27FgtX75cGzdu1PTp00uNdXNzU3BwsCIjIzVlyhQ1btz4kmWfj4+PgoODS778/C78d9Ly5cvVrl07OTs7KyQkRI8++qiKiopK3s/Pz9d9992noKAgubi46KqrrtKqVatKzfHdd98pJiZGrq6u6tatm3bv3l3+H4qdoRwEKom3q6Ni6nkaHQMAAAAoERvsJW9XR6NjAKhl4uLi1Lt3b3355ZcXHefq6qqCgoJK2eeBAwfUp08ftW3bVuvWrdPbb7+tDz74QM8880zJmEceeUTz5s3TrFmztGbNGkVHR6tnz546fvy4JGnfvn264YYb1K9fP6WlpWnkyJF69NFHKyVfXUY5CFQi1nMBAABATcLxKYCKiouLu+BVd8XFxfr444+1fv16JSUlXXSeIUOGyMPDo+Rr/vz55x331ltvKSwsTDNmzFBcXJwGDBigp556Si+99JKsVqvOnDmjt99+Wy+88IJ69+6thIQEvffee3J1ddUHH3wgSXr77bcVFRWll156SbGxsRo6dKiSk5Mv46dgH3ggCVCJ2kX4a9Zve4yOAQAAAEhivUEAFWez2c55oMhbb72l999/XwUFBTKbzXrwwQd1zz33XHSeV155Rd27dy/5PiQk5Lzj0tPT1aFDh1L77Nixo3JycrR//35lZ2ersLBQHTt2LHnf0dFR7dq1U3p6eskc7du3LzVvhw4dyvaB7RjlIFCJOPgCAABATcLxKWCfvLy8dPLkyXNez87Olre3d5nmSE9PV0RERKnXhg4dqieeeEKurq4KCQmRg8Olb0gNDg5WdHR02YLDENxWDFSiQE9nRQa4Gx0DAAAAUGSguwI8nI2OAcAAsbGxWrNmzTmvr1mzRjExMZfcfsuWLVq0aJEGDhxY6nVvb29FR0crNDS0TMVgecTHx+u3336TzWYreS01NVWenp5q0KCBoqKi5OTkpNTU1JL3CwsLtWrVKiUkJJTMsXLlylLz/v7775Wasy6iHAQqGWdnAQAAUBOw3iBgv+655x5t27ZN9913n9avX6+tW7fq5Zdf1pw5czRu3LhSY4uKinTo0CEdPHhQGzZs0BtvvKEuXbqoZcuWevjhh6st87333qt9+/Zp7Nix2rJli77++mtNnjxZDz30kBwcHOTu7q577rlHDz/8sBYtWqTNmzdr1KhRys3N1R133CFJuvvuu7V9+3Y9/PDD2rp1qz799FOlpKRU22eorbitGKhk7SL89NmqfUbHAAAAgJ3jpDVgvyIjI/Xzzz/riSeeUPfu3VVQUKC4uDjNnTtXvXr1KjV206ZNCgkJkdlslre3txISEvTYY4/pnnvukbNz9V19HBoaqu+++04PP/ywWrRoIT8/P91xxx168sknS8ZMmzZNVqtVw4YN0+nTp5WYmKjvv/9evr6+kqSGDRtq3rx5evDBB/XGG2+oXbt2+sc//qHbb7+92j5HbWSy/ff1mgAu2/4Tubpq+lKjYwAAAMDOrXg0SfV9XI2OAdRqeXl5ysjIUEREhFxcXIyOA5RZef7sclsxUMka+LoplIMwAAAAGCjUx5ViEABQJpSDQBXoEOVvdAQAAADYsSs5HgUAlBHlIFAFusUGGR0BAAAAdqxbHMejAICyoRwEqkCnmABZHExGxwAAAIAdcjSb1KlxgNExAAC1BOUgUAW8XBzVppGv0TEAAABghxIb+cnTxdHoGACAWoJyEKgiSdzKAQAAAANwHAoAKA/KQaCKcFAGAAAAI3SLCzQ6AgCgFqEcBKpI43qeauDranQMAAAA2JEwP1dFB3kaHQMAUItQDgJViKcWAwAAoDolcfwJACgnykGgCnFrMQAAAKpTV44/AdRiy5Ytk8lkUnZ2dpXuJyUlRT4+PlW6j9rEYnQAoC7rEOUvF0cH5RVajY4CAACAOs7V0awOkf5GxwDsRvDStGrb16FuLcs1Pjk5WdnZ2Zo/f/7fcxw6pGeffVbffvutDhw4oKCgILVs2VIPPPCArr76aklSeHi49uzZozlz5ujmm28uNWeTJk20efNmzZw5U8nJyaXGS5Kbm5tiY2P12GOP6aabbjpvrt27dysiIuKc14cOHaqPP/64XJ8RlYcrB4Eq5OJo1pVRAUbHAAAAgB24MspfLo5mo2MAqIF2796tNm3a6KefftILL7ygDRs2aNGiRerWrZtGjx5damxYWJhmzpxZ6rXff/9dhw4dkru7+zlzP/3008rMzNTatWvVtm1bDR48WCtWrLhonsWLFyszM7Pk680337z8D4kKoxwEqli3WJ4WBwAAgKrXjVuKAVzAvffeK5PJpJUrV2rgwIGKiYlRkyZN9NBDD+n3338vNXbo0KFavny59u3bV/Lahx9+qKFDh8piOfcGVE9PTwUHBysmJkZvvvmmXF1d9e9///uiefz9/RUcHFzy5e3tfcGx8+bNU5MmTeTs7Kzw8HC99NJLpd4/ceKEhg8fLl9fX7m5ual3797avn17qTEpKSlq2LCh3NzcdP311ysrK+ui+ewN5SBQxThIAwAAQHXguBPA+Rw/flyLFi3S6NGjz3vl3/+uvVevXj317NlTs2bNkiTl5ubq888/1+23337JfVksFjk6OqqgoKBSsq9evVqDBg3SzTffrA0bNmjKlCmaOHGiUlJSSsYkJyfrzz//1IIFC/Tbb7/JZrOpT58+KiwslCT98ccfuuOOOzRmzBilpaWpW7dueuaZZyolX11BOQhUsQa+boqp52F0DAAAANRhsfU8FerjanQMADXQjh07ZLPZFBcXV+Ztbr/9dqWkpMhms+lf//qXoqKi1LJly4tuU1BQoOeee04nT55UUlLSRcdeeeWV8vDwKPlau3btece9/PLLuvrqqzVx4kTFxMQoOTlZY8aM0QsvvCBJ2r59uxYsWKD3339fnTp1UosWLfTJJ5/owIEDJestvvbaa+rVq5ceeeQRxcTE6L777lPPnj3L/LOwB5SDQDXgLC4AAACqEsebAC7EZrOVe5trr71WOTk5+vnnn/Xhhx9e9KrBCRMmyMPDQ25ubpo+fbqmTZuma6+99qLzf/7550pLSyv5SkhIOO+49PR0dezYsdRrHTt21Pbt21VcXKz09HRZLBa1b9++5H1/f3/FxsYqPT29ZI7/fl+SOnTocNF89oanFQPVICk2SP9cvsvoGAAAAKijkigHAVxA48aNZTKZtGXLljJvY7FYNGzYME2ePFl//PGHvvrqqwuOffjhh5WcnCwPDw/Vq1dPJpPpkvOHhYUpOjq6zHlQtbhyEKgGieF+CvBwMjoGAAAA6qBAT2clNvI1OgaAGsrPz089e/bUm2++qTNnzpzzfnZ29nm3u/3227V8+XL1799fvr4X/jsmICBA0dHRCg4OLlMxWB7x8fFKTU0t9VpqaqpiYmJkNpsVHx+voqIi/fHHHyXvZ2VlaevWrSVXI8bHx5d6X9I5D2Gxd5SDQDUwO5jUq2mw0TEAAABQB/VpGiwHh8r9BzmAuuXNN99UcXGx2rVrp3nz5mn79u1KT0/X66+/fsFbbOPj43Xs2DHNnDmzmtP+bdy4cVqyZImmTp2qbdu2adasWZoxY4bGjx8v6a+rIvv3769Ro0bp119/1bp163TrrbcqNDRU/fv3lyTdd999WrRokV588UVt375dM2bM0KJFiwz7TDUR5SBQTfo1r290BAAAANRB/VpwnAng4iIjI7VmzRp169ZN48aNU9OmTdWjRw8tWbJEb7/99gW38/f3l6urcQ87at26tb744gt99tlnatq0qSZNmqSnn35aycnJJWNmzpypNm3aqG/fvurQoYNsNpu+++47OTo6SpKuuOIKvffee3rttdfUokUL/fDDD3ryyScN+kQ1k8lWkZUpAZSbzWZTh+d+0qFTeUZHAQAAQB1R39tFqY8mVfqtfAD+kpeXp4yMDEVERMjFxcXoOECZlefPLlcOAtXEZDLp2uYhRscAAABAHXJt8xCKQQDAZaEcBKoRt3wAAACgMnF8CQC4XJSDQDVqGeajhn5uRscAAABAHRDu76bmDXyMjgEAqOUoB4Fq1pdbiwEAAFAJ+vLAOwBAJaAcBKoZt34AAACgMnBcCQCoDJSDQDWLD/FS4yAPo2MAAACgFoup56HYYE+jYwB2w2q1Gh0BKJfy/Jm1VGEOABfQt3l9vbJ4m9ExAAAAUEv145ZioFo4OTnJwcFBBw8eVGBgoJycnHhCOGo0m82mgoICHT16VA4ODnJycrrkNiabzWarhmwA/suuozlKemm50TEAAABQSy0b31XhAe5GxwDsQkFBgTIzM5Wbm2t0FKDM3NzcFBISUqZykCsHAQNEBnqoSX0vbTp4yugoAAAAqGWahXpTDALVyMnJSQ0bNlRRUZGKi4uNjgNcktlslsViKfNVrpSDgEH6tahPOQgAAIBy69cixOgIgN0xmUxydHSUo6Oj0VGASscDSQCD9G0eIpaqAAAAQHmYTH+tXw0AQGWhHAQM0sDXTYmNfI2OAQAAgFqkbSM/1fdxNToGAKAOoRwEDDQoMczoCAAAAKhFbm7H8SMAoHJRDgIG6teivrxcWPoTAAAAl+bt6qg+zVhvEABQuSgHAQO5OJo1oFWo0TEAAABQC1zfKlQujmajYwAA6hjKQcBgQ9o1NDoCAAAAagFuKQYAVAXKQcBg8SFeahHmY3QMAAAA1GCtGvooLtjL6BgAgDqIchCoAYa05SwwAAAALmxIW+42AQBUDcpBoAa4rmV9eTjzYBIAAACcy9PZor4teBAJAKBqUA4CNYCbk0XXtaxvdAwAAADUQNe1rC83J04kAwCqBuUgUENwqwgAAADOhwfYAQCqEuUgUEM0a+CtpqEsMg0AAIC/NQv1VtNQb6NjAADqMMpBoAa5masHAQAA8F9ubseD6wAAVYtyEKhBBrQKlZuT2egYAAAAqAHcnMzq3zLU6BgAgDqOchCoQTycLerXnAeTAAAAQOrXvL48nHkQCQCgalEOAjUMt44AAABAkoa0Z8kZAEDVoxwEaphWDX0VH8KDSQAAAOxZfIiXWob5GB0DAGAHKAeBGui2K8ONjgAAAAAD3XFVhNERAAB2gnIQqIH6t6qvAA8no2MAAADAAMFeLurfknWoAQDVg3IQqIGcLWbdekUjo2MAAADAACOuDJejmX+qAQCqB79xgBrq1isaycnCf6IAAAD2xN3JrFt4EAkAoBrRPAA1VICHswZwOwkAAIBdGdQ2TN6ujkbHAADYEcpBoAa746pIoyMAAACgmpgdTLq9Iw8iAQBUL8pBoAaLDfZUp8YBRscAAABANejVNFhhfm5GxwAA2BnKQaCGG9WJqwcBAADswV2dOe4DAFQ/ykGghuscE6j4EC+jYwAAAKAKtYvwU/MGPkbHAADYIcpBoBbgLDIAAEDdxt0iAACjUA4CtUDf5iEK9XE1OgYAAACqQGSgu7rHBxkdAwBgpygHgVrAYnbQyE48uQ4AAKAuGnlVpEwmk9ExAAB2inIQqCVubttQvm6ORscAAABAJfJ3d9INrUONjgEAsGOUg0At4epk1rArGhkdAwAAAJVoWIdGcnE0Gx0DAGDHLEYHAFB2I64M13u/ZOhsYbHRUQAAqDBrfq6yf/lYudt/kzX3pJyCIuXb/U45h8RIko59+4rObFxSahuXiNaqN+jpC855eu13Or32OxWdPCxJcgxoKJ8rh8g1KrFkzPEl7+nMxiUyObrIp8sIeTTpVvLemS2/6szGJQq6cXJlflTgolwdzRreIdzoGAAAO0c5CNQi/h7OGtahkd79eZfRUQAAqLCsRW+o8OgeBfQdJ7OHn85sWqrDnz2p+iPfksUzQJLkEtFGAX0e+Hsjy8WX1jB7+su3ywhZfOtLknI2LtGRL59RSPJrcgpspNwdf+hM+nIFDZqqohMHlbXwNblGtJbZzVvW/DPK/vkj1bv5mar6yMB53XpFQ/m5OxkdAwBg57itGKhl7u4SJXcnbj0BANRO1sJ85W5NlU+32+QS1lSOvvXlc9VQOfqG6PTahSXjTBZHmT18//5y8bjovG7R7eUa1VaOfqFy9AuVb+fhcnByUf7BrZKkwqx9cglrJueQxnJP6CKTk1vJVYYnls6UZ6s+snjxtFhUH1dHs+7qEmV0DAAAKAeB2sbP3Ukjrgw3OgYAABVjLZZsVpnMpa8ENFmclb9/U8n3eXs3aN8bQ3XgvbuU9f2bKj57qsy7sFmLdWbzclkL8+QcGidJcgqMUMGhHSrOy1H+oR2yFeXL4ltfefs3qeDwTnm26Vc5nw8oo1uvaKgAD2ejYwAAwG3FQG10Z+dIzf5tj07nFxkdBQCAcnFwdpNz/TidXPGZHP3DZHb30Zn0n5V/cIssviGSJNeI1nKLuVIWn3oqOpGp7J8/0pG5kxV864syOVz46vmCo7t1aPZ42YoKZHJyVdD1T8gpoOFfc0a2kXuTrjo060GZLE4KuPZBOTg66/j3b8n/2gf/WrNwzTcyu3rJr+cYOQXyEDBUHa4aBADUJCabzWYzOgSA8nv5x216fcl2o2MAAFBuhScylbXwNeXv2yiZHOQUHCVH31DlH9qh0FHvnDs++5AO/nOkggY/I9fwlhec11ZcqKJTR2XNz1Xu1l+Vs+4H1btlWklB+L+yf/1U1vwz8mjWXYe/mKj6t7+psztW6vSabxSS/FplfVzgHKM6ReiJaxOMjgEAgCRuKwZqrZGdIuTtevHF2QEAqIkcfUMUfMs0hT34L4Xem6KQ4a/IZi2Wo0/w+cf7BMvB1UtF2ZkXnddkdpSjb305B0fLt0uynIIidPrPBecdW5i1T2c2L5VPp1uVt3eDXBo0ldnNW25xnVRweKes+bmX/TmB8+GqQQBATUM5CNRSXi6OGnlVhNExAACoMAcnF1k8/FScl6OzGWvk2viK844rOnVM1rOnZXb3K9f8NptNtuLC876e9f2b8k0aKQcnV8lmlc36/0t1/Od/bdZy7QsoK9YaBADUNJSDQC1221UR8nXj6kEAQO1ydtdqnd21WoXZh3Q2Y60Oz3lMjn4N5NGsu6wFZ3Vi6YfKP7BFRScP6+zuNB39cqosviFyjWhdMsfhzx7XqdX/Lvn+xPIU5e3bqKKTh1VwdLdOLE9R/t4Nck/oes7+c9Z9L7Orl9yi20uSnEPjlbdnvfIPbNGpVV/L0b+hHC7xdGSgItydzLqbqwYBADUMDyQBajEPZ4vu7Byl6Yu2GB0FAIAys+bnKvvnWSo6fUxmF0+5xV4pn87DZTJbZLMWq+BIhnI2LpE174zMHn5yjWgln063ymT5+4RY4YlDcv6vJxgXnzmpY9+8rOIzx+Xg7C6nwHAFDXparhGtSu27+MwJnfztCwXf+kLJa871Y+XV7nod+ddTcnDzVsC1D1b9DwF26baOEfLnqkEAQA3DA0mAWi63oEidn1+qYzkFRkcBAADABXi5WPTLhCTWjAYA1DjcVgzUcm5OFm5PAQAAqOHu6hJFMQgAqJEoB4E64NYrGinIk1tUAAAAaqIADyfd1jHc6BgAAJwX5SBQB7g4mnVvV64eBAAAqInu6RotNyeWewcA1EyUg0AdMaR9Q9X3djE6BgAAAP5LiLeLbr2iodExAAC4IMpBoI5wtph1f/fGRscAAADAf3mwe4ycLWajYwAAcEGUg0AdclObMCWEeBkdAwAAAJKahnrpxjYNjI4BAMBFUQ4CdYiDg0kT+yYYHQMAAACSJl6bIAcHk9ExAAC4KMpBoI7pEOWvnk3qGR0DAADArvVuGqz2kf5GxwAA4JIoB4E66Ik+CXIy8583AACAEZwsDnq8T7zRMQAAKBPaA6AOaujvpts6hhsdAwAAwC7d3jFCYX5uRscAAKBMKAeBOmpMUrQCPJyMjgEAAGBXAjycNbpblNExAAAoM8pBoI7ydHHUQz1ijY4BAABgV8ZdEyNPF0ejYwAAUGaUg0AddnPbMMWHeBkdAwAAwC7Eh3hpcGKY0TEAACgXykGgDnNwMGliXxbDBgAAqA6T+ibIwcFkdAwAAMqFchCo466MClCPhHpGxwAAAKjTrkmopw5R/kbHAACg3CgHATvwRJ94OZn5zx0AAKAqOJkd9MS13K0BAKidaAsAOxAe4K7kjuFGxwAAAKiTkjuGq5G/u9ExAACoEMpBwE6MTYpWgIeT0TEAAADqlAAPJ41NijY6BgAAFUY5CNgJTxdHjb8m1ugYAAAAdcr4a2Ll6eJodAwAACqMchCwI4PbhqltuK/RMQAAAOqEduF+Gtw2zOgYAABcFspBwI6YTCY9d0MzHk4CAABwmZwsDvrHDc1kMpmMjgIAwGWhIQDsTHSQp+7pGmV0DAAAgFrt3q5Rig7yMDoGAACXjXIQsEOju0UrKpAn6gEAAFREdJCH7u3KQ0gAAHUD5SBgh5wsDpo2sLm4CwYAAKB8TCb9tUyLhX9KAQDqBn6jAXaqbbifbm7b0OgYAAAAtcqQdg3VNtzP6BgAAFQaykHAjj3WJ05Bns5GxwAAAKgVgjyd9WjvOKNjAABQqSgHATvm5eKoyf2aGB0DAACgVphyXRN5uTgaHQMAgEpFOQjYuWubh6h7fJDRMQAAAGq07vH11KdZiNExAACodJSDADR1QFN5OFuMjgEAAFAjeThbNHUAd1sAAOomykEACvF21bhrYoyOAQAAUCONvyZGId6uRscAAKBKUA4CkCSN6BCulmE+RscAAACoUVqG+Wh4h3CjYwAAUGUoBwFIkhwcTJo2sJksDiajowAAANQIlv8/PnLg+AgAUIdRDgIoERfspXu7RhkdAwAAoEa4t1u04oK9jI4BAECVohwEUMp9VzdWiwbeRscAAAAwVIswH92XFG10DAAAqhzlIIBSLGYHvTK4pVwdzUZHAQAAMISbk1mvDm4pi5l/LgEA6j5+2wE4R2Sgh564Nt7oGAAAAIZ44tp4RQS4Gx0DAIBqQTkI4LxuvaKRkuKCjI4BAABQrbrHB2lo+0ZGxwAAoNpQDgK4oOkDm8vf3cnoGAAAANUiwMNJ0wY2NzoGAADVinIQwAUFejpzgAwAAOzG9IHNFeDhbHQMAACqFeUggIvqkVBPQ9qFGR0DAACgSg1p11BXx9czOgYAANWOchDAJU3sm6BwfzejYwAAAFSJiAB3TezLw9gAAPaJchDAJbk5WfTK4JayOJiMjgIAAFCpLA4mvTK4pdycLEZHAQDAEJSDAMqkVUNfjUmKNjoGAABApRqb1Fgtw3yMjgEAgGEoBwGU2Zhu0WrV0MfoGAAAAJWiVUMfTn4CAOwe5SCAMrOYHfTKoJZyczIbHQUAAOCyuDuZ9ergljKzbAoAwM5RDgIol/AAd03ul2B0DAAAgMsyuV8TNfJ3NzoGAACGoxwEUG6D2zbUDa1DjY4BAABQITe2aaBBbcOMjgEAQI1AOQigQv5xfTPFBXsaHQMAAKBc4kO89MyApkbHAACgxqAcBFAhLo5mvXNrG3m6WIyOAgAAUCaeLha9c2truTiyfjIAAP9BOQigwsID3PXiTS2MjgEAAHBJJpP08qCWrDMIAMD/oBwEcFl6NgnWXZ0jjY4BAABwUXd1jlKPhHpGxwAAoMahHARw2R7pFacrIv2MjgEAAHBeHSL99XDPWKNjAABQI1EOArhsZgeT3hjSWvW8nI2OAgAAUEo9L2e9cUsrmR1MRkcBAKBGohwEUCkCPZ315i2tZeHAGwAA1BCOZpPeGtpaAR6cwAQA4EIoBwFUmsRwPz3aO87oGAAAAJKkR3vHq00jlj4BAOBiKAcBVKqRnSJ1bbMQo2MAAAA7d23zEN1xVYTRMQAAqPEoBwFUuuk3NldUoLvRMQAAgJ2KCnTX8wObGx0DAIBagXIQQKXzcLbonVvbyM3JbHQUAABgZ9ydzPrnsDZyd7YYHQUAgFqBchBAlWhcz1PTOWMPAACq2bSBzRUd5Gl0DAAAag3KQQBVpl+L+rrv6sZGxwAAAHbige6N1a9FfaNjAABQq1AOAqhSD/WIUf+WHKQDAICq1b9lfT3QPcboGAAA1DqUgwCq3PM3NlebRr5GxwAAAHVUYiNfPX8jy5kAAFARlIMAqpyzxax3h7VRQz83o6MAAIA6pqGfm94dnihnCw9CAwCgIigHAVQLfw9nfZicKC8XnhwIAAAqh5eLRR8mt5Wfu5PRUQAAqLUoBwFUm+ggT719axtZHExGRwEAALWcxcGkt29to+ggD6OjAABQq1EOAqhWHaMDNHVAU6NjAACAWu6ZAU3VMTrA6BgAANR6lIMAqt2Qdg01qlOE0TEAAEAtdWfnSN3crqHRMQAAqBMoBwEY4rHe8bomoZ7RMQAAQC3Ts0k9PdorzugYAADUGZSDAAzh4GDSaze3UtNQL6OjAACAWqJZqLdeHdxKDqxfDABApaEcBGAYVyezPhjRViHeLkZHAQAANVyIt4s+GJEoVyez0VEAAKhTKAcBGKqel4veH5Eodw70AQDABbg7mfX+iEQFeXFCEQCAykY5CMBwTep76+1b28jJzF9JAACgNCezg96+tY2a1Pc2OgoAAHUS/xIHUCN0jgnUqze3lJk1hAAAwP8zO5j02s0t1Tkm0OgoAADUWZSDAGqMPs1C9Nz1zWSiHwQAwO6ZTNJzNzRT72YhRkcBAKBOoxwEUKMMahumJ/rEGx0DAAAY7Ik+8RqUGGZ0DAAA6jzKQQA1zshOkRqbFG10DAAAYJD7kqI1slOk0TEAALALlIMAaqRx18Qq+cpwo2MAAIBqlnxluB66JtboGAAA2A3KQQA11uR+CbqhVajRMQAAQDW5oXWoJvdLMDoGAAB2hXIQQI1lMpn0/I3N1SOhntFRAABAFbsmoZ5euLGFTDyZDACAakU5CKBGs5gdNOOWVroyyt/oKAAAoIp0jPbXG7e0ktmBYhAAgOpGOQigxnO2mPXe8ES1DPMxOgoAAKhkLcN89O6wRDlbzEZHAQDALlEOAqgV3J0tSrmtrWLreRodBQAAVJLYep5Kua2t3J0tRkcBAMBuUQ4CqDV83Jw0+452auTvZnQUAABwmRr6uWn2He3k4+ZkdBQAAOwa5SCAWiXIy0WfjGyvMD9Xo6MAAIAKauTvpjl3XqEgLxejowAAYPdMNpvNZnQIACivA9lnNeTd37X3eK7RUQAAQDlEBrprzqgrVI9iEACAGoFyEECtlXnyr4JwdxYFIQAAtUFMPQ99MvIKBXo6Gx0FAAD8P8pBALXaoZN5uuW937Xr2BmjowAAgIuIC/bUJyPby9+DYhAAgJqEchBArXfkVJ5ufu937TpKQQgAQE3ULNSbh48AAFBDUQ4CqBOOnM7TLe/9oR1HcoyOAgAA/kvLMB99dEc7ebk4Gh0FAACcB+UggDrjWE6+hn2wUumZp4yOAgAAJLUN99XM29rJw9lidBQAAHABlIMA6pSTuYUaPnOl1u3LNjoKAAB2rUOkvz5ITpSbE8UgAAA1GeUggDonJ79It89cpZW7jxsdBQAAu9SpcYDeG54oF0ez0VEAAMAlUA4CqJPOFhTrztl/6pftx4yOAgCAXUmKC9Lbt7aWs4ViEACA2oByEECdlV9UrNGfrNXi9MNGRwEAwC5ck1BPM25pLSeLg9FRAABAGVEOAqjTioqteuiLdVqw7qDRUQAAqNOua1FfLw9qIYuZYhAAgNqEchBAnWez2fTcwi169+ddRkcBAKBOuuOqCD15bbxMJpPRUQAAQDlRDgKwGzNTMzT1m82y8rceAACVwmSSHu0Vp7u6RBkdBQAAVBDlIAC7snBDph74PE35RVajowAAUKs5mk16/sbmur5VA6OjAACAy0A5CMDurNp9XKM++lPZuYVGRwEAoFZyczLr7VvbqEtMoNFRAADAZaIcBGCXdhzJ0YgPV+pA9lmjowAAUKv4uzvpw+S2ahHmY3QUAABQCSgHAditI6fylDxzlTZnnjI6CgAAtUJEgLtSbmurRv7uRkcBAACVhHIQgF3LyS/SPR+v1i/bjxkdBQCAGi2xka/eG54oX3cno6MAAIBKRDkIwO4VFlv16LwNmrdmv9FRAACokfo0C9bLg1rKxdFsdBQAAFDJKAcB4P+9+P1WzVi6w+gYAADUKHd2jtRjveNkMpmMjgIAAKoA5SAA/JdP/tijSV9vUrGVvxoBAPbN7GDS5H4JGt4h3OgoAACgClEOAsD/+GnLYd0/J02n84uMjgIAgCE8nS16bUhLJcXVMzoKAACoYpSDAHAeO47k6M6P/tSuY2eMjgIAQLWKDHTXe8MTFRXoYXQUAABQDSgHAeACTuUV6oHP0vTTliNGRwEAoFpcHRekV29uKU8XR6OjAACAakI5CAAXYbXa9PKP23hQCQCgTjOZpNFdo/VQjxg5OPDgEQAA7AnlIACUwXcbMjV+7jrlFhQbHQUAgErl7mTWize1UO9mIUZHAQAABqAcBIAy2nLolO78aLX2Hs81OgoAAJWioZ+b3hueqNhgT6OjAAAAg1AOAkA5ZOcWaOyctfpl+zGjowAAcFk6NQ7QG0NaycfNyegoAADAQJSDAFBOxVabpi1M13u/ZBgdBQCAChnVKUKP9o6XmfUFAQCwe5SDAFBB89ce0KNfrldeodXoKAAAlImLo4Om3dBcA1qFGh0FAADUEJSDAHAZNh44qbtmr9aB7LNGRwEA4KJCfVz1z2Ft1DTU2+goAACgBqEcBIDLlJWTrzGfrtVvu7KMjgIAwHl1iPTXjFtayd/D2egoAACghqEcBIBKYLXaNGPpDr22ZLuKrfy1CgCoGcwOJj1wdWON7hYtB9YXBAAA50E5CACVaNXu47p/zlodPJlndBQAgJ0L9XHVaze3VGK4n9FRAABADUY5CACV7GRuoR6Zt07fbzpsdBQAgJ3q2aSenh/YQt5ujkZHAQAANRzlIABUkdm/7dYz36Yrv4inGQMAqoezxUFP9k3QsCsaGR0FAADUEpSDAFCFthw6pbGfrtX2IzlGRwEA1HGNgzz0xi2tFBfsZXQUAABQi1AOAkAVO1tQrKf+vUmfrdpndBQAQB11c9swTe7XRK5OZqOjAACAWoZyEACqyTfrD+qxLzfodF6R0VEAAHWEp4tFz93QTH2b1zc6CgAAqKUoBwGgGu07nquxc9YqbV+20VEAALVcyzAfvTGklcL83IyOAgAAajHKQQCoZkXFVr34wzb98+ed4m9gAEB5mUzSXZ2jNP6aGFnMDkbHAQAAtRzlIAAYJHXHMT3yr/U6kH3W6CgAgFoi1MdVz9/YXB2jA4yOAgAA6gjKQQAwUE5+kZ77Ll2frtzLVYQAgAsymaSh7Rvqsd7xcne2GB0HAADUIZSDAFADrNh5TBPmrde+41xFCAAoraGfm6YNbKYro7haEAAAVD7KQQCoIXILijR94RZ99PseriIEAMhkkoZf0UgTesfJzYmrBQEAQNWgHASAGub3XVmaMG+99mTlGh0FAGCQcH83TR/YXO0j/Y2OAgAA6jjKQQCogc4WFOv577do1ordsvK3NADYDQeTlHxlhB7uGStXJ7PRcQAAgB2gHASAGuzP3cf1yL/Wa9exM0ZHAQBUscgAdz1/Y3MlhvsZHQUAANgRykEAqOHyCov10g9b9cGvGVxFCAB1kINJuuOqCI27JlYujlwtCAAAqhflIADUEqv3nNAj/1qnnUe5ihAA6oqoQHe9cFMLtW7oa3QUAABgpygHAaAWySss1ptLd+ifP+9SQZHV6DgAgApysjjo7s6RurdbNFcLAgAAQ1EOAkAttPvYGT31701auvWo0VEAAOV0dVyQJvVLUCN/d6OjAAAAUA4CQG22ePNhPfXNJu07ftboKACAS2jo56bJ/RJ0dXw9o6MAAACUoBwEgFour7BY7yzfqbeX7VQ+txoDQI3j4uige7pE664ukdxCDAAAahzKQQCoI/Ydz9XT32zWj5sPGx0FAPD/rkmop4l9ExTm52Z0FAAAgPOiHASAOmbp1iN6asEm7c7KNToKANitiAB3Te6XoK6xQUZHAQAAuCjKQQCog/KLivXez7v05tKdOltYbHQcALAbro5mjUmK1shOEXK2cAsxAACo+SgHAaAOO5B9Vs98s1kLNx4yOgoA1Hm9mwbryb4JCvVxNToKAABAmVEOAoAd+GX7UT39783afiTH6CgAUOc0DvLQpH4J6tQ40OgoAAAA5UY5CAB2othq07zV+/XK4m3KPJlndBwAqPXqe7vogR4xurF1Azk4mIyOAwAAUCGUgwBgZ/IKi/XRb7v11rKdys4tNDoOANQ6vm6OurdrtIZ1aCQXR9YVBAAAtRvlIADYqVN5hXpn2U7NTN3NQ0sAoAxcHc2646oI3dklUl4ujkbHAQAAqBSUgwBg546cytOrS7bri1X7VGTlVwIA/C+Lg0mD24bp/qsbK8jLxeg4AAAAlYpyEAAgSdp1NEcv/bBN323MFL8ZAEAymaQ+zUI0/ppYRQS4Gx0HAACgSlAOAgBKWb8/W9MXbVHqjiyjowCAYa6KDtCEXnFq1sDb6CgAAABVinIQAHBev2w/qucXbdWGAyeNjgIA1aZZqLcm9IrTVY0DjI4CAABQLSgHAQAXZLPZ9N2GQ3rjp+3acui00XEAoMrEh3hpTLdo9WkWLJPJZHQcAACAakM5CAC4JJvNpiXpR/Tmsh1auzfb6DgAUGnaNPLV6G5RSoqrZ3QUAAAAQ1AOAgDKZcXOY3pr6U79uuOY0VEAoMI6NQ7Q6G7RuiLS3+goAAAAhqIcBABUyLp92Xpz6Q79mH6YpxsDqBVMJqlnQrBGd4vmQSMAAAD/j3IQAHBZth8+rbeW7dS/1x1UkZVfKQBqHouDSde1qK97u0UpOsjT6DgAAAA1CuUgAKBS7Dueq3/+vFNz/9yv/CKr0XEAQM4WB92U2EB3dY5SmJ+b0XEAAABqJMpBAEClOnI6Tx/8kqFP/tirnPwio+MAsEMezhYNbd9Qd3SKUJCni9FxAAAAajTKQQBAlTiZW6iPftutj//Yo8On8o2OA8AOhHi7aGj7hhp2Rbi83RyNjgMAAFArUA4CAKpUYbFV323I1KwVu7Vmb7bRcQDUQR0i/TW8QyNd0yRYZgeT0XEAAABqFcpBAEC1Wb8/Wympu/XN+kwVFLMuIYCKc3cy64bWDTS8QyM1rsdDRgAAACqKchAAUO2Ons7XnJV79Qm3HAMop6hAdw27opEGtmkgTxduHQYAALhclIMAAMMUFVu1OP2wPv59r1J3HhO/kQCcj9nBpKvjgjS8Q7iuahxgdBwAAIA6hXIQAFAj7Dqao0/+2Kt/rd6vk2cLjY4DoAbwc3fS4LZhuvWKRgr1cTU6DgAAQJ1EOQgAqFHyCov173UH9fEfe7VuX7bRcQAYoGWYj4Zd0Uh9W4TI2WI2Og4AAECdRjkIAKixdhzJ0Zdr9mv+2gM6eDLP6DgAqlCQp7Oubx2qm9o0UHQQDxgBAACoLpSDAIAaz2az6bddWfpyzQEt2nhIOflFRkcCUAmcLA7qkVBPN7ZpoM6NA2V2MBkdCQAAwO5QDgIAapWzBcX6YfMhzVtzQKk7jqnYyq8xoLZpGeajgW0a6Lrm9eXtxhOHAQAAjEQ5CACotY6cztPXaw9q3pr92nLotNFxAFxERIC7+resrwEtQxUe4G50HAAAAPw/ykEAQJ2QnnlKX609oPlrD+jI6Xyj4wCQFODhpL7N6+v6VqFqEeZjdBwAAACcB+UgAKBOKbba9OuOY/p2/UEtTj+i42cKjI4E2BV/dyddHR+kPs1C1Il1BAEAAGo8ykEAQJ1VbLXpz93H9cPmw/ph8yHtO37W6EhAnRTm56prEoLVs0mwEhv5yoFCEAAAoNagHAQA2I3NB0/ph82H9MOmw9qcecroOECtlhDipWua1FPPJsGKD/EyOg4AAAAqiHIQAGCX9h3P/euKwk2H9OeeEzz1GLgEs4NJiY18dU2TYF2TUE9hfm5GRwIAAEAloBwEANi942cKtDj9sH7YdFi/bD+q/CKr0ZGAGsHZ4qBOjQN1TZN66h5fT37uTkZHAgAAQCWjHAQA4L/kFhTp523H9OuOo0rdkaWMY2eMjgRUq8gAd10Z7a+rogPVOSZAbk4WoyMBAACgClEOAgBwEQezzyp1xzGt2Jml1B3HdOR0vtGRgEoV5OmsjtEBujLKX1c1DlCIt6vRkQAAAFCNKAcBACiH7YdPK3XHMaXuzNLvu7J0Oq/I6EhAuXi6WHRFpL86RvmrY3SAGtfzNDoSAAAADEQ5CABABRVbbVq/P7vkqsI/95xQAesVooZxsjioTUNfXdX4r6sDmzfwkdnBZHQsAAAA1BCUgwAAVJK8wmL9ufuEftt1TGv3Zmv9/pPKyefKQlQvT2eLmod5q2WYjzpEBigx3FcujmajYwEAAKCGohwEAKCKWK027Tiao7R92X997f2/9u6lt40yCsDw8fhSO9jJRNAYkqYbGtggCP//TwTEKs4KkggbUCex5bsnLOymRWLRolCn+Z5HGo1n5MWRN5ZendEUcd4fxrL018vDqGWV+PbLTvxwnMfpcR4/Hufx9fN2ZDYDAQB4T+IgAHxEk/kqfrm+ibNfizi7XAfDq2Ky7bH4RBzlrTh9mcfpizxOX+bx3eFetBq2AgEA+O/EQQDYsj+Gszj7rYifNhuGP18WcetFJ8nbbdbi+xfrjcA3m4HPO8+2PRYAAE+MOAgAj9DvN9PoDYZx3h/FxWAYvf4oeoNR3EwW2x6NB7bXqsfJQTtOup3NuR3fdDvR3W1uezQAABIgDgLAJ2RwO43eYBS9/jDOB6O46I+iNxjG67Fo+Njt79Tj5KATJ9322xjYbcdBRwQEAGB7xEEAeAL+HM3ivD+Mi8EoLgajuHw9ietiElfFJIYeUf5oOs1aHOWt9bHfilcH7Xh1sN4E/KLtkWAAAB4fcRAAnrjhdBHXxfQ+Fl4V63C4PqbRv516g/J7qGWV6O424yhvxWHejMO8FYebEHi4uddp1rc9JgAAfBBxEAAStyrvon/7Nh5eF9P4azSLYrKIYryIm8k8ivEiiskibsaLmK/KbY/8YBq1LPJWPfKdeuStRuzt1O+vP28/i6/2mvfxr7vbjGpW2fbIAADwoMRBAOCDjOfLdSwcL6KYzONmEw7fvR7OljFblDFbrmK2LNfHYhXzN5+XZazKMpblXazKu1iWd1Fuzu+qZpWoVytRr2bRqGZRr2ZRr/3zulHL/uU7WXzWqG5iXyP2d9bBb6/VWIfAzf1Wo7qlXxEAAB4HcRAAeFRWm2BYyyqR2dQDAID/lTgIAAAAAInKtj0AAAAAALAd4iAAAAAAJEocBAAAAIBEiYMAAAAAkChxEAAAAAASJQ4CAAAAQKLEQQAAAABIlDgIAAAAAIkSBwEAAAAgUeIgAAAAACRKHAQAAACARImDAAAAAJAocRAAAAAAEiUOAgAAAECixEEAAAAASJQ4CAAAAACJEgcBAAAAIFHiIAAAAAAkShwEAAAAgESJgwAAAACQKHEQAAAAABIlDgIAAABAosRBAAAAAEiUOAgAAAAAiRIHAQAAACBR4iAAAAAAJEocBAAAAIBEiYMAAAAAkChxEAAAAAASJQ4CAAAAQKLEQQAAAABIlDgIAAAAAIkSBwEAAAAgUeIgAAAAACRKHAQAAACARImDAAAAAJAocRAAAAAAEiUOAgAAAECixEEAAAAASJQ4CAAAAACJEgcBAAAAIFHiIAAAAAAkShwEAAAAgET9DQ+4Q55nJ+++AAAAAElFTkSuQmCC",
+      "text/plain": [
+       "<Figure size 1400x1000 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "fig, ax = plt.subplots(figsize=(14, 10))\n",
+    "wedges, texts, autotexts = ax.pie(sizes, autopct='%1.1f%%', startangle=140)\n",
+    "\n",
+    "ax.axis('equal')\n",
+    "plt.legend(wedges, labels, title=\"Activities\", loc=\"center left\", bbox_to_anchor=(1, 0, 0.5, 1))\n",
+    "\n",
+    "plt.title('Distribution of Network Activities')\n",
+    "plt.show()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "KObpx4wfj3aQ"
+   },
+   "source": [
+    "## Data Preprocessing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "id": "LuWeKTG2j0hF"
+   },
+   "outputs": [],
+   "source": [
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "from sklearn.preprocessing import StandardScaler"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "id": "x0UovuBRjmE0"
+   },
+   "outputs": [],
+   "source": [
+    "X = df.drop('label', axis=1)\n",
+    "y = df['label']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from scipy import sparse\n",
+    "from sklearn.preprocessing import OneHotEncoder\n",
+    "\n",
+    "encoder = OneHotEncoder(sparse_output=True, dtype=np.float32)\n",
+    "\n",
+    "X_sparse = encoder.fit_transform(X)\n",
+    "\n",
+    "y_encoded = encoder.fit_transform(np.array(y).reshape(-1, 1))\n",
+    "y_train_dense = y_encoded.toarray()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "id": "pbRTAjhy6Yb3"
+   },
+   "outputs": [],
+   "source": [
+    "X_train, X_test, y_train, y_test = train_test_split(X_sparse, y_train_dense, test_size=0.2, random_state=42)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "id": "FBpz07hL_cxj"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((505188, 646287), (126298, 646287))"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "X_train.shape, X_test.shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "((505188, 10), (126298, 10))"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "y_train.shape, y_test.shape"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "jNDgEG-88ff9"
+   },
+   "source": [
+    "## Model Training"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "lxFMcxYX-wMg"
+   },
+   "source": [
+    "### Model 1: Random Forest Classifier"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {
+    "id": "2IhE9rN0_ZSE"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-1 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-1 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-1 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-1 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-1 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>RandomForestClassifier(n_estimators=10, random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;RandomForestClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.ensemble.RandomForestClassifier.html\">?<span>Documentation for RandomForestClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>RandomForestClassifier(n_estimators=10, random_state=42)</pre></div> </div></div></div></div>"
