-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathCA_data_analyzing.html
759 lines (652 loc) · 30.9 KB
/
CA_data_analyzing.html
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<meta name="generator" content="pandoc" />
<meta http-equiv="X-UA-Compatible" content="IE=EDGE" />
<title>California Data Analyzing</title>
<script src="site_libs/header-attrs-2.11/header-attrs.js"></script>
<script src="site_libs/jquery-3.6.0/jquery-3.6.0.min.js"></script>
<meta name="viewport" content="width=device-width, initial-scale=1" />
<link href="site_libs/bootstrap-3.3.5/css/yeti.min.css" rel="stylesheet" />
<script src="site_libs/bootstrap-3.3.5/js/bootstrap.min.js"></script>
<script src="site_libs/bootstrap-3.3.5/shim/html5shiv.min.js"></script>
<script src="site_libs/bootstrap-3.3.5/shim/respond.min.js"></script>
<style>h1 {font-size: 34px;}
h1.title {font-size: 38px;}
h2 {font-size: 30px;}
h3 {font-size: 24px;}
h4 {font-size: 18px;}
h5 {font-size: 16px;}
h6 {font-size: 12px;}
code {color: inherit; background-color: rgba(0, 0, 0, 0.04);}
pre:not([class]) { background-color: white }</style>
<script src="site_libs/jqueryui-1.11.4/jquery-ui.min.js"></script>
<link href="site_libs/tocify-1.9.1/jquery.tocify.css" rel="stylesheet" />
<script src="site_libs/tocify-1.9.1/jquery.tocify.js"></script>
<script src="site_libs/navigation-1.1/tabsets.js"></script>
<script src="site_libs/navigation-1.1/codefolding.js"></script>
<link href="site_libs/highlightjs-9.12.0/default.css" rel="stylesheet" />
<script src="site_libs/highlightjs-9.12.0/highlight.js"></script>
<script src="site_libs/htmlwidgets-1.5.4/htmlwidgets.js"></script>
<script src="site_libs/plotly-binding-4.10.0/plotly.js"></script>
<script src="site_libs/typedarray-0.1/typedarray.min.js"></script>
<link href="site_libs/crosstalk-1.1.1/css/crosstalk.css" rel="stylesheet" />
<script src="site_libs/crosstalk-1.1.1/js/crosstalk.min.js"></script>
<link href="site_libs/plotly-htmlwidgets-css-2.5.1/plotly-htmlwidgets.css" rel="stylesheet" />
<script src="site_libs/plotly-main-2.5.1/plotly-latest.min.js"></script>
<link href="site_libs/font-awesome-5.1.0/css/all.css" rel="stylesheet" />
<link href="site_libs/font-awesome-5.1.0/css/v4-shims.css" rel="stylesheet" />
<style type="text/css">
code{white-space: pre-wrap;}
span.smallcaps{font-variant: small-caps;}
span.underline{text-decoration: underline;}
div.column{display: inline-block; vertical-align: top; width: 50%;}
div.hanging-indent{margin-left: 1.5em; text-indent: -1.5em;}
ul.task-list{list-style: none;}
</style>
<style type="text/css">code{white-space: pre;}</style>
<script type="text/javascript">
if (window.hljs) {
hljs.configure({languages: []});
hljs.initHighlightingOnLoad();
if (document.readyState && document.readyState === "complete") {
window.setTimeout(function() { hljs.initHighlighting(); }, 0);
}
}
</script>
<style type = "text/css">
.main-container {
max-width: 940px;
margin-left: auto;
margin-right: auto;
}
img {
max-width:100%;
}
.tabbed-pane {
padding-top: 12px;
}
.html-widget {
margin-bottom: 20px;
}
button.code-folding-btn:focus {
outline: none;
}
summary {
display: list-item;
}
pre code {
padding: 0;
}
</style>
<style type="text/css">
.dropdown-submenu {
position: relative;
}
.dropdown-submenu>.dropdown-menu {
top: 0;
left: 100%;
margin-top: -6px;
margin-left: -1px;
border-radius: 0 6px 6px 6px;
}
.dropdown-submenu:hover>.dropdown-menu {
display: block;
}
.dropdown-submenu>a:after {
display: block;
content: " ";
float: right;
width: 0;
height: 0;
border-color: transparent;
border-style: solid;
border-width: 5px 0 5px 5px;
border-left-color: #cccccc;
margin-top: 5px;
margin-right: -10px;
}
.dropdown-submenu:hover>a:after {
border-left-color: #adb5bd;
}
.dropdown-submenu.pull-left {
float: none;
}
.dropdown-submenu.pull-left>.dropdown-menu {
left: -100%;
margin-left: 10px;
border-radius: 6px 0 6px 6px;
}
</style>
<script type="text/javascript">
