skimr

<!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>Grouped data</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 { display: inline-block; 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">Grouped data</h1> dplyr verbs are particularly powerful when you apply them to grouped data frames (<code>grouped_df</code> objects). This vignette shows you: <ul> <li>How to group, inspect, and ungroup with <code>group_by()</code> and friends.</li> <li>How individual dplyr verbs changes their behaviour when applied to grouped data frame.</li> <li>How to access data about the “current” group from within a verb.</li> </ul> We’ll start by loading dplyr: <div class="sourceCode" id="cb1"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb1-1" tabindex="-1"></a>library(dplyr)</code></pre></div> <div id="group_by" class="section level2"> <h2><code>group_by()</code></h2> The most important grouping verb is <code>group_by()</code>: it takes a data frame and one or more variables to group by: <div class="sourceCode" id="cb2"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb2-1" tabindex="-1"></a>by_species <- starwars %>% group_by(species) <a href="#cb2-2" tabindex="-1"></a>by_sex_gender <- starwars %>% group_by(sex, gender)</code></pre></div> You can see the grouping when you print the data: <div class="sourceCode" id="cb3"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb3-1" tabindex="-1"></a>by_species <a href="#cb3-2" tabindex="-1"></a>#> # A tibble: 87 × 14 <a href="#cb3-3" tabindex="-1"></a>#> # Groups: species [38] <a href="#cb3-4" tabindex="-1"></a>#> name height mass hair_color skin_color eye_color birth_year sex gender <a href="#cb3-5" tabindex="-1"></a>#> <chr> <int> <dbl> <chr> <chr> <chr> <dbl> <chr> <chr> <a href="#cb3-6" tabindex="-1"></a>#> 1 Luke Sky… 172 77 blond fair blue 19 male mascu… <a href="#cb3-7" tabindex="-1"></a>#> 2 C-3PO 167 75 <NA> gold yellow 112 none mascu… <a href="#cb3-8" tabindex="-1"></a>#> 3 R2-D2 96 32 <NA> white, bl… red 33 none mascu… <a href="#cb3-9" tabindex="-1"></a>#> 4 Darth Va… 202 136 none white yellow 41.9 male mascu… <a href="#cb3-10" tabindex="-1"></a>#> # ℹ 83 more rows <a href="#cb3-11" tabindex="-1"></a>#> # ℹ 5 more variables: homeworld <chr>, species <chr>, films <list>, <a href="#cb3-12" tabindex="-1"></a>#> # vehicles <list>, starships <list> <a href="#cb3-13" tabindex="-1"></a>by_sex_gender <a href="#cb3-14" tabindex="-1"></a>#> # A tibble: 87 × 14 <a href="#cb3-15" tabindex="-1"></a>#> # Groups: sex, gender [6] <a href="#cb3-16" tabindex="-1"></a>#> name height mass hair_color skin_color eye_color birth_year sex gender <a href="#cb3-17" tabindex="-1"></a>#> <chr> <int> <dbl> <chr> <chr> <chr> <dbl> <chr> <chr> <a href="#cb3-18" tabindex="-1"></a>#> 1 Luke Sky… 172 77 blond fair blue 19 male mascu… <a href="#cb3-19" tabindex="-1"></a>#> 2 C-3PO 167 75 <NA> gold yellow 112 none mascu… <a href="#cb3-20" tabindex="-1"></a>#> 3 R2-D2 96 32 <NA> white, bl… red 33 none mascu… <a href="#cb3-21" tabindex="-1"></a>#> 4 Darth Va… 202 136 none white yellow 41.9 male mascu… <a href="#cb3-22" tabindex="-1"></a>#> # ℹ 83 more rows <a href="#cb3-23" tabindex="-1"></a>#> # ℹ 5 more variables: homeworld <chr>, species <chr>, films <list>, <a href="#cb3-24" tabindex="-1"></a>#> # vehicles <list>, starships <list></code></pre></div> Or use <code>tally()</code> to count