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>Invariants: Comparing behavior with data frames</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">Invariants: Comparing behavior with data frames</h1> <style type="text/css"> .dftbl { width: 100%; table-layout: fixed; display: inline-table; } .error pre code { color: red; } .warning pre code { color: violet; } </style> This vignette defines invariants for subsetting and subset-assignment for tibbles, and illustrates where their behaviour differs from data frames. The goal is to define a small set of invariants that consistently define how behaviors interact. Some behaviors are defined using functions of the vctrs package, e.g. <code>vec_slice()</code>, <code>vec_recycle()</code> and <code>vec_as_index()</code>. Refer to their documentation for more details about the invariants that they follow. The subsetting and subassignment operators for data frames and tibbles are particularly tricky, because they support both row and column indexes, both of which are optionally missing. We resolve this by first defining column access with <code>[[</code> and <code>$</code>, then column-wise subsetting with <code>[</code>, then row-wise subsetting, then the composition of both. <div id="conventions" class="section level2"> <h2>Conventions</h2> In this article, all behaviors are demonstrated using one example data frame and its tibble equivalent: <div class="sourceCode" id="cb1"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a>library(tibble) <a href="#cb1-2" aria-hidden="true" tabindex="-1"></a>library(vctrs) <a href="#cb1-3" aria-hidden="true" tabindex="-1"></a>new_df <- function() { <a href="#cb1-4" aria-hidden="true" tabindex="-1"></a> df <- data.frame(n = c(1L, NA, 3L, NA)) <a href="#cb1-5" aria-hidden="true" tabindex="-1"></a> df$c <- letters[5:8] <a href="#cb1-6" aria-hidden="true" tabindex="-1"></a> df$li <- list(9, 10:11, 12:14, "text") <a href="#cb1-7" aria-hidden="true" tabindex="-1"></a> df <a href="#cb1-8" aria-hidden="true" tabindex="-1"></a>} <a href="#cb1-9" aria-hidden="true" tabindex="-1"></a>new_tbl <- function() { <a href="#cb1-10" aria-hidden="true" tabindex="-1"></a> as_tibble(new_df()) <a href="#cb1-11" aria-hidden="true" tabindex="-1"></a>}</code></pre></div> Results of the same code for data frames and tibbles are presented side by side: <table class="dftbl"> <tbody> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb2"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a>new_df() <a href="#cb2-2" aria-hidden="true" tabindex="-1"></a>#> n c li <a href="#cb2-3" aria-hidden="true" tabindex="-1"></a>#> 1 1 e 9 <a href="#cb2-4" aria-hidden="true" tabindex="-1"></a>#> 2 NA f 10, 11 <a href="#cb2-5" aria-hidden="true" tabindex="-1"></a>#> 3 3 g 12, 13, 14 <a href="#cb2-6" aria-hidden="true" tabindex="-1"></a>#> 4 NA h text</code></pre></div> </td> <td> <div class="sourceCode" id="cb3"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb3-1" aria-hidden="true" tabindex="-1"></a>new_tbl() <a href="#cb3-2" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 4 × 3 <a href="#cb3-3" aria-hidden="true" tabindex="-1"></a>#> n c li <a href="#cb3-4" aria-hidden="true" tabindex="-1"></a>#> <int> <chr> <list> <a href="#cb3-5" aria-hidden="true" tabindex="-1"></a>#> 1 1 e <dbl [1]> <a href="#cb3-6" aria-hidden="true" tabindex="-1"></a>#> 2 NA f <int [2]> <a