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
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
|
<!DOCTYPE html>
<html>
<head>
<meta charset="utf-8" />
<meta name="generator" content="pandoc" />
<meta http-equiv="X-UA-Compatible" content="IE=EDGE" />
<meta name="viewport" content="width=device-width, initial-scale=1" />
<title>Row-wise operations</title>
<script>// Pandoc 2.9 adds attributes on both header and div. We remove the former (to
// be compatible with the behavior of Pandoc < 2.8).
document.addEventListener('DOMContentLoaded', function(e) {
var hs = document.querySelectorAll("div.section[class*='level'] > :first-child");
var i, h, a;
for (i = 0; i < hs.length; i++) {
h = hs[i];
if (!/^h[1-6]$/i.test(h.tagName)) continue; // it should be a header h1-h6
a = h.attributes;
while (a.length > 0) h.removeAttribute(a[0].name);
}
});
</script>
<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;
}
.sourceCode {
overflow: visible;
}
</style>
<style type="text/css" data-origin="pandoc">
pre > code.sourceCode { white-space: pre; position: relative; }
pre > code.sourceCode > span { line-height: 1.25; }
pre > code.sourceCode > span:empty { height: 1.2em; }
.sourceCode { overflow: visible; }
code.sourceCode > span { color: inherit; text-decoration: inherit; }
div.sourceCode { margin: 1em 0; }
pre.sourceCode { margin: 0; }
@media screen {
div.sourceCode { overflow: auto; }
}
@media print {
pre > code.sourceCode { white-space: pre-wrap; }
pre > code.sourceCode > span { text-indent: -5em; padding-left: 5em; }
}
pre.numberSource code
{ counter-reset: source-line 0; }
pre.numberSource code > span
{ position: relative; left: -4em; counter-increment: source-line; }
pre.numberSource code > span > a:first-child::before
{ content: counter(source-line);
position: relative; left: -1em; text-align: right; vertical-align: baseline;
border: none; display: inline-block;
-webkit-touch-callout: none; -webkit-user-select: none;
-khtml-user-select: none; -moz-user-select: none;
-ms-user-select: none; user-select: none;
padding: 0 4px; width: 4em;
color: #aaaaaa;
}
pre.numberSource { margin-left: 3em; border-left: 1px solid #aaaaaa; padding-left: 4px; }
div.sourceCode
{ }
@media screen {
pre > code.sourceCode > span > a:first-child::before { text-decoration: underline; }
}
code span.al { color: #ff0000; font-weight: bold; }
code span.an { color: #60a0b0; font-weight: bold; font-style: italic; }
code span.at { color: #7d9029; }
code span.bn { color: #40a070; }
code span.bu { color: #008000; }
code span.cf { color: #007020; font-weight: bold; }
code span.ch { color: #4070a0; }
code span.cn { color: #880000; }
code span.co { color: #60a0b0; font-style: italic; }
code span.cv { color: #60a0b0; font-weight: bold; font-style: italic; }
code span.do { color: #ba2121; font-style: italic; }
code span.dt { color: #902000; }
code span.dv { color: #40a070; }
code span.er { color: #ff0000; font-weight: bold; }
code span.ex { }
code span.fl { color: #40a070; }
code span.fu { color: #06287e; }
code span.im { color: #008000; font-weight: bold; }
code span.in { color: #60a0b0; font-weight: bold; font-style: italic; }
code span.kw { color: #007020; font-weight: bold; }
code span.op { color: #666666; }
code span.ot { color: #007020; }
code span.pp { color: #bc7a00; }
code span.sc { color: #4070a0; }
code span.ss { color: #bb6688; }
code span.st { color: #4070a0; }
code span.va { color: #19177c; }
code span.vs { color: #4070a0; }
code span.wa { color: #60a0b0; font-weight: bold; font-style: italic; }
</style>
<script>
// apply pandoc div.sourceCode style to pre.sourceCode instead
(function() {
var sheets = document.styleSheets;
for (var i = 0; i < sheets.length; i++) {
if (sheets[i].ownerNode.dataset["origin"] !== "pandoc") continue;
try { var rules = sheets[i].cssRules; } catch (e) { continue; }
var j = 0;
while (j < rules.length) {
var rule = rules[j];
// check if there is a div.sourceCode rule
if (rule.type !== rule.STYLE_RULE || rule.selectorText !== "div.sourceCode") {
j++;
continue;
}
var style = rule.style.cssText;
// check if color or background-color is set
if (rule.style.color === '' && rule.style.backgroundColor === '') {
j++;
continue;
}
// replace div.sourceCode by a pre.sourceCode rule
sheets[i].deleteRule(j);
sheets[i].insertRule('pre.sourceCode{' + style + '}', j);
}
}
})();
</script>
<style type="text/css">body {
background-color: #fff;
margin: 1em auto;
max-width: 700px;
overflow: visible;
padding-left: 2em;
padding-right: 2em;
font-family: "Open Sans", "Helvetica Neue", Helvetica, Arial, sans-serif;
font-size: 14px;
line-height: 1.35;
}
#TOC {
clear: both;
margin: 0 0 10px 10px;
padding: 4px;
width: 400px;
border: 1px solid #CCCCCC;
border-radius: 5px;
background-color: #f6f6f6;
font-size: 13px;
line-height: 1.3;
}
#TOC .toctitle {
font-weight: bold;
font-size: 15px;
margin-left: 5px;
}
#TOC ul {
padding-left: 40px;
margin-left: -1.5em;
margin-top: 5px;
margin-bottom: 5px;
}
#TOC ul ul {
margin-left: -2em;
}
#TOC li {
line-height: 16px;
}
table {
margin: 1em auto;
border-width: 1px;
border-color: #DDDDDD;
border-style: outset;
border-collapse: collapse;
}
table th {
border-width: 2px;
padding: 5px;
border-style: inset;
}
table td {
border-width: 1px;
border-style: inset;
line-height: 18px;
padding: 5px 5px;
}
table, table th, table td {
border-left-style: none;
border-right-style: none;
}
table thead, table tr.even {
background-color: #f7f7f7;
}
p {
margin: 0.5em 0;
}
blockquote {
background-color: #f6f6f6;
padding: 0.25em 0.75em;
}
hr {
border-style: solid;
border: none;
border-top: 1px solid #777;
margin: 28px 0;
}
dl {
margin-left: 0;
}
dl dd {
margin-bottom: 13px;
margin-left: 13px;
}
dl dt {
font-weight: bold;
}
ul {
margin-top: 0;
}
ul li {
list-style: circle outside;
}
ul ul {
margin-bottom: 0;
}
pre, code {
background-color: #f7f7f7;
border-radius: 3px;
color: #333;
white-space: pre-wrap;
}
pre {
border-radius: 3px;
margin: 5px 0px 10px 0px;
padding: 10px;
}
pre:not([class]) {
background-color: #f7f7f7;
}
code {
font-family: Consolas, Monaco, 'Courier New', monospace;
font-size: 85%;
}
p > code, li > code {
padding: 2px 0px;
}
div.figure {
text-align: center;
}
img {
background-color: #FFFFFF;
padding: 2px;
border: 1px solid #DDDDDD;
border-radius: 3px;
border: 1px solid #CCCCCC;
margin: 0 5px;
}
h1 {
margin-top: 0;
font-size: 35px;
line-height: 40px;
}
h2 {
border-bottom: 4px solid #f7f7f7;
padding-top: 10px;
padding-bottom: 2px;
font-size: 145%;
}
h3 {
border-bottom: 2px solid #f7f7f7;
padding-top: 10px;
font-size: 120%;
}
h4 {
border-bottom: 1px solid #f7f7f7;
margin-left: 8px;
font-size: 105%;
}
h5, h6 {
border-bottom: 1px solid #ccc;
font-size: 105%;
}
a {
color: #0033dd;
text-decoration: none;
}
a:hover {
color: #6666ff; }
a:visited {
color: #800080; }
a:visited:hover {
color: #BB00BB; }
a[href^="http:"] {
text-decoration: underline; }
a[href^="https:"] {
text-decoration: underline; }
code > span.kw { color: #555; font-weight: bold; }
code > span.dt { color: #902000; }
code > span.dv { color: #40a070; }
code > span.bn { color: #d14; }
code > span.fl { color: #d14; }
code > span.ch { color: #d14; }
code > span.st { color: #d14; }
code > span.co { color: #888888; font-style: italic; }
code > span.ot { color: #007020; }
code > span.al { color: #ff0000; font-weight: bold; }
code > span.fu { color: #900; font-weight: bold; }
code > span.er { color: #a61717; background-color: #e3d2d2; }
</style>
</head>
<body>
<h1 class="title toc-ignore">Row-wise operations</h1>
<p>dplyr, and R in general, are particularly well suited to performing
operations over columns, and performing operations over rows is much
harder. In this vignette, you’ll learn dplyr’s approach centred around
the row-wise data frame created by <code>rowwise()</code>.</p>
<p>There are three common use cases that we discuss in this
vignette:</p>
<ul>
<li>Row-wise aggregates (e.g. compute the mean of x, y, z).</li>
<li>Calling a function multiple times with varying arguments.</li>
<li>Working with list-columns.</li>
</ul>
<p>These types of problems are often easily solved with a for loop, but
it’s nice to have a solution that fits naturally into a pipeline.</p>
<blockquote>
<p>Of course, someone has to write loops. It doesn’t have to be you. —
Jenny Bryan</p>
</blockquote>
<div class="sourceCode" id="cb1"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb1-1"><a href="#cb1-1" tabindex="-1"></a><span class="fu">library</span>(dplyr, <span class="at">warn.conflicts =</span> <span class="cn">FALSE</span>)</span></code></pre></div>
<div id="creating" class="section level2">
<h2>Creating</h2>
<p>Row-wise operations require a special type of grouping where each
group consists of a single row. You create this with
<code>rowwise()</code>:</p>
