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>dplyr <-> base R</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">dplyr <-> base R</h1> This vignette compares dplyr functions to their base R equivalents. This helps those familiar with base R understand better what dplyr does, and shows dplyr users how you might express the same ideas in base R code. We’ll start with a rough overview of the major differences, then discuss the one table verbs in more detail, followed by the two table verbs. <div id="overview" class="section level1"> <h1>Overview</h1> <ol style="list-style-type: decimal"> <li>The code dplyr verbs input and output data frames. This contrasts with base R functions which more frequently work with individual vectors.</li> <li>dplyr relies heavily on “non-standard evaluation” so that you don’t need to use <code>$</code> to refer to columns in the “current” data frame. This behaviour is inspired by the base functions <code>subset()</code> and <code>transform()</code>.</li> <li>dplyr solutions tend to use a variety of single purpose verbs, while base R solutions typically tend to use <code>[</code> in a variety of ways, depending on the task at hand.</li> <li>Multiple dplyr verbs are often strung together into a pipeline by <code>%>%</code>. In base R, you’ll typically save intermediate results to a variable that you either discard, or repeatedly overwrite.</li> <li>All dplyr verbs handle “grouped” data frames so that the code to perform a computation per-group looks very similar to code that works on a whole data frame. In base R, per-group operations tend to have varied forms.</li> </ol> </div> <div id="one-table-verbs" class="section level1"> <h1>One table verbs</h1> The following table shows a condensed translation between dplyr verbs and their base R equivalents. The following sections describe each operation in more detail. You’ll learn more about the dplyr verbs in their documentation and in <code>vignette("dplyr")</code>. <table> <colgroup> <col width="38%" /> <col width="61%" /> </colgroup> <thead> <tr class="header"> <th>dplyr</th> <th>base</th> </tr> </thead> <tbody> <tr class="odd"> <td><code>arrange(df, x)</code></td> <td><code>df[order(x), , drop = FALSE]</code></td> </tr> <tr class="even"> <td><code>distinct(df, x)</code></td> <td><code>df[!duplicated(x), , drop = FALSE]</code>, <code>unique()</code></td> </tr> <tr class="odd"> <td><code>filter(df, x)</code></td> <td><code>df[which(x), , drop = FALSE]</code>, <code>subset()</code></td> </tr> <tr class="even"> <td><code>mutate(df, z = x + y)</code></td> <td><code>df$z <- df$x + df$y</code>, <code>transform()</code></td> </tr> <tr class="odd"> <td><code>pull(df, 1)</code></td> <td><code>df[[1]]</code></td> </tr> <tr class="even"> <td><code>pull(df, x)</code></td> <td><code>df$x</code></td> </tr> <tr class="odd"> <td><code>rename(df, y = x)</code></td> <td><code>names(df)[names(df) == "x"] <- "y"</code></td> </tr> <tr class="even"> <td><code>relocate(df, y)</code></td> <td><code>df[union("y", names(df))]</code></td> </tr> <tr