-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathLab08_Tutorial_more-dplyr.html
626 lines (483 loc) · 17 KB
/
Lab08_Tutorial_more-dplyr.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
<!DOCTYPE html>
<html lang="" xml:lang="">
<head>
<title>Lab08_more-dplyr</title>
<meta charset="utf-8" />
<meta name="author" content="曾子軒 Dennis Tseng" />
<script src="libs/header-attrs-2.6/header-attrs.js"></script>
<link href="libs/remark-css-0.0.1/default.css" rel="stylesheet" />
<link href="libs/remark-css-0.0.1/metropolis.css" rel="stylesheet" />
<link href="libs/remark-css-0.0.1/metropolis-fonts.css" rel="stylesheet" />
</head>
<body>
<textarea id="source">
class: center, middle, inverse, title-slide
# Lab08_more-dplyr
## Lab06_dplyr-select-across
### 曾子軒 Dennis Tseng
### 台大新聞所 NTU Journalism
### 2021/04/27
---
<style type="text/css">
.remark-slide-content {
padding: 1em 1em 1em 1em;
font-size: 28px;
}
.my-one-page-font {
padding: 1em 1em 1em 1em;
font-size: 20px;
/*xaringan::inf_mr()*/
}
</style>
# 今日重點
- 分組
- AS06 Preview
- dplyr: more
- Lab08 Practice
---
class: inverse, center, middle
# 分組
---
class: inverse, center, middle
# [AS06](https://p4css.github.io/R4CSS_TA/AS06_Visualizing-Text-Data.html)
---
# dplyr 的未竟之業 - select()
- 懶人的福音，幫助你快速選 column
- operator: `:`, `!`, `&`, `|`, `c()`
- selection helpers:
- specific columns: `everything()`, `last_col()`
- matching patterns: `starts_with()`, `ends_with()`, `contains()`, `matches()`, `num_range()`
- character vector: `all_of()`, `any_of()`
- 搭配 function: `where()`
---
```r
library(tidyverse)
df_marriage <- read_csv("data/Lab04/109Q4_county_marriage.csv") %>%
mutate(across(where(is.character), ~iconv(.,from = "BIG5", to = "UTF8"))) %>% slice(-1) %>% mutate(across(matches("MARRY"), ~as.integer(.))) %>%
`colnames<-`(str_to_lower(colnames(.)))
head(df_marriage, 3)
```
```
## # A tibble: 3 x 7
## county_id county marry_cp_cnt marry_cnt marry_m_cnt marry_f_cnt info_time
## <chr> <chr> <int> <int> <int> <int> <chr>
## 1 65000 新北市 6529 580 189 391 109Y4S
## 2 63000 臺北市 3856 422 207 215 109Y4S
## 3 68000 桃園市 3986 370 107 263 109Y4S
```
---
# dplyr 的未竟之業 - select()
- operator: `:`, `!`, `&`, `|`, `c()`
```r
df_marriage %>% slice(1)
```
```
## # A tibble: 1 x 7
## county_id county marry_cp_cnt marry_cnt marry_m_cnt marry_f_cnt info_time
## <chr> <chr> <int> <int> <int> <int> <chr>
## 1 65000 新北市 6529 580 189 391 109Y4S
```
```r
df_marriage %>% select(county:marry_cnt) %>% slice(1)
```
```
## # A tibble: 1 x 3
## county marry_cp_cnt marry_cnt
## <chr> <int> <int>
## 1 新北市 6529 580
```
```r
df_marriage %>% select(1:2, 4) %>% slice(1)
```
```
## # A tibble: 1 x 3
## county_id county marry_cnt
## <chr> <chr> <int>
## 1 65000 新北市 580
```
```r
df_marriage %>% select(!marry_cnt) %>% slice(1)
```
```
## # A tibble: 1 x 6
## county_id county marry_cp_cnt marry_m_cnt marry_f_cnt info_time
## <chr> <chr> <int> <int> <int> <chr>
## 1 65000 新北市 6529 189 391 109Y4S
```
---
# dplyr 的未竟之業 - select()
- specific columns: `everything()`, `last_col()`
```r
df_marriage %>% select(info_time, everything()) %>% slice(1)
```
```
## # A tibble: 1 x 7
## info_time county_id county marry_cp_cnt marry_cnt marry_m_cnt marry_f_cnt
## <chr> <chr> <chr> <int> <int> <int> <int>
## 1 109Y4S 65000 新北市 6529 580 189 391
```
```r
df_marriage %>% select(-county_id, everything(), county_id) %>% slice(1)
```
```
