AMR/docs/reference/ggplot_pca.html

438 lines
20 KiB
HTML

<!-- Generated by pkgdown: do not edit by hand -->
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8">
<meta http-equiv="X-UA-Compatible" content="IE=edge">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>PCA biplot with <code>ggplot2</code> — ggplot_pca • AMR (for R)</title>
<!-- favicons -->
<link rel="icon" type="image/png" sizes="16x16" href="../favicon-16x16.png">
<link rel="icon" type="image/png" sizes="32x32" href="../favicon-32x32.png">
<link rel="apple-touch-icon" type="image/png" sizes="180x180" href="../apple-touch-icon.png" />
<link rel="apple-touch-icon" type="image/png" sizes="120x120" href="../apple-touch-icon-120x120.png" />
<link rel="apple-touch-icon" type="image/png" sizes="76x76" href="../apple-touch-icon-76x76.png" />
<link rel="apple-touch-icon" type="image/png" sizes="60x60" href="../apple-touch-icon-60x60.png" />
<!-- jquery -->
<script src="https://cdnjs.cloudflare.com/ajax/libs/jquery/3.4.1/jquery.min.js" integrity="sha256-CSXorXvZcTkaix6Yvo6HppcZGetbYMGWSFlBw8HfCJo=" crossorigin="anonymous"></script>
<!-- Bootstrap -->
<link href="https://cdnjs.cloudflare.com/ajax/libs/bootswatch/3.4.0/flatly/bootstrap.min.css" rel="stylesheet" crossorigin="anonymous" />
<script src="https://cdnjs.cloudflare.com/ajax/libs/twitter-bootstrap/3.4.1/js/bootstrap.min.js" integrity="sha256-nuL8/2cJ5NDSSwnKD8VqreErSWHtnEP9E7AySL+1ev4=" crossorigin="anonymous"></script>
<!-- bootstrap-toc -->
<link rel="stylesheet" href="../bootstrap-toc.css">
<script src="../bootstrap-toc.js"></script>
<!-- Font Awesome icons -->
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.12.1/css/all.min.css" integrity="sha256-mmgLkCYLUQbXn0B1SRqzHar6dCnv9oZFPEC1g1cwlkk=" crossorigin="anonymous" />
<link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.12.1/css/v4-shims.min.css" integrity="sha256-wZjR52fzng1pJHwx4aV2AO3yyTOXrcDW7jBpJtTwVxw=" crossorigin="anonymous" />
<!-- clipboard.js -->
<script src="https://cdnjs.cloudflare.com/ajax/libs/clipboard.js/2.0.6/clipboard.min.js" integrity="sha256-inc5kl9MA1hkeYUt+EC3BhlIgyp/2jDIyBLS6k3UxPI=" crossorigin="anonymous"></script>
<!-- headroom.js -->
<script src="https://cdnjs.cloudflare.com/ajax/libs/headroom/0.11.0/headroom.min.js" integrity="sha256-AsUX4SJE1+yuDu5+mAVzJbuYNPHj/WroHuZ8Ir/CkE0=" crossorigin="anonymous"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/headroom/0.11.0/jQuery.headroom.min.js" integrity="sha256-ZX/yNShbjqsohH1k95liqY9Gd8uOiE1S4vZc+9KQ1K4=" crossorigin="anonymous"></script>
<!-- pkgdown -->
<link href="../pkgdown.css" rel="stylesheet">
<script src="../pkgdown.js"></script>
<link href="../extra.css" rel="stylesheet">
<script src="../extra.js"></script>
<meta property="og:title" content="PCA biplot with <code>ggplot2</code> — ggplot_pca" />
<meta property="og:description" content="Produces a ggplot2 variant of a so-called biplot for PCA (principal component analysis), but is more flexible and more appealing than the base R biplot() function." />
<meta property="og:image" content="https://msberends.github.io/AMR/logo.svg" />
<!-- mathjax -->
<script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/MathJax.js" integrity="sha256-nvJJv9wWKEm88qvoQl9ekL2J+k/RWIsaSScxxlsrv8k=" crossorigin="anonymous"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/config/TeX-AMS-MML_HTMLorMML.js" integrity="sha256-84DKXVJXs0/F8OTMzX4UR909+jtl4G7SPypPavF+GfA=" crossorigin="anonymous"></script>
