skimr
Version:
CLI EDA for CSVs
468 lines (432 loc) • 16.6 kB
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" />
<meta name="author" content="Kirill Müller, Hadley Wickham" />
<title>Extending tibble</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">Extending tibble</h1>
<h4 class="author">Kirill Müller, Hadley Wickham</h4>
<p>Tibbles are S3 objects of class
<code>c("tbl_df", "tbl", "data.frame")</code>. This means that they
inherit their behavior from the <code>"data.frame"</code> class and add
two subclasses <code>"tbl"</code> and <code>"tbl_df"</code>. The pillar
and tibble packages provide methods for <code>"tbl"</code> and
<code>"tbl_df"</code>, respectively. Package authors and programmers can
implement subclasses that extend either <code>"tbl_df"</code> (and its
subclasses) or only <code>"tbl"</code> to provide custom behavior for
tibble-like objects. In addition, vectors classes can be implemented
from scratch or on top of existing classes, to be used as columns. This
article provides links to the various customization points that help you
avoiding reimplement existing behavior, and describes the difference
between <code>"tbl"</code> and <code>"tbl_df"</code>.</p>
<p>Read more in <a href="https://adv-r.hadley.nz/index.html">the second
edition of Advanced R</a>:</p>
<ul>
<li>about the internal representation of data frames and tibbles in the
<a href="https://adv-r.hadley.nz/vectors-chap.html#lists">Lists</a> and
<a href="https://adv-r.hadley.nz/vectors-chap.html#tibble">Data frames
and tibbles</a> sections of the <a href="https://adv-r.hadley.nz/vectors-chap.html">Vectors
chapter</a>,</li>
<li>about R’s S3 object-oriented system in the <a href="https://adv-r.hadley.nz/s3.html">S3 chapter</a>.</li>
</ul>
<div id="topics-documented-elsewhere" class="section level2">
<h2>Topics documented elsewhere</h2>
<ul>
<li><p>Change or tweak the way a tibble prints:
<code>vignette("extending", package = "pillar")</code></p></li>
<li><p>Change or tweak the way a column type is printed in a tibble:
<code>vignette("pillar", package = "vctrs")</code></p></li>
<li><p>Implement a new column data type:
<code>vignette("s3-vector", package = "vctrs")</code></p></li>
<li><p>Making your tibble subclass work well with dplyr:
<code>?dplyr::dplyr_extending</code></p></li>
</ul>
</div>
<div id="data-frame-subclasses" class="section level2">
<h2>Data frame subclasses</h2>
<div class="sourceCode" id="cb1"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb1-1"><a href="#cb1-1" aria-hidden="true" tabindex="-1"></a><span class="fu">library</span>(tibble)</span></code></pre></div>
<p>For tibble >= 3.0.0, the <code>"tbl"</code> class is responsible
for printing, while the <code>"tbl_df"</code> class adds tibble’s sturdy
subsetting and subset assignment behavior (see
<code>vignette("invariants")</code> for details). This means that a data
frame class that would like to (mostly) print like a tibble but keep the
behavior from base R’s data frames can inherit from
<code>c("tbl", "data.frame")</code> or just from <code>"tbl"</code>. An
example is the <code>"tbl_sql"</code> class in the dbplyr package that
is used to implement lazy database tables.</p>
<div id="tibble-example" class="section level3">
<h3>Tibble example</h3>
<div class="sourceCode" id="cb2"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb2-1"><a href="#cb2-1" aria-hidden="true" tabindex="-1"></a>my_tbl_df <span class="ot"><-</span> <span class="fu">new_tibble</span>(</span>
<span id="cb2-2"><a href="#cb2-2" aria-hidden="true" tabindex="-1"></a> <span class="fu">list</span>(<span class="at">a =</span> <span class="dv">1</span><span class="sc">:</span><span class="dv">3</span>, <span class="at">b =</span> <span class="dv">2</span><span class="sc">:</span><span class="dv">4</span>),</span>
<span id="cb2-3"><a href="#cb2-3" aria-hidden="true" tabindex="-1"></a> <span class="at">class =</span> <span class="st">"my_tbl_df"</span></span>
<span id="cb2-4"><a href="#cb2-4" aria-hidden="true" tabindex="-1"></a>)</span>