+      ],
+      "text/plain": [
+       "RandomForestClassifier(n_estimators=10, random_state=42)"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.ensemble import RandomForestClassifier\n",
+    "\n",
+    "model_1 = RandomForestClassifier(n_estimators=10, random_state=42)\n",
+    "model_1.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 37,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = model_1.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "metadata": {
+    "id": "m76sl7hf_mMY"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.9977196788547721\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       1.00      1.00      1.00    126154\n",
+      "           1       1.00      1.00      1.00    126186\n",
+      "\n",
+      "   micro avg       1.00      1.00      1.00    252340\n",
+      "   macro avg       1.00      1.00      1.00    252340\n",
+      "weighted avg       1.00      1.00      1.00    252340\n",
+      " samples avg       1.00      1.00      1.00    252340\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.preprocessing import MultiLabelBinarizer\n",
+    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
+    "\n",
+    "# Assuming y_test and y_pred are in multi-label format\n",
+    "mlb = MultiLabelBinarizer()\n",
+    "y_test_binary = mlb.fit_transform(y_test)\n",
+    "y_pred_binary = mlb.transform(y_pred)\n",
+    "\n",
+    "# Compute and print accuracy\n",
+    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
+    "print(f\"Accuracy: {accuracy}\")\n",
+    "\n",
+    "# Print classification report\n",
+    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "FsWqdWgf_PCW"
+   },
+   "source": [
+    "### Model 2: XGBClassifier"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "metadata": {
+    "id": "uPcz1c688h5U"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-2 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-2 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-2 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-2 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-2 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-2 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-2 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
+       "              colsample_bylevel=None, colsample_bynode=None,\n",
+       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
+       "              gamma=None, grow_policy=None, importance_type=None,\n",
+       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
+       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
+       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
+       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
+       "              num_parallel_tree=None, random_state=None, ...)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;XGBClassifier<span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
+       "              colsample_bylevel=None, colsample_bynode=None,\n",
+       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
+       "              gamma=None, grow_policy=None, importance_type=None,\n",
+       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
+       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
+       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
+       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
+       "              num_parallel_tree=None, random_state=None, ...)</pre></div> </div></div></div></div>"
+      ],
+      "text/plain": [
+       "XGBClassifier(base_score=None, booster=None, callbacks=None,\n",
+       "              colsample_bylevel=None, colsample_bynode=None,\n",
+       "              colsample_bytree=None, device=None, early_stopping_rounds=None,\n",
+       "              enable_categorical=False, eval_metric=None, feature_types=None,\n",
+       "              gamma=None, grow_policy=None, importance_type=None,\n",
+       "              interaction_constraints=None, learning_rate=None, max_bin=None,\n",
+       "              max_cat_threshold=None, max_cat_to_onehot=None,\n",
+       "              max_delta_step=None, max_depth=None, max_leaves=None,\n",
+       "              min_child_weight=None, missing=nan, monotone_constraints=None,\n",
+       "              multi_strategy=None, n_estimators=None, n_jobs=None,\n",
+       "              num_parallel_tree=None, random_state=None, ...)"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from xgboost import XGBClassifier\n",
+    "\n",
+    "model_2 = XGBClassifier()\n",
+    "model_2.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = model_2.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.9979176233986287\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       1.00      1.00      1.00    126154\n",
+      "           1       1.00      1.00      1.00    126186\n",
+      "\n",
+      "   micro avg       1.00      1.00      1.00    252340\n",
+      "   macro avg       1.00      1.00      1.00    252340\n",
+      "weighted avg       1.00      1.00      1.00    252340\n",
+      " samples avg       1.00      1.00      1.00    252340\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.preprocessing import MultiLabelBinarizer\n",
+    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
+    "\n",
+    "# Assuming y_test and y_pred are in multi-label format\n",
+    "mlb = MultiLabelBinarizer()\n",
+    "y_test_binary = mlb.fit_transform(y_test)\n",
+    "y_pred_binary = mlb.transform(y_pred)\n",
+    "\n",
+    "# Compute and print accuracy\n",
+    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
+    "print(f\"Accuracy: {accuracy}\")\n",
+    "\n",
+    "# Print classification report\n",
+    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Model 3: SVM"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-1 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-1 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-1 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-1 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-1 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>MultiOutputClassifier(estimator=SVC(), n_jobs=-1)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item sk-dashed-wrapped\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" ><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;MultiOutputClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.multioutput.MultiOutputClassifier.html\">?<span>Documentation for MultiOutputClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>MultiOutputClassifier(estimator=SVC(), n_jobs=-1)</pre></div> </div></div><div class=\"sk-parallel\"><div class=\"sk-parallel-item\"><div class=\"sk-item\"><div class=\"sk-label-container\"><div class=\"sk-label fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" ><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">estimator: SVC</label><div class=\"sk-toggleable__content fitted\"><pre>SVC()</pre></div> </div></div><div class=\"sk-serial\"><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" ><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;SVC<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.svm.SVC.html\">?<span>Documentation for SVC</span></a></label><div class=\"sk-toggleable__content fitted\"><pre>SVC()</pre></div> </div></div></div></div></div></div></div></div></div>"