the number of rows in each group. The <code>sort</code> argument is useful if you want to see the largest groups up front. <div class="sourceCode" id="cb4"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb4-1" tabindex="-1"></a>by_species %>% tally() <a href="#cb4-2" tabindex="-1"></a>#> # A tibble: 38 × 2 <a href="#cb4-3" tabindex="-1"></a>#> species n <a href="#cb4-4" tabindex="-1"></a>#> <chr> <int> <a href="#cb4-5" tabindex="-1"></a>#> 1 Aleena 1 <a href="#cb4-6" tabindex="-1"></a>#> 2 Besalisk 1 <a href="#cb4-7" tabindex="-1"></a>#> 3 Cerean 1 <a href="#cb4-8" tabindex="-1"></a>#> 4 Chagrian 1 <a href="#cb4-9" tabindex="-1"></a>#> # ℹ 34 more rows <a href="#cb4-10" tabindex="-1"></a> <a href="#cb4-11" tabindex="-1"></a>by_sex_gender %>% tally(sort = TRUE) <a href="#cb4-12" tabindex="-1"></a>#> # A tibble: 6 × 3 <a href="#cb4-13" tabindex="-1"></a>#> # Groups: sex [5] <a href="#cb4-14" tabindex="-1"></a>#> sex gender n <a href="#cb4-15" tabindex="-1"></a>#> <chr> <chr> <int> <a href="#cb4-16" tabindex="-1"></a>#> 1 male masculine 60 <a href="#cb4-17" tabindex="-1"></a>#> 2 female feminine 16 <a href="#cb4-18" tabindex="-1"></a>#> 3 none masculine 5 <a href="#cb4-19" tabindex="-1"></a>#> 4 <NA> <NA> 4 <a href="#cb4-20" tabindex="-1"></a>#> # ℹ 2 more rows</code></pre></div> As well as grouping by existing variables, you can group by any function of existing variables. This is equivalent to performing a <code>mutate()</code> before the <code>group_by()</code>: <div class="sourceCode" id="cb5"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb5-1" tabindex="-1"></a>bmi_breaks <- c(0, 18.5, 25, 30, Inf) <a href="#cb5-2" tabindex="-1"></a> <a href="#cb5-3" tabindex="-1"></a>starwars %>% <a href="#cb5-4" tabindex="-1"></a> group_by(bmi_cat = cut(mass/(height/100)^2, breaks=bmi_breaks)) %>% <a href="#cb5-5" tabindex="-1"></a> tally() <a href="#cb5-6" tabindex="-1"></a>#> # A tibble: 5 × 2 <a href="#cb5-7" tabindex="-1"></a>#> bmi_cat n <a href="#cb5-8" tabindex="-1"></a>#> <fct> <int> <a href="#cb5-9" tabindex="-1"></a>#> 1 (0,18.5] 10 <a href="#cb5-10" tabindex="-1"></a>#> 2 (18.5,25] 24 <a href="#cb5-11" tabindex="-1"></a>#> 3 (25,30] 13 <a href="#cb5-12" tabindex="-1"></a>#> 4 (30,Inf] 12 <a href="#cb5-13" tabindex="-1"></a>#> # ℹ 1 more row</code></pre></div> </div> <div id="group-metadata" class="section level2"> <h2>Group metadata</h2> You can see underlying group data with <code>group_keys()</code>. It has one row for each group and one column for each grouping variable: <div class="sourceCode" id="cb6"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb6-1" tabindex="-1"></a>by_species %>% group_keys() <a href="#cb6-2" tabindex="-1"></a>#> # A tibble: 38 × 1 <a href="#cb6-3" tabindex="-1"></a>#> species <a href="#cb6-4" tabindex="-1"></a>#> <chr> <a href="#cb6-5" tabindex="-1"></a>#> 1 Aleena <a href="#cb6-6" tabindex="-1"></a>#> 2 Besalisk <a href="#cb6-7" tabindex="-1"></a>#> 3 Cerean <a href="#cb6-8" tabindex="-1"></a>#> 4 Chagrian <a href="#cb6-9" tabindex="-1"></a>#> # ℹ 34 more rows <a href="#cb6-10" tabindex="-1"></a> <a href="#cb6-11" tabindex="-1"></a>by_sex_gender %>% group_keys() <a href="#cb6-12" tabindex="-1"></a>#> # A tibble: 6 × 2 <a href="#cb6-13" tabindex="-1"></a>#> sex gender <a href="#cb6-14" tabindex="-1"></a>#> <chr> <chr> <a href="#cb6-15" tabindex="-1"></a>#> 1 female feminine <a href="#cb6-16" tabindex="-1"></a>#> 2 hermaphroditic masculine <a href="#cb6-17" tabindex="-1"></a>#> 3 male masculine <a href="#cb6-18" tabindex="-1"></a>#> 4 none feminine <a href="#cb6-19" tabindex="-1"></a>#> # ℹ 2 more rows</code></pre></div> You can see which group each row belongs to with <code>group_indices()</code>: <div class="sourceCode" id="cb7"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb7-1" tabindex="-1"></a>by_species %>% group_indices() <a href="#cb7-2" tabindex="-1"></a>#> [1] 11 6 6 11 11 11 11 6 11 11 11 11 34 11 24 12 11 11 36 11 11 6 31 11 11 <a href="#cb7-3" tabindex="-1"></a>#> [26] 18 11 11 8 26 11 21 11 10 10 10 38 30 7 38 11 37 32 32 33 35 29 11 3 20 <a href="#cb7-4" tabindex="-1"></a>#> [51] 37 27 13 23 16 4 11 11 11 9 17 17 11 11 11 11 5 2 15 15 11 1 6 25 19 <a href="#cb7-5" tabindex="-1"></a>#> [76] 28 14 34 11 38 22 11 11 11 6 38 11</code></pre></div> And which rows each group contains with <code>group_rows()</code>: <div class="sourceCode" id="cb8"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb8-1" tabindex="-1"></a>by_species %>% group_rows() %>% head() <a href="#cb8-2" tabindex="-1"></a>#> <list_of<integer>[6]> <a href="#cb8-3" tabindex="-1"></a>#> [[1]] <a href="#cb8-4" tabindex="-1"></a>#> [1] 72 <a href="#cb8-5" tabindex="-1"></a>#> <a href="#cb8-6" tabindex="-1"></a>#> [[2]] <a href="#cb8-7" tabindex="-1"></a>#> [1] 68 <a href="#cb8-8" tabindex="-1"></a>#> <a href="#cb8-9" tabindex="-1"></a>#> [[3]] <a href="#cb8-10" tabindex="-1"></a>#> [1] 49 <a href="#cb8-11" tabindex="-1"></a>#> <a href="#cb8-12" tabindex="-1"></a>#> [[4]] <a href="#cb8-13" tabindex="-1"></a>#> [1] 56 <a href="#cb8-14" tabindex="-1"></a>#> <a href="#cb8-15" tabindex="-1"></a>#> [[5]] <a href="#cb8-16" tabindex="-1"></a>#> [1] 67 <a href="#cb8-17" tabindex="-1"></a>#> <a href="#cb8-18" tabindex="-1"></a>#> [[6]] <a href="#cb8-19" tabindex="-1"></a>#> [1] 2 3 8 22 73 85</code></pre></div> Use <code>group_vars()</code> if you just want the names of the grouping variables: <div class="sourceCode" id="cb9"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb9-1" tabindex="-1"></a>by_species %>% group_vars() <a href="#cb9-2" tabindex="-1"></a>#> [1] "species" <a href="#cb9-3" tabindex="-1"></a>by_sex_gender %>% group_vars() <a href="#cb9-4" tabindex="-1"></a>#> [1] "sex" "gender"</code></pre></div> <div id="changing-and-adding-to-grouping-variables" class="section level3"> <h3>Changing and adding to grouping variables</h3> If you apply <code>group_by()</code> to an already grouped dataset, will overwrite the existing grouping variables. For example, the following code groups by <code>homeworld</code> instead of <code>species</code>: <div class="sourceCode" id="cb10"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb10-1" tabindex="-1"></a>by_species %>% <a href="#cb10-2" tabindex="-1"></a> group_by(homeworld) %>% <a href="#cb10-3" tabindex="-1"></a> tally() <a href="#cb10-4" tabindex="-1"></a>#> # A tibble: 49 × 2 <a href="#cb10-5" tabindex="-1"></a>#> homeworld n <a href="#cb10-6" tabindex="-1"></a>#> <chr> <int> <a href="#cb10-7" tabindex="-1"></a>#> 1 Alderaan 3 <a href="#cb10-8" tabindex="-1"></a>#> 2 Aleen Minor 1 <a href="#cb10-9" tabindex="-1"></a>#> 3 Bespin 1 <a href="#cb10-10" tabindex="-1"></a>#> 4 Bestine IV 1 <a href="#cb10-11" tabindex="-1"></a>#> # ℹ 45 more rows</code></pre></div> To