code.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 57,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>10</th>\n",
       "      <th>11</th>\n",
       "      <th>12</th>\n",
       "      <th>13</th>\n",
       "      <th>14</th>\n",
       "      <th>15</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>b</td>\n",
       "      <td>30.83</td>\n",
       "      <td>0.000</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>w</td>\n",
       "      <td>v</td>\n",
       "      <td>1.25</td>\n",
       "      <td>t</td>\n",
       "      <td>t</td>\n",
       "      <td>1</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00202</td>\n",
       "      <td>0</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a</td>\n",
       "      <td>58.67</td>\n",
       "      <td>4.460</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>q</td>\n",
       "      <td>h</td>\n",
       "      <td>3.04</td>\n",
       "      <td>t</td>\n",
       "      <td>t</td>\n",
       "      <td>6</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00043</td>\n",
       "      <td>560</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a</td>\n",
       "      <td>24.50</td>\n",
       "      <td>0.500</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>q</td>\n",
       "      <td>h</td>\n",
       "      <td>1.50</td>\n",
       "      <td>t</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00280</td>\n",
       "      <td>824</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>b</td>\n",
       "      <td>27.83</td>\n",
       "      <td>1.540</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>w</td>\n",
       "      <td>v</td>\n",
       "      <td>3.75</td>\n",
       "      <td>t</td>\n",
       "      <td>t</td>\n",
       "      <td>5</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00100</td>\n",
       "      <td>3</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>b</td>\n",
       "      <td>20.17</td>\n",
       "      <td>5.625</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>w</td>\n",
       "      <td>v</td>\n",
       "      <td>1.71</td>\n",
       "      <td>t</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>s</td>\n",
       "      <td>00120</td>\n",
       "      <td>0</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  0      1      2  3  4  5  6     7  8  9   10 11 12     13   14 15\n",
       "0  b  30.83  0.000  u  g  w  v  1.25  t  t   1  f  g  00202    0  +\n",
       "1  a  58.67  4.460  u  g  q  h  3.04  t  t   6  f  g  00043  560  +\n",
       "2  a  24.50  0.500  u  g  q  h  1.50  t  f   0  f  g  00280  824  +\n",
       "3  b  27.83  1.540  u  g  w  v  3.75  t  t   5  t  g  00100    3  +\n",
       "4  b  20.17  5.625  u  g  w  v  1.71  t  f   0  f  s  00120    0  +"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Importing required libraries\n",
    "\n",
    "import pandas as pd\n",
    "\n",
    "#reading dataset\n",
    "data = pd.read_csv(\"crx.data\" , header = None) \n",
    "\n",
    "data.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "               2           7          10             14\n",
      "count  690.000000  690.000000  690.00000     690.000000\n",
      "mean     4.758725    2.223406    2.40000    1017.385507\n",
      "std      4.978163    3.346513    4.86294    5210.102598\n",
      "min      0.000000    0.000000    0.00000       0.000000\n",
      "25%      1.000000    0.165000    0.00000       0.000000\n",
      "50%      2.750000    1.000000    0.00000       5.000000\n",
      "75%      7.207500    2.625000    3.00000     395.500000\n",
      "max     28.000000   28.500000   67.00000  100000.000000\n",
      "\n",
      "\n",
      "<class 'pandas.core.frame.DataFrame'>\n",
      "RangeIndex: 690 entries, 0 to 689\n",
      "Data columns (total 16 columns):\n",
      "0     690 non-null object\n",
      "1     690 non-null object\n",
      "2     690 non-null float64\n",
      "3     690 non-null object\n",
      "4     690 non-null object\n",
      "5     690 non-null object\n",
      "6     690 non-null object\n",
      "7     690 non-null float64\n",
      "8     690 non-null object\n",
      "9     690 non-null object\n",
      "10    690 non-null int64\n",
      "11    690 non-null object\n",
      "12    690 non-null object\n",
      "13    690 non-null object\n",
      "14    690 non-null int64\n",
      "15    690 non-null object\n",
      "dtypes: float64(2), int64(2), object(12)\n",
      "memory usage: 86.3+ KB\n",
      "None\n"
     ]
    },
    {
     "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>10</th>\n",
       "      <th>11</th>\n",
       "      <th>12</th>\n",
       "      <th>13</th>\n",
       "      <th>14</th>\n",
       "      <th>15</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>b</td>\n",
       "      <td>30.83</td>\n",
       "      <td>0.000</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>w</td>\n",
       "      <td>v</td>\n",
       "      <td>1.250</td>\n",
       "      <td>t</td>\n",
       "      <td>t</td>\n",
       "      <td>1</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00202</td>\n",
       "      <td>0</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>a</td>\n",
       "      <td>58.67</td>\n",
       "      <td>4.460</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>q</td>\n",
       "      <td>h</td>\n",
       "      <td>3.040</td>\n",
       "      <td>t</td>\n",
       "      <td>t</td>\n",
       "      <td>6</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00043</td>\n",
       "      <td>560</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>a</td>\n",
       "      <td>24.50</td>\n",
       "      <td>0.500</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>q</td>\n",
       "      <td>h</td>\n",
       "      <td>1.500</td>\n",
       "      <td>t</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00280</td>\n",
       "      <td>824</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>b</td>\n",
       "      <td>27.83</td>\n",
       "      <td>1.540</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>w</td>\n",
       "      <td>v</td>\n",
       "      <td>3.750</td>\n",
       "      <td>t</td>\n",
       "      <td>t</td>\n",
       "      <td>5</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00100</td>\n",
       "      <td>3</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>b</td>\n",
       "      <td>20.17</td>\n",
       "      <td>5.625</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>w</td>\n",
       "      <td>v</td>\n",
       "      <td>1.710</td>\n",
       "      <td>t</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>s</td>\n",
       "      <td>00120</td>\n",
       "      <td>0</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>b</td>\n",
       "      <td>32.08</td>\n",
       "      <td>4.000</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>m</td>\n",
       "      <td>v</td>\n",
       "      <td>2.500</td>\n",
       "      <td>t</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00360</td>\n",
       "      <td>0</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>b</td>\n",
       "      <td>33.17</td>\n",
       "      <td>1.040</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>r</td>\n",
       "      <td>h</td>\n",
       "      <td>6.500</td>\n",
       "      <td>t</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00164</td>\n",
       "      <td>31285</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>a</td>\n",
       "      <td>22.92</td>\n",
       "      <td>11.585</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>cc</td>\n",
       "      <td>v</td>\n",
       "      <td>0.040</td>\n",
       "      <td>t</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00080</td>\n",
       "      <td>1349</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>b</td>\n",
       "      <td>54.42</td>\n",
       "      <td>0.500</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>k</td>\n",
       "      <td>h</td>\n",
       "      <td>3.960</td>\n",
       "      <td>t</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00180</td>\n",
       "      <td>314</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>b</td>\n",
       "      <td>42.50</td>\n",
       "      <td>4.915</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>w</td>\n",
       "      <td>v</td>\n",
       "      <td>3.165</td>\n",
       "      <td>t</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00052</td>\n",
       "      <td>1442</td>\n",
       "      <td>+</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  0      1       2  3  4   5  6      7  8  9   10 11 12     13     14 15\n",
       "0  b  30.83   0.000  u  g   w  v  1.250  t  t   1  f  g  00202      0  +\n",
       "1  a  58.67   4.460  u  g   q  h  3.040  t  t   6  f  g  00043    560  +\n",
       "2  a  24.50   0.500  u  g   q  h  1.500  t  f   0  f  g  00280    824  +\n",
       "3  b  27.83   1.540  u  g   w  v  3.750  t  t   5  t  g  00100      3  +\n",
       "4  b  20.17   5.625  u  g   w  v  1.710  t  f   0  f  s  00120      0  +\n",
       "5  b  32.08   4.000  u  g   m  v  2.500  t  f   0  t  g  00360      0  +\n",
       "6  b  33.17   1.040  u  g   r  h  6.500  t  f   0  t  g  00164  31285  +\n",
       "7  a  22.92  11.585  u  g  cc  v  0.040  t  f   0  f  g  00080   1349  +\n",
       "8  b  54.42   0.500  y  p   k  h  3.960  t  f   0  f  g  00180    314  +\n",
       "9  b  42.50   4.915  y  p   w  v  3.165  t  f   0  t  g  00052   1442  +"
      ]
     },
     "execution_count": 58,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Dataset summary\n",