class="odd"> <td><code>select(df, x, y)</code></td> <td><code>df[c("x", "y")]</code>, <code>subset()</code></td> </tr> <tr class="even"> <td><code>select(df, starts_with("x"))</code></td> <td><code>df[grepl("^x", names(df))]</code></td> </tr> <tr class="odd"> <td><code>summarise(df, mean(x))</code></td> <td><code>mean(df$x)</code>, <code>tapply()</code>, <code>aggregate()</code>, <code>by()</code></td> </tr> <tr class="even"> <td><code>slice(df, c(1, 2, 5))</code></td> <td><code>df[c(1, 2, 5), , drop = FALSE]</code></td> </tr> </tbody> </table> To begin, we’ll load dplyr and convert <code>mtcars</code> and <code>iris</code> to tibbles so that we can easily show only abbreviated output for each operation. <div class="sourceCode" id="cb1"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb1-1" tabindex="-1"></a>library(dplyr) <a href="#cb1-2" tabindex="-1"></a>mtcars <- as_tibble(mtcars) <a href="#cb1-3" tabindex="-1"></a>iris <- as_tibble(iris)</code></pre></div> <div id="arrange-arrange-rows-by-variables" class="section level2"> <h2><code>arrange()</code>: Arrange rows by variables</h2> <code>dplyr::arrange()</code> orders the rows of a data frame by the values of one or more columns: <div class="sourceCode" id="cb2"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb2-1" tabindex="-1"></a>mtcars %>% arrange(cyl, disp) <a href="#cb2-2" tabindex="-1"></a>#> # A tibble: 32 × 11 <a href="#cb2-3" tabindex="-1"></a>#> mpg cyl disp hp drat wt qsec vs am gear carb <a href="#cb2-4" tabindex="-1"></a>#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <a href="#cb2-5" tabindex="-1"></a>#> 1 33.9 4 71.1 65 4.22 1.84 19.9 1 1 4 1 <a href="#cb2-6" tabindex="-1"></a>#> 2 30.4 4 75.7 52 4.93 1.62 18.5 1 1 4 2 <a href="#cb2-7" tabindex="-1"></a>#> 3 32.4 4 78.7 66 4.08 2.2 19.5 1 1 4 1 <a href="#cb2-8" tabindex="-1"></a>#> 4 27.3 4 79 66 4.08 1.94 18.9 1 1 4 1 <a href="#cb2-9" tabindex="-1"></a>#> # ℹ 28 more rows</code></pre></div> The <code>desc()</code> helper allows you to order selected variables in descending order: <div class="sourceCode" id="cb3"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb3-1" tabindex="-1"></a>mtcars %>% arrange(desc(cyl), desc(disp)) <a href="#cb3-2" tabindex="-1"></a>#> # A tibble: 32 × 11 <a href="#cb3-3" tabindex="-1"></a>#> mpg cyl disp hp drat wt qsec vs am gear carb <a href="#cb3-4" tabindex="-1"></a>#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <a href="#cb3-5" tabindex="-1"></a>#> 1 10.4 8 472 205 2.93 5.25 18.0 0 0 3 4 <a href="#cb3-6" tabindex="-1"></a>#> 2 10.4 8 460 215 3 5.42 17.8 0 0 3 4 <a href="#cb3-7" tabindex="-1"></a>#> 3 14.7 8 440 230 3.23 5.34 17.4 0 0 3 4 <a href="#cb3-8" tabindex="-1"></a>#> 4 19.2 8 400 175 3.08 3.84 17.0 0 0 3 2 <a href="#cb3-9" tabindex="-1"></a>#> # ℹ 28 more rows</code></pre></div> We can replicate in base R by using <code>[</code> with <code>order()</code>: <div