<!--[if lt IE 9]>
<script src="https://oss.maxcdn.com/html5shiv/3.7.3/html5shiv.min.js"></script>
<script src="https://oss.maxcdn.com/respond/1.4.2/respond.min.js"></script>
<![endif]-->
</head>
<body data-spy="scroll" data-target="#toc">
<div class="container template-reference-topic">
<header>
<div class="navbar navbar-default navbar-fixed-top" role="navigation">
<div class="container">
<div class="navbar-header">
<button type="button" class="navbar-toggle collapsed" data-toggle="collapse" data-target="#navbar" aria-expanded="false">
<span class="sr-only">Toggle navigation</span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
<span class="icon-bar"></span>
</button>
<span class="navbar-brand">
<a class="navbar-link" href="../index.html">AMR (for R)</a>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.3.0</span>
</span>
</div>
<div id="navbar" class="navbar-collapse collapse">
<ul class="nav navbar-nav">
<li>
<a href="../index.html">
<span class="fa fa-home"></span>
Home
</a>
</li>
<li class="dropdown">
<a href="#" class="dropdown-toggle" data-toggle="dropdown" role="button" aria-expanded="false">
<span class="fa fa-question-circle"></span>
How to
<span class="caret"></span>
</a>
<ul class="dropdown-menu" role="menu">
<li>
<a href="../articles/AMR.html">
<span class="fa fa-directions"></span>
Conduct AMR analysis
</a>
</li>
<li>
<a href="../articles/resistance_predict.html">
<span class="fa fa-dice"></span>
Predict antimicrobial resistance
</a>
</li>
<li>
<a href="../articles/PCA.html">
<span class="fa fa-compress"></span>
Conduct principal component analysis for AMR
</a>
</li>
<li>
<a href="../articles/MDR.html">
<span class="fa fa-skull-crossbones"></span>
Determine multi-drug resistance (MDR)
</a>
</li>
<li>
<a href="../articles/WHONET.html">
<span class="fa fa-globe-americas"></span>
Work with WHONET data
</a>
</li>
<li>
<a href="../articles/SPSS.html">
<span class="fa fa-file-upload"></span>
Import data from SPSS/SAS/Stata
</a>
</li>
<li>
<a href="../articles/EUCAST.html">
<span class="fa fa-exchange-alt"></span>
Apply EUCAST rules
</a>
</li>
<li>
<a href="../reference/mo_property.html">
<span class="fa fa-bug"></span>
Get properties of a microorganism
</a>
</li>
<li>
<a href="../reference/ab_property.html">
<span class="fa fa-capsules"></span>
Get properties of an antibiotic
</a>
</li>
<li>
<a href="../articles/benchmarks.html">
<span class="fa fa-shipping-fast"></span>
Other: benchmarks
</a>
</li>
</ul>
</li>
<li>
<a href="../reference/index.html">
<span class="fa fa-book-open"></span>
Manual
</a>
</li>
<li>
<a href="../authors.html">
<span class="fa fa-users"></span>
Authors
</a>
</li>
<li>
<a href="../news/index.html">
<span class="far fa far fa-newspaper"></span>
Changelog
</a>
</li>
</ul>
<ul class="nav navbar-nav navbar-right">
<li>
<a href="https://github.com/msberends/AMR">
<span class="fab fa fab fa-github"></span>
Source Code
</a>
</li>
<li>
<a href="../survey.html">
<span class="fa fa-clipboard-list"></span>
Survey
</a>
</li>
</ul>
</div><!--/.nav-collapse -->
</div><!--/.container -->
</div><!--/.navbar -->
</header>
<div class="row">
<div class="col-md-9 contents">
<div class="page-header">
<h1>PCA biplot with <code>ggplot2</code></h1>
<small class="dont-index">Source: <a href='https://github.com/msberends/AMR/blob/master/R/ggplot_pca.R'><code>R/ggplot_pca.R</code></a></small>