// manage active state of menu based on current page
$(document).ready(function () {
// active menu anchor
href = window.location.pathname
href = href.substr(href.lastIndexOf('/') + 1)
if (href === "")
href = "index.html";
var menuAnchor = $('a[href="' + href + '"]');
// mark it active
menuAnchor.tab('show');
// if it's got a parent navbar menu mark it active as well
menuAnchor.closest('li.dropdown').addClass('active');
// Navbar adjustments
var navHeight = $(".navbar").first().height() + 15;
var style = document.createElement('style');
var pt = "padding-top: " + navHeight + "px; ";
var mt = "margin-top: -" + navHeight + "px; ";
var css = "";
// offset scroll position for anchor links (for fixed navbar)
for (var i = 1; i <= 6; i++) {
css += ".section h" + i + "{ " + pt + mt + "}\n";
}
style.innerHTML = "body {" + pt + "padding-bottom: 40px; }\n" + css;
document.head.appendChild(style);
});
</script>
<!-- tabsets -->
<style type="text/css">
.tabset-dropdown > .nav-tabs {
display: inline-table;
max-height: 500px;
min-height: 44px;
overflow-y: auto;
border: 1px solid #ddd;
border-radius: 4px;
}
.tabset-dropdown > .nav-tabs > li.active:before {
content: "";
font-family: 'Glyphicons Halflings';
display: inline-block;
padding: 10px;
border-right: 1px solid #ddd;
}
.tabset-dropdown > .nav-tabs.nav-tabs-open > li.active:before {
content: "";
border: none;
}
.tabset-dropdown > .nav-tabs.nav-tabs-open:before {
content: "";
font-family: 'Glyphicons Halflings';
display: inline-block;
padding: 10px;
border-right: 1px solid #ddd;
}
.tabset-dropdown > .nav-tabs > li.active {
display: block;
}
.tabset-dropdown > .nav-tabs > li > a,
.tabset-dropdown > .nav-tabs > li > a:focus,
.tabset-dropdown > .nav-tabs > li > a:hover {
border: none;
display: inline-block;
border-radius: 4px;
background-color: transparent;
}
.tabset-dropdown > .nav-tabs.nav-tabs-open > li {
display: block;
float: none;
}
.tabset-dropdown > .nav-tabs > li {
display: none;
}
</style>
<!-- code folding -->
<style type="text/css">
.code-folding-btn { margin-bottom: 4px; }
</style>
<style type="text/css">
#TOC {
margin: 25px 0px 20px 0px;
}
@media (max-width: 768px) {
#TOC {
position: relative;
width: 100%;
}
}
@media print {
.toc-content {
/* see https://github.com/w3c/csswg-drafts/issues/4434 */
float: right;
}
}
.toc-content {
padding-left: 30px;
padding-right: 40px;
}
div.main-container {
max-width: 1200px;
}
div.tocify {
width: 20%;
max-width: 260px;
max-height: 85%;
}
@media (min-width: 768px) and (max-width: 991px) {
div.tocify {
width: 25%;
}
}
@media (max-width: 767px) {
div.tocify {
width: 100%;
max-width: none;
}
}
.tocify ul, .tocify li {
line-height: 20px;
}
.tocify-subheader .tocify-item {
font-size: 0.90em;
}
.tocify .list-group-item {
border-radius: 0px;
}
</style>
</head>
<body>
<div class="container-fluid main-container">
<!-- setup 3col/9col grid for toc_float and main content -->
<div class="row">
<div class="col-xs-12 col-sm-4 col-md-3">
<div id="TOC" class="tocify">
</div>
</div>
<div class="toc-content col-xs-12 col-sm-8 col-md-9">
<div class="navbar navbar-default navbar-fixed-top" role="navigation">
<div class="container">
<div class="navbar-header">
<button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#navbar">
<span class="icon-bar"></span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
</button>
<a class="navbar-brand" href="index.html">Home</a>
</div>
<div id="navbar" class="navbar-collapse collapse">
<ul class="nav navbar-nav">
</ul>
<ul class="nav navbar-nav navbar-right">
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-expanded="false">
Overview
<span class="caret"></span>
</a>
<ul class="dropdown-menu" role="menu">
<li>
<a href="overview.html">Project Overview</a>
</li>
<li>
<a href="usa_analyzing.html">United States Overview</a>
</li>
</ul>
</li>
<li>
<a href="report.html">Report</a>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-expanded="false">
States of Choice
<span class="caret"></span>