<span id="cb2-5"><a href="#cb2-5" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb2-6"><a href="#cb2-6" aria-hidden="true" tabindex="-1"></a>tbl_sum.my_tbl_df <span class="ot"><-</span> <span class="cf">function</span>(x, ...) {</span>
<span id="cb2-7"><a href="#cb2-7" aria-hidden="true" tabindex="-1"></a> <span class="fu">c</span>(</span>
<span id="cb2-8"><a href="#cb2-8" aria-hidden="true" tabindex="-1"></a> <span class="st">"My custom tibble"</span> <span class="ot">=</span> <span class="st">"Some info about it"</span>,</span>
<span id="cb2-9"><a href="#cb2-9" aria-hidden="true" tabindex="-1"></a> <span class="fu">NextMethod</span>()</span>
<span id="cb2-10"><a href="#cb2-10" aria-hidden="true" tabindex="-1"></a> )</span>
<span id="cb2-11"><a href="#cb2-11" aria-hidden="true" tabindex="-1"></a>}</span>
<span id="cb2-12"><a href="#cb2-12" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb2-13"><a href="#cb2-13" aria-hidden="true" tabindex="-1"></a>my_tbl_df</span></code></pre></div>
<pre><code>## # My custom tibble: Some info about it
## # A tibble: 3 × 2
## a b
## <int> <int>
## 1 1 2
## 2 2 3
## 3 3 4</code></pre>
<div class="sourceCode" id="cb4"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb4-1"><a href="#cb4-1" aria-hidden="true" tabindex="-1"></a>my_tbl_df[, <span class="st">"a"</span>]</span></code></pre></div>
<pre><code>## # My custom tibble: Some info about it
## # A tibble: 3 × 1
## a
## <int>
## 1 1
## 2 2
## 3 3</code></pre>
</div>
<div id="data-frame-example" class="section level3">
<h3>Data frame example</h3>
<div class="sourceCode" id="cb6"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb6-1"><a href="#cb6-1" aria-hidden="true" tabindex="-1"></a>my_tbl <span class="ot"><-</span> vctrs<span class="sc">::</span><span class="fu">new_data_frame</span>(</span>
<span id="cb6-2"><a href="#cb6-2" aria-hidden="true" tabindex="-1"></a> <span class="fu">list</span>(<span class="at">a =</span> <span class="dv">1</span><span class="sc">:</span><span class="dv">3</span>, <span class="at">b =</span> <span class="dv">2</span><span class="sc">:</span><span class="dv">4</span>),</span>
<span id="cb6-3"><a href="#cb6-3" aria-hidden="true" tabindex="-1"></a> <span class="at">class =</span> <span class="fu">c</span>(<span class="st">"my_tbl"</span>, <span class="st">"tbl"</span>)</span>
<span id="cb6-4"><a href="#cb6-4" aria-hidden="true" tabindex="-1"></a>)</span>
<span id="cb6-5"><a href="#cb6-5" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb6-6"><a href="#cb6-6" aria-hidden="true" tabindex="-1"></a>tbl_sum.my_tbl <span class="ot"><-</span> <span class="cf">function</span>(x, ...) {</span>
<span id="cb6-7"><a href="#cb6-7" aria-hidden="true" tabindex="-1"></a> <span class="fu">c</span>(</span>
<span id="cb6-8"><a href="#cb6-8" aria-hidden="true" tabindex="-1"></a> <span class="st">"My custom data frame"</span> <span class="ot">=</span> <span class="st">"Some info about it"</span>,</span>
<span id="cb6-9"><a href="#cb6-9" aria-hidden="true" tabindex="-1"></a> <span class="fu">NextMethod</span>()</span>
<span id="cb6-10"><a href="#cb6-10" aria-hidden="true" tabindex="-1"></a> )</span>
<span id="cb6-11"><a href="#cb6-11" aria-hidden="true" tabindex="-1"></a>}</span>
<span id="cb6-12"><a href="#cb6-12" aria-hidden="true" tabindex="-1"></a></span>
<span id="cb6-13"><a href="#cb6-13" aria-hidden="true" tabindex="-1"></a>my_tbl</span></code></pre></div>
<pre><code>## # My custom data frame: Some info about it
## # A data frame: 3 × 2
## a b
## <int> <int>
## 1 1 2
## 2 2 3
## 3 3 4</code></pre>
<div class="sourceCode" id="cb8"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb8-1"><a href="#cb8-1" aria-hidden="true" tabindex="-1"></a>my_tbl[, <span class="st">"a"</span>]</span></code></pre></div>
<pre><code>## [1] 1 2 3</code></pre>
</div>
</div>
<!-- code folding -->
<!-- dynamically load mathjax for compatibility with self-contained -->
<script>
(function () {
var script = document.createElement("script");
script.type = "text/javascript";
script.src = "https://mathjax.rstudio.com/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML";
document.getElementsByTagName("head")[0].appendChild(script);
})();
</script>
</body>
</html>