href="#cb3-7" aria-hidden="true" tabindex="-1"></a>#> 3 3 g <int [3]> <a href="#cb3-8" aria-hidden="true" tabindex="-1"></a>#> 4 NA h <chr [1]></code></pre></div> </td> </tr> </tbody> </table> If the results are identical (after converting to a data frame if necessary), only the tibble result is shown. Subsetting operations are read-only. The same objects are reused in all examples: <div class="sourceCode" id="cb4"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a>df <- new_df() <a href="#cb4-2" aria-hidden="true" tabindex="-1"></a>tbl <- new_tbl()</code></pre></div> Where needed, we also show examples with hierarchical columns containing a data frame or a matrix: <div class="sourceCode" id="cb5"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb5-1" aria-hidden="true" tabindex="-1"></a>new_tbl2 <- function() { <a href="#cb5-2" aria-hidden="true" tabindex="-1"></a> tibble( <a href="#cb5-3" aria-hidden="true" tabindex="-1"></a> tb = tbl, <a href="#cb5-4" aria-hidden="true" tabindex="-1"></a> m = diag(4) <a href="#cb5-5" aria-hidden="true" tabindex="-1"></a> ) <a href="#cb5-6" aria-hidden="true" tabindex="-1"></a>} <a href="#cb5-7" aria-hidden="true" tabindex="-1"></a>new_df2 <- function() { <a href="#cb5-8" aria-hidden="true" tabindex="-1"></a> df2 <- new_tbl2() <a href="#cb5-9" aria-hidden="true" tabindex="-1"></a> class(df2) <- "data.frame" <a href="#cb5-10" aria-hidden="true" tabindex="-1"></a> class(df2$tb) <- "data.frame" <a href="#cb5-11" aria-hidden="true" tabindex="-1"></a> df2 <a href="#cb5-12" aria-hidden="true" tabindex="-1"></a>} <a href="#cb5-13" aria-hidden="true" tabindex="-1"></a>df2 <- new_df2() <a href="#cb5-14" aria-hidden="true" tabindex="-1"></a>tbl2 <- new_tbl2()</code></pre></div> <table class="dftbl"> <tbody> <tr style="vertical-align:top"> <td> </td> <td> <div class="sourceCode" id="cb6"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a>new_tbl() <a href="#cb6-2" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 4 × 3 <a href="#cb6-3" aria-hidden="true" tabindex="-1"></a>#> n c li <a href="#cb6-4" aria-hidden="true" tabindex="-1"></a>#> <int> <chr> <list> <a href="#cb6-5" aria-hidden="true" tabindex="-1"></a>#> 1 1 e <dbl [1]> <a href="#cb6-6" aria-hidden="true" tabindex="-1"></a>#> 2 NA f <int [2]> <a href="#cb6-7" aria-hidden="true" tabindex="-1"></a>#> 3 3 g <int [3]> <a href="#cb6-8" aria-hidden="true" tabindex="-1"></a>#> 4 NA h <chr [1]></code></pre></div> </td> </tr> </tbody> </table> For subset assignment (subassignment, for short), we need a fresh copy of the data for each test. The <code>with_*()</code> functions (omitted here for brevity) allow for a more concise notation. These functions take an assignment expression, execute it on a fresh copy of the data, and return the data for printing. The first example prints what’s really executed, further examples omit this output. <table class="dftbl"> <tbody> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb7"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb7-1" aria-hidden="true" tabindex="-1"></a>with_df(df$n <- rev(df$n), verbose = TRUE) <a href="#cb7-2" aria-hidden="true" tabindex="-1"></a>#> { <a href="#cb7-3" aria-hidden="true" tabindex="-1"></a>#> df <- new_df() <a href="#cb7-4" aria-hidden="true" tabindex="-1"></a>#> df$n <- rev(df$n) <a href="#cb7-5" aria-hidden="true" tabindex="-1"></a>#> df <a href="#cb7-6" aria-hidden="true" tabindex="-1"></a>#> } <a