<div class="sourceCode" id="cb2"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb2-1"><a href="#cb2-1" tabindex="-1"></a>df <span class="ot"><-</span> <span class="fu">tibble</span>(<span class="at">x =</span> <span class="dv">1</span><span class="sc">:</span><span class="dv">2</span>, <span class="at">y =</span> <span class="dv">3</span><span class="sc">:</span><span class="dv">4</span>, <span class="at">z =</span> <span class="dv">5</span><span class="sc">:</span><span class="dv">6</span>)</span>
<span id="cb2-2"><a href="#cb2-2" tabindex="-1"></a>df <span class="sc">%>%</span> <span class="fu">rowwise</span>()</span>
<span id="cb2-3"><a href="#cb2-3" tabindex="-1"></a><span class="co">#> # A tibble: 2 × 3</span></span>
<span id="cb2-4"><a href="#cb2-4" tabindex="-1"></a><span class="co">#> # Rowwise: </span></span>
<span id="cb2-5"><a href="#cb2-5" tabindex="-1"></a><span class="co">#> x y z</span></span>
<span id="cb2-6"><a href="#cb2-6" tabindex="-1"></a><span class="co">#> <int> <int> <int></span></span>
<span id="cb2-7"><a href="#cb2-7" tabindex="-1"></a><span class="co">#> 1 1 3 5</span></span>
<span id="cb2-8"><a href="#cb2-8" tabindex="-1"></a><span class="co">#> 2 2 4 6</span></span></code></pre></div>
<p>Like <code>group_by()</code>, <code>rowwise()</code> doesn’t really
do anything itself; it just changes how the other verbs work. For
example, compare the results of <code>mutate()</code> in the following
code:</p>
<div class="sourceCode" id="cb3"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb3-1"><a href="#cb3-1" tabindex="-1"></a>df <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">m =</span> <span class="fu">mean</span>(<span class="fu">c</span>(x, y, z)))</span>
<span id="cb3-2"><a href="#cb3-2" tabindex="-1"></a><span class="co">#> # A tibble: 2 × 4</span></span>
<span id="cb3-3"><a href="#cb3-3" tabindex="-1"></a><span class="co">#> x y z m</span></span>
<span id="cb3-4"><a href="#cb3-4" tabindex="-1"></a><span class="co">#> <int> <int> <int> <dbl></span></span>
<span id="cb3-5"><a href="#cb3-5" tabindex="-1"></a><span class="co">#> 1 1 3 5 3.5</span></span>
<span id="cb3-6"><a href="#cb3-6" tabindex="-1"></a><span class="co">#> 2 2 4 6 3.5</span></span>
<span id="cb3-7"><a href="#cb3-7" tabindex="-1"></a>df <span class="sc">%>%</span> <span class="fu">rowwise</span>() <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">m =</span> <span class="fu">mean</span>(<span class="fu">c</span>(x, y, z)))</span>
<span id="cb3-8"><a href="#cb3-8" tabindex="-1"></a><span class="co">#> # A tibble: 2 × 4</span></span>
<span id="cb3-9"><a href="#cb3-9" tabindex="-1"></a><span class="co">#> # Rowwise: </span></span>
<span id="cb3-10"><a href="#cb3-10" tabindex="-1"></a><span class="co">#> x y z m</span></span>
<span id="cb3-11"><a href="#cb3-11" tabindex="-1"></a><span class="co">#> <int> <int> <int> <dbl></span></span>
<span id="cb3-12"><a href="#cb3-12" tabindex="-1"></a><span class="co">#> 1 1 3 5 3</span></span>
<span id="cb3-13"><a href="#cb3-13" tabindex="-1"></a><span class="co">#> 2 2 4 6 4</span></span></code></pre></div>
<p>If you use <code>mutate()</code> with a regular data frame, it
computes the mean of <code>x</code>, <code>y</code>, and <code>z</code>
across all rows. If you apply it to a row-wise data frame, it computes
the mean for each row.</p>
<p>You can optionally supply “identifier” variables in your call to
<code>rowwise()</code>. These variables are preserved when you call
<code>summarise()</code>, so they behave somewhat similarly to the
grouping variables passed to <code>group_by()</code>:</p>
<div class="sourceCode" id="cb4"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb4-1"><a href="#cb4-1" tabindex="-1"></a>df <span class="ot"><-</span> <span class="fu">tibble</span>(<span class="at">name =</span> <span class="fu">c</span>(<span class="st">"Mara"</span>, <span class="st">"Hadley"</span>), <span class="at">x =</span> <span class="dv">1</span><span class="sc">:</span><span class="dv">2</span>, <span class="at">y =</span> <span class="dv">3</span><span class="sc">:</span><span class="dv">4</span>, <span class="at">z =</span> <span class="dv">5</span><span class="sc">:</span><span class="dv">6</span>)</span>
<span id="cb4-2"><a href="#cb4-2" tabindex="-1"></a></span>
<span id="cb4-3"><a href="#cb4-3" tabindex="-1"></a>df <span class="sc">%>%</span> </span>
<span id="cb4-4"><a href="#cb4-4" tabindex="-1"></a> <span class="fu">rowwise</span>() <span class="sc">%>%</span> </span>
<span id="cb4-5"><a href="#cb4-5" tabindex="-1"></a> <span class="fu">summarise</span>(<span class="at">m =</span> <span class="fu">mean</span>(<span class="fu">c</span>(x, y, z)))</span>
<span id="cb4-6"><a href="#cb4-6" tabindex="-1"></a><span class="co">#> # A tibble: 2 × 1</span></span>
<span id="cb4-7"><a href="#cb4-7" tabindex="-1"></a><span class="co">#> m</span></span>
<span id="cb4-8"><a href="#cb4-8" tabindex="-1"></a><span class="co">#> <dbl></span></span>
<span id="cb4-9"><a href="#cb4-9" tabindex="-1"></a><span class="co">#> 1 3</span></span>
<span id="cb4-10"><a href="#cb4-10" tabindex="-1"></a><span class="co">#> 2 4</span></span>
<span id="cb4-11"><a href="#cb4-11" tabindex="-1"></a></span>
<span id="cb4-12"><a href="#cb4-12" tabindex="-1"></a>df <span class="sc">%>%</span> </span>
<span id="cb4-13"><a href="#cb4-13" tabindex="-1"></a> <span class="fu">rowwise</span>(name) <span class="sc">%>%</span> </span>
<span id="cb4-14"><a href="#cb4-14" tabindex="-1"></a> <span class="fu">summarise</span>(<span class="at">m =</span> <span class="fu">mean</span>(<span class="fu">c</span>(x, y, z)))</span>
<span id="cb4-15"><a href="#cb4-15" tabindex="-1"></a><span class="co">#> `summarise()` has grouped output by 'name'. You can override using the</span></span>
<span id="cb4-16"><a href="#cb4-16" tabindex="-1"></a><span class="co">#> `.groups` argument.</span></span>
<span id="cb4-17"><a href="#cb4-17" tabindex="-1"></a><span class="co">#> # A tibble: 2 × 2</span></span>
<span id="cb4-18"><a href="#cb4-18" tabindex="-1"></a><span class="co">#> # Groups: name [2]</span></span>
<span id="cb4-19"><a href="#cb4-19" tabindex="-1"></a><span class="co">#> name m</span></span>
<span id="cb4-20"><a href="#cb4-20" tabindex="-1"></a><span class="co">#> <chr> <dbl></span></span>
<span id="cb4-21"><a href="#cb4-21" tabindex="-1"></a><span class="co">#> 1 Mara 3</span></span>
<span id="cb4-22"><a href="#cb4-22" tabindex="-1"></a><span class="co">#> 2 Hadley 4</span></span></code></pre></div>
<p><code>rowwise()</code> is just a special form of grouping, so if you
want to remove it from a data frame, just call
<code>ungroup()</code>.</p>
</div>
<div id="per-row-summary-statistics" class="section level2">
<h2>Per row summary statistics</h2>
<p><code>dplyr::summarise()</code> makes it really easy to summarise
values across rows within one column. When combined with
<code>rowwise()</code> it also makes it easy to summarise values across
columns within one row. To see how, we’ll start by making a little
dataset:</p>
<div class="sourceCode" id="cb5"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb5-1"><a href="#cb5-1" tabindex="-1"></a>df <span class="ot"><-</span> <span class="fu">tibble</span>(<span class="at">id =</span> <span class="dv">1</span><span class="sc">:</span><span class="dv">6</span>, <span class="at">w =</span> <span class="dv">10</span><span class="sc">:</span><span class="dv">15</span>, <span class="at">x =</span> <span class="dv">20</span><span class="sc">:</span><span class="dv">25</span>, <span class="at">y =</span> <span class="dv">30</span><span class="sc">:</span><span class="dv">35</span>, <span class="at">z =</span> <span class="dv">40</span><span class="sc">:</span><span class="dv">45</span>)</span>
<span id="cb5-2"><a href="#cb5-2" tabindex="-1"></a>df</span>
<span id="cb5-3"><a href="#cb5-3" tabindex="-1"></a><span class="co">#> # A tibble: 6 × 5</span></span>
<span id="cb5-4"><a href="#cb5-4" tabindex="-1"></a><span class="co">#> id w x y z</span></span>
<span id="cb5-5"><a href="#cb5-5" tabindex="-1"></a><span class="co">#> <int> <int> <int> <int> <int></span></span>
<span id="cb5-6"><a href="#cb5-6" tabindex="-1"></a><span class="co">#> 1 1 10 20 30 40</span></span>
<span id="cb5-7"><a href="#cb5-7" tabindex="-1"></a><span class="co">#> 2 2 11 21 31 41</span></span>
<span id="cb5-8"><a href="#cb5-8" tabindex="-1"></a><span class="co">#> 3 3 12 22 32 42</span></span>
<span id="cb5-9"><a href="#cb5-9" tabindex="-1"></a><span class="co">#> 4 4 13 23 33 43</span></span>
<span id="cb5-10"><a href="#cb5-10" tabindex="-1"></a><span class="co">#> # ℹ 2 more rows</span></span></code></pre></div>
<p>Let’s say we want compute the sum of <code>w</code>, <code>x</code>,