</a>
<ul class="dropdown-menu" role="menu">
<li>
<a href="CA_data_analyzing.html">California</a>
</li>
<li>
<a href="FL_data_analyzing.html">Florida</a>
</li>
<li>
<a href="NY_data_analyzing.html">New York City</a>
</li>
<li>
<a href="Ohio_data_analyzing.html">Ohio</a>
</li>
</ul>
</li>
<li>
<a href="https://paulawucu.shinyapps.io/shiny_dashboard_upload/">Interactive Maps</a>
</li>
<li>
<a href="regression_us.html">Regression</a>
</li>
<li>
<a href="fact.html">Facts About</a>
</li>
<li>
<a href="https://youtu.be/nDrmCsTRqqs">
<span class="fa fa-play-circle fa-sm"></span>
</a>
</li>
<li>
<a href="https://github.com/paulawucu/final_project">
<span class="fa fa-github fa-lg"></span>
</a>
</li>
</ul>
</div><!--/.nav-collapse -->
</div><!--/.container -->
</div><!--/.navbar -->
<div id="header">
<div class="btn-group pull-right float-right">
<button type="button" class="btn btn-default btn-xs btn-secondary btn-sm dropdown-toggle" data-toggle="dropdown" aria-haspopup="true" aria-expanded="false"><span>Code</span> <span class="caret"></span></button>
<ul class="dropdown-menu dropdown-menu-right" style="min-width: 50px;">
<li><a id="rmd-show-all-code" href="#">Show All Code</a></li>
<li><a id="rmd-hide-all-code" href="#">Hide All Code</a></li>
</ul>
</div>
<h1 class="title toc-ignore">California Data Analyzing</h1>
</div>
<p><strong>Import the Libraries and Data Cleaning</strong></p>
<pre class="r"><code>drug_overdose = read_csv("./data/VSRR_Provisional_Drug_Overdose_Death_Counts.csv") %>%
janitor::clean_names()
state_level = c(state.name[1:8], "District of Columbia", state.name[9:32],"New York City", state.name[33:50])
drug_overdose_52 =
drug_overdose %>%
filter(!(state_name %in% c("United States"))) %>%
relocate(state_name) %>%
mutate(month = factor(month, levels = month.name), # change month and year to factor
year = factor(year),
state_name = factor(state_name, levels = state_level)) %>%
arrange(state_name) %>%
group_by(state_name, year) %>%
mutate(month = sort(month))
drug_overdose_death =
drug_overdose_52 %>%
select(-c(state, footnote_symbol, percent_complete, period, percent_pending_investigation, predicted_value)) %>%
filter(indicator %in% c("Number of Deaths", "Percent with drugs specified", "Number of Drug Overdose Deaths"))
drug_categories =
drug_overdose_52 %>%
ungroup() %>%
select(-c(state, footnote_symbol, percent_complete, period, percent_pending_investigation, footnote, predicted_value)) %>%
filter(str_detect(indicator, "T4"))</code></pre>
<div id="by-drug-type" class="section level2">
<h2>By Drug Type</h2>
<pre class="r"><code>CA_death =
drug_overdose_52 %>%
filter(state_name %in% "California",
indicator %in% c("Number of Deaths", "Number of Drug Overdose Deaths")) %>%
select(year, month, indicator, deaths = data_value) %>%
pivot_wider(
names_from = indicator,
values_from = deaths
) %>%
janitor::clean_names() %>%
group_by(year, month) %>%
mutate(
percent_overdose_death = number_of_drug_overdose_deaths / number_of_deaths
) %>%
mutate(year = factor(year))
CA_df =
drug_categories %>%
filter(state_name %in% c("California"))
ggplot(CA_df, aes(indicator, data_value))+
geom_boxplot(aes(fill = indicator), alpha = 0.5) +
scale_x_discrete(labels = c("Psychostimulants \n with abuse potential \n (T43.6)", "Methadone \n (T40.3)", "Natural & \n semi-synthetic \n opioids \n (T40.2)", "Natural & semi-\n synthetic opioids, \n incl. methadone \n (T40.2, T40.3)", "Heroin \n (T40.1)", "Cocaine \n (T40.5)", "Synthetic opioids, \n excl. \n methadone \n (T40.4)", "Natural, \n semi-synthetic, & \n synthetic opioids, \n incl. methadone \n (T40.2-T40.4)", "Opioids \n (T40.0-T40.4,\n T40.6)")) +
guides(fill = guide_legend(nrow = 6, byrow = TRUE)) +
labs(
title = "CA Number of Drug Overdose Deaths with Drug Categories (2015 - 2021)",
x = "Drug Categories",
y = "Number of Drug Overdose Deaths",
caption = "Data comes from VSRR_Provisional_Drug_Overdose_Death_Counts dataset."