href="#cb7-7" aria-hidden="true" tabindex="-1"></a>#> n c li <a href="#cb7-8" aria-hidden="true" tabindex="-1"></a>#> 1 NA e 9 <a href="#cb7-9" aria-hidden="true" tabindex="-1"></a>#> 2 3 f 10, 11 <a href="#cb7-10" aria-hidden="true" tabindex="-1"></a>#> 3 NA g 12, 13, 14 <a href="#cb7-11" aria-hidden="true" tabindex="-1"></a>#> 4 1 h text</code></pre></div> </td> <td> <div class="sourceCode" id="cb8"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a>with_tbl(tbl$n <- rev(tbl$n), verbose = TRUE) <a href="#cb8-2" aria-hidden="true" tabindex="-1"></a>#> { <a href="#cb8-3" aria-hidden="true" tabindex="-1"></a>#> tbl <- new_tbl() <a href="#cb8-4" aria-hidden="true" tabindex="-1"></a>#> tbl$n <- rev(tbl$n) <a href="#cb8-5" aria-hidden="true" tabindex="-1"></a>#> tbl <a href="#cb8-6" aria-hidden="true" tabindex="-1"></a>#> } <a href="#cb8-7" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 4 × 3 <a href="#cb8-8" aria-hidden="true" tabindex="-1"></a>#> n c li <a href="#cb8-9" aria-hidden="true" tabindex="-1"></a>#> <int> <chr> <list> <a href="#cb8-10" aria-hidden="true" tabindex="-1"></a>#> 1 NA e <dbl [1]> <a href="#cb8-11" aria-hidden="true" tabindex="-1"></a>#> 2 3 f <int [2]> <a href="#cb8-12" aria-hidden="true" tabindex="-1"></a>#> 3 NA g <int [3]> <a href="#cb8-13" aria-hidden="true" tabindex="-1"></a>#> 4 1 h <chr [1]></code></pre></div> </td> </tr> </tbody> </table> </div> <div id="column-extraction" class="section level2"> <h2>Column extraction</h2> <div id="definition-of-xj" class="section level3"> <h3>Definition of <code>x[[j]]</code></h3> <code>x[[j]]</code> is equal to <code>.subset2(x, j)</code>. <table class="dftbl"> <tbody> <tr style="vertical-align:top"> <td> </td> <td> <div class="sourceCode" id="cb9"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb9-1" aria-hidden="true" tabindex="-1"></a>tbl[[1]] <a href="#cb9-2" aria-hidden="true" tabindex="-1"></a>#> [1] 1 NA 3 NA</code></pre></div> </td> </tr> <tr style="vertical-align:top"> <td> </td> <td> <div class="sourceCode" id="cb10"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb10-1" aria-hidden="true" tabindex="-1"></a>.subset2(tbl, 1) <a href="#cb10-2" aria-hidden="true" tabindex="-1"></a>#> [1] 1 NA 3 NA</code></pre></div> </td> </tr> </tbody> </table> NB: <code>x[[j]]</code> always returns an object of size <code>nrow(x)</code> if the column exists. <code>j</code> must be a single number or a string, as enforced by <code>.subset2(x, j)</code>. <table class="dftbl"> <tbody> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb11"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb11-1" aria-hidden="true" tabindex="-1"></a>df[[1:2]] <a href="#cb11-2" aria-hidden="true" tabindex="-1"></a>#> [1] NA</code></pre></div> </td> <td> <div class="sourceCode" id="cb12"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb12-1" aria-hidden="true" tabindex="-1"></a>tbl[[1:2]] <a href="#cb12-2" aria-hidden="true" tabindex="-1"></a>#> Error: <a href="#cb12-3" aria-hidden="true" tabindex="-1"></a>#> ! The `j` argument of <a href="#cb12-4" aria-hidden="true" tabindex="-1"></a>#> `[[.tbl_df` can't be a vector of <a href="#cb12-5" aria-hidden="true" tabindex="-1"></a>#> length 2 as of tibble 3.0.0. <a href="#cb12-6" aria-hidden="true" tabindex="-1"></a>#> ℹ Recursive subsetting is <a href="#cb12-7" aria-hidden="true" tabindex="-1"></a>#> deprecated for tibbles.