<code>y</code>, and <code>z</code> for each row. We start by making a
row-wise data frame:</p>
<div class="sourceCode" id="cb6"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb6-1"><a href="#cb6-1" tabindex="-1"></a>rf <span class="ot"><-</span> df <span class="sc">%>%</span> <span class="fu">rowwise</span>(id)</span></code></pre></div>
<p>We can then use <code>mutate()</code> to add a new column to each
row, or <code>summarise()</code> to return just that one summary:</p>
<div class="sourceCode" id="cb7"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb7-1"><a href="#cb7-1" tabindex="-1"></a>rf <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">total =</span> <span class="fu">sum</span>(<span class="fu">c</span>(w, x, y, z)))</span>
<span id="cb7-2"><a href="#cb7-2" tabindex="-1"></a><span class="co">#> # A tibble: 6 × 6</span></span>
<span id="cb7-3"><a href="#cb7-3" tabindex="-1"></a><span class="co">#> # Rowwise: id</span></span>
<span id="cb7-4"><a href="#cb7-4" tabindex="-1"></a><span class="co">#> id w x y z total</span></span>
<span id="cb7-5"><a href="#cb7-5" tabindex="-1"></a><span class="co">#> <int> <int> <int> <int> <int> <int></span></span>
<span id="cb7-6"><a href="#cb7-6" tabindex="-1"></a><span class="co">#> 1 1 10 20 30 40 100</span></span>
<span id="cb7-7"><a href="#cb7-7" tabindex="-1"></a><span class="co">#> 2 2 11 21 31 41 104</span></span>
<span id="cb7-8"><a href="#cb7-8" tabindex="-1"></a><span class="co">#> 3 3 12 22 32 42 108</span></span>
<span id="cb7-9"><a href="#cb7-9" tabindex="-1"></a><span class="co">#> 4 4 13 23 33 43 112</span></span>
<span id="cb7-10"><a href="#cb7-10" tabindex="-1"></a><span class="co">#> # ℹ 2 more rows</span></span>
<span id="cb7-11"><a href="#cb7-11" tabindex="-1"></a>rf <span class="sc">%>%</span> <span class="fu">summarise</span>(<span class="at">total =</span> <span class="fu">sum</span>(<span class="fu">c</span>(w, x, y, z)))</span>
<span id="cb7-12"><a href="#cb7-12" tabindex="-1"></a><span class="co">#> `summarise()` has grouped output by 'id'. You can override using the `.groups`</span></span>
<span id="cb7-13"><a href="#cb7-13" tabindex="-1"></a><span class="co">#> argument.</span></span>
<span id="cb7-14"><a href="#cb7-14" tabindex="-1"></a><span class="co">#> # A tibble: 6 × 2</span></span>
<span id="cb7-15"><a href="#cb7-15" tabindex="-1"></a><span class="co">#> # Groups: id [6]</span></span>
<span id="cb7-16"><a href="#cb7-16" tabindex="-1"></a><span class="co">#> id total</span></span>
<span id="cb7-17"><a href="#cb7-17" tabindex="-1"></a><span class="co">#> <int> <int></span></span>
<span id="cb7-18"><a href="#cb7-18" tabindex="-1"></a><span class="co">#> 1 1 100</span></span>
<span id="cb7-19"><a href="#cb7-19" tabindex="-1"></a><span class="co">#> 2 2 104</span></span>
<span id="cb7-20"><a href="#cb7-20" tabindex="-1"></a><span class="co">#> 3 3 108</span></span>
<span id="cb7-21"><a href="#cb7-21" tabindex="-1"></a><span class="co">#> 4 4 112</span></span>
<span id="cb7-22"><a href="#cb7-22" tabindex="-1"></a><span class="co">#> # ℹ 2 more rows</span></span></code></pre></div>
<p>Of course, if you have a lot of variables, it’s going to be tedious
to type in every variable name. Instead, you can use
<code>c_across()</code> which uses tidy selection syntax so you can to
succinctly select many variables:</p>
<div class="sourceCode" id="cb8"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb8-1"><a href="#cb8-1" tabindex="-1"></a>rf <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">total =</span> <span class="fu">sum</span>(<span class="fu">c_across</span>(w<span class="sc">:</span>z)))</span>
<span id="cb8-2"><a href="#cb8-2" tabindex="-1"></a><span class="co">#> # A tibble: 6 × 6</span></span>
<span id="cb8-3"><a href="#cb8-3" tabindex="-1"></a><span class="co">#> # Rowwise: id</span></span>
<span id="cb8-4"><a href="#cb8-4" tabindex="-1"></a><span class="co">#> id w x y z total</span></span>
<span id="cb8-5"><a href="#cb8-5" tabindex="-1"></a><span class="co">#> <int> <int> <int> <int> <int> <int></span></span>
<span id="cb8-6"><a href="#cb8-6" tabindex="-1"></a><span class="co">#> 1 1 10 20 30 40 100</span></span>
<span id="cb8-7"><a href="#cb8-7" tabindex="-1"></a><span class="co">#> 2 2 11 21 31 41 104</span></span>
<span id="cb8-8"><a href="#cb8-8" tabindex="-1"></a><span class="co">#> 3 3 12 22 32 42 108</span></span>
<span id="cb8-9"><a href="#cb8-9" tabindex="-1"></a><span class="co">#> 4 4 13 23 33 43 112</span></span>
<span id="cb8-10"><a href="#cb8-10" tabindex="-1"></a><span class="co">#> # ℹ 2 more rows</span></span>
<span id="cb8-11"><a href="#cb8-11" tabindex="-1"></a>rf <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">total =</span> <span class="fu">sum</span>(<span class="fu">c_across</span>(<span class="fu">where</span>(is.numeric))))</span>
<span id="cb8-12"><a href="#cb8-12" tabindex="-1"></a><span class="co">#> # A tibble: 6 × 6</span></span>
<span id="cb8-13"><a href="#cb8-13" tabindex="-1"></a><span class="co">#> # Rowwise: id</span></span>
<span id="cb8-14"><a href="#cb8-14" tabindex="-1"></a><span class="co">#> id w x y z total</span></span>
<span id="cb8-15"><a href="#cb8-15" tabindex="-1"></a><span class="co">#> <int> <int> <int> <int> <int> <int></span></span>
<span id="cb8-16"><a href="#cb8-16" tabindex="-1"></a><span class="co">#> 1 1 10 20 30 40 100</span></span>
<span id="cb8-17"><a href="#cb8-17" tabindex="-1"></a><span class="co">#> 2 2 11 21 31 41 104</span></span>
<span id="cb8-18"><a href="#cb8-18" tabindex="-1"></a><span class="co">#> 3 3 12 22 32 42 108</span></span>
<span id="cb8-19"><a href="#cb8-19" tabindex="-1"></a><span class="co">#> 4 4 13 23 33 43 112</span></span>
<span id="cb8-20"><a href="#cb8-20" tabindex="-1"></a><span class="co">#> # ℹ 2 more rows</span></span></code></pre></div>
<p>You could combine this with column-wise operations (see
<code>vignette("colwise")</code> for more details) to compute the
proportion of the total for each column:</p>
<div class="sourceCode" id="cb9"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb9-1"><a href="#cb9-1" tabindex="-1"></a>rf <span class="sc">%>%</span> </span>
<span id="cb9-2"><a href="#cb9-2" tabindex="-1"></a> <span class="fu">mutate</span>(<span class="at">total =</span> <span class="fu">sum</span>(<span class="fu">c_across</span>(w<span class="sc">:</span>z))) <span class="sc">%>%</span> </span>
<span id="cb9-3"><a href="#cb9-3" tabindex="-1"></a> <span class="fu">ungroup</span>() <span class="sc">%>%</span> </span>
<span id="cb9-4"><a href="#cb9-4" tabindex="-1"></a> <span class="fu">mutate</span>(<span class="fu">across</span>(w<span class="sc">:</span>z, <span class="sc">~</span> . <span class="sc">/</span> total))</span>
<span id="cb9-5"><a href="#cb9-5" tabindex="-1"></a><span class="co">#> # A tibble: 6 × 6</span></span>
<span id="cb9-6"><a href="#cb9-6" tabindex="-1"></a><span class="co">#> id w x y z total</span></span>
<span id="cb9-7"><a href="#cb9-7" tabindex="-1"></a><span class="co">#> <int> <dbl> <dbl> <dbl> <dbl> <int></span></span>
<span id="cb9-8"><a href="#cb9-8" tabindex="-1"></a><span class="co">#> 1 1 0.1 0.2 0.3 0.4 100</span></span>
<span id="cb9-9"><a href="#cb9-9" tabindex="-1"></a><span class="co">#> 2 2 0.106 0.202 0.298 0.394 104</span></span>
<span id="cb9-10"><a href="#cb9-10" tabindex="-1"></a><span class="co">#> 3 3 0.111 0.204 0.296 0.389 108</span></span>
<span id="cb9-11"><a href="#cb9-11" tabindex="-1"></a><span class="co">#> 4 4 0.116 0.205 0.295 0.384 112</span></span>
<span id="cb9-12"><a href="#cb9-12" tabindex="-1"></a><span class="co">#> # ℹ 2 more rows</span></span></code></pre></div>
<div id="row-wise-summary-functions" class="section level3">
<h3>Row-wise summary functions</h3>
<p>The <code>rowwise()</code> approach will work for any summary
function. But if you need greater speed, it’s worth looking for a
built-in row-wise variant of your summary function. These are more
efficient because they operate on the data frame as whole; they don’t
split it into rows, compute the summary, and then join the results back
together again.</p>
<div class="sourceCode" id="cb10"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb10-1"><a href="#cb10-1" tabindex="-1"></a>df <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">total =</span> <span class="fu">rowSums</span>(<span class="fu">pick</span>(<span class="fu">where</span>(is.numeric), <span class="sc">-</span>id)))</span>
<span id="cb10-2"><a href="#cb10-2" tabindex="-1"></a><span class="co">#> # A tibble: 6 × 6</span></span>
<span id="cb10-3"><a href="#cb10-3" tabindex="-1"></a><span class="co">#> id w x y z total</span></span>
<span id="cb10-4"><a href="#cb10-4" tabindex="-1"></a><span class="co">#> <int> <int> <int> <int> <int> <dbl></span></span>
