-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathcleaning_data.html
More file actions
746 lines (664 loc) · 25.6 KB
/
cleaning_data.html
File metadata and controls
746 lines (664 loc) · 25.6 KB
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
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<meta name="generator" content="pandoc" />
<meta http-equiv="X-UA-Compatible" content="IE=EDGE" />
<title>Data Sources and Processing</title>
<script src="site_libs/header-attrs-2.28/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/flatly.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/navigation-1.1/tabsets.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>
<link href="site_libs/font-awesome-6.4.2/css/all.min.css" rel="stylesheet" />
<link href="site_libs/font-awesome-6.4.2/css/v4-shims.min.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;
}
details > summary > p:only-child {
display: inline;
}
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 the anchor link active (and if it's in a dropdown, also mark that active)
var dropdown = menuAnchor.closest('li.dropdown');
if (window.bootstrap) { // Bootstrap 4+
menuAnchor.addClass('active');
dropdown.find('> .dropdown-toggle').addClass('active');
} else { // Bootstrap 3
menuAnchor.parent().addClass('active');
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, .tabset-dropdown > .nav-tabs.nav-tabs-open:before {
content: "\e259";
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: "\e258";
font-family: 'Glyphicons Halflings';
border: none;
}
.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 -->
</head>
<body>
<div class="container-fluid main-container">
<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-bs-toggle="collapse" data-target="#navbar" data-bs-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">
<li>
<a href="cleaning_data.html">Data</a>
</li>
<li>
<a href="report_graphics.html">Report</a>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" data-bs-toggle="dropdown" aria-expanded="false">
Analysis
<span class="caret"></span>
</a>
<ul class="dropdown-menu" role="menu">
<li>
<a href="elk_analysis.html">Elk Analysis</a>
</li>
<li>
<a href="water_analysis.html">Water Analysis</a>
</li>
<li>
<a href="weather_analysis.html">Weather Analysis</a>
</li>
<li>
<a href="land_cover_analysis.html">Land Cover Analysis</a>
</li>
</ul>
</li>
</ul>
<ul class="nav navbar-nav navbar-right">
<li>
<a href="about_team.html">Meet the Team</a>
</li>
<li>
<a href="https://github.com/brooklynnrm/Elk-Migration.github.io.git">
<span class="fa fa-github fa-lg"></span>
</a>
</li>
</ul>
</div><!--/.nav-collapse -->
</div><!--/.container -->
</div><!--/.navbar -->
<div id="header">
<h1 class="title toc-ignore">Data Sources and Processing</h1>
</div>
<p>Library load</p>
<pre class="r"><code>library(dplyr)</code></pre>
<pre><code>##
## Attaching package: 'dplyr'</code></pre>
<pre><code>## The following objects are masked from 'package:stats':
##
## filter, lag</code></pre>
<pre><code>## The following objects are masked from 'package:base':
##
## intersect, setdiff, setequal, union</code></pre>
<pre class="r"><code>library(tidyverse)</code></pre>
<pre><code>## ── Attaching core tidyverse packages ─────────── tidyverse 2.0.0 ──
## ✔ forcats 1.0.0 ✔ readr 2.1.5
## ✔ ggplot2 3.5.1 ✔ stringr 1.5.1
## ✔ lubridate 1.9.3 ✔ tibble 3.2.1
## ✔ purrr 1.0.2 ✔ tidyr 1.3.1</code></pre>
<pre><code>## ── Conflicts ───────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag() masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors</code></pre>
<pre class="r"><code>library(stringr)
library(raster)</code></pre>
<pre><code>## Loading required package: sp
##
## Attaching package: 'raster'
##
## The following object is masked from 'package:dplyr':
##
## select</code></pre>
<pre class="r"><code>library(sf)</code></pre>
<pre><code>## Linking to GEOS 3.10.2, GDAL 3.4.2, PROJ 8.2.1; sf_use_s2() is TRUE</code></pre>
<pre class="r"><code>library(terra) </code></pre>
<pre><code>## terra 1.7.65
##
## Attaching package: 'terra'
##
## The following object is masked from 'package:tidyr':
##
## extract</code></pre>
<pre class="r"><code>library(geosphere)
library(leaflet)
library(leaflet.extras2)</code></pre>
<div id="elk-data-source" class="section level2">
<h2>Elk Data Source</h2>
<p>Our main data set is the Elk GPS collar data from National Elk Refuge
(2006-2015) published by the Northern Rocky Mountain Science Center in
2018. The data follows 17 adult female elk captured in the National Elk
Refuge in their migration to Yellowstone National Park. Elk that did not
migrate to Yellowstone National Park were not included in the data set.