+      ],
+      "text/plain": [
+       "MultiOutputClassifier(estimator=SVC(), n_jobs=-1)"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.multioutput import MultiOutputClassifier\n",
+    "from sklearn.svm import SVC\n",
+    "\n",
+    "svm = SVC(kernel='rbf', gamma='scale', C=1.0)\n",
+    "\n",
+    "model_3 = MultiOutputClassifier(svm, n_jobs=-1)\n",
+    "\n",
+    "model_3.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = model_3.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.9999287399642116\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       1.00      1.00      1.00    126298\n",
+      "           1       1.00      1.00      1.00    126298\n",
+      "\n",
+      "   micro avg       1.00      1.00      1.00    252596\n",
+      "   macro avg       1.00      1.00      1.00    252596\n",
+      "weighted avg       1.00      1.00      1.00    252596\n",
+      " samples avg       1.00      1.00      1.00    252596\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.preprocessing import MultiLabelBinarizer\n",
+    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
+    "\n",
+    "# Assuming y_test and y_pred are in multi-label format\n",
+    "mlb = MultiLabelBinarizer()\n",
+    "y_test_binary = mlb.fit_transform(y_test)\n",
+    "y_pred_binary = mlb.transform(y_pred)\n",
+    "\n",
+    "# Compute and print accuracy\n",
+    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
+    "print(f\"Accuracy: {accuracy}\")\n",
+    "\n",
+    "# Print classification report\n",
+    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Model 4: KNN"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-1 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-1 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-1 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-1 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-1 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>KNeighborsClassifier(n_neighbors=3)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;KNeighborsClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.neighbors.KNeighborsClassifier.html\">?<span>Documentation for KNeighborsClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>KNeighborsClassifier(n_neighbors=3)</pre></div> </div></div></div></div>"
+      ],
+      "text/plain": [
+       "KNeighborsClassifier(n_neighbors=3)"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.neighbors import KNeighborsClassifier\n",
+    "\n",
+    "model_4 = KNeighborsClassifier(n_neighbors=3)\n",
+    "model_4.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = model_4.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 0.9999841644364915\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       1.00      1.00      1.00    126298\n",
+      "           1       1.00      1.00      1.00    126298\n",
+      "\n",
+      "   micro avg       1.00      1.00      1.00    252596\n",
+      "   macro avg       1.00      1.00      1.00    252596\n",
+      "weighted avg       1.00      1.00      1.00    252596\n",
+      " samples avg       1.00      1.00      1.00    252596\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.preprocessing import MultiLabelBinarizer\n",
+    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
+    "\n",
+    "# Assuming y_test and y_pred are in multi-label format\n",
+    "mlb = MultiLabelBinarizer()\n",
+    "y_test_binary = mlb.fit_transform(y_test)\n",
+    "y_pred_binary = mlb.transform(y_pred)\n",
+    "\n",
+    "# Compute and print accuracy\n",
+    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
+    "print(f\"Accuracy: {accuracy}\")\n",
+    "\n",
+    "# Print classification report\n",
+    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Model 5: Decision Tree"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<style>#sk-container-id-2 {\n",
+       "  /* Definition of color scheme common for light and dark mode */\n",
+       "  --sklearn-color-text: black;\n",
+       "  --sklearn-color-line: gray;\n",
+       "  /* Definition of color scheme for unfitted estimators */\n",
+       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
+       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
+       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
+       "  --sklearn-color-unfitted-level-3: chocolate;\n",
+       "  /* Definition of color scheme for fitted estimators */\n",
+       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
+       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
+       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
+       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
+       "\n",
+       "  /* Specific color for light theme */\n",
+       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
+       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
+       "  --sklearn-color-icon: #696969;\n",
+       "\n",
+       "  @media (prefers-color-scheme: dark) {\n",
+       "    /* Redefinition of color scheme for dark theme */\n",
+       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
+       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
+       "    --sklearn-color-icon: #878787;\n",
+       "  }\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 pre {\n",
+       "  padding: 0;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 input.sk-hidden--visually {\n",
+       "  border: 0;\n",
+       "  clip: rect(1px 1px 1px 1px);\n",
+       "  clip: rect(1px, 1px, 1px, 1px);\n",
+       "  height: 1px;\n",
+       "  margin: -1px;\n",
+       "  overflow: hidden;\n",
+       "  padding: 0;\n",
+       "  position: absolute;\n",
+       "  width: 1px;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-dashed-wrapped {\n",
+       "  border: 1px dashed var(--sklearn-color-line);\n",
+       "  margin: 0 0.4em 0.5em 0.4em;\n",
+       "  box-sizing: border-box;\n",
+       "  padding-bottom: 0.4em;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-container {\n",
+       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
+       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
+       "     so we also need the `!important` here to be able to override the\n",
+       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