<span id="cb10-5"><a href="#cb10-5" tabindex="-1"></a><span class="co">#> 1 1 10 20 30 40 100</span></span>
<span id="cb10-6"><a href="#cb10-6" tabindex="-1"></a><span class="co">#> 2 2 11 21 31 41 104</span></span>
<span id="cb10-7"><a href="#cb10-7" tabindex="-1"></a><span class="co">#> 3 3 12 22 32 42 108</span></span>
<span id="cb10-8"><a href="#cb10-8" tabindex="-1"></a><span class="co">#> 4 4 13 23 33 43 112</span></span>
<span id="cb10-9"><a href="#cb10-9" tabindex="-1"></a><span class="co">#> # ℹ 2 more rows</span></span>
<span id="cb10-10"><a href="#cb10-10" tabindex="-1"></a>df <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">mean =</span> <span class="fu">rowMeans</span>(<span class="fu">pick</span>(<span class="fu">where</span>(is.numeric), <span class="sc">-</span>id)))</span>
<span id="cb10-11"><a href="#cb10-11" tabindex="-1"></a><span class="co">#> # A tibble: 6 × 6</span></span>
<span id="cb10-12"><a href="#cb10-12" tabindex="-1"></a><span class="co">#> id w x y z mean</span></span>
<span id="cb10-13"><a href="#cb10-13" tabindex="-1"></a><span class="co">#> <int> <int> <int> <int> <int> <dbl></span></span>
<span id="cb10-14"><a href="#cb10-14" tabindex="-1"></a><span class="co">#> 1 1 10 20 30 40 25</span></span>
<span id="cb10-15"><a href="#cb10-15" tabindex="-1"></a><span class="co">#> 2 2 11 21 31 41 26</span></span>
<span id="cb10-16"><a href="#cb10-16" tabindex="-1"></a><span class="co">#> 3 3 12 22 32 42 27</span></span>
<span id="cb10-17"><a href="#cb10-17" tabindex="-1"></a><span class="co">#> 4 4 13 23 33 43 28</span></span>
<span id="cb10-18"><a href="#cb10-18" tabindex="-1"></a><span class="co">#> # ℹ 2 more rows</span></span></code></pre></div>
<p><strong>NB</strong>: I use <code>df</code> (not <code>rf</code>) and
<code>pick()</code> (not <code>c_across()</code>) here because
<code>rowMeans()</code> and <code>rowSums()</code> take a multi-row data
frame as input. Also note that <code>-id</code> is needed to avoid
selecting <code>id</code> in <code>pick()</code>. This wasn’t required
with the rowwise data frame because we had specified <code>id</code> as
an identifier in our original call to <code>rowwise()</code>, preventing
it from being selected as a grouping column.</p>
</div>
</div>
<div id="list-columns" class="section level2">
<h2>List-columns</h2>
<p><code>rowwise()</code> operations are a natural pairing when you have
list-columns. They allow you to avoid explicit loops and/or functions
from the <code>apply()</code> or <code>purrr::map()</code> families.</p>
<div id="motivation" class="section level3">
<h3>Motivation</h3>
<p>Imagine you have this data frame, and you want to count the lengths
of each element:</p>
<div class="sourceCode" id="cb11"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb11-1"><a href="#cb11-1" tabindex="-1"></a>df <span class="ot"><-</span> <span class="fu">tibble</span>(</span>
<span id="cb11-2"><a href="#cb11-2" tabindex="-1"></a> <span class="at">x =</span> <span class="fu">list</span>(<span class="dv">1</span>, <span class="dv">2</span><span class="sc">:</span><span class="dv">3</span>, <span class="dv">4</span><span class="sc">:</span><span class="dv">6</span>)</span>
<span id="cb11-3"><a href="#cb11-3" tabindex="-1"></a>)</span></code></pre></div>
<p>You might try calling <code>length()</code>:</p>
<div class="sourceCode" id="cb12"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb12-1"><a href="#cb12-1" tabindex="-1"></a>df <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">l =</span> <span class="fu">length</span>(x))</span>
<span id="cb12-2"><a href="#cb12-2" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 2</span></span>
<span id="cb12-3"><a href="#cb12-3" tabindex="-1"></a><span class="co">#> x l</span></span>
<span id="cb12-4"><a href="#cb12-4" tabindex="-1"></a><span class="co">#> <list> <int></span></span>
<span id="cb12-5"><a href="#cb12-5" tabindex="-1"></a><span class="co">#> 1 <dbl [1]> 3</span></span>
<span id="cb12-6"><a href="#cb12-6" tabindex="-1"></a><span class="co">#> 2 <int [2]> 3</span></span>
<span id="cb12-7"><a href="#cb12-7" tabindex="-1"></a><span class="co">#> 3 <int [3]> 3</span></span></code></pre></div>
<p>But that returns the length of the column, not the length of the
individual values. If you’re an R documentation aficionado, you might
know there’s already a base R function just for this purpose:</p>
<div class="sourceCode" id="cb13"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb13-1"><a href="#cb13-1" tabindex="-1"></a>df <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">l =</span> <span class="fu">lengths</span>(x))</span>
<span id="cb13-2"><a href="#cb13-2" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 2</span></span>
<span id="cb13-3"><a href="#cb13-3" tabindex="-1"></a><span class="co">#> x l</span></span>
<span id="cb13-4"><a href="#cb13-4" tabindex="-1"></a><span class="co">#> <list> <int></span></span>
<span id="cb13-5"><a href="#cb13-5" tabindex="-1"></a><span class="co">#> 1 <dbl [1]> 1</span></span>
<span id="cb13-6"><a href="#cb13-6" tabindex="-1"></a><span class="co">#> 2 <int [2]> 2</span></span>
<span id="cb13-7"><a href="#cb13-7" tabindex="-1"></a><span class="co">#> 3 <int [3]> 3</span></span></code></pre></div>
<p>Or if you’re an experienced R programmer, you might know how to apply
a function to each element of a list using <code>sapply()</code>,
<code>vapply()</code>, or one of the purrr <code>map()</code>
functions:</p>
<div class="sourceCode" id="cb14"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb14-1"><a href="#cb14-1" tabindex="-1"></a>df <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">l =</span> <span class="fu">sapply</span>(x, length))</span>
<span id="cb14-2"><a href="#cb14-2" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 2</span></span>
<span id="cb14-3"><a href="#cb14-3" tabindex="-1"></a><span class="co">#> x l</span></span>
<span id="cb14-4"><a href="#cb14-4" tabindex="-1"></a><span class="co">#> <list> <int></span></span>
<span id="cb14-5"><a href="#cb14-5" tabindex="-1"></a><span class="co">#> 1 <dbl [1]> 1</span></span>
<span id="cb14-6"><a href="#cb14-6" tabindex="-1"></a><span class="co">#> 2 <int [2]> 2</span></span>
<span id="cb14-7"><a href="#cb14-7" tabindex="-1"></a><span class="co">#> 3 <int [3]> 3</span></span>
<span id="cb14-8"><a href="#cb14-8" tabindex="-1"></a>df <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">l =</span> purrr<span class="sc">::</span><span class="fu">map_int</span>(x, length))</span>
<span id="cb14-9"><a href="#cb14-9" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 2</span></span>
<span id="cb14-10"><a href="#cb14-10" tabindex="-1"></a><span class="co">#> x l</span></span>
<span id="cb14-11"><a href="#cb14-11" tabindex="-1"></a><span class="co">#> <list> <int></span></span>
<span id="cb14-12"><a href="#cb14-12" tabindex="-1"></a><span class="co">#> 1 <dbl [1]> 1</span></span>
<span id="cb14-13"><a href="#cb14-13" tabindex="-1"></a><span class="co">#> 2 <int [2]> 2</span></span>
<span id="cb14-14"><a href="#cb14-14" tabindex="-1"></a><span class="co">#> 3 <int [3]> 3</span></span></code></pre></div>
<p>But wouldn’t it be nice if you could just write
<code>length(x)</code> and dplyr would figure out that you wanted to
compute the length of the element inside of <code>x</code>? Since you’re
here, you might already be guessing at the answer: this is just another
application of the row-wise pattern.</p>
<div class="sourceCode" id="cb15"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb15-1"><a href="#cb15-1" tabindex="-1"></a>df <span class="sc">%>%</span> </span>
<span id="cb15-2"><a href="#cb15-2" tabindex="-1"></a> <span class="fu">rowwise</span>() <span class="sc">%>%</span> </span>
<span id="cb15-3"><a href="#cb15-3" tabindex="-1"></a> <span class="fu">mutate</span>(<span class="at">l =</span> <span class="fu">length</span>(x))</span>
<span id="cb15-4"><a href="#cb15-4" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 2</span></span>
<span id="cb15-5"><a href="#cb15-5" tabindex="-1"></a><span class="co">#> # Rowwise: </span></span>
<span id="cb15-6"><a href="#cb15-6" tabindex="-1"></a><span class="co">#> x l</span></span>
<span id="cb15-7"><a href="#cb15-7" tabindex="-1"></a><span class="co">#> <list> <int></span></span>
<span id="cb15-8"><a href="#cb15-8" tabindex="-1"></a><span class="co">#> 1 <dbl [1]> 1</span></span>
<span id="cb15-9"><a href="#cb15-9" tabindex="-1"></a><span class="co">#> 2 <int [2]> 2</span></span>
<span id="cb15-10"><a href="#cb15-10" tabindex="-1"></a><span class="co">#> 3 <int [3]> 3</span></span></code></pre></div>
</div>
<div id="subsetting" class="section level3">
<h3>Subsetting</h3>
<p>Before we continue on, I wanted to briefly mention the magic that