The data is available <a
href="https://www.usgs.gov/data/elk-gps-collar-data-national-elk-refuge-2006-2015">here</a>.</p>
</div>
<div id="cleaning-elk-data" class="section level2">
<h2>Cleaning Elk Data</h2>
<p>The elk data contains a unique ID for each of the 17 elk. It includes
a date-time variable and coordinates. There are To clean the elk data,
we we drop the <code>tz</code> timezone variable, because it is
homogeneous. We drop the <code>utm_x</code> and <code>utm_y</code>
variables because they are simply another kind of location tracking, and
we already have latitude and longitude. We create the
<code>dist_km</code> variable, which measures the distance traveled in
kilometers between observed points using the <code>distHaversine</code>
function from the <code>geosphere</code> package. The length of the
shortest line between two points on a sphere is the Haversine
distance.</p>
<pre class="r"><code>elk =
read_csv('raw_data/Elk GPS collar data from National Elk Refuge 2006-2015.csv') |>
janitor::clean_names() |>
dplyr::mutate(
day = day(dt),
hour = hour(dt),
dist_km =
ifelse(
elk_id == lag(elk_id),
geosphere::distHaversine(cbind(long, lat), cbind(lag(long), lag(lat)))/1000,
NA)
) |>
dplyr::select(
elk_id,
dt,
year,
month,
day,
hour,
lat,
long,
dist_km
)</code></pre>
<pre><code>## Rows: 104913 Columns: 11
## ── Column specification ───────────────────────────────────────────
## Delimiter: ","
## chr (1): TZ
## dbl (9): Elk_ID, UTM_X, UTM_Y, Zone, Lat, Long, month, year, t
## dttm (1): DT
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.</code></pre>
</div>
<div id="land-cover-cleaning" class="section level2">
<h2>Land Cover Cleaning</h2>
<p>Our second data set is the land cover data in the state of Wyoming
published by the GAP Analysis Project in 2019. This data set uses
satellite imagery from 2011 to get land cover data accurate to thirty
square meters. While our elk migration data ranges from 2006 to 2015, we
make the assumption that land coverage in the form of water or
vegetation stays approximately constant over time. The data is available
<a
href="https://www.usgs.gov/programs/gap-analysis-project/science/land-cover-data-download">here</a>.</p>
<p>We use the <a
href="https://bookdown.org/mcwimberly/gdswr-book/coordinate-reference-systems.html#reprojecting-raster-data">terra
package</a> to import and transform the data into latitude and longitude
coordinates. We save a cleaned, cropped version of the land cover data.