</code></pre></div> </td> </tr> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb13"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb13-1" aria-hidden="true" tabindex="-1"></a>df[[c("n", "c")]] <a href="#cb13-2" aria-hidden="true" tabindex="-1"></a>#> Error in .subset2(x, i, exact = exact): subscript out of bounds</code></pre></div> </td> <td> <div class="sourceCode" id="cb14"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb14-1" aria-hidden="true" tabindex="-1"></a>tbl[[c("n", "c")]] <a href="#cb14-2" aria-hidden="true" tabindex="-1"></a>#> Error in `tbl[[c("n", "c")]]`: <a href="#cb14-3" aria-hidden="true" tabindex="-1"></a>#> ! Can't extract column with `c("n", "c")`. <a href="#cb14-4" aria-hidden="true" tabindex="-1"></a>#> ✖ Subscript `c("n", "c")` must be size 1, not 2.</code></pre></div> </td> </tr> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb15"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb15-1" aria-hidden="true" tabindex="-1"></a>df[[TRUE]] <a href="#cb15-2" aria-hidden="true" tabindex="-1"></a>#> [1] 1 NA 3 NA</code></pre></div> </td> <td> <div class="sourceCode" id="cb16"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb16-1" aria-hidden="true" tabindex="-1"></a>tbl[[TRUE]] <a href="#cb16-2" aria-hidden="true" tabindex="-1"></a>#> Error in `tbl[[TRUE]]`: <a href="#cb16-3" aria-hidden="true" tabindex="-1"></a>#> ! Can't extract column with `TRUE`. <a href="#cb16-4" aria-hidden="true" tabindex="-1"></a>#> ✖ `TRUE` must be numeric or character, not `TRUE`.</code></pre></div> </td> </tr> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb17"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb17-1" aria-hidden="true" tabindex="-1"></a>df[[mean]] <a href="#cb17-2" aria-hidden="true" tabindex="-1"></a>#> Error in .subset2(x, i, exact = exact): invalid subscript type 'closure'</code></pre></div> </td> <td> <div class="sourceCode" id="cb18"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb18-1" aria-hidden="true" tabindex="-1"></a>tbl[[mean]] <a href="#cb18-2" aria-hidden="true" tabindex="-1"></a>#> Error in `tbl[[mean]]`: <a href="#cb18-3" aria-hidden="true" tabindex="-1"></a>#> ! Can't extract column with `mean`. <a href="#cb18-4" aria-hidden="true" tabindex="-1"></a>#> ✖ `mean` must be numeric or character, not a function.</code></pre></div> </td> </tr> </tbody> </table> <code>NA</code> indexes, numeric out-of-bounds (OOB) values, and non-integers throw an error: <table class="dftbl"> <tbody> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb19"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb19-1" aria-hidden="true" tabindex="-1"></a>df[[NA]] <a href="#cb19-2" aria-hidden="true" tabindex="-1"></a>#> NULL</code></pre></div> </td> <td> <div class="sourceCode" id="cb20"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb20-1" aria-hidden="true" tabindex="-1"></a>tbl[[NA]] <a href="#cb20-2" aria-hidden="true" tabindex="-1"></a>#> Error in `tbl[[NA]]`: <a href="#cb20-3" aria-hidden="true" tabindex="-1"></a>#> ! Can't extract column with `NA`. <a href="#cb20-4" aria-hidden="true" tabindex="-1"></a>#> ✖ Subscript `NA` must be a location, not an integer `NA`.