) </code></pre>
<p><img src="CA_data_analyzing_files/figure-html/unnamed-chunk-3-1.png" width="90%" /></p>
<p>From this graph we can see that highest drug overdose death for California is caused by Synthetic opioids,methadone (T40.4). The following Drug Categories cause high overdose death are Cocaine and semi-synthetic opioids.</p>
<p><br><br></p>
</div>
<div id="by-year" class="section level2">
<h2>By Year</h2>
<pre class="r"><code>ca_death_by_year =
drug_overdose_52 %>%
filter(state_name %in% c("California")) %>%
ungroup() %>%
select(year, month, indicator, data_value) %>%
filter(indicator %in% c("Number of Deaths", "Number of Drug Overdose Deaths")) %>%
pivot_wider(
names_from = indicator,
values_from = data_value
) %>%
janitor::clean_names() %>%
group_by(year, month) %>%
mutate(
percent_overdose_death = number_of_drug_overdose_deaths / number_of_deaths
)
ca_death_by_year %>%
ungroup() %>%
ggplot(aes(x = month, y = percent_overdose_death, color = year)) +
geom_point() +
geom_line(aes(group = year)) +
labs(
title = "Percent of Drug Overdose Deaths over Total Number of Deaths by Year in CA",
x = "Months",
y = "Percent of Drug Overdose Deaths",
caption = "Data comes from VSRR_Provisional_Drug_Overdose_Death_Counts dataset from 2015 to 2021)."
)</code></pre>
<p><img src="CA_data_analyzing_files/figure-html/unnamed-chunk-4-1.png" width="100%" /></p>
<p>In the graph of Drug Overdose Deaths with Drug Categories by Year, I can observe that year 2020 have higher number of drug overdose death than other years, which can be cause by covid-19 and self-isolation.</p>
<pre class="r"><code>ggplot(ca_death_by_year, aes(x = month, y = percent_overdose_death, group = year, color = year)) +
labs(title = "") +
geom_line() +
geom_point() +
facet_grid(.~year) +
labs(
title = "Percent of Number of Drug Overdose Deaths with Drug Categories by Year in CA",
x = "Month",
y = "Percent of Drug Overdose Deaths",
caption = "Data comes from VSRR_Provisional_Drug_Overdose_Death_Counts dataset between 2015 and 2021."
) +
theme(axis.text.x = element_text(angle = 90, hjust = 1)) </code></pre>
<p><img src="CA_data_analyzing_files/figure-html/unnamed-chunk-5-1.png" width="90%" /></p>
<p>In the graph of Each month Drug Overdose Death Within a Year, we are able to see the increasing trend of drug overdose in continuous years. Cause by the COVID-19, there is large increase in number of drug overdose death.</p>
<p><br><br></p>
</div>
<div id="drug-year" class="section level2">
<h2>Drug ~ Year</h2>
<pre class="r"><code>CA_df %>%
filter(year %in% (2019:2021)) %>%
ggplot(aes(x = year, y = data_value, color = indicator)) +
geom_smooth(aes(group = indicator), se = FALSE) +
guides(color = guide_legend(nrow = 6, byrow = TRUE)) +
labs(
title = "Number of Drug Overdose Deaths by Year in CA",
x = "Year",
y = "Number of Drug Overdose Deaths",
caption = "Data comes from VSRR_Provisional_Drug_Overdose_Death_Counts dataset between 2019 and 2021."