    "\n",
    "print(data.describe())\n",
    "print(\"\\n\")\n",
    "print(data.info())\n",
    "\n",
    "# Checking missing data\n",
    "data.head(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 59,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>10</th>\n",
       "      <th>11</th>\n",
       "      <th>12</th>\n",
       "      <th>13</th>\n",
       "      <th>14</th>\n",
       "      <th>15</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>680</th>\n",
       "      <td>b</td>\n",
       "      <td>19.50</td>\n",
       "      <td>0.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>k</td>\n",
       "      <td>v</td>\n",
       "      <td>0.290</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00280</td>\n",
       "      <td>364</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>681</th>\n",
       "      <td>b</td>\n",
       "      <td>27.83</td>\n",
       "      <td>1.000</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>d</td>\n",
       "      <td>h</td>\n",
       "      <td>3.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00176</td>\n",
       "      <td>537</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>682</th>\n",
       "      <td>b</td>\n",
       "      <td>17.08</td>\n",
       "      <td>3.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>i</td>\n",
       "      <td>v</td>\n",
       "      <td>0.335</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00140</td>\n",
       "      <td>2</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>683</th>\n",
       "      <td>b</td>\n",
       "      <td>36.42</td>\n",
       "      <td>0.750</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>d</td>\n",
       "      <td>v</td>\n",
       "      <td>0.585</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00240</td>\n",
       "      <td>3</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>684</th>\n",
       "      <td>b</td>\n",
       "      <td>40.58</td>\n",
       "      <td>3.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>m</td>\n",
       "      <td>v</td>\n",
       "      <td>3.500</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>s</td>\n",
       "      <td>00400</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>685</th>\n",
       "      <td>b</td>\n",
       "      <td>21.08</td>\n",
       "      <td>10.085</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>e</td>\n",
       "      <td>h</td>\n",
       "      <td>1.250</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00260</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>686</th>\n",
       "      <td>a</td>\n",
       "      <td>22.67</td>\n",
       "      <td>0.750</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>v</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>2</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00200</td>\n",
       "      <td>394</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>687</th>\n",
       "      <td>a</td>\n",
       "      <td>25.25</td>\n",
       "      <td>13.500</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>ff</td>\n",
       "      <td>ff</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>1</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00200</td>\n",
       "      <td>1</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>688</th>\n",
       "      <td>b</td>\n",
       "      <td>17.92</td>\n",
       "      <td>0.205</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>aa</td>\n",
       "      <td>v</td>\n",
       "      <td>0.040</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00280</td>\n",
       "      <td>750</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>689</th>\n",
       "      <td>b</td>\n",
       "      <td>35.00</td>\n",
       "      <td>3.375</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>h</td>\n",
       "      <td>8.290</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    0      1       2  3  4   5   6      7  8  9   10 11 12     13   14 15\n",
       "680  b  19.50   0.290  u  g   k   v  0.290  f  f   0  f  g  00280  364  -\n",
       "681  b  27.83   1.000  y  p   d   h  3.000  f  f   0  f  g  00176  537  -\n",
       "682  b  17.08   3.290  u  g   i   v  0.335  f  f   0  t  g  00140    2  -\n",
       "683  b  36.42   0.750  y  p   d   v  0.585  f  f   0  f  g  00240    3  -\n",
       "684  b  40.58   3.290  u  g   m   v  3.500  f  f   0  t  s  00400    0  -\n",
       "685  b  21.08  10.085  y  p   e   h  1.250  f  f   0  f  g  00260    0  -\n",
       "686  a  22.67   0.750  u  g   c   v  2.000  f  t   2  t  g  00200  394  -\n",
       "687  a  25.25  13.500  y  p  ff  ff  2.000  f  t   1  t  g  00200    1  -\n",
       "688  b  17.92   0.205  u  g  aa   v  0.040  f  f   0  f  g  00280  750  -\n",
       "689  b  35.00   3.375  u  g   c   h  8.290  f  f   0  t  g  00000    0  -"
      ]
     },
     "execution_count": 59,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.tail(10)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>10</th>\n",
       "      <th>11</th>\n",
       "      <th>12</th>\n",
       "      <th>13</th>\n",
       "      <th>14</th>\n",
       "      <th>15</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>670</th>\n",
       "      <td>b</td>\n",
       "      <td>47.17</td>\n",
       "      <td>5.835</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>w</td>\n",
       "      <td>v</td>\n",
       "      <td>5.500</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00465</td>\n",
       "      <td>150</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>671</th>\n",
       "      <td>b</td>\n",
       "      <td>25.83</td>\n",
       "      <td>12.835</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>cc</td>\n",
       "      <td>v</td>\n",
       "      <td>0.500</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>2</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>672</th>\n",
       "      <td>a</td>\n",
       "      <td>50.25</td>\n",
       "      <td>0.835</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>aa</td>\n",
       "      <td>v</td>\n",
       "      <td>0.500</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00240</td>\n",
       "      <td>117</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>673</th>\n",
       "      <td>?</td>\n",
       "      <td>29.50</td>\n",
       "      <td>2.000</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>e</td>\n",
       "      <td>h</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00256</td>\n",
       "      <td>17</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>674</th>\n",
       "      <td>a</td>\n",
       "      <td>37.33</td>\n",
       "      <td>2.500</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>i</td>\n",
       "      <td>h</td>\n",
       "      <td>0.210</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00260</td>\n",
       "      <td>246</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>675</th>\n",
       "      <td>a</td>\n",
       "      <td>41.58</td>\n",
       "      <td>1.040</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>aa</td>\n",
       "      <td>v</td>\n",
       "      <td>0.665</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00240</td>\n",
       "      <td>237</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>676</th>\n",
       "      <td>a</td>\n",
       "      <td>30.58</td>\n",
       "      <td>10.665</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>q</td>\n",
       "      <td>h</td>\n",
       "      <td>0.085</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>12</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00129</td>\n",
       "      <td>3</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>677</th>\n",
       "      <td>b</td>\n",
       "      <td>19.42</td>\n",
       "      <td>7.250</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>m</td>\n",
       "      <td>v</td>\n",
       "      <td>0.040</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>1</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00100</td>\n",
       "      <td>1</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>678</th>\n",
       "      <td>a</td>\n",
       "      <td>17.92</td>\n",
       "      <td>10.210</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>ff</td>\n",
       "      <td>ff</td>\n",
       "      <td>0.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>50</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>679</th>\n",
       "      <td>a</td>\n",
       "      <td>20.08</td>\n",
       "      <td>1.250</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>v</td>\n",
       "      <td>0.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>680</th>\n",
       "      <td>b</td>\n",
       "      <td>19.50</td>\n",
       "      <td>0.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>k</td>\n",
       "      <td>v</td>\n",
       "      <td>0.290</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00280</td>\n",
       "      <td>364</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>681</th>\n",
       "      <td>b</td>\n",
       "      <td>27.83</td>\n",
       "      <td>1.000</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>d</td>\n",
       "      <td>h</td>\n",
       "      <td>3.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00176</td>\n",
       "      <td>537</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>682</th>\n",
       "      <td>b</td>\n",
       "      <td>17.08</td>\n",
       "      <td>3.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>i</td>\n",