makes this work. This isn’t something you’ll generally need to think
about (it’ll just work), but it’s useful to know about when something
goes wrong.</p>
<p>There’s an important difference between a grouped data frame where
each group happens to have one row, and a row-wise data frame where
every group always has one row. Take these two data frames:</p>
<div class="sourceCode" id="cb16"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb16-1"><a href="#cb16-1" tabindex="-1"></a>df <span class="ot"><-</span> <span class="fu">tibble</span>(<span class="at">g =</span> <span class="dv">1</span><span class="sc">:</span><span class="dv">2</span>, <span class="at">y =</span> <span class="fu">list</span>(<span class="dv">1</span><span class="sc">:</span><span class="dv">3</span>, <span class="st">"a"</span>))</span>
<span id="cb16-2"><a href="#cb16-2" tabindex="-1"></a>gf <span class="ot"><-</span> df <span class="sc">%>%</span> <span class="fu">group_by</span>(g)</span>
<span id="cb16-3"><a href="#cb16-3" tabindex="-1"></a>rf <span class="ot"><-</span> df <span class="sc">%>%</span> <span class="fu">rowwise</span>(g)</span></code></pre></div>
<p>If we compute some properties of <code>y</code>, you’ll notice the
results look different:</p>
<div class="sourceCode" id="cb17"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb17-1"><a href="#cb17-1" tabindex="-1"></a>gf <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">type =</span> <span class="fu">typeof</span>(y), <span class="at">length =</span> <span class="fu">length</span>(y))</span>
<span id="cb17-2"><a href="#cb17-2" tabindex="-1"></a><span class="co">#> # A tibble: 2 × 4</span></span>
<span id="cb17-3"><a href="#cb17-3" tabindex="-1"></a><span class="co">#> # Groups: g [2]</span></span>
<span id="cb17-4"><a href="#cb17-4" tabindex="-1"></a><span class="co">#> g y type length</span></span>
<span id="cb17-5"><a href="#cb17-5" tabindex="-1"></a><span class="co">#> <int> <list> <chr> <int></span></span>
<span id="cb17-6"><a href="#cb17-6" tabindex="-1"></a><span class="co">#> 1 1 <int [3]> list 1</span></span>
<span id="cb17-7"><a href="#cb17-7" tabindex="-1"></a><span class="co">#> 2 2 <chr [1]> list 1</span></span>
<span id="cb17-8"><a href="#cb17-8" tabindex="-1"></a>rf <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">type =</span> <span class="fu">typeof</span>(y), <span class="at">length =</span> <span class="fu">length</span>(y))</span>
<span id="cb17-9"><a href="#cb17-9" tabindex="-1"></a><span class="co">#> # A tibble: 2 × 4</span></span>
<span id="cb17-10"><a href="#cb17-10" tabindex="-1"></a><span class="co">#> # Rowwise: g</span></span>
<span id="cb17-11"><a href="#cb17-11" tabindex="-1"></a><span class="co">#> g y type length</span></span>
<span id="cb17-12"><a href="#cb17-12" tabindex="-1"></a><span class="co">#> <int> <list> <chr> <int></span></span>
<span id="cb17-13"><a href="#cb17-13" tabindex="-1"></a><span class="co">#> 1 1 <int [3]> integer 3</span></span>
<span id="cb17-14"><a href="#cb17-14" tabindex="-1"></a><span class="co">#> 2 2 <chr [1]> character 1</span></span></code></pre></div>
<p>They key difference is that when <code>mutate()</code> slices up the
columns to pass to <code>length(y)</code> the grouped mutate uses
<code>[</code> and the row-wise mutate uses <code>[[</code>. The
following code gives a flavour of the differences if you used a for
loop:</p>
<div class="sourceCode" id="cb18"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb18-1"><a href="#cb18-1" tabindex="-1"></a><span class="co"># grouped</span></span>
<span id="cb18-2"><a href="#cb18-2" tabindex="-1"></a>out1 <span class="ot"><-</span> <span class="fu">integer</span>(<span class="dv">2</span>)</span>
<span id="cb18-3"><a href="#cb18-3" tabindex="-1"></a><span class="cf">for</span> (i <span class="cf">in</span> <span class="dv">1</span><span class="sc">:</span><span class="dv">2</span>) {</span>
<span id="cb18-4"><a href="#cb18-4" tabindex="-1"></a> out1[[i]] <span class="ot"><-</span> <span class="fu">length</span>(df<span class="sc">$</span>y[i])</span>
<span id="cb18-5"><a href="#cb18-5" tabindex="-1"></a>}</span>
<span id="cb18-6"><a href="#cb18-6" tabindex="-1"></a>out1</span>
<span id="cb18-7"><a href="#cb18-7" tabindex="-1"></a><span class="co">#> [1] 1 1</span></span>
<span id="cb18-8"><a href="#cb18-8" tabindex="-1"></a></span>
<span id="cb18-9"><a href="#cb18-9" tabindex="-1"></a><span class="co"># rowwise</span></span>
<span id="cb18-10"><a href="#cb18-10" tabindex="-1"></a>out2 <span class="ot"><-</span> <span class="fu">integer</span>(<span class="dv">2</span>)</span>
<span id="cb18-11"><a href="#cb18-11" tabindex="-1"></a><span class="cf">for</span> (i <span class="cf">in</span> <span class="dv">1</span><span class="sc">:</span><span class="dv">2</span>) {</span>
<span id="cb18-12"><a href="#cb18-12" tabindex="-1"></a> out2[[i]] <span class="ot"><-</span> <span class="fu">length</span>(df<span class="sc">$</span>y[[i]])</span>
<span id="cb18-13"><a href="#cb18-13" tabindex="-1"></a>}</span>
<span id="cb18-14"><a href="#cb18-14" tabindex="-1"></a>out2</span>
<span id="cb18-15"><a href="#cb18-15" tabindex="-1"></a><span class="co">#> [1] 3 1</span></span></code></pre></div>
<p>Note that this magic only applies when you’re referring to existing
columns, not when you’re creating new rows. This is potentially
confusing, but we’re fairly confident it’s the least worst solution,
particularly given the hint in the error message.</p>
<div class="sourceCode" id="cb19"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb19-1"><a href="#cb19-1" tabindex="-1"></a>gf <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">y2 =</span> y)</span>
<span id="cb19-2"><a href="#cb19-2" tabindex="-1"></a><span class="co">#> # A tibble: 2 × 3</span></span>
<span id="cb19-3"><a href="#cb19-3" tabindex="-1"></a><span class="co">#> # Groups: g [2]</span></span>
<span id="cb19-4"><a href="#cb19-4" tabindex="-1"></a><span class="co">#> g y y2 </span></span>
<span id="cb19-5"><a href="#cb19-5" tabindex="-1"></a><span class="co">#> <int> <list> <list> </span></span>
<span id="cb19-6"><a href="#cb19-6" tabindex="-1"></a><span class="co">#> 1 1 <int [3]> <int [3]></span></span>
<span id="cb19-7"><a href="#cb19-7" tabindex="-1"></a><span class="co">#> 2 2 <chr [1]> <chr [1]></span></span>
<span id="cb19-8"><a href="#cb19-8" tabindex="-1"></a>rf <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">y2 =</span> y)</span>
<span id="cb19-9"><a href="#cb19-9" tabindex="-1"></a><span class="co">#> Error in `mutate()`:</span></span>
<span id="cb19-10"><a href="#cb19-10" tabindex="-1"></a><span class="co">#> ℹ In argument: `y2 = y`.</span></span>
<span id="cb19-11"><a href="#cb19-11" tabindex="-1"></a><span class="co">#> ℹ In row 1.</span></span>
<span id="cb19-12"><a href="#cb19-12" tabindex="-1"></a><span class="co">#> Caused by error:</span></span>
<span id="cb19-13"><a href="#cb19-13" tabindex="-1"></a><span class="co">#> ! `y2` must be size 1, not 3.</span></span>
<span id="cb19-14"><a href="#cb19-14" tabindex="-1"></a><span class="co">#> ℹ Did you mean: `y2 = list(y)` ?</span></span>
<span id="cb19-15"><a href="#cb19-15" tabindex="-1"></a>rf <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">y2 =</span> <span class="fu">list</span>(y))</span>
<span id="cb19-16"><a href="#cb19-16" tabindex="-1"></a><span class="co">#> # A tibble: 2 × 3</span></span>
<span id="cb19-17"><a href="#cb19-17" tabindex="-1"></a><span class="co">#> # Rowwise: g</span></span>
<span id="cb19-18"><a href="#cb19-18" tabindex="-1"></a><span class="co">#> g y y2 </span></span>
<span id="cb19-19"><a href="#cb19-19" tabindex="-1"></a><span class="co">#> <int> <list> <list> </span></span>
<span id="cb19-20"><a href="#cb19-20" tabindex="-1"></a><span class="co">#> 1 1 <int [3]> <int [3]></span></span>
<span id="cb19-21"><a href="#cb19-21" tabindex="-1"></a><span class="co">#> 2 2 <chr [1]> <chr [1]></span></span></code></pre></div>
</div>
<div id="modelling" class="section level3">
<h3>Modelling</h3>
<p><code>rowwise()</code> data frames allow you to solve a variety of
modelling problems in what I think is a particularly elegant way. We’ll
start by creating a nested data frame:</p>
<div class="sourceCode" id="cb20"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb20-1"><a href="#cb20-1" tabindex="-1"></a>by_cyl <span class="ot"><-</span> mtcars <span class="sc">%>%</span> <span class="fu">nest_by</span>(cyl)</span>
<span id="cb20-2"><a href="#cb20-2" tabindex="-1"></a>by_cyl</span>
<span id="cb20-3"><a href="#cb20-3" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 2</span></span>
<span id="cb20-4"><a href="#cb20-4" tabindex="-1"></a><span class="co">#> # Rowwise: cyl</span></span>