augment the grouping, using <code>.add = TRUE</code><a href="#fn1" class="footnote-ref" id="fnref1">1</a>. For example, the following code groups by species and homeworld: <div class="sourceCode" id="cb11"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb11-1" tabindex="-1"></a>by_species %>% <a href="#cb11-2" tabindex="-1"></a> group_by(homeworld, .add = TRUE) %>% <a href="#cb11-3" tabindex="-1"></a> tally() <a href="#cb11-4" tabindex="-1"></a>#> # A tibble: 58 × 3 <a href="#cb11-5" tabindex="-1"></a>#> # Groups: species [38] <a href="#cb11-6" tabindex="-1"></a>#> species homeworld n <a href="#cb11-7" tabindex="-1"></a>#> <chr> <chr> <int> <a href="#cb11-8" tabindex="-1"></a>#> 1 Aleena Aleen Minor 1 <a href="#cb11-9" tabindex="-1"></a>#> 2 Besalisk Ojom 1 <a href="#cb11-10" tabindex="-1"></a>#> 3 Cerean Cerea 1 <a href="#cb11-11" tabindex="-1"></a>#> 4 Chagrian Champala 1 <a href="#cb11-12" tabindex="-1"></a>#> # ℹ 54 more rows</code></pre></div> </div> <div id="removing-grouping-variables" class="section level3"> <h3>Removing grouping variables</h3> To remove all grouping variables, use <code>ungroup()</code>: <div class="sourceCode" id="cb12"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb12-1" tabindex="-1"></a>by_species %>% <a href="#cb12-2" tabindex="-1"></a> ungroup() %>% <a href="#cb12-3" tabindex="-1"></a> tally() <a href="#cb12-4" tabindex="-1"></a>#> # A tibble: 1 × 1 <a href="#cb12-5" tabindex="-1"></a>#> n <a href="#cb12-6" tabindex="-1"></a>#> <int> <a href="#cb12-7" tabindex="-1"></a>#> 1 87</code></pre></div> You can also choose to selectively ungroup by listing the variables you want to remove: <div class="sourceCode" id="cb13"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb13-1" tabindex="-1"></a>by_sex_gender %>% <a href="#cb13-2" tabindex="-1"></a> ungroup(sex) %>% <a href="#cb13-3" tabindex="-1"></a> tally() <a href="#cb13-4" tabindex="-1"></a>#> # A tibble: 3 × 2 <a href="#cb13-5" tabindex="-1"></a>#> gender n <a href="#cb13-6" tabindex="-1"></a>#> <chr> <int> <a href="#cb13-7" tabindex="-1"></a>#> 1 feminine 17 <a href="#cb13-8" tabindex="-1"></a>#> 2 masculine 66 <a href="#cb13-9" tabindex="-1"></a>#> 3 <NA> 4</code></pre></div> </div> </div> <div id="verbs" class="section level2"> <h2>Verbs</h2> The following sections describe how grouping affects the main dplyr verbs. <div id="summarise" class="section level3"> <h3><code>summarise()</code></h3> <code>summarise()</code> computes a summary for each group. This means that it starts from <code>group_keys()</code>, adding summary variables to the right hand side: <div class="sourceCode" id="cb14"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb14-1" tabindex="-1"></a>by_species %>% <a href="#cb14-2" tabindex="-1"></a> summarise( <a href="#cb14-3" tabindex="-1"></a> n = n(), <a href="#cb14-4" tabindex="-1"></a> height = mean(height, na.rm = TRUE) <a href="#cb14-5" tabindex="-1"></a> ) <a href="#cb14-6" tabindex="-1"></a>#> # A tibble: 38 × 3 <a href="#cb14-7" tabindex="-1"></a>#> species n height <a href="#cb14-8" tabindex="-1"></a>#> <chr> <int> <dbl> <a href="#cb14-9" tabindex="-1"></a>#> 1 Aleena 1 79 <a href="#cb14-10" tabindex="-1"></a>#> 2 Besalisk 1 198 <a href="#cb14-11" tabindex="-1"></a>#> 3 Cerean 1 198 <a href="#cb14-12" tabindex="-1"></a>#> 4 Chagrian 1 196 <a href="#cb14-13" tabindex="-1"></a>#> # ℹ 