       "      <td>v</td>\n",
       "      <td>0.335</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00140</td>\n",
       "      <td>2</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>683</th>\n",
       "      <td>b</td>\n",
       "      <td>36.42</td>\n",
       "      <td>0.750</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>d</td>\n",
       "      <td>v</td>\n",
       "      <td>0.585</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00240</td>\n",
       "      <td>3</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>684</th>\n",
       "      <td>b</td>\n",
       "      <td>40.58</td>\n",
       "      <td>3.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>m</td>\n",
       "      <td>v</td>\n",
       "      <td>3.500</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>s</td>\n",
       "      <td>00400</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>685</th>\n",
       "      <td>b</td>\n",
       "      <td>21.08</td>\n",
       "      <td>10.085</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>e</td>\n",
       "      <td>h</td>\n",
       "      <td>1.250</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00260</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>686</th>\n",
       "      <td>a</td>\n",
       "      <td>22.67</td>\n",
       "      <td>0.750</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>v</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>2</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00200</td>\n",
       "      <td>394</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>687</th>\n",
       "      <td>a</td>\n",
       "      <td>25.25</td>\n",
       "      <td>13.500</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>ff</td>\n",
       "      <td>ff</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>1</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00200</td>\n",
       "      <td>1</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>688</th>\n",
       "      <td>b</td>\n",
       "      <td>17.92</td>\n",
       "      <td>0.205</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>aa</td>\n",
       "      <td>v</td>\n",
       "      <td>0.040</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00280</td>\n",
       "      <td>750</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>689</th>\n",
       "      <td>b</td>\n",
       "      <td>35.00</td>\n",
       "      <td>3.375</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>h</td>\n",
       "      <td>8.290</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    0      1       2  3  4   5   6      7  8  9   10 11 12     13   14 15\n",
       "670  b  47.17   5.835  u  g   w   v  5.500  f  f   0  f  g  00465  150  -\n",
       "671  b  25.83  12.835  u  g  cc   v  0.500  f  f   0  f  g  00000    2  -\n",
       "672  a  50.25   0.835  u  g  aa   v  0.500  f  f   0  t  g  00240  117  -\n",
       "673  ?  29.50   2.000  y  p   e   h  2.000  f  f   0  f  g  00256   17  -\n",
       "674  a  37.33   2.500  u  g   i   h  0.210  f  f   0  f  g  00260  246  -\n",
       "675  a  41.58   1.040  u  g  aa   v  0.665  f  f   0  f  g  00240  237  -\n",
       "676  a  30.58  10.665  u  g   q   h  0.085  f  t  12  t  g  00129    3  -\n",
       "677  b  19.42   7.250  u  g   m   v  0.040  f  t   1  f  g  00100    1  -\n",
       "678  a  17.92  10.210  u  g  ff  ff  0.000  f  f   0  f  g  00000   50  -\n",
       "679  a  20.08   1.250  u  g   c   v  0.000  f  f   0  f  g  00000    0  -\n",
       "680  b  19.50   0.290  u  g   k   v  0.290  f  f   0  f  g  00280  364  -\n",
       "681  b  27.83   1.000  y  p   d   h  3.000  f  f   0  f  g  00176  537  -\n",
       "682  b  17.08   3.290  u  g   i   v  0.335  f  f   0  t  g  00140    2  -\n",
       "683  b  36.42   0.750  y  p   d   v  0.585  f  f   0  f  g  00240    3  -\n",
       "684  b  40.58   3.290  u  g   m   v  3.500  f  f   0  t  s  00400    0  -\n",
       "685  b  21.08  10.085  y  p   e   h  1.250  f  f   0  f  g  00260    0  -\n",
       "686  a  22.67   0.750  u  g   c   v  2.000  f  t   2  t  g  00200  394  -\n",
       "687  a  25.25  13.500  y  p  ff  ff  2.000  f  t   1  t  g  00200    1  -\n",
       "688  b  17.92   0.205  u  g  aa   v  0.040  f  f   0  f  g  00280  750  -\n",
       "689  b  35.00   3.375  u  g   c   h  8.290  f  f   0  t  g  00000    0  -"
      ]
     },
     "execution_count": 60,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.tail(20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 61,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>10</th>\n",
       "      <th>11</th>\n",
       "      <th>12</th>\n",
       "      <th>13</th>\n",
       "      <th>14</th>\n",
       "      <th>15</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>670</th>\n",
       "      <td>b</td>\n",
       "      <td>47.17</td>\n",
       "      <td>5.835</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>w</td>\n",
       "      <td>v</td>\n",
       "      <td>5.500</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00465</td>\n",
       "      <td>150</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>671</th>\n",
       "      <td>b</td>\n",
       "      <td>25.83</td>\n",
       "      <td>12.835</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>cc</td>\n",
       "      <td>v</td>\n",
       "      <td>0.500</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>2</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>672</th>\n",
       "      <td>a</td>\n",
       "      <td>50.25</td>\n",
       "      <td>0.835</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>aa</td>\n",
       "      <td>v</td>\n",
       "      <td>0.500</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00240</td>\n",
       "      <td>117</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>673</th>\n",
       "      <td>NaN</td>\n",
       "      <td>29.50</td>\n",
       "      <td>2.000</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>e</td>\n",
       "      <td>h</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00256</td>\n",
       "      <td>17</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>674</th>\n",
       "      <td>a</td>\n",
       "      <td>37.33</td>\n",
       "      <td>2.500</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>i</td>\n",
       "      <td>h</td>\n",
       "      <td>0.210</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00260</td>\n",
       "      <td>246</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>675</th>\n",
       "      <td>a</td>\n",
       "      <td>41.58</td>\n",
       "      <td>1.040</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>aa</td>\n",
       "      <td>v</td>\n",
       "      <td>0.665</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00240</td>\n",
       "      <td>237</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>676</th>\n",
       "      <td>a</td>\n",
       "      <td>30.58</td>\n",
       "      <td>10.665</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>q</td>\n",
       "      <td>h</td>\n",
       "      <td>0.085</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>12</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00129</td>\n",
       "      <td>3</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>677</th>\n",
       "      <td>b</td>\n",
       "      <td>19.42</td>\n",
       "      <td>7.250</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>m</td>\n",
       "      <td>v</td>\n",
       "      <td>0.040</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>1</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00100</td>\n",
       "      <td>1</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>678</th>\n",
       "      <td>a</td>\n",
       "      <td>17.92</td>\n",
       "      <td>10.210</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>ff</td>\n",
       "      <td>ff</td>\n",
       "      <td>0.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>50</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>679</th>\n",
       "      <td>a</td>\n",
       "      <td>20.08</td>\n",
       "      <td>1.250</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>v</td>\n",
       "      <td>0.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>680</th>\n",
       "      <td>b</td>\n",
       "      <td>19.50</td>\n",
       "      <td>0.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>k</td>\n",
       "      <td>v</td>\n",
       "      <td>0.290</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00280</td>\n",
       "      <td>364</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>681</th>\n",
       "      <td>b</td>\n",
       "      <td>27.83</td>\n",
       "      <td>1.000</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>d</td>\n",
       "      <td>h</td>\n",
       "      <td>3.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00176</td>\n",
       "      <td>537</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>682</th>\n",
       "      <td>b</td>\n",
       "      <td>17.08</td>\n",
       "      <td>3.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>i</td>\n",
       "      <td>v</td>\n",
       "      <td>0.335</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00140</td>\n",
       "      <td>2</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>683</th>\n",
       "      <td>b</td>\n",
       "      <td>36.42</td>\n",
       "      <td>0.750</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>d</td>\n",
       "      <td>v</td>\n",
       "      <td>0.585</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00240</td>\n",