</code></pre></div> </td> </tr> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb21"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb21-1" aria-hidden="true" tabindex="-1"></a>df[[NA_character_]] <a href="#cb21-2" aria-hidden="true" tabindex="-1"></a>#> NULL</code></pre></div> </td> <td> <div class="sourceCode" id="cb22"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb22-1" aria-hidden="true" tabindex="-1"></a>tbl[[NA_character_]] <a href="#cb22-2" aria-hidden="true" tabindex="-1"></a>#> Error in `tbl[[NA_character_]]`: <a href="#cb22-3" aria-hidden="true" tabindex="-1"></a>#> ! Can't extract column with `NA_character_`. <a href="#cb22-4" aria-hidden="true" tabindex="-1"></a>#> ✖ Subscript `NA_character_` must be a location, not a character `NA`.</code></pre></div> </td> </tr> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb23"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb23-1" aria-hidden="true" tabindex="-1"></a>df[[NA_integer_]] <a href="#cb23-2" aria-hidden="true" tabindex="-1"></a>#> NULL</code></pre></div> </td> <td> <div class="sourceCode" id="cb24"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb24-1" aria-hidden="true" tabindex="-1"></a>tbl[[NA_integer_]] <a href="#cb24-2" aria-hidden="true" tabindex="-1"></a>#> Error in `tbl[[NA_integer_]]`: <a href="#cb24-3" aria-hidden="true" tabindex="-1"></a>#> ! Can't extract column with `NA_integer_`. <a href="#cb24-4" aria-hidden="true" tabindex="-1"></a>#> ✖ Subscript `NA_integer_` must be a location, not an integer `NA`.</code></pre></div> </td> </tr> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb25"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb25-1" aria-hidden="true" tabindex="-1"></a>df[[-1]] <a href="#cb25-2" aria-hidden="true" tabindex="-1"></a>#> Error in .subset2(x, i, exact = exact): invalid negative subscript in get1index <real></code></pre></div> </td> <td> <div class="sourceCode" id="cb26"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb26-1" aria-hidden="true" tabindex="-1"></a>tbl[[-1]] <a href="#cb26-2" aria-hidden="true" tabindex="-1"></a>#> Error in `tbl[[-1]]`: <a href="#cb26-3" aria-hidden="true" tabindex="-1"></a>#> ! Can't extract column with `-1`. <a href="#cb26-4" aria-hidden="true" tabindex="-1"></a>#> ✖ Subscript `-1` must be a positive location, not -1.</code></pre></div> </td> </tr> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb27"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb27-1" aria-hidden="true" tabindex="-1"></a>df[[4]] <a href="#cb27-2" aria-hidden="true" tabindex="-1"></a>#> Error in .subset2(x, i, exact = exact): subscript out of bounds</code></pre></div> </td> <td> <div class="sourceCode" id="cb28"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb28-1" aria-hidden="true" tabindex="-1"></a>tbl[[4]] <a href="#cb28-2" aria-hidden="true" tabindex="-1"></a>#> Error in `tbl[[4]]`: <a href="#cb28-3" aria-hidden="true" tabindex="-1"></a>#> ! Can't extract columns past the end. <a href="#cb28-4" aria-hidden="true" tabindex="-1"></a>#> ℹ Location 4 doesn't exist. <a href="#cb28-5" aria-hidden="true" tabindex="-1"></a>#> ℹ There are only 3 columns.</code></pre></div> </td> </tr> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb29"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb29-1" aria-hidden="true" tabindex="-1"></a>df[[1.5]] <a href="#cb29-2" aria-hidden="true" tabindex="-1"></a>#> [1] 1 NA 3 NA</code></pre></div> </td> <td> <div class="sourceCode" id="cb30"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb30-1" aria-hidden="true" tabindex="-1"></a>tbl[[1.5]] <a href="#cb30-2" aria-hidden="true" tabindex="-1"></a>#> Error in `tbl[[1.5]]`: <a href="#cb30-3" aria-hidden="true" tabindex="-1"></a>#> ! Can't extract column with `1.5`. <a href="#cb30-4" aria-hidden="true" tabindex="-1"></a>#> ✖ Can't convert from `j` <double> to <integer> due to loss of precision.