34 more rows</code></pre></div> The <code>.groups=</code> argument controls the grouping structure of the output. The historical behaviour of removing the right hand side grouping variable corresponds to <code>.groups = "drop_last"</code> without a message or <code>.groups = NULL</code> with a message (the default). <div class="sourceCode" id="cb15"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb15-1" tabindex="-1"></a>by_sex_gender %>% <a href="#cb15-2" tabindex="-1"></a> summarise(n = n()) %>% <a href="#cb15-3" tabindex="-1"></a> group_vars() <a href="#cb15-4" tabindex="-1"></a>#> `summarise()` has grouped output by 'sex'. You can override using the `.groups` <a href="#cb15-5" tabindex="-1"></a>#> argument. <a href="#cb15-6" tabindex="-1"></a>#> [1] "sex" <a href="#cb15-7" tabindex="-1"></a> <a href="#cb15-8" tabindex="-1"></a>by_sex_gender %>% <a href="#cb15-9" tabindex="-1"></a> summarise(n = n(), .groups = "drop_last") %>% <a href="#cb15-10" tabindex="-1"></a> group_vars() <a href="#cb15-11" tabindex="-1"></a>#> [1] "sex"</code></pre></div> Since version 1.0.0 the groups may also be kept (<code>.groups = "keep"</code>) or dropped (<code>.groups = "drop"</code>). <div class="sourceCode" id="cb16"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb16-1" tabindex="-1"></a>by_sex_gender %>% <a href="#cb16-2" tabindex="-1"></a> summarise(n = n(), .groups = "keep") %>% <a href="#cb16-3" tabindex="-1"></a> group_vars() <a href="#cb16-4" tabindex="-1"></a>#> [1] "sex" "gender" <a href="#cb16-5" tabindex="-1"></a> <a href="#cb16-6" tabindex="-1"></a>by_sex_gender %>% <a href="#cb16-7" tabindex="-1"></a> summarise(n = n(), .groups = "drop") %>% <a href="#cb16-8" tabindex="-1"></a> group_vars() <a href="#cb16-9" tabindex="-1"></a>#> character(0)</code></pre></div> When the output no longer have grouping variables, it becomes ungrouped (i.e. a regular tibble). </div> <div id="select-rename-and-relocate" class="section level3"> <h3><code>select()</code>, <code>rename()</code>, and <code>relocate()</code></h3> <code>rename()</code> and <code>relocate()</code> behave identically with grouped and ungrouped data because they only affect the name or position of existing columns. Grouped <code>select()</code> is almost identical to ungrouped select, except that it always includes the grouping variables: <div class="sourceCode" id="cb17"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb17-1" tabindex="-1"></a>by_species %>% select(mass) <a href="#cb17-2" tabindex="-1"></a>#> Adding missing grouping variables: `species` <a href="#cb17-3" tabindex="-1"></a>#> # A tibble: 87 × 2 <a href="#cb17-4" tabindex="-1"></a>#> # Groups: species [38] <a href="#cb17-5" tabindex="-1"></a>#> species mass <a href="#cb17-6" tabindex="-1"></a>#> <chr> <dbl> <a href="#cb17-7" tabindex="-1"></a>#> 1 Human 77 <a href="#cb17-8" tabindex="-1"></a>#> 2 Droid 75 <a href="#cb17-9" tabindex="-1"></a>#> 3 Droid 32 <a href="#cb17-10" tabindex="-1"></a>#> 4 Human 136 <a href="#cb17-11" tabindex="-1"></a>#> # ℹ 83 more rows</code></pre></div> If you don’t want the grouping variables, you’ll have to first <code>ungroup()</code>. (This design is possibly a mistake, but we’re stuck with it for now.) </div> <div id="arrange" class="section level3"> <h3><code>arrange()</code></h3> Grouped <code>arrange()</code> is the same as ungrouped <code>arrange()</code>, unless you set <code>.by_group = TRUE</code>, in which case it will order first by the grouping variables. <div class="sourceCode" id="cb18"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb18-1" tabindex="-1"></a>by_species %>% <a href="#cb18-2" tabindex="-1"></a> arrange(desc(mass)) %>% <a href="#cb18-3" tabindex="-1"></a> relocate(species, mass) <a href="#cb18-4" tabindex="-1"></a>#> # A tibble: 87 × 14 <a href="#cb18-5" tabindex="-1"></a>#> # Groups: species [38] <a href="#cb18-6" tabindex="-1"></a>#> species mass name height hair_color skin_color eye_color birth_year sex <a href="#cb18-7" tabindex="-1"></a>#> <chr> <dbl> <chr> <int> <chr> <chr> <chr> <dbl> <chr> <a href="#cb18-8" tabindex="-1"></a>#> 1 Hutt 1358 Jabba D… 175 <NA> green-tan… orange 600 herm… <a href="#cb18-9" tabindex="-1"></a>#> 2 Kaleesh 159 Grievous 216 none brown, wh… green, y… NA male <a href="#cb18-10" tabindex="-1"></a>#> 3 Droid 140 IG-88 200 none metal red 15 none <a href="#cb18-11" tabindex="-1"></a>#> 4 Human 136 Darth V… 202 none white yellow 41.9 male <a href="#cb18-12" tabindex="-1"></a>#> # ℹ 83 more rows <a href="#cb18-13" tabindex="-1"></a>#> # ℹ 5 more variables: gender <chr>, homeworld <chr>, films <list>, <a href="#cb18-14" tabindex="-1"></a>#> # vehicles <list>, starships <list> <a href="#cb18-15" tabindex="-1"></a> <a href="#cb18-16" tabindex="-1"></a>by_species %>% <a href="#cb18-17" tabindex="-1"></a> arrange(desc(mass), .by_group = TRUE) %>% <a href="#cb18-18" tabindex="-1"></a> relocate(species, mass) <a href="#cb18-19" tabindex="-1"></a>#> # A tibble: 87 × 14 <a href="#cb18-20" tabindex="-1"></a>#> # Groups: species [38] <a href="#cb18-21" tabindex="-1"></a>#> species mass name height hair_color skin_color eye_color birth_year sex <a href="#cb18-22" tabindex="-1"></a>#> <chr> <dbl> <chr> <int> <chr> <chr> <chr> <dbl> <chr> <a href="#cb18-23" tabindex="-1"></a>#> 1 Aleena 15 Ratts … 79 none grey, blue unknown NA male <a href="#cb18-24" tabindex="-1"></a>#> 2 Besalisk 102 Dexter… 198 none brown yellow NA male <a href="#cb18-25" tabindex="-1"></a>#> 3 Cerean 82 Ki-Adi… 198 white pale yellow 92 male <a href="#cb18-26" tabindex="-1"></a>#> 4 Chagrian NA Mas Am… 196 none blue blue NA male <a href="#cb18-27" tabindex="-1"></a>#> # ℹ 83 more rows <a href="#cb18-28" tabindex="-1"></a>#> # ℹ 5 more variables: gender <chr>, homeworld <chr>, films <list>, <a href="#cb18-29" tabindex="-1"></a>#> # vehicles <list>, starships <list></code></pre></div> Note that second example is sorted by <code>species</code> (from the <code>group_by()</code> statement) and then by <code>mass</code> (within species). </div> <div id="mutate" class="section level3"> <h3><code>mutate()</code></h3> In simple cases with vectorised functions, grouped and ungrouped <code>mutate()</code> give the same results. They differ when used with summary functions: <div class="sourceCode" id="cb19"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb19-1" tabindex="-1"></a># Subtract off global mean <a href="#cb19-2" tabindex="-1"></a>starwars %>% <a href="#cb19-3" tabindex="-1"></a> select(name, homeworld, mass) %>% <a href="#cb19-4" tabindex="-1"></a> mutate(standard_mass = mass - mean(mass, na.rm = TRUE)) <a href="#cb19-5" tabindex="-1"></a>#> # A tibble: 87 × 4 <a href="#cb19-6" tabindex="-1"></a>#> name homeworld mass standard_mass <a