+       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
+       "  display: inline-block !important;\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-text-repr-fallback {\n",
+       "  display: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-parallel-item,\n",
+       "div.sk-serial,\n",
+       "div.sk-item {\n",
+       "  /* draw centered vertical line to link estimators */\n",
+       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
+       "  background-size: 2px 100%;\n",
+       "  background-repeat: no-repeat;\n",
+       "  background-position: center center;\n",
+       "}\n",
+       "\n",
+       "/* Parallel-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item::after {\n",
+       "  content: \"\";\n",
+       "  width: 100%;\n",
+       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
+       "  flex-grow: 1;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel {\n",
+       "  display: flex;\n",
+       "  align-items: stretch;\n",
+       "  justify-content: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  position: relative;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item:first-child::after {\n",
+       "  align-self: flex-end;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item:last-child::after {\n",
+       "  align-self: flex-start;\n",
+       "  width: 50%;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-parallel-item:only-child::after {\n",
+       "  width: 0;\n",
+       "}\n",
+       "\n",
+       "/* Serial-specific style estimator block */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-serial {\n",
+       "  display: flex;\n",
+       "  flex-direction: column;\n",
+       "  align-items: center;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  padding-right: 1em;\n",
+       "  padding-left: 1em;\n",
+       "}\n",
+       "\n",
+       "\n",
+       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
+       "clickable and can be expanded/collapsed.\n",
+       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
+       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
+       "*/\n",
+       "\n",
+       "/* Pipeline and ColumnTransformer style (default) */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable {\n",
+       "  /* Default theme specific background. It is overwritten whether we have a\n",
+       "  specific estimator or a Pipeline/ColumnTransformer */\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable label */\n",
+       "#sk-container-id-2 label.sk-toggleable__label {\n",
+       "  cursor: pointer;\n",
+       "  display: block;\n",
+       "  width: 100%;\n",
+       "  margin-bottom: 0;\n",
+       "  padding: 0.5em;\n",
+       "  box-sizing: border-box;\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 label.sk-toggleable__label-arrow:before {\n",
+       "  /* Arrow on the left of the label */\n",
+       "  content: \"▸\";\n",
+       "  float: left;\n",
+       "  margin-right: 0.25em;\n",
+       "  color: var(--sklearn-color-icon);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 label.sk-toggleable__label-arrow:hover:before {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "}\n",
+       "\n",
+       "/* Toggleable content - dropdown */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content {\n",
+       "  max-height: 0;\n",
+       "  max-width: 0;\n",
+       "  overflow: hidden;\n",
+       "  text-align: left;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content pre {\n",
+       "  margin: 0.2em;\n",
+       "  border-radius: 0.25em;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-toggleable__content.fitted pre {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
+       "  /* Expand drop-down */\n",
+       "  max-height: 200px;\n",
+       "  max-width: 100%;\n",
+       "  overflow: auto;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
+       "  content: \"▾\";\n",
+       "}\n",
+       "\n",
+       "/* Pipeline/ColumnTransformer-specific style */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific style */\n",
+       "\n",
+       "/* Colorize estimator box */\n",
+       "#sk-container-id-2 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label label.sk-toggleable__label,\n",
+       "#sk-container-id-2 div.sk-label label {\n",
+       "  /* The background is the default theme color */\n",
+       "  color: var(--sklearn-color-text-on-default-background);\n",
+       "}\n",
+       "\n",
+       "/* On hover, darken the color of the background */\n",
+       "#sk-container-id-2 div.sk-label:hover label.sk-toggleable__label {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Label box, darken color on hover, fitted */\n",
+       "#sk-container-id-2 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Estimator label */\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label label {\n",
+       "  font-family: monospace;\n",
+       "  font-weight: bold;\n",
+       "  display: inline-block;\n",
+       "  line-height: 1.2em;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-label-container {\n",
+       "  text-align: center;\n",
+       "}\n",
+       "\n",
+       "/* Estimator-specific */\n",
+       "#sk-container-id-2 div.sk-estimator {\n",
+       "  font-family: monospace;\n",
+       "  border: 1px dotted var(--sklearn-color-border-box);\n",
+       "  border-radius: 0.25em;\n",
+       "  box-sizing: border-box;\n",
+       "  margin-bottom: 0.5em;\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-estimator.fitted {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-0);\n",
+       "}\n",
+       "\n",
+       "/* on hover */\n",
+       "#sk-container-id-2 div.sk-estimator:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 div.sk-estimator.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-2);\n",
+       "}\n",
+       "\n",
+       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
+       "\n",
+       "/* Common style for \"i\" and \"?\" */\n",
+       "\n",
+       ".sk-estimator-doc-link,\n",
+       "a:link.sk-estimator-doc-link,\n",
+       "a:visited.sk-estimator-doc-link {\n",
+       "  float: right;\n",
+       "  font-size: smaller;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1em;\n",
+       "  height: 1em;\n",
+       "  width: 1em;\n",
+       "  text-decoration: none !important;\n",
+       "  margin-left: 1ex;\n",
+       "  /* unfitted */\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted,\n",
+       "a:link.sk-estimator-doc-link.fitted,\n",
+       "a:visited.sk-estimator-doc-link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
+       ".sk-estimator-doc-link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover,\n",
+       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