class="sourceCode" id="cb4"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb4-1" tabindex="-1"></a>mtcars[order(mtcars$cyl, mtcars$disp), , drop = FALSE] <a href="#cb4-2" tabindex="-1"></a>#> # A tibble: 32 × 11 <a href="#cb4-3" tabindex="-1"></a>#> mpg cyl disp hp drat wt qsec vs am gear carb <a href="#cb4-4" tabindex="-1"></a>#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <a href="#cb4-5" tabindex="-1"></a>#> 1 33.9 4 71.1 65 4.22 1.84 19.9 1 1 4 1 <a href="#cb4-6" tabindex="-1"></a>#> 2 30.4 4 75.7 52 4.93 1.62 18.5 1 1 4 2 <a href="#cb4-7" tabindex="-1"></a>#> 3 32.4 4 78.7 66 4.08 2.2 19.5 1 1 4 1 <a href="#cb4-8" tabindex="-1"></a>#> 4 27.3 4 79 66 4.08 1.94 18.9 1 1 4 1 <a href="#cb4-9" tabindex="-1"></a>#> # ℹ 28 more rows</code></pre></div> Note the use of <code>drop = FALSE</code>. If you forget this, and the input is a data frame with a single column, the output will be a vector, not a data frame. This is a source of subtle bugs. Base R does not provide a convenient and general way to sort individual variables in descending order, so you have two options: <ul> <li>For numeric variables, you can use <code>-x</code>.</li> <li>You can request <code>order()</code> to sort all variables in descending order.</li> </ul> <div class="sourceCode" id="cb5"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb5-1" tabindex="-1"></a>mtcars[order(mtcars$cyl, mtcars$disp, decreasing = TRUE), , drop = FALSE] <a href="#cb5-2" tabindex="-1"></a>mtcars[order(-mtcars$cyl, -mtcars$disp), , drop = FALSE]</code></pre></div> </div> <div id="distinct-select-distinctunique-rows" class="section level2"> <h2><code>distinct()</code>: Select distinct/unique rows</h2> <code>dplyr::distinct()</code> selects unique rows: <div class="sourceCode" id="cb6"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb6-1" tabindex="-1"></a>df <- tibble( <a href="#cb6-2" tabindex="-1"></a> x = sample(10, 100, rep = TRUE), <a href="#cb6-3" tabindex="-1"></a> y = sample(10, 100, rep = TRUE) <a href="#cb6-4" tabindex="-1"></a>) <a href="#cb6-5" tabindex="-1"></a> <a href="#cb6-6" tabindex="-1"></a>df %>% distinct(x) # selected columns <a href="#cb6-7" tabindex="-1"></a>#> # A tibble: 10 × 1 <a href="#cb6-8" tabindex="-1"></a>#> x <a href="#cb6-9" tabindex="-1"></a>#> <int> <a href="#cb6-10" tabindex="-1"></a>#> 1 8 <a href="#cb6-11" tabindex="-1"></a>#> 2 7 <a href="#cb6-12" tabindex="-1"></a>#> 3 10 <a href="#cb6-13" tabindex="-1"></a>#> 4 4 <a href="#cb6-14" tabindex="-1"></a>#> # ℹ 6 more rows <a href="#cb6-15" tabindex="-1"></a>df %>% distinct(x, .keep_all = TRUE) # whole data frame <a href="#cb6-16" tabindex="-1"></a>#> # A tibble: 10 × 2 <a href="#cb6-17" tabindex="-1"></a>#> x y <a href="#cb6-18" tabindex="-1"></a>#> <int> <int> <a href="#cb6-19" tabindex="-1"></a>#> 1 8 7 <a href="#cb6-20" tabindex="-1"></a>#> 2 7 3 <a href="#cb6-21" tabindex="-1"></a>#> 3 10 1 <a href="#cb6-22" tabindex="-1"></a>#> 4 4 2 <a href="#cb6-23" tabindex="-1"></a>#> # ℹ 6 more rows</code></pre></div> There are two equivalents in base R, depending on