       "      <td>3</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>684</th>\n",
       "      <td>b</td>\n",
       "      <td>40.58</td>\n",
       "      <td>3.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>m</td>\n",
       "      <td>v</td>\n",
       "      <td>3.500</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>s</td>\n",
       "      <td>00400</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>685</th>\n",
       "      <td>b</td>\n",
       "      <td>21.08</td>\n",
       "      <td>10.085</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>e</td>\n",
       "      <td>h</td>\n",
       "      <td>1.250</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00260</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>686</th>\n",
       "      <td>a</td>\n",
       "      <td>22.67</td>\n",
       "      <td>0.750</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>v</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>2</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00200</td>\n",
       "      <td>394</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>687</th>\n",
       "      <td>a</td>\n",
       "      <td>25.25</td>\n",
       "      <td>13.500</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>ff</td>\n",
       "      <td>ff</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>1</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00200</td>\n",
       "      <td>1</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>688</th>\n",
       "      <td>b</td>\n",
       "      <td>17.92</td>\n",
       "      <td>0.205</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>aa</td>\n",
       "      <td>v</td>\n",
       "      <td>0.040</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00280</td>\n",
       "      <td>750</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>689</th>\n",
       "      <td>b</td>\n",
       "      <td>35.00</td>\n",
       "      <td>3.375</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>h</td>\n",
       "      <td>8.290</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      0      1       2  3  4   5   6      7  8  9   10 11 12     13   14 15\n",
       "670    b  47.17   5.835  u  g   w   v  5.500  f  f   0  f  g  00465  150  -\n",
       "671    b  25.83  12.835  u  g  cc   v  0.500  f  f   0  f  g  00000    2  -\n",
       "672    a  50.25   0.835  u  g  aa   v  0.500  f  f   0  t  g  00240  117  -\n",
       "673  NaN  29.50   2.000  y  p   e   h  2.000  f  f   0  f  g  00256   17  -\n",
       "674    a  37.33   2.500  u  g   i   h  0.210  f  f   0  f  g  00260  246  -\n",
       "675    a  41.58   1.040  u  g  aa   v  0.665  f  f   0  f  g  00240  237  -\n",
       "676    a  30.58  10.665  u  g   q   h  0.085  f  t  12  t  g  00129    3  -\n",
       "677    b  19.42   7.250  u  g   m   v  0.040  f  t   1  f  g  00100    1  -\n",
       "678    a  17.92  10.210  u  g  ff  ff  0.000  f  f   0  f  g  00000   50  -\n",
       "679    a  20.08   1.250  u  g   c   v  0.000  f  f   0  f  g  00000    0  -\n",
       "680    b  19.50   0.290  u  g   k   v  0.290  f  f   0  f  g  00280  364  -\n",
       "681    b  27.83   1.000  y  p   d   h  3.000  f  f   0  f  g  00176  537  -\n",
       "682    b  17.08   3.290  u  g   i   v  0.335  f  f   0  t  g  00140    2  -\n",
       "683    b  36.42   0.750  y  p   d   v  0.585  f  f   0  f  g  00240    3  -\n",
       "684    b  40.58   3.290  u  g   m   v  3.500  f  f   0  t  s  00400    0  -\n",
       "685    b  21.08  10.085  y  p   e   h  1.250  f  f   0  f  g  00260    0  -\n",
       "686    a  22.67   0.750  u  g   c   v  2.000  f  t   2  t  g  00200  394  -\n",
       "687    a  25.25  13.500  y  p  ff  ff  2.000  f  t   1  t  g  00200    1  -\n",
       "688    b  17.92   0.205  u  g  aa   v  0.040  f  f   0  f  g  00280  750  -\n",
       "689    b  35.00   3.375  u  g   c   h  8.290  f  f   0  t  g  00000    0  -"
      ]
     },
     "execution_count": 61,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Importing numpy library\n",
    "import numpy as np\n",
    "\n",
    "# Replacing non-standard data with NaN\n",
    "data = data.replace( \"?\" , np.NaN)\n",
    "\n",
    "# Checking if the values are replaced correctly\n",
    "data.tail(20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     12\n",
       "1     12\n",
       "2      0\n",
       "3      6\n",
       "4      6\n",
       "5      9\n",
       "6      9\n",
       "7      0\n",
       "8      0\n",
       "9      0\n",
       "10     0\n",
       "11     0\n",
       "12     0\n",
       "13    13\n",
       "14     0\n",
       "15     0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 62,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Replacing NaN values in numeric variables with mean values for that variable\n",
    "data.fillna(data.mean(), inplace=True)\n",
    "\n",
    "# Let us check if the numeric variables have any missing values\n",
    "data.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 63,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>10</th>\n",
       "      <th>11</th>\n",
       "      <th>12</th>\n",
       "      <th>13</th>\n",
       "      <th>14</th>\n",
       "      <th>15</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>670</th>\n",
       "      <td>b</td>\n",
       "      <td>47.17</td>\n",
       "      <td>5.835</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>w</td>\n",
       "      <td>v</td>\n",
       "      <td>5.500</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00465</td>\n",
       "      <td>150</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>671</th>\n",
       "      <td>b</td>\n",
       "      <td>25.83</td>\n",
       "      <td>12.835</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>cc</td>\n",
       "      <td>v</td>\n",
       "      <td>0.500</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>2</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>672</th>\n",
       "      <td>a</td>\n",
       "      <td>50.25</td>\n",
       "      <td>0.835</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>aa</td>\n",
       "      <td>v</td>\n",
       "      <td>0.500</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00240</td>\n",
       "      <td>117</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>673</th>\n",
       "      <td>NaN</td>\n",
       "      <td>29.50</td>\n",
       "      <td>2.000</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>e</td>\n",
       "      <td>h</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00256</td>\n",
       "      <td>17</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>674</th>\n",
       "      <td>a</td>\n",
       "      <td>37.33</td>\n",
       "      <td>2.500</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>i</td>\n",
       "      <td>h</td>\n",
       "      <td>0.210</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00260</td>\n",
       "      <td>246</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>675</th>\n",
       "      <td>a</td>\n",
       "      <td>41.58</td>\n",
       "      <td>1.040</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>aa</td>\n",
       "      <td>v</td>\n",
       "      <td>0.665</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00240</td>\n",
       "      <td>237</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>676</th>\n",
       "      <td>a</td>\n",
       "      <td>30.58</td>\n",
       "      <td>10.665</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>q</td>\n",
       "      <td>h</td>\n",
       "      <td>0.085</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>12</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00129</td>\n",
       "      <td>3</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>677</th>\n",
       "      <td>b</td>\n",
       "      <td>19.42</td>\n",
       "      <td>7.250</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>m</td>\n",
       "      <td>v</td>\n",
       "      <td>0.040</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>1</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00100</td>\n",
       "      <td>1</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>678</th>\n",
       "      <td>a</td>\n",
       "      <td>17.92</td>\n",
       "      <td>10.210</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>ff</td>\n",
       "      <td>ff</td>\n",
       "      <td>0.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>50</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>679</th>\n",
       "      <td>a</td>\n",
       "      <td>20.08</td>\n",
       "      <td>1.250</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>v</td>\n",
       "      <td>0.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>680</th>\n",
       "      <td>b</td>\n",
       "      <td>19.50</td>\n",
       "      <td>0.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>k</td>\n",
       "      <td>v</td>\n",
       "      <td>0.290</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00280</td>\n",
       "      <td>364</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>681</th>\n",
       "      <td>b</td>\n",
       "      <td>27.83</td>\n",
       "      <td>1.000</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>d</td>\n",
       "      <td>h</td>\n",
       "      <td>3.000</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00176</td>\n",
       "      <td>537</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>682</th>\n",
       "      <td>b</td>\n",
       "      <td>17.08</td>\n",