</code></pre></div> </td> </tr> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb31"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb31-1" aria-hidden="true" tabindex="-1"></a>df[[Inf]] <a href="#cb31-2" aria-hidden="true" tabindex="-1"></a>#> NULL</code></pre></div> </td> <td> <div class="sourceCode" id="cb32"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb32-1" aria-hidden="true" tabindex="-1"></a>tbl[[Inf]] <a href="#cb32-2" aria-hidden="true" tabindex="-1"></a>#> Error in `tbl[[Inf]]`: <a href="#cb32-3" aria-hidden="true" tabindex="-1"></a>#> ! Can't extract column with `Inf`. <a href="#cb32-4" aria-hidden="true" tabindex="-1"></a>#> ✖ Can't convert from `j` <double> to <integer> due to loss of precision.</code></pre></div> </td> </tr> </tbody> </table> Character OOB access is silent because a common package idiom is to check for the absence of a column with <code>is.null(df[[var]])</code>. <table class="dftbl"> <tbody> <tr style="vertical-align:top"> <td> </td> <td> <div class="sourceCode" id="cb33"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb33-1" aria-hidden="true" tabindex="-1"></a>tbl[["x"]] <a href="#cb33-2" aria-hidden="true" tabindex="-1"></a>#> NULL</code></pre></div> </td> </tr> </tbody> </table> </div> <div id="definition-of-xname" class="section level3"> <h3>Definition of <code>x$name</code></h3> <code>x$name</code> and <code>x$"name"</code> are equal to <code>x[["name"]]</code>. <table class="dftbl"> <tbody> <tr style="vertical-align:top"> <td> </td> <td> <div class="sourceCode" id="cb34"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb34-1" aria-hidden="true" tabindex="-1"></a>tbl$n <a href="#cb34-2" aria-hidden="true" tabindex="-1"></a>#> [1] 1 NA 3 NA</code></pre></div> </td> </tr> <tr style="vertical-align:top"> <td> </td> <td> <div class="sourceCode" id="cb35"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb35-1" aria-hidden="true" tabindex="-1"></a>tbl$"n" <a href="#cb35-2" aria-hidden="true" tabindex="-1"></a>#> [1] 1 NA 3 NA</code></pre></div> </td> </tr> <tr style="vertical-align:top"> <td> </td> <td> <div class="sourceCode" id="cb36"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb36-1" aria-hidden="true" tabindex="-1"></a>tbl[["n"]] <a href="#cb36-2" aria-hidden="true" tabindex="-1"></a>#> [1] 1 NA 3 NA</code></pre></div> </td> </tr> </tbody> </table> Unlike data frames, tibbles do not partially match names. Because <code>df$x</code> is rarely used in packages, it can raise a warning: <table class="dftbl"> <tbody> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb37"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb37-1" aria-hidden="true" tabindex="-1"></a>df$l <a href="#cb37-2" aria-hidden="true" tabindex="-1"></a>#> [[1]] <a href="#cb37-3" aria-hidden="true" tabindex="-1"></a>#> [1] 9 <a href="#cb37-4" aria-hidden="true" tabindex="-1"></a>#> <a href="#cb37-5" aria-hidden="true" tabindex="-1"></a>#> [[2]] <a href="#cb37-6" aria-hidden="true" tabindex="-1"></a>#> [1] 10 11 <a href="#cb37-7" aria-hidden="true" tabindex="-1"></a>#> <a href="#cb37-8" aria-hidden="true" tabindex="-1"></a>#> [[3]] <a