)</code></pre>
<p><img src="CA_data_analyzing_files/figure-html/unnamed-chunk-6-1.png" width="90%" /></p>
<p>In the graph of Number of Drug Overdose Deaths with Drug Categories by Year, we can see that drug overdose death keep increasing over the years with almost all type of drug. Since we miss data from 2015-2018, so we just include 2019-2021 in this graph.</p>
<p><br><br></p>
</div>
<div id="by-age-and-race" class="section level2">
<h2>By Age and Race</h2>
<pre class="r"><code>ca_death_by_age =
read_csv("./data/agegroup_race_state_year_99-19.csv") %>%
janitor::clean_names() %>%
select(state, year, ten_year_age_groups, race, deaths, population) %>%
filter(state %in% c("California")) %>%
mutate(year = factor(year),
crude_rate = deaths/population * 100000)
ca_death_by_age %>%
mutate(ten_year_age_groups = gsub("years", "", ten_year_age_groups)) %>%
ggplot(aes(x = ten_year_age_groups , y = crude_rate, fill = race)) +
geom_boxplot(alpha = 0.5)+
labs(y = "Drug Overdose Death Crude Rates", x = "Age Groups")+
facet_grid(~race) +
labs(
title = "Number of Drug Overdose Deaths with Drug Categories by Age and Race in CA") +
theme(axis.text.x = element_text(angle = 90, vjust = 0.4, hjust = 1))</code></pre>
<p><img src="CA_data_analyzing_files/figure-html/unnamed-chunk-7-1.png" width="90%" /></p>
<p>Overdose death with Drug Categories by Age and Race shows that people among age 55-64 across all races have highest death rate. Black or African Americans have highest death rate among all races.</p>
<p><br><br></p>
</div>
<div id="income" class="section level2">
<h2>Income</h2>
<p><strong>Number of death vs median household income</strong></p>
<pre class="r"><code>CA_income_df =
read_csv("./data/median_household_income_CA.csv") %>%
janitor::clean_names() %>%
select(year, household_income_by_race, household_income_by_race_moe, geography) %>%
filter(str_detect(geography,"CA|California|United States"),
year >= "2015") %>%
mutate(year = factor(year))
CA_income_df %>%
mutate(text_label = str_c("Year: ", year, "\nMedian Household Income: $", household_income_by_race,
"\nMargin of error: ± $", household_income_by_race_moe)) %>%
plot_ly(
x = ~year, y = ~household_income_by_race, color = ~geography, text = ~text_label,
alpha = 0.5, type = "scatter", mode = "markers+lines", colors = "viridis", error_y = ~list(array = household_income_by_race_moe)) %>%
layout(
title = "Median Household Income: CA vs. The U.S",
xaxis = list(title = "Year"),
yaxis = list(title = "Median Household Income"))</code></pre>
<div id="htmlwidget-f9a5ee7975379247b2ff" style="width:90%;height:576px;" class="plotly html-widget"></div>
<script type="application/json" data-for="htmlwidget-f9a5ee7975379247b2ff">{"x":{"visdat":{"f8826f0a4dda":["function () ","plotlyVisDat"]},"cur_data":"f8826f0a4dda","attrs":{"f8826f0a4dda":{"x":{},"y":{},"text":{},"mode":"markers+lines","error_y":{},"color":{},"colors":"viridis","alpha":0.5,"alpha_stroke":1,"sizes":[10,100],"spans":[1,20],"type":"scatter"}},"layout":{"margin":{"b":40,"l":60,"t":25,"r":10},"title":"Median Household Income: CA vs. The U.S","xaxis":{"domain":[0,1],"automargin":true,"title":"Year","type":"category","categoryorder":"array","categoryarray":["2015","2016","2017","2018","2019"]},"yaxis":{"domain":[0,1],"automargin":true,"title":"Median Household Income"},"hovermode":"closest","showlegend":true},"source":"A","config":{"modeBarButtonsToAdd":["hoverclosest","hovercompare"],"showSendToCloud":false},"data":[{"x":["2019","2018","2017","2016","2015"],"y":[80440,75277,71805,67739,64500],"text":["Year: 2019<br />Median Household Income: $80440<br />Margin