<span id="cb20-5"><a href="#cb20-5" tabindex="-1"></a><span class="co">#> cyl data </span></span>
<span id="cb20-6"><a href="#cb20-6" tabindex="-1"></a><span class="co">#> <dbl> <list> </span></span>
<span id="cb20-7"><a href="#cb20-7" tabindex="-1"></a><span class="co">#> 1 4 <tibble [11 × 12]></span></span>
<span id="cb20-8"><a href="#cb20-8" tabindex="-1"></a><span class="co">#> 2 6 <tibble [7 × 12]> </span></span>
<span id="cb20-9"><a href="#cb20-9" tabindex="-1"></a><span class="co">#> 3 8 <tibble [14 × 12]></span></span></code></pre></div>
<p>This is a little different to the usual <code>group_by()</code>
output: we have visibly changed the structure of the data. Now we have
three rows (one for each group), and we have a list-col,
<code>data</code>, that stores the data for that group. Also note that
the output is <code>rowwise()</code>; this is important because it’s
going to make working with that list of data frames much easier.</p>
<p>Once we have one data frame per row, it’s straightforward to make one
model per row:</p>
<div class="sourceCode" id="cb21"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb21-1"><a href="#cb21-1" tabindex="-1"></a>mods <span class="ot"><-</span> by_cyl <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">mod =</span> <span class="fu">list</span>(<span class="fu">lm</span>(mpg <span class="sc">~</span> wt, <span class="at">data =</span> data)))</span>
<span id="cb21-2"><a href="#cb21-2" tabindex="-1"></a>mods</span>
<span id="cb21-3"><a href="#cb21-3" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 3</span></span>
<span id="cb21-4"><a href="#cb21-4" tabindex="-1"></a><span class="co">#> # Rowwise: cyl</span></span>
<span id="cb21-5"><a href="#cb21-5" tabindex="-1"></a><span class="co">#> cyl data mod </span></span>
<span id="cb21-6"><a href="#cb21-6" tabindex="-1"></a><span class="co">#> <dbl> <list> <list></span></span>
<span id="cb21-7"><a href="#cb21-7" tabindex="-1"></a><span class="co">#> 1 4 <tibble [11 × 12]> <lm> </span></span>
<span id="cb21-8"><a href="#cb21-8" tabindex="-1"></a><span class="co">#> 2 6 <tibble [7 × 12]> <lm> </span></span>
<span id="cb21-9"><a href="#cb21-9" tabindex="-1"></a><span class="co">#> 3 8 <tibble [14 × 12]> <lm></span></span></code></pre></div>
<p>And supplement that with one set of predictions per row:</p>
<div class="sourceCode" id="cb22"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb22-1"><a href="#cb22-1" tabindex="-1"></a>mods <span class="ot"><-</span> mods <span class="sc">%>%</span> <span class="fu">mutate</span>(<span class="at">pred =</span> <span class="fu">list</span>(<span class="fu">predict</span>(mod, data)))</span>
<span id="cb22-2"><a href="#cb22-2" tabindex="-1"></a>mods</span>
<span id="cb22-3"><a href="#cb22-3" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 4</span></span>
<span id="cb22-4"><a href="#cb22-4" tabindex="-1"></a><span class="co">#> # Rowwise: cyl</span></span>
<span id="cb22-5"><a href="#cb22-5" tabindex="-1"></a><span class="co">#> cyl data mod pred </span></span>
<span id="cb22-6"><a href="#cb22-6" tabindex="-1"></a><span class="co">#> <dbl> <list> <list> <list> </span></span>
<span id="cb22-7"><a href="#cb22-7" tabindex="-1"></a><span class="co">#> 1 4 <tibble [11 × 12]> <lm> <dbl [11]></span></span>
<span id="cb22-8"><a href="#cb22-8" tabindex="-1"></a><span class="co">#> 2 6 <tibble [7 × 12]> <lm> <dbl [7]> </span></span>
<span id="cb22-9"><a href="#cb22-9" tabindex="-1"></a><span class="co">#> 3 8 <tibble [14 × 12]> <lm> <dbl [14]></span></span></code></pre></div>
<p>You could then summarise the model in a variety of ways:</p>
<div class="sourceCode" id="cb23"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb23-1"><a href="#cb23-1" tabindex="-1"></a>mods <span class="sc">%>%</span> <span class="fu">summarise</span>(<span class="at">rmse =</span> <span class="fu">sqrt</span>(<span class="fu">mean</span>((pred <span class="sc">-</span> data<span class="sc">$</span>mpg) <span class="sc">^</span> <span class="dv">2</span>)))</span>
<span id="cb23-2"><a href="#cb23-2" tabindex="-1"></a><span class="co">#> `summarise()` has grouped output by 'cyl'. You can override using the `.groups`</span></span>
<span id="cb23-3"><a href="#cb23-3" tabindex="-1"></a><span class="co">#> argument.</span></span>
<span id="cb23-4"><a href="#cb23-4" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 2</span></span>
<span id="cb23-5"><a href="#cb23-5" tabindex="-1"></a><span class="co">#> # Groups: cyl [3]</span></span>
<span id="cb23-6"><a href="#cb23-6" tabindex="-1"></a><span class="co">#> cyl rmse</span></span>
<span id="cb23-7"><a href="#cb23-7" tabindex="-1"></a><span class="co">#> <dbl> <dbl></span></span>
<span id="cb23-8"><a href="#cb23-8" tabindex="-1"></a><span class="co">#> 1 4 3.01 </span></span>
<span id="cb23-9"><a href="#cb23-9" tabindex="-1"></a><span class="co">#> 2 6 0.985</span></span>
<span id="cb23-10"><a href="#cb23-10" tabindex="-1"></a><span class="co">#> 3 8 1.87</span></span>
<span id="cb23-11"><a href="#cb23-11" tabindex="-1"></a>mods <span class="sc">%>%</span> <span class="fu">summarise</span>(<span class="at">rsq =</span> <span class="fu">summary</span>(mod)<span class="sc">$</span>r.squared)</span>
<span id="cb23-12"><a href="#cb23-12" tabindex="-1"></a><span class="co">#> `summarise()` has grouped output by 'cyl'. You can override using the `.groups`</span></span>
<span id="cb23-13"><a href="#cb23-13" tabindex="-1"></a><span class="co">#> argument.</span></span>
<span id="cb23-14"><a href="#cb23-14" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 2</span></span>
<span id="cb23-15"><a href="#cb23-15" tabindex="-1"></a><span class="co">#> # Groups: cyl [3]</span></span>
<span id="cb23-16"><a href="#cb23-16" tabindex="-1"></a><span class="co">#> cyl rsq</span></span>
<span id="cb23-17"><a href="#cb23-17" tabindex="-1"></a><span class="co">#> <dbl> <dbl></span></span>
<span id="cb23-18"><a href="#cb23-18" tabindex="-1"></a><span class="co">#> 1 4 0.509</span></span>
<span id="cb23-19"><a href="#cb23-19" tabindex="-1"></a><span class="co">#> 2 6 0.465</span></span>
<span id="cb23-20"><a href="#cb23-20" tabindex="-1"></a><span class="co">#> 3 8 0.423</span></span>
<span id="cb23-21"><a href="#cb23-21" tabindex="-1"></a>mods <span class="sc">%>%</span> <span class="fu">summarise</span>(broom<span class="sc">::</span><span class="fu">glance</span>(mod))</span>
<span id="cb23-22"><a href="#cb23-22" tabindex="-1"></a><span class="co">#> `summarise()` has grouped output by 'cyl'. You can override using the `.groups`</span></span>
<span id="cb23-23"><a href="#cb23-23" tabindex="-1"></a><span class="co">#> argument.</span></span>
<span id="cb23-24"><a href="#cb23-24" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 13</span></span>
<span id="cb23-25"><a href="#cb23-25" tabindex="-1"></a><span class="co">#> # Groups: cyl [3]</span></span>
<span id="cb23-26"><a href="#cb23-26" tabindex="-1"></a><span class="co">#> cyl r.squared adj.r.squared sigma statistic p.value df logLik AIC BIC</span></span>
<span id="cb23-27"><a href="#cb23-27" tabindex="-1"></a><span class="co">#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl></span></span>
<span id="cb23-28"><a href="#cb23-28" tabindex="-1"></a><span class="co">#> 1 4 0.509 0.454 3.33 9.32 0.0137 1 -27.7 61.5 62.7</span></span>
<span id="cb23-29"><a href="#cb23-29" tabindex="-1"></a><span class="co">#> 2 6 0.465 0.357 1.17 4.34 0.0918 1 -9.83 25.7 25.5</span></span>
<span id="cb23-30"><a href="#cb23-30" tabindex="-1"></a><span class="co">#> 3 8 0.423 0.375 2.02 8.80 0.0118 1 -28.7 63.3 65.2</span></span>
<span id="cb23-31"><a href="#cb23-31" tabindex="-1"></a><span class="co">#> # ℹ 3 more variables: deviance <dbl>, df.residual <int>, nobs <int></span></span></code></pre></div>
<p>Or easily access the parameters of each model:</p>
<div class="sourceCode" id="cb24"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb24-1"><a href="#cb24-1" tabindex="-1"></a>mods <span class="sc">%>%</span> <span class="fu">reframe</span>(broom<span class="sc">::</span><span class="fu">tidy</span>(mod))</span>
<span id="cb24-2"><a href="#cb24-2" tabindex="-1"></a><span class="co">#> # A tibble: 6 × 6</span></span>
<span id="cb24-3"><a href="#cb24-3" tabindex="-1"></a><span class="co">#> cyl term estimate std.error statistic p.value</span></span>
<span id="cb24-4"><a href="#cb24-4" tabindex="-1"></a><span class="co">#> <dbl> <chr> <dbl> <dbl> <dbl> <dbl></span></span>
<span id="cb24-5"><a href="#cb24-5" tabindex="-1"></a><span class="co">#> 1 4 (Intercept) 39.6 4.35 9.10 0.00000777</span></span>
<span id="cb24-6"><a href="#cb24-6" tabindex="-1"></a><span class="co">#> 2 4 wt -5.65 1.85 -3.05 0.0137 </span></span>