whether you want the whole data frame, or just selected variables: <div class="sourceCode" id="cb7"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb7-1" tabindex="-1"></a>unique(df["x"]) # selected columns <a href="#cb7-2" tabindex="-1"></a>#> # A tibble: 10 × 1 <a href="#cb7-3" tabindex="-1"></a>#> x <a href="#cb7-4" tabindex="-1"></a>#> <int> <a href="#cb7-5" tabindex="-1"></a>#> 1 8 <a href="#cb7-6" tabindex="-1"></a>#> 2 7 <a href="#cb7-7" tabindex="-1"></a>#> 3 10 <a href="#cb7-8" tabindex="-1"></a>#> 4 4 <a href="#cb7-9" tabindex="-1"></a>#> # ℹ 6 more rows <a href="#cb7-10" tabindex="-1"></a>df[!duplicated(df$x), , drop = FALSE] # whole data frame <a href="#cb7-11" tabindex="-1"></a>#> # A tibble: 10 × 2 <a href="#cb7-12" tabindex="-1"></a>#> x y <a href="#cb7-13" tabindex="-1"></a>#> <int> <int> <a href="#cb7-14" tabindex="-1"></a>#> 1 8 7 <a href="#cb7-15" tabindex="-1"></a>#> 2 7 3 <a href="#cb7-16" tabindex="-1"></a>#> 3 10 1 <a href="#cb7-17" tabindex="-1"></a>#> 4 4 2 <a href="#cb7-18" tabindex="-1"></a>#> # ℹ 6 more rows</code></pre></div> </div> <div id="filter-return-rows-with-matching-conditions" class="section level2"> <h2><code>filter()</code>: Return rows with matching conditions</h2> <code>dplyr::filter()</code> selects rows where an expression is <code>TRUE</code>: <div class="sourceCode" id="cb8"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb8-1" tabindex="-1"></a>starwars %>% filter(species == "Human") <a href="#cb8-2" tabindex="-1"></a>#> # A tibble: 35 × 14 <a href="#cb8-3" tabindex="-1"></a>#> name height mass hair_color skin_color eye_color birth_year sex gender <a href="#cb8-4" tabindex="-1"></a>#> <chr> <int> <dbl> <chr> <chr> <chr> <dbl> <chr> <chr> <a href="#cb8-5" tabindex="-1"></a>#> 1 Luke Sky… 172 77 blond fair blue 19 male mascu… <a href="#cb8-6" tabindex="-1"></a>#> 2 Darth Va… 202 136 none white yellow 41.9 male mascu… <a href="#cb8-7" tabindex="-1"></a>#> 3 Leia Org… 150 49 brown light brown 19 fema… femin… <a href="#cb8-8" tabindex="-1"></a>#> 4 Owen Lars 178 120 brown, gr… light blue 52 male mascu… <a href="#cb8-9" tabindex="-1"></a>#> # ℹ 31 more rows <a href="#cb8-10" tabindex="-1"></a>#> # ℹ 5 more variables: homeworld <chr>, species <chr>, films <list>, <a href="#cb8-11" tabindex="-1"></a>#> # vehicles <list>, starships <list> <a href="#cb8-12" tabindex="-1"></a>starwars %>% filter(mass > 1000) <a href="#cb8-13" tabindex="-1"></a>#> # A tibble: 1 × 14 <a href="#cb8-14" tabindex="-1"></a>#> name height mass hair_color skin_color eye_color birth_year sex gender <a href="#cb8-15" tabindex="-1"></a>#> <chr> <int> <dbl> <chr> <chr> <chr> <dbl> <chr> <chr> <a href="#cb8-16" tabindex="-1"></a>#> 1 Jabba De… 175 1358 <NA> green-tan… orange 600 herm… mascu… <a href="#cb8-17" tabindex="-1"></a>#> # ℹ 5 more variables: homeworld <chr>, species <chr>, films <list>, <a href="#cb8-18" tabindex="-1"></a>#> # vehicles <list>, starships <list> <a href="#cb8-19" tabindex="-1"></a>starwars %>% filter(hair_color == "none" & eye_color == "black") <a href="#cb8-20" tabindex="-1"></a>#> # A tibble: 9 × 14 <a href="#cb8-21" tabindex="-1"></a>#> name height mass hair_color skin_color eye_color birth_year sex gender <a href="#cb8-22" tabindex="-1"></a>#> <chr> <int> <dbl> <chr> <chr> <chr> <dbl> <chr> <chr> <a href="#cb8-23" tabindex="-1"></a>#> 1 Nien Nunb 160 68 none grey black NA male mascu… <a href="#cb8-24" tabindex="-1"></a>#> 2 Gasgano 122 NA none white, bl… black NA male mascu… <a href="#cb8-25" tabindex="-1"></a>#> 3 Kit Fisto 196 87 none green black NA male mascu… <a href="#cb8-26" tabindex="-1"></a>#> 4 Plo Koon 188 80 none orange black 22 male mascu… <a href="#cb8-27" tabindex="-1"></a>#> # ℹ 5 more rows <a href="#cb8-28" tabindex="-1"></a>#> # ℹ 5 more variables: homeworld <chr>, species <chr>, films <list>, <a href="#cb8-29" tabindex="-1"></a>#> # vehicles <list>, starships <list></code></pre></div> The closest base equivalent (and the inspiration for <code>filter()</code>) is <code>subset()</code>: <div class="sourceCode" id="cb9"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb9-1" tabindex="-1"></a>subset(starwars, species == "Human") <a href="#cb9-2" tabindex="-1"></a>#> # A tibble: 35 × 14 <a href="#cb9-3" tabindex="-1"></a>#> name height mass hair_color skin_color eye_color birth_year sex gender <a href="#cb9-4" tabindex="-1"></a>#> <chr> <int> <dbl> <chr> <chr> <chr> <dbl> <chr> <chr> <a href="#cb9-5" tabindex="-1"></a>#> 1 Luke Sky… 172 77 blond fair blue 19 male mascu… <a href="#cb9-6" tabindex="-1"></a>#> 2 Darth Va… 202 136 none white yellow 41.9 male mascu… <a href="#cb9-7" tabindex="-1"></a>#> 3 Leia Org… 150 49 brown light brown 19 fema… femin… <a href="#cb9-8" tabindex="-1"></a>#> 4 Owen Lars 178 120 brown, gr… light blue 52 male mascu… <a href="#cb9-9" tabindex="-1"></a>#> # ℹ 31 more rows <a href="#cb9-10" tabindex="-1"></a>#> # ℹ 5 more variables: homeworld <chr>, species <chr>, films <list>, <a href="#cb9-11" tabindex="-1"></a>#> # vehicles <list>, starships <list> <a href="#cb9-12" tabindex="-1"></a>subset(starwars, mass > 1000) <a href="#cb9-13" tabindex="-1"></a>#> # A tibble: 1 × 14 <a href="#cb9-14" tabindex="-1"></a>#> name height mass hair_color skin_color eye_color birth_year sex gender <a href="#cb9-15" tabindex="-1"></a>#> <chr> <int> <dbl> <chr> <chr> <chr> <dbl> <chr> <chr> <a href="#cb9-16" tabindex="-1"></a>#> 1 Jabba De… 175 1358 <NA> green-tan… orange 600 herm… mascu… <a href="#cb9-17" tabindex="-1"></a>#> # ℹ 5 more variables: homeworld <chr>, species <chr>, films <list>, <a href="#cb9-18" tabindex="-1"></a>#> # vehicles <list>, starships <list> <a href="#cb9-19" tabindex="-1"></a>subset(starwars, hair_color == "none" & eye_color == "black") <a href="#cb9-20" tabindex="-1"></a>#> # A tibble: 9 × 14 <a href="#cb9-21" tabindex="-1"></a>#> name height mass hair_color skin_color eye_color birth_year sex gender <a href="#cb9-22" tabindex="-1"></a>#> <chr> <int> <dbl> <chr> <chr> <chr> <dbl> <chr> <chr> <a href="#cb9-23" tabindex="-1"></a>#> 