+       ".sk-estimator-doc-link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "/* Span, style for the box shown on hovering the info icon */\n",
+       ".sk-estimator-doc-link span {\n",
+       "  display: none;\n",
+       "  z-index: 9999;\n",
+       "  position: relative;\n",
+       "  font-weight: normal;\n",
+       "  right: .2ex;\n",
+       "  padding: .5ex;\n",
+       "  margin: .5ex;\n",
+       "  width: min-content;\n",
+       "  min-width: 20ex;\n",
+       "  max-width: 50ex;\n",
+       "  color: var(--sklearn-color-text);\n",
+       "  box-shadow: 2pt 2pt 4pt #999;\n",
+       "  /* unfitted */\n",
+       "  background: var(--sklearn-color-unfitted-level-0);\n",
+       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link.fitted span {\n",
+       "  /* fitted */\n",
+       "  background: var(--sklearn-color-fitted-level-0);\n",
+       "  border: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "\n",
+       ".sk-estimator-doc-link:hover span {\n",
+       "  display: block;\n",
+       "}\n",
+       "\n",
+       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
+       "\n",
+       "#sk-container-id-2 a.estimator_doc_link {\n",
+       "  float: right;\n",
+       "  font-size: 1rem;\n",
+       "  line-height: 1em;\n",
+       "  font-family: monospace;\n",
+       "  background-color: var(--sklearn-color-background);\n",
+       "  border-radius: 1rem;\n",
+       "  height: 1rem;\n",
+       "  width: 1rem;\n",
+       "  text-decoration: none;\n",
+       "  /* unfitted */\n",
+       "  color: var(--sklearn-color-unfitted-level-1);\n",
+       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 a.estimator_doc_link.fitted {\n",
+       "  /* fitted */\n",
+       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
+       "  color: var(--sklearn-color-fitted-level-1);\n",
+       "}\n",
+       "\n",
+       "/* On hover */\n",
+       "#sk-container-id-2 a.estimator_doc_link:hover {\n",
+       "  /* unfitted */\n",
+       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
+       "  color: var(--sklearn-color-background);\n",
+       "  text-decoration: none;\n",
+       "}\n",
+       "\n",
+       "#sk-container-id-2 a.estimator_doc_link.fitted:hover {\n",
+       "  /* fitted */\n",
+       "  background-color: var(--sklearn-color-fitted-level-3);\n",
+       "}\n",
+       "</style><div id=\"sk-container-id-2\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>DecisionTreeClassifier(random_state=42)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator fitted sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-2\" type=\"checkbox\" checked><label for=\"sk-estimator-id-2\" class=\"sk-toggleable__label fitted sk-toggleable__label-arrow fitted\">&nbsp;&nbsp;DecisionTreeClassifier<a class=\"sk-estimator-doc-link fitted\" rel=\"noreferrer\" target=\"_blank\" href=\"https://scikit-learn.org/1.5/modules/generated/sklearn.tree.DecisionTreeClassifier.html\">?<span>Documentation for DecisionTreeClassifier</span></a><span class=\"sk-estimator-doc-link fitted\">i<span>Fitted</span></span></label><div class=\"sk-toggleable__content fitted\"><pre>DecisionTreeClassifier(random_state=42)</pre></div> </div></div></div></div>"
+      ],
+      "text/plain": [
+       "DecisionTreeClassifier(random_state=42)"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.tree import DecisionTreeClassifier\n",
+    "\n",
+    "model_5 = DecisionTreeClassifier(random_state=42)\n",
+    "model_5.fit(X_train, y_train)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "y_pred = model_5.predict(X_test)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Accuracy: 1.0\n",
+      "              precision    recall  f1-score   support\n",
+      "\n",
+      "           0       1.00      1.00      1.00    126298\n",
+      "           1       1.00      1.00      1.00    126298\n",
+      "\n",
+      "   micro avg       1.00      1.00      1.00    252596\n",
+      "   macro avg       1.00      1.00      1.00    252596\n",
+      "weighted avg       1.00      1.00      1.00    252596\n",
+      " samples avg       1.00      1.00      1.00    252596\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "from sklearn.preprocessing import MultiLabelBinarizer\n",
+    "from sklearn.metrics import confusion_matrix, accuracy_score, classification_report\n",
+    "\n",
+    "# Assuming y_test and y_pred are in multi-label format\n",
+    "mlb = MultiLabelBinarizer()\n",
+    "y_test_binary = mlb.fit_transform(y_test)\n",
+    "y_pred_binary = mlb.transform(y_pred)\n",
+    "\n",
+    "# Compute and print accuracy\n",
+    "accuracy = accuracy_score(y_test_binary, y_pred_binary)\n",
+    "print(f\"Accuracy: {accuracy}\")\n",
+    "\n",
+    "# Print classification report\n",
+    "print(classification_report(y_test_binary, y_pred_binary, zero_division=1))"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "### Model 6: Dense Model"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential_1\"</span>\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1mModel: \"sequential_1\"\u001b[0m\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
+       "┃<span style=\"font-weight: bold\"> Layer (type)                         </span>┃<span style=\"font-weight: bold\"> Output Shape                </span>┃<span style=\"font-weight: bold\">         Param # </span>┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
+       "│ dense_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>)                  │       <span style=\"color: #00af00; text-decoration-color: #00af00\">6,462,880</span> │\n",
+       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+       "│ dense_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">10</span>)                  │             <span style=\"color: #00af00; text-decoration-color: #00af00\">110</span> │\n",
+       "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
+       "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                        \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape               \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m        Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
+       "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
+       "│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m)                  │       \u001b[38;5;34m6,462,880\u001b[0m │\n",
+       "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
+       "│ dense_3 (\u001b[38;5;33mDense\u001b[0m)                      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m10\u001b[0m)                  │             \u001b[38;5;34m110\u001b[0m │\n",
+       "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">6,462,990</span> (24.65 MB)\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m6,462,990\u001b[0m (24.65 MB)\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">6,462,990</span> (24.65 MB)\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m6,462,990\u001b[0m (24.65 MB)\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "text/html": [
+       "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
+       "</pre>\n"
+      ],
+      "text/plain": [
+       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "input_shape = X_train.shape[1]\n",
+    "\n",
+    "model_6 = tf.keras.Sequential([\n",
+    "    tf.keras.layers.Input(shape=(input_shape,)),\n",
+    "    tf.keras.layers.Dense(10, activation='relu'),\n",
+    "    tf.keras.layers.Dense(y_train.shape[1], activation='softmax')\n",
+    "])\n",
+    "\n",
+    "model_6.compile(loss='categorical_crossentropy',\n",
+    "                optimizer=tf.keras.optimizers.SGD(),\n",
+    "                metrics=['accuracy'])\n",
+    "\n",
+    "model_6.summary()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 1/10\n",
+      "\u001b[1m15788/15788\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m126s\u001b[0m 8ms/step - accuracy: 0.9728 - loss: 0.1719 - val_accuracy: 0.9928 - val_loss: 0.0325\n",
+      "Epoch 2/10\n",
+      "\u001b[1m15788/15788\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m125s\u001b[0m 8ms/step - accuracy: 0.9947 - loss: 0.0283 - val_accuracy: 0.9971 - val_loss: 0.0202\n",
+      "Epoch 3/10\n",
+      "\u001b[1m15788/15788\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m133s\u001b[0m 8ms/step - accuracy: 0.9972 - loss: 0.0181 - val_accuracy: 0.9971 - val_loss: 0.0153\n",
+      "Epoch 4/10\n",
+      "\u001b[1m15788/15788\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m132s\u001b[0m 8ms/step - accuracy: 0.9972 - loss: 0.0144 - val_accuracy: 0.9971 - val_loss: 0.0128\n",
+      "Epoch 5/10\n",
+      "\u001b[1m15788/15788\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m469s\u001b[0m 30ms/step - accuracy: 0.9972 - loss: 0.0120 - val_accuracy: 0.9971 - val_loss: 0.0113\n",
+      "Epoch 6/10\n",
+      "\u001b[1m15788/15788\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m138s\u001b[0m 9ms/step - accuracy: 0.9974 - loss: 0.0102 - val_accuracy: 0.9973 - val_loss: 0.0102\n",
+      "Epoch 7/10\n",
+      "\u001b[1m15788/15788\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m142s\u001b[0m 9ms/step - accuracy: 0.9975 - loss: 0.0092 - val_accuracy: 0.9975 - val_loss: 0.0094\n",
+      "Epoch 8/10\n",
+      "\u001b[1m15788/15788\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m4099s\u001b[0m 256ms/step - accuracy: 0.9976 - loss: 0.0087 - val_accuracy: 0.9977 - val_loss: 0.0088\n",
+      "Epoch 9/10\n",
+      "\u001b[1m15788/15788\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m144s\u001b[0m 8ms/step - accuracy: 0.9980 - loss: 0.0079 - val_accuracy: 0.9979 - val_loss: 0.0083\n",
+      "Epoch 10/10\n",
+      "\u001b[1m15788/15788\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1035s\u001b[0m 65ms/step - accuracy: 0.9980 - loss: 0.0077 - val_accuracy: 0.9980 - val_loss: 0.0078\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<keras.src.callbacks.history.History at 0x10582bb84d0>"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "model_6.fit(X_train, y_train,\n",
+    "            epochs=10,\n",
+    "            validation_data=(X_test, y_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def evaluate_preds(y_true, y_pred, threshold=0.1):\n",
+    "    # Make sure float32 (for metric calculations)\n",
+    "    y_true = tf.cast(y_true, dtype=tf.float32)\n",
+    "    y_pred = tf.cast(y_pred, dtype=tf.float32)\n",
+    "\n",
+    "    # Calculate various metrics\n",
+    "    mae = tf.reduce_mean(tf.abs(y_true - y_pred))\n",
+    "    mse = tf.reduce_mean(tf.square(y_true - y_pred))\n",
+    "    rmse = tf.sqrt(mse)\n",
+    "    mape = tf.reduce_mean(tf.abs((y_true - y_pred) / tf.clip_by_value(tf.abs(y_true), 1e-7, tf.reduce_max(tf.abs(y_true))))) * 100\n",
+    "\n",
+    "    # Calculate accuracy\n",
+    "    # Predictions are considered accurate if the absolute error is within the threshold\n",
+    "    accurate_predictions = tf.abs(y_true - y_pred) < (threshold * tf.abs(y_true))\n",
+    "    accuracy = tf.reduce_mean(tf.cast(accurate_predictions, dtype=tf.float32))\n",
+    "\n",
+    "    return {\n",
+    "        \"mae\": mae.numpy(),\n",
+    "        \"mse\": mse.numpy(),\n",
+    "        \"rmse\": rmse.numpy(),\n",
+    "        \"mape\": mape.numpy(),\n",
+    "        \"accuracy\": accuracy.numpy()\n",
+    "    }"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1m3947/3947\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m30s\u001b[0m 8ms/step\n"
+     ]
+    }
+   ],
+   "source": [
+    "y_preds = tf.squeeze(model_6.predict(X_test))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'mae': 0.0007503413,\n",
+       " 'mse': 0.0003056716,\n",
+       " 'rmse': 0.017483467,\n",
+       " 'mape': 375171.03,\n",
+       " 'accuracy': 0.099478215}"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "evaluate_preds(y_true=y_test, y_pred=y_preds, threshold=0.1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\u001b[1m3947/3947\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m27s\u001b[0m 7ms/step - accuracy: 0.9980 - loss: 0.0079\n",
+      "Accuracy: 99.80%\n"
+     ]
+    }
+   ],
+   "source": [
+    "loss, accuracy = model_6.evaluate(X_test, y_test)\n",
+    "print(f'Accuracy: {accuracy * 100:.2f}%')"
+   ]
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "gpuType": "T4",
+   "provenance": [],
+   "toc_visible": true
+  },
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.11.0"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}

From d57660b413fbb2d8c60a2800c4176d9f8b6236aa Mon Sep 17 00:00:00 2001
From: Aditi Kala <130339327+why-aditi@users.noreply.github.com>
Date: Sat, 22 Jun 2024 17:39:28 +0530
Subject: [PATCH 10/10] Update README.md

---
 ACI IoT Network Traffic Dataset Analysis/Model/README.md | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/ACI IoT Network Traffic Dataset Analysis/Model/README.md b/ACI IoT Network Traffic Dataset Analysis/Model/README.md
index 5c4759bb3..dc909f79f 100644
--- a/ACI IoT Network Traffic Dataset Analysis/Model/README.md	
+++ b/ACI IoT Network Traffic Dataset Analysis/Model/README.md	
@@ -20,6 +20,9 @@ Load the data using appropriate tools and conduct an initial inspection to ident
 1. Random Forest Classifier
 2. XGBoost
 3. SVM
+4. KNN
+5. Decision Tree
+6. Dense Model
 
 ### 📚 **Libraries Needed**
 
@@ -38,11 +41,14 @@ Load the data using appropriate tools and conduct an initial inspection to ident
 1. Random Forest Classifier: 99.77%
 2. XGBoost: 99.79%
 3. SVM: 99.99%
+4. KNN: 99.99%
+5. Decision Tree: 100%
+6. Dense Model: 99.80%
 
 
 ### 📢 **Conclusion**
 
-SVM is proven to be the best model with the accuracy score of 99.99%
+Decision Tree is proven to be the best model with the accuracy score of 100%
 
 ### ✒️ **Your Signature**