<span id="cb24-7"><a href="#cb24-7" tabindex="-1"></a><span class="co">#> 3 6 (Intercept) 28.4 4.18 6.79 0.00105 </span></span>
<span id="cb24-8"><a href="#cb24-8" tabindex="-1"></a><span class="co">#> 4 6 wt -2.78 1.33 -2.08 0.0918 </span></span>
<span id="cb24-9"><a href="#cb24-9" tabindex="-1"></a><span class="co">#> # ℹ 2 more rows</span></span></code></pre></div>
</div>
</div>
<div id="repeated-function-calls" class="section level2">
<h2>Repeated function calls</h2>
<p><code>rowwise()</code> doesn’t just work with functions that return a
length-1 vector (aka summary functions); it can work with any function
if the result is a list. This means that <code>rowwise()</code> and
<code>mutate()</code> provide an elegant way to call a function many
times with varying arguments, storing the outputs alongside the
inputs.</p>
<div id="simulations" class="section level3">
<h3>Simulations</h3>
<p>I think this is a particularly elegant way to perform simulations,
because it lets you store simulated values along with the parameters
that generated them. For example, imagine you have the following data
frame that describes the properties of 3 samples from the uniform
distribution:</p>
<div class="sourceCode" id="cb25"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb25-1"><a href="#cb25-1" tabindex="-1"></a>df <span class="ot"><-</span> <span class="fu">tribble</span>(</span>
<span id="cb25-2"><a href="#cb25-2" tabindex="-1"></a> <span class="sc">~</span> n, <span class="sc">~</span> min, <span class="sc">~</span> max,</span>
<span id="cb25-3"><a href="#cb25-3" tabindex="-1"></a> <span class="dv">1</span>, <span class="dv">0</span>, <span class="dv">1</span>,</span>
<span id="cb25-4"><a href="#cb25-4" tabindex="-1"></a> <span class="dv">2</span>, <span class="dv">10</span>, <span class="dv">100</span>,</span>
<span id="cb25-5"><a href="#cb25-5" tabindex="-1"></a> <span class="dv">3</span>, <span class="dv">100</span>, <span class="dv">1000</span>,</span>
<span id="cb25-6"><a href="#cb25-6" tabindex="-1"></a>)</span></code></pre></div>
<p>You can supply these parameters to <code>runif()</code> by using
<code>rowwise()</code> and <code>mutate()</code>:</p>
<div class="sourceCode" id="cb26"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb26-1"><a href="#cb26-1" tabindex="-1"></a>df <span class="sc">%>%</span> </span>
<span id="cb26-2"><a href="#cb26-2" tabindex="-1"></a> <span class="fu">rowwise</span>() <span class="sc">%>%</span> </span>
<span id="cb26-3"><a href="#cb26-3" tabindex="-1"></a> <span class="fu">mutate</span>(<span class="at">data =</span> <span class="fu">list</span>(<span class="fu">runif</span>(n, min, max)))</span>
<span id="cb26-4"><a href="#cb26-4" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 4</span></span>
<span id="cb26-5"><a href="#cb26-5" tabindex="-1"></a><span class="co">#> # Rowwise: </span></span>
<span id="cb26-6"><a href="#cb26-6" tabindex="-1"></a><span class="co">#> n min max data </span></span>
<span id="cb26-7"><a href="#cb26-7" tabindex="-1"></a><span class="co">#> <dbl> <dbl> <dbl> <list> </span></span>
<span id="cb26-8"><a href="#cb26-8" tabindex="-1"></a><span class="co">#> 1 1 0 1 <dbl [1]></span></span>
<span id="cb26-9"><a href="#cb26-9" tabindex="-1"></a><span class="co">#> 2 2 10 100 <dbl [2]></span></span>
<span id="cb26-10"><a href="#cb26-10" tabindex="-1"></a><span class="co">#> 3 3 100 1000 <dbl [3]></span></span></code></pre></div>
<p>Note the use of <code>list()</code> here - <code>runif()</code>
returns multiple values and a <code>mutate()</code> expression has to
return something of length 1. <code>list()</code> means that we’ll get a
list column where each row is a list containing multiple values. If you
forget to use <code>list()</code>, dplyr will give you a hint:</p>
<div class="sourceCode" id="cb27"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb27-1"><a href="#cb27-1" tabindex="-1"></a>df <span class="sc">%>%</span> </span>
<span id="cb27-2"><a href="#cb27-2" tabindex="-1"></a> <span class="fu">rowwise</span>() <span class="sc">%>%</span> </span>
<span id="cb27-3"><a href="#cb27-3" tabindex="-1"></a> <span class="fu">mutate</span>(<span class="at">data =</span> <span class="fu">runif</span>(n, min, max))</span>
<span id="cb27-4"><a href="#cb27-4" tabindex="-1"></a><span class="co">#> Error in `mutate()`:</span></span>
<span id="cb27-5"><a href="#cb27-5" tabindex="-1"></a><span class="co">#> ℹ In argument: `data = runif(n, min, max)`.</span></span>
<span id="cb27-6"><a href="#cb27-6" tabindex="-1"></a><span class="co">#> ℹ In row 2.</span></span>
<span id="cb27-7"><a href="#cb27-7" tabindex="-1"></a><span class="co">#> Caused by error:</span></span>
<span id="cb27-8"><a href="#cb27-8" tabindex="-1"></a><span class="co">#> ! `data` must be size 1, not 2.</span></span>
<span id="cb27-9"><a href="#cb27-9" tabindex="-1"></a><span class="co">#> ℹ Did you mean: `data = list(runif(n, min, max))` ?</span></span></code></pre></div>
</div>
<div id="multiple-combinations" class="section level3">
<h3>Multiple combinations</h3>
<p>What if you want to call a function for every combination of inputs?
You can use <code>expand.grid()</code> (or
<code>tidyr::expand_grid()</code>) to generate the data frame and then
repeat the same pattern as above:</p>
<div class="sourceCode" id="cb28"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb28-1"><a href="#cb28-1" tabindex="-1"></a>df <span class="ot"><-</span> <span class="fu">expand.grid</span>(<span class="at">mean =</span> <span class="fu">c</span>(<span class="sc">-</span><span class="dv">1</span>, <span class="dv">0</span>, <span class="dv">1</span>), <span class="at">sd =</span> <span class="fu">c</span>(<span class="dv">1</span>, <span class="dv">10</span>, <span class="dv">100</span>))</span>
<span id="cb28-2"><a href="#cb28-2" tabindex="-1"></a></span>
<span id="cb28-3"><a href="#cb28-3" tabindex="-1"></a>df <span class="sc">%>%</span> </span>
<span id="cb28-4"><a href="#cb28-4" tabindex="-1"></a> <span class="fu">rowwise</span>() <span class="sc">%>%</span> </span>
<span id="cb28-5"><a href="#cb28-5" tabindex="-1"></a> <span class="fu">mutate</span>(<span class="at">data =</span> <span class="fu">list</span>(<span class="fu">rnorm</span>(<span class="dv">10</span>, mean, sd)))</span>
<span id="cb28-6"><a href="#cb28-6" tabindex="-1"></a><span class="co">#> # A tibble: 9 × 3</span></span>
<span id="cb28-7"><a href="#cb28-7" tabindex="-1"></a><span class="co">#> # Rowwise: </span></span>
<span id="cb28-8"><a href="#cb28-8" tabindex="-1"></a><span class="co">#> mean sd data </span></span>
<span id="cb28-9"><a href="#cb28-9" tabindex="-1"></a><span class="co">#> <dbl> <dbl> <list> </span></span>
<span id="cb28-10"><a href="#cb28-10" tabindex="-1"></a><span class="co">#> 1 -1 1 <dbl [10]></span></span>
<span id="cb28-11"><a href="#cb28-11" tabindex="-1"></a><span class="co">#> 2 0 1 <dbl [10]></span></span>
<span id="cb28-12"><a href="#cb28-12" tabindex="-1"></a><span class="co">#> 3 1 1 <dbl [10]></span></span>
<span id="cb28-13"><a href="#cb28-13" tabindex="-1"></a><span class="co">#> 4 -1 10 <dbl [10]></span></span>
<span id="cb28-14"><a href="#cb28-14" tabindex="-1"></a><span class="co">#> # ℹ 5 more rows</span></span></code></pre></div>
</div>
<div id="varying-functions" class="section level3">
<h3>Varying functions</h3>
<p>In more complicated problems, you might also want to vary the
function being called. This tends to be a bit more of an awkward fit
with this approach because the columns in the input tibble will be less
regular. But it’s still possible, and it’s a natural place to use
<code>do.call()</code>:</p>
<div class="sourceCode" id="cb29"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb29-1"><a href="#cb29-1" tabindex="-1"></a>df <span class="ot"><-</span> <span class="fu">tribble</span>(</span>
<span id="cb29-2"><a href="#cb29-2" tabindex="-1"></a> <span class="sc">~</span>rng, <span class="sc">~</span>params,</span>
<span id="cb29-3"><a href="#cb29-3" tabindex="-1"></a> <span class="st">"runif"</span>, <span class="fu">list</span>(<span class="at">n =</span> <span class="dv">10</span>), </span>
<span id="cb29-4"><a href="#cb29-4" tabindex="-1"></a> <span class="st">"rnorm"</span>, <span class="fu">list</span>(<span class="at">n =</span> <span class="dv">20</span>),</span>
<span id="cb29-5"><a href="#cb29-5" tabindex="-1"></a> <span class="st">"rpois"</span>, <span class="fu">list</span>(<span class="at">n =</span> <span class="dv">10</span>, <span class="at">lambda =</span> <span class="dv">5</span>),</span>
<span id="cb29-6"><a href="#cb29-6" tabindex="-1"></a>) <span class="sc">%>%</span></span>
<span id="cb29-7"><a href="#cb29-7" tabindex="-1"></a> <span class="fu">rowwise</span>()</span>