For the purpose of this website, we won’t evaluate the code chunk
below.</p>
<pre class="r"><code>land = rast('raw_data/land_cover/land_cover.tif')
# Reprojecting in latitude and longitude
land_coord = project(land, "EPSG:4326")
plot(land_coord)
# Subset to the relevant area
min_long = elk |> pull(long) |> min()
max_long = elk |> pull(long) |> max()
rng_long = abs(min_long - max_long)
lowerleftlon = min_long - 0.1 * rng_long
upperrightlon = max_long + 0.1 * rng_long
min_lat = elk |> pull(lat) |> min()
max_lat = elk |> pull(lat) |> max()
rng_lat = abs(min_lat - max_lat)
lowerleftlat = min_lat - 0.1 * rng_lat
upperrightlat = max_lat + 0.1 * rng_lat
# cropping
small_land_coord = crop(
land_coord,
extent(lowerleftlon, upperrightlon, lowerleftlat, upperrightlat))
plot(small_land_coord)
# writing raster
terra::writeRaster(small_land_coord, 'clean_data/land_cover.tif', overwrite=TRUE)</code></pre>
<p>Using terra’s <code>extract</code> function, we get the land cover at
the relevant points of the analysis, i.e. the locations of the elk.</p>
<pre class="r"><code>small_land_coord = rast('clean_data/land_cover.tif')
temp_elk =
elk |>
mutate(
longitude = long,
latitude = lat) |>
dplyr::select(
longitude,
latitude
)
elk_land_cover = terra::extract(x = small_land_coord, y = temp_elk)</code></pre>
<p>We add the elk land cover data to the elk data frame. We save the elk
data frame.</p>
<pre class="r"><code>elk =
elk |>
mutate(land_cover = elk_land_cover$land_cover)
elk |> write.csv('clean_data/elk.csv', row.names = FALSE)</code></pre>
</div>
<div id="cleaning-water-quality-data" class="section level2">
<h2>Cleaning Water Quality Data</h2>
<p>The water quality data is sourced from the Greater Yellowstone
Network and published by the National Park Service. The data contains
readings on a variety of water quality measures including mineral
composition, flow speed, and temperature. The two locations relevant to
this analysis are GRTE_SNR01 and GRTE_SNR02, where the elk migrate. The
data is available <a
href="https://catalog.data.gov/dataset/greater-yellowstone-network-published-water-quality-data-through-2023-from-the-bicawq01-g-">here</a></p>
<div id="locations" class="section level3">
<h3>Locations</h3>
<p>This data set gives the locations that water was sampled from. We
drop the <code>org_code</code> variable because it is homogenous.</p>
<pre class="r"><code>water_quality_locations =
read_csv('raw_data/water_quality/Locations.csv')|>
janitor::clean_names() |>
dplyr::select(
location_id,
location_name,
park_code,
location_type,
latitude,
longitude
)</code></pre>
<pre><code>## Rows: 18 Columns: 40
## ── Column specification ───────────────────────────────────────────
## Delimiter: ","
## chr (38): Org_Code, Park_Code, Location_ID, Location_Name, Location_Type, La...
## dbl (2): Latitude, Longitude
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.</code></pre>
</div>
<div id="results" class="section level3">
<h3>Results</h3>
<p>Here we read in the results of the water quality sampling.</p>
<pre class="r"><code>water_quality_results =
read_csv('raw_data/water_quality/Results.csv')|>
janitor::clean_names()</code></pre>
<pre><code>## Warning: One or more parsing issues, call `problems()` on your data frame
## for details, e.g.:
## dat <- vroom(...)
## problems(dat)</code></pre>
<pre><code>## Rows: 35397 Columns: 89
## ── Column specification ───────────────────────────────────────────
## Delimiter: ","
## chr (87): Org_Code, Project_ID, Location_ID, Activity_ID, Activity_Type, Me...
## date (2): Activity_Start_Date, Analysis_Start_Date
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.</code></pre>
<p>We find the most common observations.</p>
<pre class="r"><code>common_obs =
water_quality_results |>
drop_na(result_text) |>
group_by(characteristic_name) |>
summarize(n = n())|>
arrange(desc(n)) |>
filter(
n > 875,
characteristic_name != "Weather Comments (text)") |>
pull(characteristic_name)</code></pre>
<p>We filter for the most common observations. We filter for readings
that we can use, given in the <code>acceptable_readings</code> variable.