href="#cb37-9" aria-hidden="true" tabindex="-1"></a>#> [1] 12 13 14 <a href="#cb37-10" aria-hidden="true" tabindex="-1"></a>#> <a href="#cb37-11" aria-hidden="true" tabindex="-1"></a>#> [[4]] <a href="#cb37-12" aria-hidden="true" tabindex="-1"></a>#> [1] "text"</code></pre></div> </td> <td> <div class="sourceCode" id="cb38"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb38-1" aria-hidden="true" tabindex="-1"></a>tbl$l <a href="#cb38-2" aria-hidden="true" tabindex="-1"></a>#> Warning: Unknown or uninitialised <a href="#cb38-3" aria-hidden="true" tabindex="-1"></a>#> column: `l`. <a href="#cb38-4" aria-hidden="true" tabindex="-1"></a>#> NULL</code></pre></div> </td> </tr> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb39"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb39-1" aria-hidden="true" tabindex="-1"></a>df$not_present <a href="#cb39-2" aria-hidden="true" tabindex="-1"></a>#> NULL</code></pre></div> </td> <td> <div class="sourceCode" id="cb40"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb40-1" aria-hidden="true" tabindex="-1"></a>tbl$not_present <a href="#cb40-2" aria-hidden="true" tabindex="-1"></a>#> Warning: Unknown or uninitialised <a href="#cb40-3" aria-hidden="true" tabindex="-1"></a>#> column: `not_present`. <a href="#cb40-4" aria-hidden="true" tabindex="-1"></a>#> NULL</code></pre></div> </td> </tr> </tbody> </table> </div> </div> <div id="column-subsetting" class="section level2"> <h2>Column subsetting</h2> <div id="definition-of-xj-1" class="section level3"> <h3>Definition of <code>x[j]</code></h3> <code>j</code> is converted to an integer vector by <code>vec_as_index(j, ncol(x), names = names(x))</code>. Then <code>x[c(j_1, j_2, ..., j_n)]</code> is equivalent to <code>tibble(x[[j_1]], x[[j_2]], ..., x[[j_n]])</code>, keeping the corresponding column names. This implies that <code>j</code> must be a numeric or character vector, or a logical vector with length 1 or <code>ncol(x)</code>.<a href="#fn1" class="footnote-ref" id="fnref1">1</a> <table class="dftbl"> <tbody> <tr style="vertical-align:top"> <td> </td> <td> <div class="sourceCode" id="cb41"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb41-1" aria-hidden="true" tabindex="-1"></a>tbl[1:2] <a href="#cb41-2" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 4 × 2 <a href="#cb41-3" aria-hidden="true" tabindex="-1"></a>#> n c <a href="#cb41-4" aria-hidden="true" tabindex="-1"></a>#> <int> <chr> <a href="#cb41-5" aria-hidden="true" tabindex="-1"></a>#> 1 1 e <a href="#cb41-6" aria-hidden="true" tabindex="-1"></a>#> 2 NA f <a href="#cb41-7" aria-hidden="true" tabindex="-1"></a>#> 3 3 g <a href="#cb41-8" aria-hidden="true" tabindex="-1"></a>#> 4 NA h</code></pre></div> </td> </tr> </tbody> </table> When subsetting repeated indexes, the resulting column names are undefined, do not rely on them. <table class="dftbl"> <tbody> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb42"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb42-1" aria-hidden="true" tabindex="-1"></a>df[c(1, 1)] <a href="#cb42-2" aria-hidden="true" tabindex="-1"></a>#> n n.1 <a href="#cb42-3" aria-hidden="true" tabindex="-1"></a>#> 1 1 1 <a href="#cb42-4" aria-hidden="true" tabindex="-1"></a>#> 2 NA NA <a href="#cb42-5" aria-hidden="true" tabindex="-1"></a>#> 3 3 3 <a href="#cb42-6" aria-hidden="true" tabindex="-1"></a>#> 4 NA NA</code></pre></div> </td> <td> <div