<span id="cb29-8"><a href="#cb29-8" tabindex="-1"></a></span>
<span id="cb29-9"><a href="#cb29-9" tabindex="-1"></a>df <span class="sc">%>%</span> </span>
<span id="cb29-10"><a href="#cb29-10" tabindex="-1"></a> <span class="fu">mutate</span>(<span class="at">data =</span> <span class="fu">list</span>(<span class="fu">do.call</span>(rng, params)))</span>
<span id="cb29-11"><a href="#cb29-11" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 3</span></span>
<span id="cb29-12"><a href="#cb29-12" tabindex="-1"></a><span class="co">#> # Rowwise: </span></span>
<span id="cb29-13"><a href="#cb29-13" tabindex="-1"></a><span class="co">#> rng params data </span></span>
<span id="cb29-14"><a href="#cb29-14" tabindex="-1"></a><span class="co">#> <chr> <list> <list> </span></span>
<span id="cb29-15"><a href="#cb29-15" tabindex="-1"></a><span class="co">#> 1 runif <named list [1]> <dbl [10]></span></span>
<span id="cb29-16"><a href="#cb29-16" tabindex="-1"></a><span class="co">#> 2 rnorm <named list [1]> <dbl [20]></span></span>
<span id="cb29-17"><a href="#cb29-17" tabindex="-1"></a><span class="co">#> 3 rpois <named list [2]> <int [10]></span></span></code></pre></div>
</div>
</div>
<div id="previously" class="section level2">
<h2>Previously</h2>
<div id="rowwise" class="section level3">
<h3><code>rowwise()</code></h3>
<p><code>rowwise()</code> was also questioning for quite some time,
partly because I didn’t appreciate how many people needed the native
ability to compute summaries across multiple variables for each row. As
an alternative, we recommended performing row-wise operations with the
purrr <code>map()</code> functions. However, this was challenging
because you needed to pick a map function based on the number of
arguments that were varying and the type of result, which required quite
some knowledge of purrr functions.</p>
<p>I was also resistant to <code>rowwise()</code> because I felt like
automatically switching between <code>[</code> to <code>[[</code> was
too magical in the same way that automatically <code>list()</code>-ing
results made <code>do()</code> too magical. I’ve now persuaded myself
that the row-wise magic is good magic partly because most people find
the distinction between <code>[</code> and <code>[[</code> mystifying
and <code>rowwise()</code> means that you don’t need to think about
it.</p>
<p>Since <code>rowwise()</code> clearly is useful it is not longer
questioning, and we expect it to be around for the long term.</p>
</div>
<div id="do" class="section level3">
<h3><code>do()</code></h3>
<p>We’ve questioned the need for <code>do()</code> for quite some time,
because it never felt very similar to the other dplyr verbs. It had two
main modes of operation:</p>
<ul>
<li><p>Without argument names: you could call functions that input and
output data frames using <code>.</code> to refer to the “current” group.
For example, the following code gets the first row of each group:</p>
<div class="sourceCode" id="cb30"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb30-1"><a href="#cb30-1" tabindex="-1"></a>mtcars <span class="sc">%>%</span> </span>
<span id="cb30-2"><a href="#cb30-2" tabindex="-1"></a> <span class="fu">group_by</span>(cyl) <span class="sc">%>%</span> </span>
<span id="cb30-3"><a href="#cb30-3" tabindex="-1"></a> <span class="fu">do</span>(<span class="fu">head</span>(., <span class="dv">1</span>))</span>
<span id="cb30-4"><a href="#cb30-4" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 13</span></span>
<span id="cb30-5"><a href="#cb30-5" tabindex="-1"></a><span class="co">#> # Groups: cyl [3]</span></span>
<span id="cb30-6"><a href="#cb30-6" tabindex="-1"></a><span class="co">#> mpg cyl disp hp drat wt qsec vs am gear carb cyl2 cyl4</span></span>
<span id="cb30-7"><a href="#cb30-7" tabindex="-1"></a><span class="co">#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl></span></span>
<span id="cb30-8"><a href="#cb30-8" tabindex="-1"></a><span class="co">#> 1 22.8 4 108 93 3.85 2.32 18.6 1 1 4 1 8 16</span></span>
<span id="cb30-9"><a href="#cb30-9" tabindex="-1"></a><span class="co">#> 2 21 6 160 110 3.9 2.62 16.5 0 1 4 4 12 24</span></span>
<span id="cb30-10"><a href="#cb30-10" tabindex="-1"></a><span class="co">#> 3 18.7 8 360 175 3.15 3.44 17.0 0 0 3 2 16 32</span></span></code></pre></div>
<p>This has been superseded by <code>pick()</code> plus
<code>reframe()</code>, a variant of <code>summarise()</code> that can
create multiple rows and columns per group.</p>
<div class="sourceCode" id="cb31"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb31-1"><a href="#cb31-1" tabindex="-1"></a>mtcars <span class="sc">%>%</span> </span>
<span id="cb31-2"><a href="#cb31-2" tabindex="-1"></a> <span class="fu">group_by</span>(cyl) <span class="sc">%>%</span> </span>
<span id="cb31-3"><a href="#cb31-3" tabindex="-1"></a> <span class="fu">reframe</span>(<span class="fu">head</span>(<span class="fu">pick</span>(<span class="fu">everything</span>()), <span class="dv">1</span>))</span>
<span id="cb31-4"><a href="#cb31-4" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 13</span></span>
<span id="cb31-5"><a href="#cb31-5" tabindex="-1"></a><span class="co">#> cyl mpg disp hp drat wt qsec vs am gear carb cyl2 cyl4</span></span>
<span id="cb31-6"><a href="#cb31-6" tabindex="-1"></a><span class="co">#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl></span></span>
<span id="cb31-7"><a href="#cb31-7" tabindex="-1"></a><span class="co">#> 1 4 22.8 108 93 3.85 2.32 18.6 1 1 4 1 8 16</span></span>
<span id="cb31-8"><a href="#cb31-8" tabindex="-1"></a><span class="co">#> 2 6 21 160 110 3.9 2.62 16.5 0 1 4 4 12 24</span></span>
<span id="cb31-9"><a href="#cb31-9" tabindex="-1"></a><span class="co">#> 3 8 18.7 360 175 3.15 3.44 17.0 0 0 3 2 16 32</span></span></code></pre></div></li>
<li><p>With arguments: it worked like <code>mutate()</code> but
automatically wrapped every element in a list:</p>
<div class="sourceCode" id="cb32"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb32-1"><a href="#cb32-1" tabindex="-1"></a>mtcars <span class="sc">%>%</span> </span>
<span id="cb32-2"><a href="#cb32-2" tabindex="-1"></a> <span class="fu">group_by</span>(cyl) <span class="sc">%>%</span> </span>
<span id="cb32-3"><a href="#cb32-3" tabindex="-1"></a> <span class="fu">do</span>(<span class="at">nrows =</span> <span class="fu">nrow</span>(.))</span>
<span id="cb32-4"><a href="#cb32-4" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 2</span></span>
<span id="cb32-5"><a href="#cb32-5" tabindex="-1"></a><span class="co">#> # Rowwise: </span></span>
<span id="cb32-6"><a href="#cb32-6" tabindex="-1"></a><span class="co">#> cyl nrows </span></span>
<span id="cb32-7"><a href="#cb32-7" tabindex="-1"></a><span class="co">#> <dbl> <list> </span></span>
<span id="cb32-8"><a href="#cb32-8" tabindex="-1"></a><span class="co">#> 1 4 <int [1]></span></span>
<span id="cb32-9"><a href="#cb32-9" tabindex="-1"></a><span class="co">#> 2 6 <int [1]></span></span>
<span id="cb32-10"><a href="#cb32-10" tabindex="-1"></a><span class="co">#> 3 8 <int [1]></span></span></code></pre></div>
<p>I now believe that behaviour is both too magical and not very useful,
and it can be replaced by <code>summarise()</code> and
<code>pick()</code>.</p>
<div class="sourceCode" id="cb33"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb33-1"><a href="#cb33-1" tabindex="-1"></a>mtcars <span class="sc">%>%</span> </span>
<span id="cb33-2"><a href="#cb33-2" tabindex="-1"></a> <span class="fu">group_by</span>(cyl) <span class="sc">%>%</span> </span>
<span id="cb33-3"><a href="#cb33-3" tabindex="-1"></a> <span class="fu">summarise</span>(<span class="at">nrows =</span> <span class="fu">nrow</span>(<span class="fu">pick</span>(<span class="fu">everything</span>())))</span>
<span id="cb33-4"><a href="#cb33-4" tabindex="-1"></a><span class="co">#> # A tibble: 3 × 2</span></span>
<span id="cb33-5"><a href="#cb33-5" tabindex="-1"></a><span class="co">#> cyl nrows</span></span>
<span id="cb33-6"><a href="#cb33-6" tabindex="-1"></a><span class="co">#> <dbl> <int></span></span>
<span id="cb33-7"><a href="#cb33-7" tabindex="-1"></a><span class="co">#> 1 4 11</span></span>
<span id="cb33-8"><a href="#cb33-8" tabindex="-1"></a><span class="co">#> 2 6 7</span></span>
<span id="cb33-9"><a href="#cb33-9" tabindex="-1"></a><span class="co">#> 3 8 14</span></span></code></pre></div>
<p>If needed (unlike here), you can wrap the results in a list
yourself.</p></li>
</ul>
<p>The addition of <code>pick()</code>/<code>across()</code> and the
increased scope of <code>summarise()</code>/<code>reframe()</code> means
that <code>do()</code> is no longer needed, so it is now superseded.</p>
</div>
</div>
<!-- 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>
|