of error: ± $313","Year: 2018<br />Median Household Income: $75277<br />Margin of error: ± $317","Year: 2017<br />Median Household Income: $71805<br />Margin of error: ± $294","Year: 2016<br />Median Household Income: $67739<br />Margin of error: ± $356","Year: 2015<br />Median Household Income: $64500<br />Margin of error: ± $395"],"mode":"markers+lines","error_y":{"color":"rgba(68,1,84,0.5)","array":[118,313,850,1028,1908]},"type":"scatter","name":"California","marker":{"color":"rgba(68,1,84,0.5)","line":{"color":"rgba(68,1,84,1)"}},"textfont":{"color":"rgba(68,1,84,0.5)"},"error_x":{"color":"rgba(68,1,84,0.5)"},"line":{"color":"rgba(68,1,84,0.5)"},"xaxis":"x","yaxis":"y","frame":null},{"x":["2019","2018","2017","2016","2015"],"y":[77774,72563,69992,65950,62544],"text":["Year: 2019<br />Median Household Income: $77774<br />Margin of error: ± $850","Year: 2018<br />Median Household Income: $72563<br />Margin of error: ± $671","Year: 2017<br />Median Household Income: $69992<br />Margin of error: ± $679","Year: 2016<br />Median Household Income: $65950<br />Margin of error: ± $495","Year: 2015<br />Median Household Income: $62544<br />Margin of error: ± $556"],"mode":"markers+lines","error_y":{"color":"rgba(65,68,135,0.5)","array":[1965,94,317,671,906]},"type":"scatter","name":"Los Angeles-Long Beach-Anaheim, CA","marker":{"color":"rgba(65,68,135,0.5)","line":{"color":"rgba(65,68,135,1)"}},"textfont":{"color":"rgba(65,68,135,0.5)"},"error_x":{"color":"rgba(65,68,135,0.5)"},"line":{"color":"rgba(65,68,135,0.5)"},"xaxis":"x","yaxis":"y","frame":null},{"x":["2019","2018","2017","2016","2015"],"y":[70954,65671,61994,58236,56087],"text":["Year: 2019<br />Median Household Income: $70954<br />Margin of error: ± $1028","Year: 2018<br />Median Household Income: $65671<br />Margin of error: ± $906","Year: 2017<br />Median Household Income: $61994<br />Margin of error: ± $688","Year: 2016<br />Median Household Income: $58236<br />Margin of error: ± $1104","Year: 2015<br />Median Household Income: $56087<br />Margin of error: ± $983"],"mode":"markers+lines","error_y":{"color":"rgba(42,120,142,0.5)","array":[1474,1779,86,294,679]},"type":"scatter","name":"Riverside-San Bernardino-Ontario, CA","marker":{"color":"rgba(42,120,142,0.5)","line":{"color":"rgba(42,120,142,1)"}},"textfont":{"color":"rgba(42,120,142,0.5)"},"error_x":{"color":"rgba(42,120,142,0.5)"},"line":{"color":"rgba(42,120,142,0.5)"},"xaxis":"x","yaxis":"y","frame":null},{"x":["2019","2018","2017","2016","2015"],"y":[83985,79079,76207,70824,67320],"text":["Year: 2019<br />Median Household Income: $83985<br />Margin of error: ± $1908","Year: 2018<br />Median Household Income: $79079<br />Margin of error: ± $1474","Year: 2017<br />Median Household Income: $76207<br />Margin of error: ± $1049","Year: 2016<br />Median Household Income: $70824<br />Margin of error: ± $995","Year: 2015<br />Median Household Income: $67320<br />Margin of error: ± $1448"],"mode":"markers+lines","error_y":{"color":"rgba(34,168,132,0.5)","array":[688,1049,833,115,356]},"type":"scatter","name":"San Diego-Carlsbad, CA","marker":{"color":"rgba(34,168,132,0.5)","line":{"color":"rgba(34,168,132,1)"}},"textfont":{"color":"rgba(34,168,132,0.5)"},"error_x":{"color":"rgba(34,168,132,0.5)"},"line":{"color":"rgba(34,168,132,0.5)"},"xaxis":"x","yaxis":"y","frame":null},{"x":["2019","2018","2017","2016","2015"],"y":[114696,107898,101714,96677,88518],"text":["Year: 2019<br />Median Household Income: $114696<br />Margin of error: ± $1965","Year: 2018<br />Median Household Income: $107898<br />Margin of error: ± $1779","Year: 2017<br />Median Household Income: $101714<br />Margin of error: ± $833","Year: 2016<br />Median Household Income: $96677<br />Margin of error: ± $1273","Year: 2015<br />Median Household Income: $88518<br />Margin of error: ± $1665"],"mode":"markers+lines","error_y":{"color":"rgba(122,209,81,0.5)","array":[495,1104,995,1273,85]},"type":"scatter","name":"San Francisco-Oakland-Hayward, CA","marker":{"color":"rgba(122,209,81,0.5)","line":{"color":"rgba(122,209,81,1)"}},"textfont":{"color":"rgba(122,209,81,0.5)"},"error_x":{"color":"rgba(122,209,81,0.5)"},"line":{"color":"rgba(122,209,81,0.5)"},"xaxis":"x","yaxis":"y","frame":null},{"x":["2019","2018","2017","2016","2015"],"y":[65712,61937,60336,57617,55775],"text":["Year: 2019<br />Median Household Income: $65712<br />Margin of error: ± $118","Year: 2018<br />Median Household Income: $61937<br />Margin of error: ± $94","Year: 2017<br />Median Household Income: $60336<br />Margin of error: ± $86","Year: 2016<br />Median Household Income: $57617<br />Margin of error: ± $115","Year: 2015<br />Median Household Income: $55775<br />Margin of error: ± $85"],"mode":"markers+lines","error_y":{"color":"rgba(253,231,37,0.5)","array":[395,556,983,1448,1665]},"type":"scatter","name":"United States","marker":{"color":"rgba(253,231,37,0.5)","line":{"color":"rgba(253,231,37,1)"}},"textfont":{"color":"rgba(253,231,37,0.5)"},"error_x":{"color":"rgba(253,231,37,0.5)"},"line":{"color":"rgba(253,231,37,0.5)"},"xaxis":"x","yaxis":"y","frame":null}],"highlight":{"on":"plotly_click","persistent":false,"dynamic":false,"selectize":false,"opacityDim":0.2,"selected":{"opacity":1},"debounce":0},"shinyEvents":["plotly_hover","plotly_click","plotly_selected","plotly_relayout","plotly_brushed","plotly_brushing","plotly_clickannotation","plotly_doubleclick","plotly_deselect","plotly_afterplot","plotly_sunburstclick"],"base_url":"https://plot.ly"},"evals":[],"jsHooks":[]}</script>
<p>From the graph Median Household Income: CA vs. The U.S, we can see that California have higher median household income then US and northern part of California have highest income compare other parts of California.</p>
<p><br></p>
<p><strong>Income and drug overdose death percent by year</strong></p>
<pre class="r"><code>CAincome_drug_df =
CA_death %>%
ungroup() %>%
group_by(year) %>%
summarize(overdose_death_rate = sum(number_of_drug_overdose_deaths)/sum(number_of_deaths)) %>%
inner_join(., CA_income_df %>% filter(geography %in% "California"))
year_death =
CAincome_drug_df %>%
ggplot(aes(x = year, y = overdose_death_rate, group = NA))+
geom_point()+
geom_line()
income_year =
CAincome_drug_df %>%
ggplot(aes(x = year, y = household_income_by_race, group = NA))+
geom_point()+
geom_line()
income_year =
CAincome_drug_df %>%
ggplot(aes(x = year, y = household_income_by_race, group = NA))+
geom_point()+
geom_line()
smooth =
CAincome_drug_df %>%
ggplot(aes(x = household_income_by_race, y = overdose_death_rate, group = NA))+
geom_point() +
labs(y = "Drug Overdose Death Crude Rates", x = "Median Household Income") +
geom_smooth(method = "lm", se = FALSE, color = "royalblue4")
(year_death + income_year)/smooth</code></pre>
<p><img src="CA_data_analyzing_files/figure-html/unnamed-chunk-9-1.png" width="90%" /></p>
<p>From graph income VS drug overdose we can find that higher drug overdose rate have association with higher income.</p>
<p><br><br></p>
</div>
<div id="ca-drug-map" class="section level2">
<h2>CA Drug Map</h2>
<pre class="r"><code>ca_county_df =
read_csv("./data/NCHS_-_Drug_Poisoning_Mortality_by_County__United_States.csv") %>%
janitor::clean_names() %>%