       "      <td>3.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>i</td>\n",
       "      <td>v</td>\n",
       "      <td>0.335</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00140</td>\n",
       "      <td>2</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>683</th>\n",
       "      <td>b</td>\n",
       "      <td>36.42</td>\n",
       "      <td>0.750</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>d</td>\n",
       "      <td>v</td>\n",
       "      <td>0.585</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00240</td>\n",
       "      <td>3</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>684</th>\n",
       "      <td>b</td>\n",
       "      <td>40.58</td>\n",
       "      <td>3.290</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>m</td>\n",
       "      <td>v</td>\n",
       "      <td>3.500</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>s</td>\n",
       "      <td>00400</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>685</th>\n",
       "      <td>b</td>\n",
       "      <td>21.08</td>\n",
       "      <td>10.085</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>e</td>\n",
       "      <td>h</td>\n",
       "      <td>1.250</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00260</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>686</th>\n",
       "      <td>a</td>\n",
       "      <td>22.67</td>\n",
       "      <td>0.750</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>v</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>2</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00200</td>\n",
       "      <td>394</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>687</th>\n",
       "      <td>a</td>\n",
       "      <td>25.25</td>\n",
       "      <td>13.500</td>\n",
       "      <td>y</td>\n",
       "      <td>p</td>\n",
       "      <td>ff</td>\n",
       "      <td>ff</td>\n",
       "      <td>2.000</td>\n",
       "      <td>f</td>\n",
       "      <td>t</td>\n",
       "      <td>1</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00200</td>\n",
       "      <td>1</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>688</th>\n",
       "      <td>b</td>\n",
       "      <td>17.92</td>\n",
       "      <td>0.205</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>aa</td>\n",
       "      <td>v</td>\n",
       "      <td>0.040</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>f</td>\n",
       "      <td>g</td>\n",
       "      <td>00280</td>\n",
       "      <td>750</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>689</th>\n",
       "      <td>b</td>\n",
       "      <td>35.00</td>\n",
       "      <td>3.375</td>\n",
       "      <td>u</td>\n",
       "      <td>g</td>\n",
       "      <td>c</td>\n",
       "      <td>h</td>\n",
       "      <td>8.290</td>\n",
       "      <td>f</td>\n",
       "      <td>f</td>\n",
       "      <td>0</td>\n",
       "      <td>t</td>\n",
       "      <td>g</td>\n",
       "      <td>00000</td>\n",
       "      <td>0</td>\n",
       "      <td>-</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      0      1       2  3  4   5   6      7  8  9   10 11 12     13   14 15\n",
       "670    b  47.17   5.835  u  g   w   v  5.500  f  f   0  f  g  00465  150  -\n",
       "671    b  25.83  12.835  u  g  cc   v  0.500  f  f   0  f  g  00000    2  -\n",
       "672    a  50.25   0.835  u  g  aa   v  0.500  f  f   0  t  g  00240  117  -\n",
       "673  NaN  29.50   2.000  y  p   e   h  2.000  f  f   0  f  g  00256   17  -\n",
       "674    a  37.33   2.500  u  g   i   h  0.210  f  f   0  f  g  00260  246  -\n",
       "675    a  41.58   1.040  u  g  aa   v  0.665  f  f   0  f  g  00240  237  -\n",
       "676    a  30.58  10.665  u  g   q   h  0.085  f  t  12  t  g  00129    3  -\n",
       "677    b  19.42   7.250  u  g   m   v  0.040  f  t   1  f  g  00100    1  -\n",
       "678    a  17.92  10.210  u  g  ff  ff  0.000  f  f   0  f  g  00000   50  -\n",
       "679    a  20.08   1.250  u  g   c   v  0.000  f  f   0  f  g  00000    0  -\n",
       "680    b  19.50   0.290  u  g   k   v  0.290  f  f   0  f  g  00280  364  -\n",
       "681    b  27.83   1.000  y  p   d   h  3.000  f  f   0  f  g  00176  537  -\n",
       "682    b  17.08   3.290  u  g   i   v  0.335  f  f   0  t  g  00140    2  -\n",
       "683    b  36.42   0.750  y  p   d   v  0.585  f  f   0  f  g  00240    3  -\n",
       "684    b  40.58   3.290  u  g   m   v  3.500  f  f   0  t  s  00400    0  -\n",
       "685    b  21.08  10.085  y  p   e   h  1.250  f  f   0  f  g  00260    0  -\n",
       "686    a  22.67   0.750  u  g   c   v  2.000  f  t   2  t  g  00200  394  -\n",
       "687    a  25.25  13.500  y  p  ff  ff  2.000  f  t   1  t  g  00200    1  -\n",
       "688    b  17.92   0.205  u  g  aa   v  0.040  f  f   0  f  g  00280  750  -\n",
       "689    b  35.00   3.375  u  g   c   h  8.290  f  f   0  t  g  00000    0  -"
      ]
     },
     "execution_count": 63,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#the character variables still have NaN values\n",
    "data.tail(20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 64,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0     0\n",
       "1     0\n",
       "2     0\n",
       "3     0\n",
       "4     0\n",
       "5     0\n",
       "6     0\n",
       "7     0\n",
       "8     0\n",
       "9     0\n",
       "10    0\n",
       "11    0\n",
       "12    0\n",
       "13    0\n",
       "14    0\n",
       "15    0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 64,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# Creating a loop to run on character variables to replace NaN values with most frequent values in that variable\n",
    "for i in data:\n",
    "    # if the variable is object type\n",
    "    if data[i].dtypes == 'object':\n",
    "        # replace with the most frequent value\n",
    "        data = data.fillna(data[i].value_counts().index[0])\n",
    "\n",
    "# Let us check if any variables have any missing values\n",
    "data.isna().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 65,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Converting non-numeric data into numeric data using LabelEncoder\n",
    "\n",
    "from sklearn import preprocessing\n",
    "\n",
    "encode = preprocessing.LabelEncoder()\n",
    "\n",
    "#extracting data types for each column and performing numeric transformation\n",
    "for i in data:\n",
    "    if data[i].dtypes =='object':\n",
    "        data[i]=encode.fit_transform(data[i])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 66,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>10</th>\n",
       "      <th>11</th>\n",
       "      <th>12</th>\n",
       "      <th>13</th>\n",
       "      <th>14</th>\n",
       "      <th>15</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>670</th>\n",
       "      <td>1</td>\n",
       "      <td>275</td>\n",
       "      <td>5.835</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>13</td>\n",
       "      <td>8</td>\n",
       "      <td>5.500</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>145</td>\n",
       "      <td>150</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>671</th>\n",
       "      <td>1</td>\n",
       "      <td>104</td>\n",
       "      <td>12.835</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>3</td>\n",
       "      <td>8</td>\n",
       "      <td>0.500</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>672</th>\n",
       "      <td>0</td>\n",
       "      <td>295</td>\n",
       "      <td>0.835</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>0.500</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>84</td>\n",
       "      <td>117</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>673</th>\n",
       "      <td>1</td>\n",
       "      <td>140</td>\n",
       "      <td>2.000</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>2.000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>89</td>\n",
       "      <td>17</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>674</th>\n",
       "      <td>0</td>\n",
       "      <td>214</td>\n",
       "      <td>2.500</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>4</td>\n",
       "      <td>0.210</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>90</td>\n",
       "      <td>246</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>675</th>\n",
       "      <td>0</td>\n",
       "      <td>248</td>\n",
       "      <td>1.040</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>0.665</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>84</td>\n",
       "      <td>237</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>676</th>\n",
       "      <td>0</td>\n",
       "      <td>153</td>\n",
       "      <td>10.665</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>11</td>\n",
       "      <td>4</td>\n",
       "      <td>0.085</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>12</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>40</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>677</th>\n",
       "      <td>1</td>\n",
       "      <td>36</td>\n",
       "      <td>7.250</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>8</td>\n",
       "      <td>0.040</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>31</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>678</th>\n",
       "      <td>0</td>\n",
       "      <td>20</td>\n",
       "      <td>10.210</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>6</td>\n",