## # A tibble: 1 x 7
## county marry_cp_cnt marry_cnt marry_m_cnt marry_f_cnt info_time county_id
## <chr> <int> <int> <int> <int> <chr> <chr>
## 1 新北市 6529 580 189 391 109Y4S 65000
```
---
# dplyr 的未竟之業 - select()
- specific columns: `everything()`, `last_col()`
```r
df_marriage %>% select(last_col()) %>% slice(1)
```
```
## # A tibble: 1 x 1
## info_time
## <chr>
## 1 109Y4S
```
```r
df_marriage %>% select(1:last_col(1)) %>% slice(1)
```
```
## # A tibble: 1 x 6
## county_id county marry_cp_cnt marry_cnt marry_m_cnt marry_f_cnt
## <chr> <chr> <int> <int> <int> <int>
## 1 65000 新北市 6529 580 189 391
```
---
# dplyr 的未竟之業 - select()
- matching patterns: `starts_with()`, `ends_with()`, `contains()`, `matches()`, `num_range()`
```r
df_marriage %>% select(starts_with("marry")) %>% slice(1)
```
```
## # A tibble: 1 x 4
## marry_cp_cnt marry_cnt marry_m_cnt marry_f_cnt
## <int> <int> <int> <int>
## 1 6529 580 189 391
```
```r
df_marriage %>% select(starts_with(c("marry_cp", "county"))) %>% slice(1)
```
```
## # A tibble: 1 x 3
## marry_cp_cnt county_id county
## <int> <chr> <chr>
## 1 6529 65000 新北市
```
---
# dplyr 的未竟之業 - select()
- matching patterns: `starts_with()`, `ends_with()`, `contains()`, `matches()`, `num_range()`
```r
df_marriage %>% select(contains("marry")) %>% slice(1)
```
```
## # A tibble: 1 x 4
## marry_cp_cnt marry_cnt marry_m_cnt marry_f_cnt
## <int> <int> <int> <int>
## 1 6529 580 189 391
```
```r
df_marriage %>% select(contains("marry.*cnt")) %>% slice(1)
```
```
## # A tibble: 1 x 0
```
---
# dplyr 的未竟之業 - select()
- matching patterns: `starts_with()`, `ends_with()`, `contains()`, `matches()`, `num_range()`
- 注意！ `matches()` 放正規表示式
```r
df_marriage %>% select(matches("marry.*cnt")) %>% slice(1)
```
```
## # A tibble: 1 x 4
## marry_cp_cnt marry_cnt marry_m_cnt marry_f_cnt
## <int> <int> <int> <int>
## 1 6529 580 189 391
```
---
# dplyr 的未竟之業 - select()
- selection helpers:
- character vector: `all_of()`, `any_of()`
```r
vars <- c("marry_m_cnt", "marry_f_cnt")
vars2 <- c("marry_m_cnt", "marry_f_cnt", "divorce_m_cnt", "divorce_f_cnt")
df_marriage %>% select(all_of(vars)) %>% slice(1)
```
```
## # A tibble: 1 x 2
## marry_m_cnt marry_f_cnt
## <int> <int>
## 1 189 391
```
```r
df_marriage %>% select(all_of(vars2)) %>% slice(1)
```
```
## Error: Can't subset columns that don't exist.
## x Columns `divorce_m_cnt` and `divorce_f_cnt` don't exist.
```
---
# dplyr 的未竟之業 - select()
- selection helpers:
- character vector: `all_of()`, `any_of()`
```r
df_marriage %>% select(any_of(vars)) %>% slice(1)
```
```
## # A tibble: 1 x 2
## marry_m_cnt marry_f_cnt
## <int> <int>
## 1 189 391
```
```r
df_marriage %>% select(any_of(vars2)) %>% slice(1)
```
```
## # A tibble: 1 x 2
## marry_m_cnt marry_f_cnt
## <int> <int>
## 1 189 391
```
---
# dplyr 的未竟之業 - select()
- selection helpers:
- 搭配 function: `where()`
- 通常跟 `across()` 一起使用
---
# dplyr 的未竟之業 - across()
- 懶人的福音，幫助你對不同 column 使用 function
- Apply a function (or functions) across multiple columns
- 動詞裡面放 `across(.cols = everything(), .fns = NULL, ..., .names = NULL)`
- 先選你要的欄位，接著指定函數
- 欄位部分可以活用上面的教的 selection 方法，函數可以使用完整的或匿名函數
---
# dplyr 的未竟之業 - across()
```r
df_marriage %>% mutate(across(matches("marry_"), ~(./100))) %>% slice(1)
```
```
## # A tibble: 1 x 7
## county_id county marry_cp_cnt marry_cnt marry_m_cnt marry_f_cnt info_time
## <chr> <chr> <dbl> <dbl> <dbl> <dbl> <chr>
## 1 65000 新北市 65.3 5.8 1.89 3.91 109Y4S
```
```r
df_marriage %>% summarise(across(where(is.numeric), ~sum(.)))