1 Nien Nunb 160 68 none grey black NA male mascu… <a href="#cb9-24" tabindex="-1"></a>#> 2 Gasgano 122 NA none white, bl… black NA male mascu… <a href="#cb9-25" tabindex="-1"></a>#> 3 Kit Fisto 196 87 none green black NA male mascu… <a href="#cb9-26" tabindex="-1"></a>#> 4 Plo Koon 188 80 none orange black 22 male mascu… <a href="#cb9-27" tabindex="-1"></a>#> # ℹ 5 more rows <a href="#cb9-28" tabindex="-1"></a>#> # ℹ 5 more variables: homeworld <chr>, species <chr>, films <list>, <a href="#cb9-29" tabindex="-1"></a>#> # vehicles <list>, starships <list></code></pre></div> You can also use <code>[</code> but this also requires the use of <code>which()</code> to remove <code>NA</code>s: <div class="sourceCode" id="cb10"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb10-1" tabindex="-1"></a>starwars[which(starwars$species == "Human"), , drop = FALSE] <a href="#cb10-2" tabindex="-1"></a>#> # A tibble: 35 × 14 <a href="#cb10-3" tabindex="-1"></a>#> name height mass hair_color skin_color eye_color birth_year sex gender <a href="#cb10-4" tabindex="-1"></a>#> <chr> <int> <dbl> <chr> <chr> <chr> <dbl> <chr> <chr> <a href="#cb10-5" tabindex="-1"></a>#> 1 Luke Sky… 172 77 blond fair blue 19 male mascu… <a href="#cb10-6" tabindex="-1"></a>#> 2 Darth Va… 202 136 none white yellow 41.9 male mascu… <a href="#cb10-7" tabindex="-1"></a>#> 3 Leia Org… 150 49 brown light brown 19 fema… femin… <a href="#cb10-8" tabindex="-1"></a>#> 4 Owen Lars 178 120 brown, gr… light blue 52 male mascu… <a href="#cb10-9" tabindex="-1"></a>#> # ℹ 31 more rows <a href="#cb10-10" tabindex="-1"></a>#> # ℹ 5 more variables: homeworld <chr>, species <chr>, films <list>, <a href="#cb10-11" tabindex="-1"></a>#> # vehicles <list>, starships <list> <a href="#cb10-12" tabindex="-1"></a>starwars[which(starwars$mass > 1000), , drop = FALSE] <a href="#cb10-13" tabindex="-1"></a>#> # A tibble: 1 × 14 <a href="#cb10-14" tabindex="-1"></a>#> name height mass hair_color skin_color eye_color birth_year sex gender <a href="#cb10-15" tabindex="-1"></a>#> <chr> <int> <dbl> <chr> <chr> <chr> <dbl> <chr> <chr> <a href="#cb10-16" tabindex="-1"></a>#> 1 Jabba De… 175 1358 <NA> green-tan… orange 600 herm… mascu… <a href="#cb10-17" tabindex="-1"></a>#> # ℹ 5 more variables: homeworld <chr>, species <chr>, films <list>, <a href="#cb10-18" tabindex="-1"></a>#> # vehicles <list>, starships <list> <a href="#cb10-19" tabindex="-1"></a>starwars[which(starwars$hair_color == "none" & starwars$eye_color == "black"), , drop = FALSE] <a href="#cb10-20" tabindex="-1"></a>#> # A tibble: 9 × 14 <a href="#cb10-21" tabindex="-1"></a>#> name height mass hair_color skin_color eye_color birth_year sex gender <a href="#cb10-22" tabindex="-1"></a>#> <chr> <int> <dbl> <chr> <chr> <chr> <dbl> <chr> <chr> <a href="#cb10-23" tabindex="-1"></a>#> 1 Nien Nunb 160 68 none grey black NA male mascu… <a href="#cb10-24" tabindex="-1"></a>#> 2 Gasgano 122 NA none white, bl… black NA male mascu… <a href="#cb10-25" tabindex="-1"></a>#> 