       "      <td>3</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>50</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>679</th>\n",
       "      <td>0</td>\n",
       "      <td>42</td>\n",
       "      <td>1.250</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>0.000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>680</th>\n",
       "      <td>1</td>\n",
       "      <td>37</td>\n",
       "      <td>0.290</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>9</td>\n",
       "      <td>8</td>\n",
       "      <td>0.290</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>96</td>\n",
       "      <td>364</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>681</th>\n",
       "      <td>1</td>\n",
       "      <td>125</td>\n",
       "      <td>1.000</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>4</td>\n",
       "      <td>3.000</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>60</td>\n",
       "      <td>537</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>682</th>\n",
       "      <td>1</td>\n",
       "      <td>12</td>\n",
       "      <td>3.290</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>7</td>\n",
       "      <td>8</td>\n",
       "      <td>0.335</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>44</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>683</th>\n",
       "      <td>1</td>\n",
       "      <td>208</td>\n",
       "      <td>0.750</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>4</td>\n",
       "      <td>8</td>\n",
       "      <td>0.585</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>84</td>\n",
       "      <td>3</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>684</th>\n",
       "      <td>1</td>\n",
       "      <td>240</td>\n",
       "      <td>3.290</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>10</td>\n",
       "      <td>8</td>\n",
       "      <td>3.500</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>129</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>685</th>\n",
       "      <td>1</td>\n",
       "      <td>52</td>\n",
       "      <td>10.085</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>1.250</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>90</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>686</th>\n",
       "      <td>0</td>\n",
       "      <td>71</td>\n",
       "      <td>0.750</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>8</td>\n",
       "      <td>2.000</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>67</td>\n",
       "      <td>394</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>687</th>\n",
       "      <td>0</td>\n",
       "      <td>97</td>\n",
       "      <td>13.500</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>6</td>\n",
       "      <td>3</td>\n",
       "      <td>2.000</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>67</td>\n",
       "      <td>1</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>688</th>\n",
       "      <td>1</td>\n",
       "      <td>20</td>\n",
       "      <td>0.205</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>8</td>\n",
       "      <td>0.040</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>96</td>\n",
       "      <td>750</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>689</th>\n",
       "      <td>1</td>\n",
       "      <td>197</td>\n",
       "      <td>3.375</td>\n",
       "      <td>2</td>\n",
       "      <td>1</td>\n",
       "      <td>2</td>\n",
       "      <td>4</td>\n",
       "      <td>8.290</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     0    1       2   3   4   5   6      7   8   9   10  11  12   13   14  15\n",
       "670   1  275   5.835   2   1  13   8  5.500   0   0   0   0   0  145  150   1\n",
       "671   1  104  12.835   2   1   3   8  0.500   0   0   0   0   0    0    2   1\n",
       "672   0  295   0.835   2   1   0   8  0.500   0   0   0   1   0   84  117   1\n",
       "673   1  140   2.000   3   3   5   4  2.000   0   0   0   0   0   89   17   1\n",
       "674   0  214   2.500   2   1   7   4  0.210   0   0   0   0   0   90  246   1\n",
       "675   0  248   1.040   2   1   0   8  0.665   0   0   0   0   0   84  237   1\n",
       "676   0  153  10.665   2   1  11   4  0.085   0   1  12   1   0   40    3   1\n",
       "677   1   36   7.250   2   1  10   8  0.040   0   1   1   0   0   31    1   1\n",
       "678   0   20  10.210   2   1   6   3  0.000   0   0   0   0   0    0   50   1\n",
       "679   0   42   1.250   2   1   2   8  0.000   0   0   0   0   0    0    0   1\n",
       "680   1   37   0.290   2   1   9   8  0.290   0   0   0   0   0   96  364   1\n",
       "681   1  125   1.000   3   3   4   4  3.000   0   0   0   0   0   60  537   1\n",
       "682   1   12   3.290   2   1   7   8  0.335   0   0   0   1   0   44    2   1\n",
       "683   1  208   0.750   3   3   4   8  0.585   0   0   0   0   0   84    3   1\n",
       "684   1  240   3.290   2   1  10   8  3.500   0   0   0   1   2  129    0   1\n",
       "685   1   52  10.085   3   3   5   4  1.250   0   0   0   0   0   90    0   1\n",
       "686   0   71   0.750   2   1   2   8  2.000   0   1   2   1   0   67  394   1\n",
       "687   0   97  13.500   3   3   6   3  2.000   0   1   1   1   0   67    1   1\n",
       "688   1   20   0.205   2   1   0   8  0.040   0   0   0   0   0   96  750   1\n",
       "689   1  197   3.375   2   1   2   4  8.290   0   0   0   1   0    0    0   1"
      ]
     },
     "execution_count": 66,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#lets check if transformation has worked correctly\n",
    "data.tail(20)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {},
   "outputs": [],
   "source": [
    "#creating correlation matrix for our data to check correlation of variables and possibility of multicollinearity\n",
    "corr = data.corr()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 68,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x26b0e289160>"
      ]
     },
     "execution_count": 68,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAlIAAAIMCAYAAAA+W0L0AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADl0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uIDMuMC4yLCBodHRwOi8vbWF0cGxvdGxpYi5vcmcvOIA7rQAAIABJREFUeJzt3XuUZWV95//3p7u5CF3cobk0CCJeiBqiDjoxcbyOmDgQx/GnMjMhBu3J+sWJ/jJJJMv5OcFMEvlpNFkTJ7G8RZ1EE00iLRoViWgSo1IqIBcJFxWahgblVohKt/39/VGnZ4qyqk7XrjrPOXXq/Vprrzpn733O99nV1dWffp7nPDtVhSRJkpZu3bAbIEmStFoZpCRJkjoySEmSJHVkkJIkSerIICVJktSRQUqSJKkjg5QkSVJHBilJkqSODFKSJEkdGaQkSZI62tCghvegkSRpNGXYDVjt7JGSJEnqyCAlSZLUkUFKkiSpI4OUJElSRwYpSZKkjgxSkiRJHRmkJEmSOjJISZIkdWSQkiRJ6sggJUmS1JFBSpIkqaO+99pL8hjgLOA4Zu6btx3YWlXXDrhtkiRJI23RHqkkrwU+yMxNDb8EXNZ7/IEk5w2+eZIkSaMrVbXwweSfgR+rqp1z9u8LXF1Vp+xFjYULSJKkYcqwG7Da9ZsjtRs4dp79x/SOzSvJliRTSaYmJyeX0z5JkqSR1a9H6gzgj4DrgVt6u08AHgm8qqo+sRc17JGSJGk02SO1TIsGKYAk64DTmZlsHmAbcFlV/XAvaxikJEkaTQapZeobpFaAQUqSpNFkkFom15GSJEnqyCAlSZLUkUFKkiSpI4OUJElSRwYpSZKkjgxSkiRJHRmkJEmSOjJISZIkdWSQkiRJ6sggJUmS1JFBSpIkqSODlCRJUkcbWhTZefuOFmUeYp+jNzWvKUmS1hZ7pCRJkjoySEmSJHVkkJIkSerIICVJktSRQUqSJKkjg5QkSVJHBilJkqSODFKSJEkdGaQkSZI6MkhJkiR1ZJCSJEnqyCAlSZLUUecgleTlK9kQSZKk1WY5PVLnL3QgyZYkU0mmJicnl1FCkiRpdKWqFj6YXLnQIeBRVbXfXtSonbfv6NK2Zdnn6E3Na0qStMpk2A1Y7Tb0Ob4JeB5w95z9AT4/kBZJkiStEv2C1EXAxqq6fO6BJJcOpEWSJEmrxKJDeyvEoT1JkkaTQ3vL5PIHkiRJHRmkJEmSOjJISZIkdWSQkiRJ6sggJUmS1JFBSpIkqSODlCRJUkcGKUmSpI4MUpIkSR0ZpCRJkjpqcouYQReQJEmdeIuYZep30+IVcdcD329R5iEOO2B/AH5w3Q3Na+/36Ec2rylJktpzaE+SJKkjg5QkSVJHBilJkqSODFKSJEkdGaQkSZI6MkhJkiR1ZJCSJEnqyCAlSZLUkUFKkiSpI4OUJElSRwYpSZKkjgxSkiRJHfUNUkkek+TZSTbO2X/G4JolSZI0+hYNUkl+BbgQ+M/AVUnOmnX4dwfZMEmSpFHXr0fqlcCTqurngGcA/2+SV/eOZaEXJdmSZCrJ1OTk5Mq0VJIkacRs6HN8fVXdD1BV30zyDODDSR7OIkGqqiaBPQmq7nrg+yvRVkmSpJHSr0fq9iSn7XnSC1UvAI4AHj/IhkmSJI26fkHq54HbZ++oql1V9fPA0wfWKkmSpFVg0aG9qtq2yLF/XPnmSJIkrR6uIyVJktSRQUqSJKkjg5QkSVJHBilJkqSODFKSJEkdGaQkSZI6MkhJkiR1ZJCSJEnqyCAlSZLUkUFKkiSpo1TVoGsMvIAkSeokw27AarfovfZWys7tt/c/aYXtc+zRANwx/UDz2kdNHMBdD3y/ed3DDti/eU1JktYyh/YkSZI6MkhJkiR1ZJCSJEnqyCAlSZLUkUFKkiSpI4OUJElSRwYpSZKkjgxSkiRJHRmkJEmSOjJISZIkdWSQkiRJ6qjvvfaSnA5UVV2W5FTgDODrVfXxgbdOkiRphC0apJL8N+D5wIYkFwNPAS4FzkvyE1X1O4NvoiRJ0mjq1yP174DTgP2A24HNVXVfkjcBXwQMUpIkac3qN0dqV1X9sKoeAG6sqvsAqup7wO6FXpRkS5KpJFOTk5Mr2FxJkqTR0a9H6sEkB/SC1JP27ExyMIsEqaqaBPYkqNq5/fZlN1SSJGnU9AtST6+qHwBU1ezgtA9wzsBaJUmStAosGqT2hKh59n8b+PZAWiRJkrRKuI6UJElSRwYpSZKkjgxSkiRJHRmkJEmSOjJISZIkdWSQkiRJ6sggJUmS1JFBSpIkqSODlCRJUkcGKUmSpI5SVYOuMfACkiSpkwy7Aatdv5sWS5Ikrbjrf+p5S+poOeUfPjmSoa9JkNq5/fYWZR5in2OPBmD7Pfc3r33sIRvZcd93m9fddNCBANzwnLOa137kpy9sXlOSpGGzR0qSJLWX8ZimbZCSJEntZSRH6pbMICVJkprLOoOUJElSNw7tSZIkdeTQniRJUkdjMrQ3Hv1qkiRJQ2CPlCRJai5jMrRnj5QkSWpv3bqlbXshyRlJrktyQ5Lz5jn+8CSXJLkyyaVJNi/7Mpb7BpIkSUuWLG3r+3ZZD7wNeD5wKvCyJKfOOe3NwPuq6gnAG4DfW+5lGKQkSVJ7KxykgNOBG6rqpqp6EPggMPeeaacCl/Qef2ae40u25CCV5H3LLSpJkta2rFu3pG0vHAfcMuv5tt6+2a4AXtR7/EJgIsnhy7mORSebJ9k6dxfwzCSHAFTVmcspLkmS1qi9nPe0R5ItwJZZuyaranL2KfO8rOY8/zXgj5L8AvA54FZg15IaMke/T+1tBq4B3tlrTIAnA7+/2ItmX+zb3/52Xv4C85YkSequF5omFzllG3D8rOebge1z3mM78G8BkmwEXlRV9y6nXf2C1JOBVwOvA369qi5P8r2q+uxiL5pzsbVz++3LaaMkSRo3K7/8wWXAKUlOYqan6aXA2Q8tmSOAu6pqN/CbwLuXW3TRINUr9NYkH+p93dHvNZIkSf2s9DpSVbUryauATwLrgXdX1dVJ3gBMVdVW4BnA7yUpZob2fnm5dfcqFFXVNuDFSX4WuG+5RSVJ0ho3gFvEVNXHgY/P2ff6WY8/DHx4JWsuqXepqj4GfGwlGyBJktag9euH3YIV4TCdJElqzlvESJIkrXH2SEmSpPYyHn05BilJktTeACabD4NBSpIkNbeXt30ZeQYpSZLU3phMNjdISZKk9gxSkiRJHTm0J0mS1I3rSEmSJK1xTXqk9jn26BZl5nXsIRuHUnfTQQcOpS7AIz994dBqS5K0V1z+YO9NT0+3KPMQExMTQ63tNberK0lahVyQU5IkqaMxmSNlkJIkSc3FoT1JkqSO7JGSJEnqaEzWkRqPq5AkSRoCe6QkSVJz3rRYkiSpK+dISZIkdWSQkiRJ6sihPUmSpG7GZY7UeFyFJEnSECypRyrJTwGnA1dV1acG0yRJkjT2xmRl80V7pJJ8adbjVwJ/BEwA/y3JeQNumyRJGldZt7RtRPXrkdpn1uMtwHOr6s4kbwa+ALxxYC2TJElja1zutdcv4q1LcmiSw4FU1Z0AVfVdYNdCL0qyJclUkqnJyckVbK4kSRoL69YtbRtR/XqkDga+DASoJEdX1e1JNvb2zauqJoE9Caqmp6dXpLGSJGlMrIV1pKrqxAUO7QZeuOKtkSRJa0LWQpBaSFU9AHxjhdsiSZLWihEerluK8bgKSZKkIXBlc0mS1N5aHtqTJElaljEJUg7tSZKk5rJu3ZK2vXrP5Iwk1yW5YaGFw5P8X0muSXJ1kj9f7nXYIyVJktpb4R6pJOuBtwHPBbYBlyXZWlXXzDrnFOA3gadV1d1JjlpuXXukJElSe+uytK2/04EbquqmqnoQ+CBw1pxzXgm8raruBqiqO5Z9Gct9A0mSpCVLlrb1dxxwy6zn23r7ZnsU8Kgk/5jkC0nOWO5lOLQnSZJGXpItzNz3d4/J3p1U/vcp87ys5jzfAJwCPAPYDPx9ksdV1T1d22WQkiRJze3tBPI95tx+bj7bgONnPd8MbJ/nnC9U1U7gG0muYyZYXbakxszi0J4kSWov65a29XcZcEqSk5LsC7wU2DrnnI8AzwRIcgQzQ303LecymvRITUxMtCgzUrW9ZkmSFrF3E8j3WlXtSvIq4JPAeuDdVXV1kjcAU1W1tXfsXye5Bvgh8OtV9Z3l1E3V3OHDFTfwApIkqZOhrYp5xwV/sKR8cNRrXzOSK3g26ZHadee3W5R5iA1HHgHAVdt2NK/9uM2bmJ6ebl53T4/QztvbX/M+Rw/3modZW5LUwfr1w27BinCOlCRJUkd+ak+SJLU3JvfaM0hJkqTmssKTzYfFICVJktrbuyUNRp5BSpIktefQniRJUkcO7UmSJHWz1FvEjCqDlCRJam9M5kiNx1VIkiQNgT1SkiSpPedISZIkdZMx+dTeokN7SZ6S5KDe44clOT/JR5NckOTgNk2UJEljJ1naNqL6zZF6N/BA7/EfAgcDF/T2vWeA7ZIkSeNs3bqlbSOqX8vWVdWu3uMnV9Vrquofqup84BELvSjJliRTSaYmJydXrLGSJGlMjEmPVL85UlcleXlVvQe4IsmTq2oqyaOAnQu9qKomgT0Jqnbd+e0Vaq4kSRoHa2KOFPAK4F8luRE4FfinJDcB7+gdkyRJWrMW7ZGqqnuBX0gywcxQ3gZgW1XtaNE4SZI0pkZ43tNS7NXyB1U1DVwx4LZIkqS1YkyG9lxHSpIktbeWeqQkSZJWUlzZXJIkqSOH9iRJkjqKQ3uSJEmdOLQnSZLUlUN7kiRJHTm0J0mS1JFDe5IkSd2My732DFKSJKk9e6SWUOTII1qUmdfjNm8aSt2JiYmh1AXY5+i1d83DrC1J6sCVzffegzdva1HmIfY9YTMA93zowua1D3nxWUxf/JnmdSee+0wAvvPd7zevffiB+3PH9APN6x41cQAAu+78dvPaG448gh33fbd53U0HHdi8piRpfg7tSZKk9vzUniRJUjdONpckSepqTCabj0e/miRJWl2SpW179ZY5I8l1SW5Ict48x38pydeSXJ7kH5KcutzLMEhJkqT2sm5pW7+3S9YDbwOeD5wKvGyeoPTnVfX4qjoN+P+Atyz3MhzakyRJzQ3gpsWnAzdU1U0AST4InAVcs+eEqrpv1vkHArXcogYpSZI08pJsAbbM2jVZVZOznh8H3DLr+TbgKfO8zy8DvwrsCzxrue0ySEmSpPaW+Km9XmiaXOSU+d7wR3qcquptwNuSnA38V+CcJTVkDoOUJElqb+VXNt8GHD/r+WZg+yLnfxD44+UWdbK5JElqLsmStr1wGXBKkpOS7Au8FNg6p+Yps57+LHD9cq/DHilJktTeCvdIVdWuJK8CPgmsB95dVVcneQMwVVVbgVcleQ6wE7ibZQ7rQZ8gleRXgL+pqlsWO0+SJGlJBrCyeVV9HPj4nH2vn/X41Stds18c/G3gi0n+Psn/neTIlW6AJElag9ZladuI6hekbmJmstZvA08CrknyiSTnJJkYeOskSdJYStYtaRtV/VpWVbW7qj5VVecCxwL/EziDmZA1ryRbkkwlmZqcXOyTipIkaU0awC1ihqHfZPOHtLyqdjIzA35rkoct9KI5az3UgzdvW1YjJUnSmBnh4bql6BekXrLQgar63gq3RZIkrRUjPFy3FIsGqar651YNkSRJa8cA7rU3FK4jJUmS2hvheU9LYZCSJEntjUmQGo8BSkmSpCGwR0qSJDWXlb9p8VAYpCRJUnsGKUmSpI7GZI6UQUqSJLXn8geSJEndjPL985bCICVJktobk6G98YiDkiRJQ5CqGnSNgReQJEmdDK1b6PvXXrekfLD/Yx89kl1YDu1JkqT2xmRor0mQmp6eblHmISYmJgD43leuaF77YU/8cb77j19sXvfApz0FgNvuvb957WMO3siNd9zdvO7JRx0KwIM3fbN57X0fceJQf7bv/egnmtc++N+c0bympPHkZHNJkqSuXP5AkiSpI1c2lyRJ6ibOkZIkSerIHilJkqSO7JGSJEnqyCAlSZLUTfzUniRJUkeuIyVJktSRQ3uSJEkdjcnQ3nj0q0mSJA3Boj1SSfYFXgpsr6pPJzkb+EngWmCyqnY2aKMkSRoza+Vee+/pnXNAknOAjcBfA88GTgfOGWzzJEnSWBqTob1+QerxVfWEJBuAW4Fjq+qHSf4XcMVCL0qyBdgC8Pa3v52XvexlK9ZgSZK0+n1v//2WdP7EgNqxXP2C1Lre8N6BwAHAwcBdwH7APgu9qKomgck9T6enp1egqZIkSQtLcgbwh8B64J1V9cY5x/cD3gc8CfgO8JKq+uZyavYLUu8Cvt5r0OuADyW5CXgq8MHlFJYkSVopSdYDbwOeC2wDLkuytaqumXXaucDdVfXIJC8FLgBespy6iwapqnprkr/oPd6e5H3Ac4B3VNWXllNYkiRpBZ0O3FBVNwEk+SBwFjA7SJ0F/Fbv8YeBP0qSqqquRfuuI1VV22c9vqdXWJIkaZQcB9wy6/k24CkLnVNVu5LcCxwOfLtr0fH47KEkSRprSbYkmZq1bZl7yjwvm9vTtDfnLIkrm0uSpJE354Ns89kGHD/r+WZg+wLnbOutSLDnQ3Sd2SMlSZLGwWXAKUlOmrWg+NY552zl/6yB+e+Av1vO/CiwR0qSJI2B3pynVwGfZGa1gXdX1dVJ3gBMVdVWZlYjeH+SG5jpiXrpcusapCRJ0lioqo8DH5+z7/WzHn8fePFK1nRoT5IkqSN7pCRJUnM71y94g5RVxSAlSZKaW94U79FhkJIkSc3tHpMkZZCSJEnNLXPVgZGRBhcyHt8pSZLGz3wrfTex477vLikfbDrowKG1dTH2SEmSpOYc2luC2+69v0WZhzjm4I0A7NpxZ/PaGzYdyfe+dnXzug97/I8BcPNd9zavfcJhB3Pd7Z3v+djZo48+AoAfXH9j89r7nXIy09PTzetOTEwA8MCXvty89gGnPwmAu97/F81rH/YfX9K8pqTBGZMc5TpSkiRJXTm0J0mSmhuXyeYGKUmS1NzuMfksmkFKkiQ1Z4+UJElSR35qT5IkqaPduw1SkiRJnYxJh5TLH0iSJHVlj5QkSWrOyeaSJEkdufyBJElSR2umRyrJycALgeOBXcD1wAeqqv0N3SRJ0lgYlyC16GTzJL8C/AmwP/AvgIcxE6j+KckzBt46SZI0lnbX0rZR1e9Te68Ezqiq/w48Bzi1ql4HnAG8daEXJdmSZCrJ1OTk5Mq1VpIkjYWqWtI2qvZmjtQG4IfAfsAEQFXdnGSfhV5QVZPAngRVt917/3LbKUmSxsgoh6Ol6Bek3glcluQLwNOBCwCSHAncNeC2SZKkMbUmbhFTVX+Y5NPAY4G3VNXXe/vvZCZYSZIkLdmaCFIAVXU1cHWDtkiSpDVirQztSZIkrbg10yMlSZK00sYkRxmkJElSe+MytNdvHSlJkiQtwB4pSZLUnHOkJEmSOhqXoT2DlCRJam5McpRBSpIktTcuQ3tONpckSc21vGlxksOSXJzk+t7XQ+c55+FJvpzk8iRXJ/mlvXlvg5QkSWpud9WStmU6D7ikqk4BLuk9n+s24Cer6jTgKcB5SY7t98ZpMNlrPPruJEkaPxlW4c99/RtLygdPf8xJndua5DrgGVV1W5JjgEur6tGLnH848FXgqVW1fbH3bjJHanp6ukWZh5iYmADg+1d/vXnt/X/sMdz/2X9sXnfjv3oaALfde3/z2sccvJFb7r6ved3jDz0IGN7P2DB/tu/724ub1z7o+c8F4J6/2tq89iEvOpM7LviD5nWPeu1rmteU1oLGc6Q2VdVtAL0wddR8JyU5HvgY8Ejg1/uFKHCyuSRJGoKljogl2QJsmbVrsqomZx3/NHD0PC993RLadAvwhN6Q3keSfLiqdiz2GoOUJElqbqlBqheaJhc5/pyFjiXZkeSYWUN7d/SptT3J1cBPAx9e7Fwnm0uSpOZ219K2ZdoKnNN7fA5w4dwTkmxO8rDe40OBpwHX9Xtjg5QkSWqu5fIHwBuB5ya5Hnhu7zlJnpzknb1zHgt8MckVwGeBN1fV1/q9sUN7kiSpuZa3iKmq7wDPnmf/FPCK3uOLgScs9b3tkZIkSerIHilJktTcD2v3sJuwIgxSkiSpuRWYQD4SDFKSJKm53WOSpAxSkiSpuZaTzQfJICVJkpozSEmSJHW0m/EIUi5/IEmS1NGiQSrJwUnemOTrSb7T267t7TukVSMlSdJ4abyy+cD065H6S+Bu4BlVdXhVHQ48s7fvQwu9KMmWJFNJpiYnF7y/oCRJWqOqlraNqn5zpE6sqgtm76iq24ELkvziQi+ac4fmmp6eXl4rJUnSWNk9yuloCfr1SH0ryW8k2bRnR5JNSV4L3DLYpkmSpHG1Vob2XgIcDnw2yV1J7gIuBQ4DXjzgtkmSpDE1LkFq0aG9qrobeG1ve4gkLwfeM6B2SZKkMbZWhvYWc/6KtUKSJGkVWrRHKsmVCx0CNi1wTJIkaVHj0iPV71N7m4DnMbPcwWwBPj+QFkmSpLE3yvOelqJfkLoI2FhVl889kOTSgbRIkiSNvd3jkaP6TjY/d5FjZ698cyRJ0lqwVnqkJEmSVpxBSpIkqaNxmWy+nOUPJEmS1jR7pCRJUnO7x2S2eRqMUY7Hd0qSpPGTYRWevOQLS8oHW5791KG1dTH2SEmSpOacbL4Eu3bc2aLMQ2zYdCQAO7fd2rz2PpuPY3p6unndiYkJgKHVHuY177z1tua19znumKFe8w+uu6F57f0e/UgAHrx5W/Pa+56weU3+vZLG1bhMNrdHSpIkNWeQkiRJ6mhchvZc/kCSJKkje6QkSVJzY9IhZZCSJEntOUdKkiSpo3GZI2WQkiRJzRmkJEmSOhqXoT0/tSdJkpqrJW7LkeSwJBcnub739dAFzjshyaeSXJvkmiQn9ntvg5QkSRp35wGXVNUpwCW95/N5H/CmqnoscDpwR783NkhJkqTmdlctaVums4D39h6/F/i5uSckORXYUFUXA1TV/VX1QL83NkhJkqTmqmpJW5ItSaZmbVuWUG5TVd3Wq3sbcNQ85zwKuCfJXyf5apI3JVnf742dbC5JkprbvXtpvUxVNQlMLnQ8yaeBo+c59Lq9LLEB+GngJ4Cbgb8AfgF412Iv6twjleRvFzn2v1Pj5OSC1yxJktaopfZI7cX7PaeqHjfPdiGwI8kxAL2v88192gZ8tapuqqpdwEeAJ/aru2iPVJKF3iDAaYtczOzUWLt23NmvHZIkaQ1pvPzBVuAc4I29rxfOc85lwKFJjqyqO4FnAVP93rjf0N5lwGeZCU5zHdLvzSVJkubTeBWpNwJ/meRcZobtXgyQ5MnAL1XVK6rqh0l+DbgkSYAvA+/o98b9gtS1wH+qquvnHkhyyxIvQpIkqbmq+g7w7Hn2TwGvmPX8YuAJS3nvfkHqt1h4HtV/XkohSZKkPdbELWKq6sOLHJ53VVBJkqR+frh797CbsCKWs47U+SvWCkmStKY0XpBzYPp9au/KhQ4Bm1a+OZIkaS0Y4Wy0JP3mSG0CngfcPWd/gM8PpEWSJGnsrYk5UsBFwMaqunzugSSXDqRFkiRp7I3ycN1S9Jtsfu4ix85e+eZIkiStHt5rT5IkNbcmeqQkSZIGYa3MkZIkSVpxBilJkqSOdo9HjiINEuGYfKskSRo7GXYDVrsmPVI7t93aosxD7LP5OACmp6eb156YmOCb37mned0TDz8EgO333N+89rGHbBza9xqG9+e8Fq8Z4Oa77m1e+4TDDuaym7Y1r/svHrEZgBvvmLuc3uCdfNShQ/1zltTfcm4RI0mStKYZpCRJkjoySEmSJHVkkJIkSerIICVJktSRQUqSJKkjg5QkSVJHBilJkqSODFKSJEkdGaQkSZI6MkhJkiR1ZJCSJEnqyCAlSZLUkUFKkiSpo0WDVJKDkvxekvcnOXvOsf+5yOu2JJlKMjU5OblSbZUkSRopG/ocfw9wPfBXwC8meRFwdlX9AHjqQi+qqklgT4KqndtuXYm2SpIkjZR+Q3snV9V5VfWRqjoT+Arwd0kOb9A2SZKkkdavR2q/JOuqajdAVf1Okm3A54CNA2+dJEnSCOvXI/VR4Fmzd1TVe4H/Ajw4qEZJkiStBov2SFXVbyyw/xNJfncwTZIkSVodlrP8wfkr1gpJkqRVaNEeqSRXLnQI2LTyzZEkSVo9+k023wQ8D7h7zv4Anx9IiyRJklaJfkHqImBjVV0+90CSSwfSIkmSpFWi32Tzcxc5dvZCxyRJktYC77UnSZLUkUFKkiSpI4OUJElSR6mqQdcYeAFJktRJht2A1c4eKUmSpI76LX+wIh781i0tyjzEvg8/HoDp6enmtScmJvin629uXvdfnnICANvvub957WMP2Ti07zXAzu23N6+9z7FHc8f0A83rHjVxAAC33H1f89rHH3oQALfe3f7P+rhDJ4b2sw1w4x1zl9MbvJOPOpQfXHdD87r7PfqRADz4zfa/x/Y98YTmNaXlsEdKkiSpI4OUJElSRwYpSZKkjgxSkiRJHRmkJEmSOjJISZIkdWSQkiRJ6sggJUmS1JFBSpIkqSODlCRJUkcGKUmSpI4MUpIkSR0ZpCRJkjpaNEglOTrJHyd5W5LDk/xWkq8l+cskxyzyui1JppJMTU5OrnyrJUmSRsCGPsf/FPgYcCDwGeDPgJ8FzgL+pPf1R1TVJLAnQdWD37plJdoqSZI0UvoN7W2qqv9RVW8EDqmqC6rq5qr6H8DDG7RPkiRpZPULUrOPv2/OsfUr3BZJkqRVpV+QujDJRoCq+q97diZ5JHDdIBsmSZI06hadI1VVr19g/w1JPjaYJkmSJK0Oy1n+4PwVa4UkSdIqtGiPVJIrFzoEbFr55kiSJK0e/ZY/2AQ8D7h7zv4Anx9IiyRJklaJfkHqImBjVV0+90CSSwfSIkmSpFWi32Tzcxc5dvbKN0eSJGn18F57kiRJHRmkJEmSOjJISZIkdWSQkiRJ6ihVNegaAy8gSZI6ybAbsNr1W/5gRUxPT7co8xATExNDrf2DG7/RvO5+J58EwK13t7++XVEAAAAKLklEQVTm4w6dWJN/zsO85l077mxee8OmIwF48OZtzWvve8Jmdt56W/O6+xx3DAA7b9/RvvbRm9bk36th/HzBzM+YtFQO7UmSJHVkkJIkSerIICVJktSRQUqSJKkjg5QkSVJHBilJkqSODFKSJEkdGaQkSZI6MkhJkiR1ZJCSJEnqyCAlSZLUkUFKkiSpI4OUJElSR0sOUkmOGkRDJEmSVptFg1SSw+ZshwNfSnJoksMWed2WJFNJpiYnJ1e80ZIkSaNgQ5/j3wa+NWffccBXgAIeMd+LqmoS2JOganp6ejltlCRJGkn9hvZ+A7gOOLOqTqqqk4BtvcfzhihJkqS1YtEgVVVvBl4BvD7JW5JMMNMTJUmStOb1nWxeVduq6sXAZ4CLgQMG3ipJkqRVYK8/tVdVHwWeCTwHIMnLB9UoSZKk1WBJyx9U1feq6qre0/MH0B5JkqRVY9FP7SW5cqFDwKaVb44kSdLq0W/5g03A84C75+wP8PmBtEiSJGmV6BekLgI2VtXlcw8kuXQgLZIkSVolFg1SVXXuIsfOXvnmSJIkrR7etFiSJKkjg5QkSVJHBilJkqSOUjXwO754SxlJkkZTht2A1c4eKUmSpI76LX+wIqanp1uUeYiJiQkAbrxj7hJYg3fyUYdy+c23Na972gnHAPC9y7/WvPbDTnv80OrC8P6ch/mzffHXrm9e+7mPPwWAX33fhc1rv+Xnz+J9f//l5nV//qefBMCHvrjQ+sSD8+KnPGGoP2MPfvPm5rX3PfEEHvzWLc3rAuz78OO5ZvudzeueeuyRzWtq5dgjJUmS1JFBSpIkqSODlCRJUkcGKUmSpI4MUpIkSR0ZpCRJkjoySEmSJHVkkJIkSerIICVJktSRQUqSJKkjg5QkSVJHBilJkqSODFKSJEkdLRqkkpwx6/HBSd6V5Mokf55k0+CbJ0mSNLr69Uj97qzHvw/cBvwb4DLg7Qu9KMmWJFNJpiYnJ5ffSkmSpBG0YQnnPrmqTus9fmuScxY6saomgT0Jqqanp7u2T5IkaWT1C1JHJflVIMBBSVJV1Tvm/CpJkrSm9QtD7wAmgI3Ae4EjAJIcDVw+2KZJkiSNtkV7pKrq/AX2357kM4NpkiRJ0uqwnOG5eUOWJEnSWrFoj1SSKxc6BLj8gSRJWtP6TTbfBDwPuHvO/gCfH0iLJEmSVol+QeoiYGNV/cjE8iSXDqRFkiRJq0S/yebnLnLs7JVvjiRJ0urhWlCSJEkdGaQkSZI6MkhJkiR1ZJCSJEnqKP/n1nkDM/ACkiSpkwy7Aatdix6pdN2S/KflvN7aq6Ou17x2anvNa6P2WrzmVfz91jKN+tDeFmuvibrDrL0Wr3mYtb3mtVF7LV7zMGsP85rXvFEPUpIkSSPLICVJktTRqAepSWuvibrDrL0Wr3mYtb3mtVF7LV7zMGsP85rXvBaf2pMkSRpLo94jJUmSNLJGNkglOSPJdUluSHJew7rvTnJHkqta1ezVPT7JZ5Jcm+TqJK9uWHv/JF9KckWv9vmtavfqr0/y1SQXNa77zSRfS3J5kqnGtQ9J8uEkX+/9mf/LBjUf3bvWPdt9SV4z6Lqz6v8/vZ+vq5J8IMn+jeq+ulfz6kFf73y/P5IcluTiJNf3vh7asPaLe9e9O8mTG9Z9U+9n+8okf5PkkIa1f7tX9/Ikn0pybIu6s479WpJKcsRK112odpLfSnLrrL/bPzOI2prfSAapJOuBtwHPB04FXpbk1Ebl/xQ4o1Gt2XYB/6WqHgs8Ffjlhtf8A+BZVfXjwGnAGUme2qg2wKuBaxvWm+2ZVXVaVQ3kH5lF/CHwiap6DPDjNLj+qrqud62nAU8CHgD+ZtB1AZIcB/wK8OSqehywHnhpg7qPA14JnM7M9/kFSU4ZYMk/5Ud/f5wHXFJVpwCX9J63qn0V8G+Bzw2o5kJ1LwYeV1VPAP4Z+M2Gtd9UVU/o/ZxfBLy+UV2SHA88F7h5ADUXrQ28dc/f76r6+ADra46RDFLM/NK7oapuqqoHgQ8CZ7UoXFWfA+5qUWtO3duq6iu9x9PM/MN6XKPaVVX3957u09uaTJ5Lshn4WeCdLeqNgiQHAU8H3gVQVQ9W1T2Nm/Fs4Maq+lbDmhuAhyXZABwAbG9Q87HAF6rqgaraBXwWeOGgii3w++Ms4L29x+8Ffq5V7aq6tqquG0S9PnU/1ft+A3wB2Nyw9n2znh7IAH6XLfLvxFuB3xhEzb2orSEZ1SB1HHDLrOfbaBQqRkGSE4GfAL7YsOb6JJcDdwAXV1Wr2n/AzC+e3Y3qzVbAp5J8OUnLBe0eAdwJvKc3pPnOJAc2rA8zvUEfaFWsqm4F3szM/9RvA+6tqk81KH0V8PQkhyc5APgZ4PgGdWfbVFW3wcx/mICjGtcftl8E/rZlwSS/k+QW4N8zmB6p+WqeCdxaVVe0qDePV/WGNN89qOFjzW9Ug9R8y9aviY8XJtkI/BXwmjn/sxqoqvphryt8M3B6b0hkoJK8ALijqr486FoLeFpVPZGZIeRfTvL0RnU3AE8E/riqfgL4LoMb7vkRSfYFzgQ+1LDmocz0zJwEHAscmOQ/DLpuVV0LXMDMUNMngCuYGUZXA0lex8z3+89a1q2q11XV8b26rxp0vV5Ifx2NQts8/hg4mZmpGbcBvz+kdqxJoxqktvHQ/zVups0wwFAl2YeZEPVnVfXXw2hDb4jpUtrME3sacGaSbzIzfPusJP+rQV0Aqmp77+sdzMwVOr1R6W3Atlm9fh9mJli18nzgK1W1o2HN5wDfqKo7q2on8NfAT7YoXFXvqqonVtXTmRkSub5F3Vl2JDkGoPf1jsb1hyLJOcALgH9fw1tn58+BFzWoczIz/0m4ovf7bDPwlSRHN6hNVe3o/Wd4N/AO2v0uE6MbpC4DTklyUu9/zy8Ftg65TQOVJMzMmbm2qt7SuPaRez5Vk+RhzPyj9/VB162q36yqzVV1IjN/xn9XVQPvpQBIcmCSiT2PgX/NzDDQwFXV7cAtSR7d2/Vs4JoWtXteRsNhvZ6bgacmOaD3s/5sGn3AIMlRva8nMDPxuvW1bwXO6T0+B7iwcf3mkpwBvBY4s6oeaFx79ocJzqTN77KvVdVRVXVi7/fZNuCJvb/rA7cnqPe8kEa/y9RTVSO5MTOX4Z+BG4HXNaz7AWa6Rncy85fh3EZ1f4qZ4csrgct72880qv0E4Ku92lcBrx/Cn/czgIsa1nsEM8M8VwBXt/wZ69U/DZjqfc8/AhzaqO4BwHeAg4fwZ3w+M/+oXQW8H9ivUd2/ZyaoXgE8e8C1fuT3B3A4M5/Wu7739bCGtV/Ye/wDYAfwyUZ1b2Bmnuue32V/0vCa/6r3M3Yl8FHguBZ15xz/JnBEw2t+P/C13jVvBY4Z1M+4249urmwuSZLU0agO7UmSJI08g5QkSVJHBilJkqSODFKSJEkdGaQkSZI6MkhJkiR1ZJCSJEnqyCAlSZLU0f8PM2VSf2FAf1cAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 