We replace non-detected values with zero. We select for the relevant
columns</p>
<pre class="r"><code>acceptable_readings = c("Detected and Quantified", "Not Detected", "Present Below Quantification Limit")
water_quality_results=
water_quality_results |>
filter(
characteristic_name %in% common_obs,
result_detection_condition %in% acceptable_readings) |>
mutate(
result_text = stringr::str_replace(result_text, "NULL", "0"),
result_unit = stringr::str_replace(result_unit, "None", ""),
characteristic_name = paste0(characteristic_name, " ", result_unit) |> trimws(),
year = year(activity_start_date),
month = month(activity_start_date),
day = day(activity_start_date)
) |>
dplyr::select(
location_id,
activity_id,
activity_type,
activity_start_date,
year,
month,
day,
characteristic_name,
result_text
) </code></pre>
</div>
<div id="combining-water-data" class="section level3">
<h3>Combining Water Data</h3>
<p>We aggregate the data at the month level by taking the minimum, mean,
and maximum readings. We filter for the GRTE_SNR01 and GRTE_SNR02
locations, which are the two relevant locations to our analysis. We save
the water quality data in raw, cleaned, and wide formats for ease of
use.</p>
<pre class="r"><code>water_quality =
water_quality_locations |>
left_join(water_quality_results) |>
filter(location_id %in% c('GRTE_SNR01', 'GRTE_SNR02'))</code></pre>
<pre><code>## Joining with `by = join_by(location_id)`</code></pre>
<pre class="r"><code>water_quality2 =
water_quality %>%
mutate(
result_text = stringr::str_replace(result_text, 'LOW', '1'),
result_text = stringr::str_replace(result_text, 'ABOVE NORMAL', '3'),
result_text = stringr::str_replace(result_text, 'NORMAL', '2'),
result_text = stringr::str_replace(result_text, 'FLOOD', '4'),
) |>
group_by(
location_id,
location_name,
year,
month,
characteristic_name
) %>%
summarize(
monthly_mean = mean(as.numeric(result_text),na.rm = TRUE),
monthly_min = min(as.numeric(result_text),na.rm = TRUE),
monthly_max = max(as.numeric(result_text),na.rm = TRUE)
) </code></pre>
<pre><code>## `summarise()` has grouped output by 'location_id',
## 'location_name', 'year', 'month'. You can override using the
## `.groups` argument.</code></pre>
<pre class="r"><code>water_quality |> write.csv('clean_data/water_quality.csv', row.names = FALSE)
water_quality2 |> write.csv('clean_data/water_quality2.csv', row.names = FALSE)
clean_water =
water_quality2 %>%
pivot_wider(
names_from = characteristic_name,
values_from = c('monthly_mean', 'monthly_min', 'monthly_max')
)
write.csv(clean_water, 'clean_data/clean_water.csv', row.names = FALSE)</code></pre>
</div>
</div>
<div id="reading-in-weather-data" class="section level2">
<h2>Reading in Weather Data</h2>
<p>To explore the relationship between temperature, precipitation, and
migration, we use the Global Historical Climatology Network’s data. The
data is available <a
href="https://www.ncei.noaa.gov/products/land-based-station/global-historical-climatology-network-daily">here</a></p>
<p>We read in the data, we filter for the four closest stations to the
elk, we filter for the correct date range, and finally we average the
temperature and snowfall across the stations. Since we only have weather
data at four points in the general area of the elk, we average the
readings from the four stations.</p>
<pre class="r"><code># closest four stations
four_stations <-
c("SNAKE RIVER STATION, WY US", "MORAN 5 WNW, WY US", "BURRO HILL WYOMING, WY US", "MOOSE 1 NNE, WY US")
weather = read_csv("raw_data/raw_weather_data.csv") |>
janitor::clean_names() |>
filter(
name %in% four_stations,
date >= '2006-03-01',
date <= '2015-08-25') |>
group_by(date) |>
summarize(
tavg = mean(tavg, na.rm = TRUE),
tmin = mean(tmin, na.rm = TRUE),
tmax = mean(tmin, na.rm = TRUE),
prcp = mean(prcp, na.rm = TRUE),
snow = mean(snow, na.rm = TRUE),
snwd = mean(snwd, na.rm = TRUE),
) |>
mutate(
year = year(date),
month = month(date),
day = day(date)
)</code></pre>
<pre><code>## Warning: One or more parsing issues, call `problems()` on your data frame