3 Kit Fisto 196 87 none green black NA male mascu… <a href="#cb10-26" tabindex="-1"></a>#> 4 Plo Koon 188 80 none orange black 22 male mascu… <a href="#cb10-27" tabindex="-1"></a>#> # ℹ 5 more rows <a href="#cb10-28" tabindex="-1"></a>#> # ℹ 5 more variables: homeworld <chr>, species <chr>, films <list>, <a href="#cb10-29" tabindex="-1"></a>#> # vehicles <list>, starships <list></code></pre></div> </div> <div id="mutate-create-or-transform-variables" class="section level2"> <h2><code>mutate()</code>: Create or transform variables</h2> <code>dplyr::mutate()</code> creates new variables from existing variables: <div class="sourceCode" id="cb11"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb11-1" tabindex="-1"></a>df %>% mutate(z = x + y, z2 = z ^ 2) <a href="#cb11-2" tabindex="-1"></a>#> # A tibble: 100 × 4 <a href="#cb11-3" tabindex="-1"></a>#> x y z z2 <a href="#cb11-4" tabindex="-1"></a>#> <int> <int> <int> <dbl> <a href="#cb11-5" tabindex="-1"></a>#> 1 8 7 15 225 <a href="#cb11-6" tabindex="-1"></a>#> 2 8 9 17 289 <a href="#cb11-7" tabindex="-1"></a>#> 3 7 3 10 100 <a href="#cb11-8" tabindex="-1"></a>#> 4 10 1 11 121 <a href="#cb11-9" tabindex="-1"></a>#> # ℹ 96 more rows</code></pre></div> The closest base equivalent is <code>transform()</code>, but note that it cannot use freshly created variables: <div class="sourceCode" id="cb12"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb12-1" tabindex="-1"></a>head(transform(df, z = x + y, z2 = (x + y) ^ 2)) <a href="#cb12-2" tabindex="-1"></a>#> x y z z2 <a href="#cb12-3" tabindex="-1"></a>#> 1 8 7 15 225 <a href="#cb12-4" tabindex="-1"></a>#> 2 8 9 17 289 <a href="#cb12-5" tabindex="-1"></a>#> 3 7 3 10 100 <a href="#cb12-6" tabindex="-1"></a>#> 4 10 1 11 121 <a href="#cb12-7" tabindex="-1"></a>#> 5 4 2 6 36 <a href="#cb12-8" tabindex="-1"></a>#> 6 2 1 3 9</code></pre></div> Alternatively, you can use <code>$<-</code>: <div class="sourceCode" id="cb13"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb13-1" tabindex="-1"></a>mtcars$cyl2 <- mtcars$cyl * 2 <a href="#cb13-2" tabindex="-1"></a>mtcars$cyl4 <- mtcars$cyl2 * 2</code></pre></div> When applied to a grouped data frame, <code>dplyr::mutate()</code> computes new variable once per group: <div class="sourceCode" id="cb14"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb14-1" tabindex="-1"></a>gf <- tibble(g = c(1, 1, 2, 2), x = c(0.5, 1.5, 2.5, 3.5)) <a href="#cb14-2" tabindex="-1"></a>gf %>% <a href="#cb14-3" tabindex="-1"></a> group_by(g) %>% <a href="#cb14-4" tabindex="-1"></a> mutate(x_mean = mean(x), x_rank = rank(x)) <a href="#cb14-5" tabindex="-1"></a>#> # A tibble: 4 × 4 <a href="#cb14-6" tabindex="-1"></a>#> # Groups: g [2] <a href="#cb14-7" tabindex="-1"></a>#> g x x_mean x_rank <a href="#cb14-8" tabindex="-1"></a>#> <dbl> <dbl> <dbl> <dbl> <a href="#cb14-9" tabindex="-1"></a>#> 1 1 0.5 1 1 <a href="#cb14-10" tabindex="-1"></a>#> 2 1 1.5 1 2 <a href="#cb14-11" tabindex="-1"></a>#> 3 2 2.5 3 1 <a href="#cb14-12" tabindex="-1"></a>#> 