792x648 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "mask = np.zeros_like(corr, dtype=np.bool)\n",
    "mask[np.triu_indices_from(mask)] = True\n",
    "\n",
    "# Set up the matplotlib figure\n",
    "f, ax = plt.subplots(figsize=(11, 9))\n",
    "\n",
    "# Generate a custom diverging colormap\n",
    "cmap = sns.diverging_palette(220, 10, as_cmap=True)\n",
    "\n",
    "# Draw the heatmap with the mask and correct aspect ratio\n",
    "sns.heatmap(corr, mask=mask, cmap=cmap, center=0,\n",
    "            square=True, linewidths=.5, cbar_kws={\"shrink\": .5})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 69,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.axes._subplots.AxesSubplot at 0x26b0e8d6160>"
      ]
     },
     "execution_count": 69,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 792x648 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#We can observe feature 4,3 and 9,10 are highly correlated, this might lead to multicollinearity\n",
    "#we can also observe that feature 0,6,11 have very less correlation with variable 15 which is our dependent variable\n",
    "\n",
    "# So we decide to drop features 0,4,6,9,11 and convert the DataFrame to a NumPy array\n",
    "\n",
    "data = data.drop([0,4,6,9,11],axis=1)\n",
    "\n",
    "corr = data.corr()\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "\n",
    "mask = np.zeros_like(corr, dtype=np.bool)\n",
    "mask[np.triu_indices_from(mask)] = True\n",
    "\n",
    "# Set up the matplotlib figure\n",
    "f, ax = plt.subplots(figsize=(11, 9))\n",
    "\n",
    "# Generate a custom diverging colormap\n",
    "cmap = sns.diverging_palette(220, 10, as_cmap=True)\n",
    "\n",
    "# Draw the heatmap with the mask and correct aspect ratio\n",
    "sns.heatmap(corr, mask=mask, cmap=cmap, center=0,\n",
    "            square=True, linewidths=.5, cbar_kws={\"shrink\": .5})\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 70,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Now we will scale the data using MinMaxScaler\n",
    "\n",
    "from sklearn.preprocessing import MinMaxScaler\n",
    "\n",
    "data = data.values\n",
    "\n",
    "# We will split independent variables(x) and dependent variable(y)\n",
    "x = data[:,0:9] \n",
    "y = data[:,10]\n",
    "\n",
    "#Scaling the data\n",
    "scale = MinMaxScaler(feature_range=(0,1))\n",
    "new_x = scale.fit_transform(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 71,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[[1.560e+02 0.000e+00 2.000e+00 ... 6.800e+01 0.000e+00 0.000e+00]\n",
      " [3.280e+02 4.460e+00 2.000e+00 ... 1.100e+01 5.600e+02 0.000e+00]\n",
      " [8.900e+01 5.000e-01 2.000e+00 ... 9.600e+01 8.240e+02 0.000e+00]\n",
      " ...\n",
      " [9.700e+01 1.350e+01 3.000e+00 ... 6.700e+01 1.000e+00 1.000e+00]\n",
      " [2.000e+01 2.050e-01 2.000e+00 ... 9.600e+01 7.500e+02 1.000e+00]\n",
      " [1.970e+02 3.375e+00 2.000e+00 ... 0.000e+00 0.000e+00 1.000e+00]]\n"
     ]
    }
   ],
   "source": [
    "#let check how our data looks like now\n",
    "print(data)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 89,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Now we will split the data into train(80%) and test(20%) set to build a model\n",
    "\n",
    "from sklearn.model_selection import train_test_split\n",
    "\n",
    "x_train, x_test, y_train, y_test = train_test_split(x, y, test_size=0.30)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 90,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "KNeighborsClassifier(algorithm='auto', leaf_size=30, metric='minkowski',\n",
       "           metric_params=None, n_jobs=None, n_neighbors=5, p=2,\n",
       "           weights='uniform')"
      ]
     },
     "execution_count": 90,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Now we will build our first model using KNN\n",
    "\n",
    "from sklearn.neighbors import KNeighborsClassifier  \n",
    "\n",
    "kmodel = KNeighborsClassifier(n_neighbors=5)  \n",
    "kmodel.fit(x_train, y_train) "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 91,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy:  0.6618357487922706\n",
      "[[49 37]\n",
      " [33 88]]\n"
     ]
    }
   ],
   "source": [
    "# To check our model performance, we will check the confusion matrix ie, True +ve,-ve and False +ve,-ve\n",
    "\n",
    "from sklearn.metrics import confusion_matrix\n",
    "\n",
    "predicted = kmodel.predict(x_test)\n",
    "modelscore = kmodel.score(x_test,y_test)\n",
    "\n",
    "print(\"Accuracy: \", modelscore)\n",
    "\n",
    "print(confusion_matrix(y_test,predicted))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 92,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\jspar\\Anaconda3\\lib\\site-packages\\sklearn\\linear_model\\logistic.py:433: FutureWarning: Default solver will be changed to 'lbfgs' in 0.22. Specify a solver to silence this warning.\n",
      "  FutureWarning)\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "LogisticRegression(C=1.0, class_weight=None, dual=False, fit_intercept=True,\n",
       "          intercept_scaling=1, max_iter=100, multi_class='warn',\n",
       "          n_jobs=None, penalty='l2', random_state=None, solver='warn',\n",
       "          tol=0.0001, verbose=0, warm_start=False)"
      ]
     },
     "execution_count": 92,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Now we will build our second model using Logistic Regression\n",
    "\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "\n",
    "# Initialize a Logistic Regression classifier and fit model on train set\n",
    "\n",
    "lmodel = LogisticRegression()\n",
    "\n",
    "lmodel.fit(x_train,y_train)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 93,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Accuracy:  0.8502415458937198\n",
      "[[78  8]\n",
      " [23 98]]\n"
     ]
    }
   ],
   "source": [
    "# Now again we predict the values of dependent variable using new model and check model accuracy\n",
    "predicted = lmodel.predict(x_test)\n",
    "\n",
    "print(\"Accuracy: \", lmodel.score(x_test,y_test))\n",
    "\n",
    "print(confusion_matrix(y_test,predicted))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 94,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 432x288 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "#checking the ROC curve\n",
    "from sklearn.metrics import roc_curve\n",
    "\n",
    "fpr,tpr,thresholds = roc_curve(y_test , predicted)\n",
    "\n",
    "plt.plot([0,1], [0,1], 'k--')\n",
    "plt.plot(fpr,tpr)\n",
    "plt.xlabel(\"False positive\")\n",
    "plt.ylabel(\"True positive\")\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "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>0</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>accuracy</th>\n",
       "      <td>0.869565</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>recall</th>\n",
       "      <td>0.851240</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>precision</th>\n",
       "      <td>0.919643</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>roc_auc_score</th>\n",
       "      <td>0.873294</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                      0\n",
       "accuracy       0.869565\n",
       "recall         0.851240\n",
       "precision      0.919643\n",
       "roc_auc_score  0.873294"
      ]
     },
     "execution_count": 100,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from sklearn.datasets import make_classification\n",
    "from sklearn.model_selection import train_test_split\n",
    "from sklearn.linear_model import LogisticRegression\n",
    "from sklearn.metrics import accuracy_score, confusion_matrix, recall_score, roc_auc_score, precision_score\n",
    "THRESHOLD = 0.4\n",
    "preds = np.where(lmodel.predict_proba(x_test)[:,1] > THRESHOLD, 1, 0)\n",
    "\n",
    "pd.DataFrame(data=[accuracy_score(y_test, preds), recall_score(y_test, preds),\n",
    "                   precision_score(y_test, preds), roc_auc_score(y_test, preds)], \n",
    "             index=[\"accuracy\", \"recall\", \"precision\", \"roc_auc_score\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.7.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}