class="sourceCode" id="cb43"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb43-1" aria-hidden="true" tabindex="-1"></a>tbl[c(1, 1)] <a href="#cb43-2" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 4 × 2 <a href="#cb43-3" aria-hidden="true" tabindex="-1"></a>#> n n <a href="#cb43-4" aria-hidden="true" tabindex="-1"></a>#> <int> <int> <a href="#cb43-5" aria-hidden="true" tabindex="-1"></a>#> 1 1 1 <a href="#cb43-6" aria-hidden="true" tabindex="-1"></a>#> 2 NA NA <a href="#cb43-7" aria-hidden="true" tabindex="-1"></a>#> 3 3 3 <a href="#cb43-8" aria-hidden="true" tabindex="-1"></a>#> 4 NA NA</code></pre></div> </td> </tr> </tbody> </table> For tibbles with repeated column names, subsetting by name uses the first matching column. <code>nrow(df[j])</code> equals <code>nrow(df)</code>. <table class="dftbl"> <tbody> <tr style="vertical-align:top"> <td> </td> <td> <div class="sourceCode" id="cb44"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb44-1" aria-hidden="true" tabindex="-1"></a>tbl[integer()] <a href="#cb44-2" aria-hidden="true" tabindex="-1"></a>#> # A tibble: 4 × 0</code></pre></div> </td> </tr> </tbody> </table> Tibbles support indexing by a logical matrix, but only if all values in the returned vector are compatible. <table class="dftbl"> <tbody> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb45"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb45-1" aria-hidden="true" tabindex="-1"></a>df[is.na(df)] <a href="#cb45-2" aria-hidden="true" tabindex="-1"></a>#> [[1]] <a href="#cb45-3" aria-hidden="true" tabindex="-1"></a>#> [1] NA <a href="#cb45-4" aria-hidden="true" tabindex="-1"></a>#> <a href="#cb45-5" aria-hidden="true" tabindex="-1"></a>#> [[2]] <a href="#cb45-6" aria-hidden="true" tabindex="-1"></a>#> [1] NA</code></pre></div> </td> <td> <div class="sourceCode" id="cb46"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb46-1" aria-hidden="true" tabindex="-1"></a>tbl[is.na(tbl)] <a href="#cb46-2" aria-hidden="true" tabindex="-1"></a>#> [1] NA NA</code></pre></div> </td> </tr> <tr style="vertical-align:top"> <td> <div class="sourceCode" id="cb47"><pre class="sourceCode r"><code class="sourceCode r"><a href="#cb47-1" aria-hidden="true" tabindex="-1"></a>df[!is.na(df)] <a href="#cb47-2" aria-hidden="true" tabindex="-1"></a>#> [[1]] <a href="#cb47-3" aria-hidden="true" tabindex="-1"></a>#> [1] 1 <a href="#cb47-4" aria-hidden="true" tabindex="-1"></a>#> <a href="#cb47-5" aria-hidden="true" tabindex="-1"></a>#> [[2]] <a href="#cb47-6" aria-hidden="true" tabindex="-1"></a>#> [1] 3 <a href="#cb47-7" aria-hidden="true" tabindex="-1"></a>#> <a href="#cb47-8" aria-hidden="true" tabindex="-1"></a>#> [[3]] <a href="#cb47-9" aria-hidden="true" tabindex="-1"></a>#> [1] "e" <a href="#cb47-10" aria-hidden="true" tabindex="-1"></a>#> <a href="#cb47-11" aria-hidden="true" tabindex="-1"></a>#> [[4]] <a href="#cb47-12" aria-hidden="true" tabindex="-1"></a>#> [1] "f" <a href="#cb47-13" aria-hidden="true" tabindex="-1"></a>#> <a href="#cb47-14" aria-hidden="true" tabindex="-1"></a>#> [[5]] <a href="#cb47-15" aria-hidden="true" tabindex="-1"></a>#> [1] "g" <a href="#cb47-16" aria-hidden="true" tabindex="-1"></a>#> <a href="#cb47-17" aria-hidden="true" tabindex="-1"></a>#> [[6]] <a href="#cb47-18" aria-hidden="true" tabindex="-1"></a>#> [1] "h" <a href="#cb47-19" aria-hidden="true" tabindex="-1"></a>#> <a href="#cb47-20" ar