## for details, e.g.:
## dat <- vroom(...)
## problems(dat)</code></pre>
<pre><code>## Rows: 54745 Columns: 31
## ── Column specification ───────────────────────────────────────────
## Delimiter: ","
## chr (2): STATION, NAME
## dbl (21): LATITUDE, LONGITUDE, ELEVATION, AWND, DAPR, MDPR, PRCP, SNOW, SNW...
## lgl (7): MDSF, WT02, WT03, WT04, WT05, WT06, WT11
## date (1): DATE
##
## ℹ Use `spec()` to retrieve the full column specification for this data.
## ℹ Specify the column types or set `show_col_types = FALSE` to quiet this message.</code></pre>
<pre class="r"><code>weather |> write.csv('clean_data/weather.csv', row.names = FALSE)</code></pre>
</div>
<div id="combining-all-data" class="section level2">
<h2>Combining all data</h2>
<p>We combine the data for ease of comparison. We begin with the elk
data, then left join the weather data by date. We find the closest water
quality location, then join on the relevant water quality data. We save
the data.</p>
<pre class="r"><code>all_data =
elk %>%
left_join(weather |> dplyr::select(-date)) %>%
mutate(
dist_to_GRTE_SNR01 = distHaversine(cbind(long, lat), c(-110.6716, 44.10177))/1000,
dist_to_GRTE_SNR02 = distHaversine(cbind(long, lat), c(-110.7159, 43.65261))/1000,
location_id =
ifelse(dist_to_GRTE_SNR01 < dist_to_GRTE_SNR02, 'GRTE_SNR01', 'GRTE_SNR02')
) %>%
left_join(clean_water) %>%
dplyr::select(-dist_to_GRTE_SNR01, -dist_to_GRTE_SNR02)</code></pre>
<pre><code>## Joining with `by = join_by(year, month, day)`
## Joining with `by = join_by(year, month, location_id)`</code></pre>
<pre class="r"><code>all_data |> drop_na(location_name)</code></pre>
<pre><code>## # A tibble: 36,754 × 78
## elk_id dt year month day hour lat long dist_km
## <dbl> <dttm> <dbl> <dbl> <int> <int> <dbl> <dbl> <dbl>
## 1 572 2006-06-30 19:00:00 2006 7 30 19 44.1 -110. 1.13
## 2 572 2006-07-01 00:01:00 2006 7 1 0 44.1 -110. 0.117
## 3 572 2006-07-01 05:00:00 2006 7 1 5 44.1 -110. 0.962
## 4 572 2006-07-01 10:01:00 2006 7 1 10 44.1 -110. 0.156
## 5 572 2006-07-01 15:01:00 2006 7 1 15 44.1 -110. 0.369
## 6 572 2006-07-01 20:00:00 2006 7 1 20 44.1 -110. 0.182
## 7 572 2006-07-02 01:01:00 2006 7 2 1 44.1 -110. 0.127
## 8 572 2006-07-02 06:01:00 2006 7 2 6 44.1 -110. 0.800
## 9 572 2006-07-02 11:03:00 2006 7 2 11 44.1 -110. 0.0780
## 10 572 2006-07-02 16:00:00 2006 7 2 16 44.1 -110. 0.719
## # ℹ 36,744 more rows
## # ℹ 69 more variables: land_cover <dbl>, tavg <dbl>, tmin <dbl>, tmax <dbl>,
## # prcp <dbl>, snow <dbl>, snwd <dbl>, location_id <chr>, location_name <chr>,
## # `monthly_mean_Arsenic mg/l` <dbl>, `monthly_mean_Calcium mg/l` <dbl>,
## # `monthly_mean_Chloride mg/l` <dbl>,
## # `monthly_mean_Dissolved oxygen (DO) mg/l` <dbl>,
## # `monthly_mean_Flow cfs` <dbl>, …</code></pre>
<pre class="r"><code>all_data |> write.csv('clean_data/all_data.csv', row.names = FALSE)</code></pre>
</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 -->
<!-- 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>