```
```
## # A tibble: 1 x 4
## marry_cp_cnt marry_cnt marry_m_cnt marry_f_cnt
## <int> <int> <int> <int>
## 1 36607 3153 993 2160
```
---
# Anonymous Function 匿名函數
- function
- 平常寫函數
- 但為了方便也可以不要寫完整，一次性使用
- `.` 點點代表前面的變數/資料
- 匿名函數的形式
- `~ function(x){x + 5}`
- `~ as.integer(.) + 5`
---
# dplyr 的未竟之業 - across()
```r
df_marriage %>% slice(1)
```
```
## # A tibble: 1 x 7
## county_id county marry_cp_cnt marry_cnt marry_m_cnt marry_f_cnt info_time
## <chr> <chr> <int> <int> <int> <int> <chr>
## 1 65000 新北市 6529 580 189 391 109Y4S
```
```r
df_marriage %>% mutate(across(starts_with("county"), ~str_c(., "-bad"))) %>% slice(1)
```
```
## # A tibble: 1 x 7
## county_id county marry_cp_cnt marry_cnt marry_m_cnt marry_f_cnt info_time
## <chr> <chr> <int> <int> <int> <int> <chr>
## 1 65000-bad 新北市-bad 6529 580 189 391 109Y4S
```
---
# dplyr 的未竟之業 - across()
```r
df_marriage %>% mutate(across(matches("marry") & -matches("marry_cp"), ~(./marry_cnt))) %>% slice(1)
```
```
## # A tibble: 1 x 7
## county_id county marry_cp_cnt marry_cnt marry_m_cnt marry_f_cnt info_time
## <chr> <chr> <int> <dbl> <dbl> <dbl> <chr>
## 1 65000 新北市 6529 1 189 391 109Y4S
```
```r
df_marriage %>% select(matches("marry_.*_cnt"), -starts_with("county"), matches("marry")) %>%
mutate(across(matches("marry") & -matches("marry_cp"), ~(./marry_cnt))) %>% slice(1)
```
```
## # A tibble: 1 x 4
## marry_cp_cnt marry_m_cnt marry_f_cnt marry_cnt
## <int> <dbl> <dbl> <dbl>
## 1 6529 0.326 0.674 1
```
---
# dplyr 的未竟之業 - across()
```r
df_marriage <- read_csv("data/Lab04/109Q4_county_marriage.csv") %>%
mutate(across(where(is.character), ~iconv(.,from = "BIG5", to = "UTF8"))) %>%
slice(-1) %>%
mutate(across(matches("MARRY"), ~as.integer(.))) %>%
`colnames<-`(str_to_lower(colnames(.)))