href="#cb19-7" tabindex="-1"></a>#> <chr> <chr> <dbl> <dbl> <a href="#cb19-8" tabindex="-1"></a>#> 1 Luke Skywalker Tatooine 77 -20.3 <a href="#cb19-9" tabindex="-1"></a>#> 2 C-3PO Tatooine 75 -22.3 <a href="#cb19-10" tabindex="-1"></a>#> 3 R2-D2 Naboo 32 -65.3 <a href="#cb19-11" tabindex="-1"></a>#> 4 Darth Vader Tatooine 136 38.7 <a href="#cb19-12" tabindex="-1"></a>#> # ℹ 83 more rows <a href="#cb19-13" tabindex="-1"></a> <a href="#cb19-14" tabindex="-1"></a># Subtract off homeworld mean <a href="#cb19-15" tabindex="-1"></a>starwars %>% <a href="#cb19-16" tabindex="-1"></a> select(name, homeworld, mass) %>% <a href="#cb19-17" tabindex="-1"></a> group_by(homeworld) %>% <a href="#cb19-18" tabindex="-1"></a> mutate(standard_mass = mass - mean(mass, na.rm = TRUE)) <a href="#cb19-19" tabindex="-1"></a>#> # A tibble: 87 × 4 <a href="#cb19-20" tabindex="-1"></a>#> # Groups: homeworld [49] <a href="#cb19-21" tabindex="-1"></a>#> name homeworld mass standard_mass <a href="#cb19-22" tabindex="-1"></a>#> <chr> <chr> <dbl> <dbl> <a href="#cb19-23" tabindex="-1"></a>#> 1 Luke Skywalker Tatooine 77 -8.38 <a href="#cb19-24" tabindex="-1"></a>#> 2 C-3PO Tatooine 75 -10.4 <a href="#cb19-25" tabindex="-1"></a>#> 3 R2-D2 Naboo 32 -32.2 <a href="#cb19-26" tabindex="-1"></a>#> 4 Darth Vader Tatooine 136 50.6 <a href="#cb19-27" tabindex="-1"></a>#> # ℹ 83 more rows</code></pre></div> Or with window functions like <code>min_rank()</code>: <div class="sourceCode" id="cb20"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb20-1" tabindex="-1"></a># Overall rank <a href="#cb20-2" tabindex="-1"></a>starwars %>% <a href="#cb20-3" tabindex="-1"></a> select(name, homeworld, height) %>% <a href="#cb20-4" tabindex="-1"></a> mutate(rank = min_rank(height)) <a href="#cb20-5" tabindex="-1"></a>#> # A tibble: 87 × 4 <a href="#cb20-6" tabindex="-1"></a>#> name homeworld height rank <a href="#cb20-7" tabindex="-1"></a>#> <chr> <chr> <int> <int> <a href="#cb20-8" tabindex="-1"></a>#> 1 Luke Skywalker Tatooine 172 29 <a href="#cb20-9" tabindex="-1"></a>#> 2 C-3PO Tatooine 167 21 <a href="#cb20-10" tabindex="-1"></a>#> 3 R2-D2 Naboo 96 5 <a href="#cb20-11" tabindex="-1"></a>#> 4 Darth Vader Tatooine 202 72 <a href="#cb20-12" tabindex="-1"></a>#> # ℹ 83 more rows <a href="#cb20-13" tabindex="-1"></a> <a href="#cb20-14" tabindex="-1"></a># Rank per homeworld <a href="#cb20-15" tabindex="-1"></a>starwars %>% <a href="#cb20-16" tabindex="-1"></a> select(name, homeworld, height) %>% <a href="#cb20-17" tabindex="-1"></a> group_by(homeworld) %>% <a href="#cb20-18" tabindex="-1"></a> mutate(rank = min_rank(height)) <a href="#cb20-19" tabindex="-1"></a>#> # A tibble: 87 × 4 <a href="#cb20-20" tabindex="-1"></a>#> # Groups: homeworld [49] <a href="#cb20-21" tabindex="-1"></a>#> name homeworld height rank <a href="#cb20-22" tabindex="-1"></a>#> <chr> <chr> <int> <int> <a href="#cb20-23" tabindex="-1"></a>#> 1 Luke Skywalker Tatooine 172 5 <a href="#cb20-24" tabindex="-1"></a>#> 2 C-3PO Tatooine 167 4 <a href="#cb20-25" tabindex="-1"></a>#> 3 R2-D2 Naboo 96 1 <a href="#cb20-26" tabindex="-1"></a>#> 4 Darth Vader Tatooine 202 10 <a href="#cb20-27" tabindex="-1"></a>#> # ℹ 83 more rows</code></pre></div> </div> <div id="filter" class="section level3"> <h3><code>filter()</code></h3> A grouped <code>filter()</code> effectively does a <code>mutate()</code> to generate a logical v