4 2 3.5 3 2</code></pre></div> To replicate this in base R, you can use <code>ave()</code>: <div class="sourceCode" id="cb15"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb15-1" tabindex="-1"></a>transform(gf, <a href="#cb15-2" tabindex="-1"></a> x_mean = ave(x, g, FUN = mean), <a href="#cb15-3" tabindex="-1"></a> x_rank = ave(x, g, FUN = rank) <a href="#cb15-4" tabindex="-1"></a>) <a href="#cb15-5" tabindex="-1"></a>#> g x x_mean x_rank <a href="#cb15-6" tabindex="-1"></a>#> 1 1 0.5 1 1 <a href="#cb15-7" tabindex="-1"></a>#> 2 1 1.5 1 2 <a href="#cb15-8" tabindex="-1"></a>#> 3 2 2.5 3 1 <a href="#cb15-9" tabindex="-1"></a>#> 4 2 3.5 3 2</code></pre></div> </div> <div id="pull-pull-out-a-single-variable" class="section level2"> <h2><code>pull()</code>: Pull out a single variable</h2> <code>dplyr::pull()</code> extracts a variable either by name or position: <div class="sourceCode" id="cb16"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb16-1" tabindex="-1"></a>mtcars %>% pull(1) <a href="#cb16-2" tabindex="-1"></a>#> [1] 21.0 21.0 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 17.8 16.4 17.3 15.2 10.4 <a href="#cb16-3" tabindex="-1"></a>#> [16] 10.4 14.7 32.4 30.4 33.9 21.5 15.5 15.2 13.3 19.2 27.3 26.0 30.4 15.8 19.7 <a href="#cb16-4" tabindex="-1"></a>#> [31] 15.0 21.4 <a href="#cb16-5" tabindex="-1"></a>mtcars %>% pull(cyl) <a href="#cb16-6" tabindex="-1"></a>#> [1] 6 6 4 6 8 6 8 4 4 6 6 8 8 8 8 8 8 4 4 4 4 8 8 8 8 4 4 4 8 6 8 4</code></pre></div> This equivalent to <code>[[</code> for positions and <code>$</code> for names: <div class="sourceCode" id="cb17"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb17-1" tabindex="-1"></a>mtcars[[1]] <a href="#cb17-2" tabindex="-1"></a>#> [1] 21.0 21.0 22.8 21.4 18.7 18.1 14.3 24.4 22.8 19.2 17.8 16.4 17.3 15.2 10.4 <a href="#cb17-3" tabindex="-1"></a>#> [16] 10.4 14.7 32.4 30.4 33.9 21.5 15.5 15.2 13.3 19.2 27.3 26.0 30.4 15.8 19.7 <a href="#cb17-4" tabindex="-1"></a>#> [31] 15.0 21.4 <a href="#cb17-5" tabindex="-1"></a>mtcars$cyl <a href="#cb17-6" tabindex="-1"></a>#> [1] 6 6 4 6 8 6 8 4 4 6 6 8 8 8 8 8 8 4 4 4 4 8 8 8 8 4 4 4 8 6 8 4</code></pre></div> </div> <div id="relocate-change-column-order" class="section level2"> <h2><code>relocate()</code>: Change column order</h2> <code>dplyr::relocate()</code> makes it easy to move a set of columns to a new position (by default, the front): <div class="sourceCode" id="cb18"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb18-1" tabindex="-1"></a># to front <a href="#cb18-2" tabindex="-1"></a>mtcars %>% relocate(gear, carb) <a href="#cb18-3" tabindex="-1"></a>#> # A tibble: 32 × 13 <a href="#cb18-4" tabindex="-1"></a>#> gear carb mpg cyl disp hp drat wt qsec vs am cyl2 cyl4 <a href="#cb18-5" tabindex="-1"></a>#> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <dbl> <a href="#cb18-6" tabindex="-1"></a>#> 1 4 4 21 6 160 110 3.9 2.62 16.5 0 1 12 24 <a href="#cb18-7" tabindex="-1"></a>#> 2 4 4 21 6 160 110 3.9 2.88 17.0 0 1