```
---
# dplyr 的未竟之業 - rowwise(), c_across()
```r
df_marriage %>% rowwise() %>% mutate(
marry_sum = sum(c_across(marry_cp_cnt:marry_f_cnt)),
marry_mean = mean(c_across(marry_cp_cnt:marry_f_cnt))
) %>% ungroup()
```
```
## # A tibble: 22 x 9
## county_id county marry_cp_cnt marry_cnt marry_m_cnt marry_f_cnt info_time
## <chr> <chr> <int> <int> <int> <int> <chr>
## 1 65000 新北市 6529 580 189 391 109Y4S
## 2 63000 臺北市 3856 422 207 215 109Y4S
## 3 68000 桃園市 3986 370 107 263 109Y4S
## 4 66000 臺中市 4837 381 130 251 109Y4S
## 5 67000 臺南市 2706 185 57 128 109Y4S
## 6 64000 高雄市 4139 343 112 231 109Y4S
## 7 10002 宜蘭縣 725 62 11 51 109Y4S
## 8 10004 新竹縣 1003 71 13 58 109Y4S
## 9 10005 苗栗縣 859 75 19 56 109Y4S
## 10 10007 彰化縣 1882 161 32 129 109Y4S
## # … with 12 more rows, and 2 more variables: marry_sum <int>, marry_mean <dbl>
```
---
class: inverse, center, middle
# [Lab08](https://p4css.github.io/R4CSS_TA/Lab08_Homework_more-dplyr.html)
</textarea>
<style data-target="print-only">@media screen {.remark-slide-container{display:block;}.remark-slide-scaler{box-shadow:none;}}</style>
<script src="https://remarkjs.com/downloads/remark-latest.min.js"></script>
<script>var slideshow = remark.create({
"highlightStyle": "github",
"highlightLines": true,
"countIncrementalSlides": false,
"self_contained": true
});
if (window.HTMLWidgets) slideshow.on('afterShowSlide', function (slide) {
window.dispatchEvent(new Event('resize'));
});
(function(d) {
var s = d.createElement("style"), r = d.querySelector(".remark-slide-scaler");
if (!r) return;
s.type = "text/css"; s.innerHTML = "@page {size: " + r.style.width + " " + r.style.height +"; }";
d.head.appendChild(s);
})(document);
(function(d) {
var el = d.getElementsByClassName("remark-slides-area");
if (!el) return;
var slide, slides = slideshow.getSlides(), els = el[0].children;
for (var i = 1; i < slides.length; i++) {
slide = slides[i];
if (slide.properties.continued === "true" || slide.properties.count === "false") {
els[i - 1].className += ' has-continuation';
}
}
var s = d.createElement("style");
s.type = "text/css"; s.innerHTML = "@media print { .has-continuation { display: none; } }";
d.head.appendChild(s);
})(document);
// delete the temporary CSS (for displaying all slides initially) when the user
// starts to view slides
(function() {
var deleted = false;
slideshow.on('beforeShowSlide', function(slide) {
if (deleted) return;
var sheets = document.styleSheets, node;
for (var i = 0; i < sheets.length; i++) {
node = sheets[i].ownerNode;
if (node.dataset["target"] !== "print-only") continue;
node.parentNode.removeChild(node);
}
deleted = true;
});
})();
(function() {
"use strict"
// Replace <script> tags in slides area to make them executable
var scripts = document.querySelectorAll(
'.remark-slides-area .remark-slide-container script'
);
if (!scripts.length) return;
for (var i = 0; i < scripts.length; i++) {
var s = document.createElement('script');
var code = document.createTextNode(scripts[i].textContent);
s.appendChild(code);
var scriptAttrs = scripts[i].attributes;
for (var j = 0; j < scriptAttrs.length; j++) {
s.setAttribute(scriptAttrs[j].name, scriptAttrs[j].value);
}
scripts[i].parentElement.replaceChild(s, scripts[i]);
}
})();
(function() {
var links = document.getElementsByTagName('a');
for (var i = 0; i < links.length; i++) {
if (/^(https?:)?\/\//.test(links[i].getAttribute('href'))) {
links[i].target = '_blank';
}
}
})();
// adds .remark-code-has-line-highlighted class to <pre> parent elements
// of code chunks containing highlighted lines with class .remark-code-line-highlighted
(function(d) {
const hlines = d.querySelectorAll('.remark-code-line-highlighted');
const preParents = [];
const findPreParent = function(line, p = 0) {
if (p > 1) return null; // traverse up no further than grandparent
const el = line.parentElement;
return el.tagName === "PRE" ? el : findPreParent(el, ++p);
};
for (let line of hlines) {
let pre = findPreParent(line);
if (pre && !preParents.includes(pre)) preParents.push(pre);
}
preParents.forEach(p => p.classList.add("remark-code-has-line-highlighted"));
})(document);</script>
<script>
slideshow._releaseMath = function(el) {
var i, text, code, codes = el.getElementsByTagName('code');
for (i = 0; i < codes.length;) {
code = codes[i];
if (code.parentNode.tagName !== 'PRE' && code.childElementCount === 0) {
text = code.textContent;
if (/^\\\((.|\s)+\\\)$/.test(text) || /^\\\[(.|\s)+\\\]$/.test(text) ||
/^\$\$(.|\s)+\$\$$/.test(text) ||
/^\\begin\{([^}]+)\}(.|\s)+\\end\{[^}]+\}$/.test(text)) {
code.outerHTML = code.innerHTML; // remove <code></code>
continue;
}
}
i++;
}
};
slideshow._releaseMath(document);
</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-MML-AM_CHTML';
if (location.protocol !== 'file:' && /^https?:/.test(script.src))
script.src = script.src.replace(/^https?:/, '');
document.getElementsByTagName('head')[0].appendChild(script);
})();
</script>
</body>
</html>