filter(state %in% "California") %>%
select(year, county, population, death_rate = model_based_death_rate) %>%
separate(county, into = c("county", "useless"), sep = " County") %>%
select(-useless) %>%
mutate(year = factor(year),
county = str_to_lower(county)) %>%
relocate(county)</code></pre>
<p>We can see that the highest death rate occur in north California across the years. From the income graph, north California have the highest income compare to other part of California. So we can find that higher drug overdose rate have association with higher income.</p>
<div id="counties-change-5-yr-interval" class="section level3 tabset">
<h3 class="tabset">Counties change, 5-yr interval</h3>
<div id="section" class="section level4">
<h4>2003</h4>
<pre class="r"><code>year_select = 2003
start_county_df = left_join(ca_county_df ,abc, by = "county") %>%
select(county, year, death_rate, fips) %>%
filter(year == year_select)
start_county_df %>%
group_by(fips) %>%
mutate(fips = as.numeric(fips)) %>%
rename(region = fips,
value = death_rate) %>%
county_choropleth(state_zoom = c("california"),
legend = "death_rate")+
highlight_county(start_county_df[which.max(pull(start_county_df, death_rate)),])+
add_text_county(start_county_df[which.max(pull(start_county_df, death_rate)),])</code></pre>
<p><img src="CA_data_analyzing_files/figure-html/unnamed-chunk-12-1.png" width="90%" /></p>
</div>
<div id="section-1" class="section level4">
<h4>2008</h4>
<p><img src="CA_data_analyzing_files/figure-html/unnamed-chunk-13-1.png" width="90%" /></p>
</div>
<div id="section-2" class="section level4">
<h4>2013</h4>
<p><img src="CA_data_analyzing_files/figure-html/unnamed-chunk-14-1.png" width="90%" /></p>
</div>
<div id="section-3" class="section level4">
<h4>2018</h4>
<p><img src="CA_data_analyzing_files/figure-html/unnamed-chunk-15-1.png" width="90%" /></p>
</div>
</div>
</div>
</div>
</div>
</div>
<script>
// add bootstrap table styles to pandoc tables
function bootstrapStylePandocTables() {
$('tr.odd').parent('tbody').parent('table').addClass('table table-condensed');
}
$(document).ready(function () {
bootstrapStylePandocTables();
});
</script>
<!-- tabsets -->
<script>
$(document).ready(function () {
window.buildTabsets("TOC");
});
$(document).ready(function () {
$('.tabset-dropdown > .nav-tabs > li').click(function () {
$(this).parent().toggleClass('nav-tabs-open');
});
});
</script>
<!-- code folding -->
<script>
$(document).ready(function () {
window.initializeCodeFolding("hide" === "show");
});
</script>
<script>
$(document).ready(function () {
// temporarily add toc-ignore selector to headers for the consistency with Pandoc
$('.unlisted.unnumbered').addClass('toc-ignore')
// move toc-ignore selectors from section div to header
$('div.section.toc-ignore')
.removeClass('toc-ignore')
.children('h1,h2,h3,h4,h5').addClass('toc-ignore');
// establish options
var options = {
selectors: "h1,h2,h3",
theme: "bootstrap3",
context: '.toc-content',
hashGenerator: function (text) {
return text.replace(/[.\\/?&!#<>]/g, '').replace(/\s/g, '_');
},
ignoreSelector: ".toc-ignore",
scrollTo: 0
};
options.showAndHide = true;
options.smoothScroll = true;
// tocify
var toc = $("#TOC").tocify(options).data("toc-tocify");
});
</script>
<!-- dynamically load mathjax for compatibility with self-contained -->
<script>
(function () {
var script = document.createElement("script");
script.type = "text/javascript";
script.src = "https://mathjax.rstudio.com/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML";
document.getElementsByTagName("head")[0].appendChild(script);
})();
</script>
</body>
</html>