<div class="hidden name"><code>ggplot_pca.Rd</code></div>
</div>
<div class="ref-description">
<p>Produces a <code>ggplot2</code> variant of a so-called <a href='https://en.wikipedia.org/wiki/Biplot'>biplot</a> for PCA (principal component analysis), but is more flexible and more appealing than the base <span style="R">R</span> <code><a href='https://rdrr.io/r/stats/biplot.html'>biplot()</a></code> function.</p>
</div>
<pre class="usage"><span class='fu'>ggplot_pca</span>(
<span class='no'>x</span>,
<span class='kw'>choices</span> <span class='kw'>=</span> <span class='fl'>1</span>:<span class='fl'>2</span>,
<span class='kw'>scale</span> <span class='kw'>=</span> <span class='fl'>TRUE</span>,
<span class='kw'>pc.biplot</span> <span class='kw'>=</span> <span class='fl'>TRUE</span>,
<span class='kw'>labels</span> <span class='kw'>=</span> <span class='kw'>NULL</span>,
<span class='kw'>labels_textsize</span> <span class='kw'>=</span> <span class='fl'>3</span>,
<span class='kw'>labels_text_placement</span> <span class='kw'>=</span> <span class='fl'>1.5</span>,
<span class='kw'>groups</span> <span class='kw'>=</span> <span class='kw'>NULL</span>,
<span class='kw'>ellipse</span> <span class='kw'>=</span> <span class='fl'>TRUE</span>,
<span class='kw'>ellipse_prob</span> <span class='kw'>=</span> <span class='fl'>0.68</span>,
<span class='kw'>ellipse_size</span> <span class='kw'>=</span> <span class='fl'>0.5</span>,
<span class='kw'>ellipse_alpha</span> <span class='kw'>=</span> <span class='fl'>0.5</span>,
<span class='kw'>points_size</span> <span class='kw'>=</span> <span class='fl'>2</span>,
<span class='kw'>points_alpha</span> <span class='kw'>=</span> <span class='fl'>0.25</span>,
<span class='kw'>arrows</span> <span class='kw'>=</span> <span class='fl'>TRUE</span>,
<span class='kw'>arrows_colour</span> <span class='kw'>=</span> <span class='st'>"darkblue"</span>,
<span class='kw'>arrows_size</span> <span class='kw'>=</span> <span class='fl'>0.5</span>,
<span class='kw'>arrows_textsize</span> <span class='kw'>=</span> <span class='fl'>3</span>,
<span class='kw'>arrows_textangled</span> <span class='kw'>=</span> <span class='fl'>TRUE</span>,
<span class='kw'>arrows_alpha</span> <span class='kw'>=</span> <span class='fl'>0.75</span>,
<span class='kw'>base_textsize</span> <span class='kw'>=</span> <span class='fl'>10</span>,
<span class='no'>...</span>
)</pre>
<h2 class="hasAnchor" id="arguments"><a class="anchor" href="#arguments"></a>Arguments</h2>
<table class="ref-arguments">
<colgroup><col class="name" /><col class="desc" /></colgroup>
<tr>
<th>x</th>
<td><p>an object returned by <code><a href='pca.html'>pca()</a></code>, <code><a href='https://rdrr.io/r/stats/prcomp.html'>prcomp()</a></code> or <code><a href='https://rdrr.io/r/stats/princomp.html'>princomp()</a></code></p></td>
</tr>
<tr>
<th>choices</th>
<td><p>length 2 vector specifying the components to plot. Only the default
is a biplot in the strict sense.</p></td>
</tr>
<tr>
<th>scale</th>
<td><p>The variables are scaled by <code>lambda ^ scale</code> and the
observations are scaled by <code>lambda ^ (1-scale)</code> where
<code>lambda</code> are the singular values as computed by
<code><a href='https://rdrr.io/r/stats/princomp.html'>princomp</a></code>. Normally <code>0 &lt;= scale &lt;= 1</code>, and a warning
will be issued if the specified <code>scale</code> is outside this range.</p></td>
</tr>
<tr>
<th>pc.biplot</th>
<td><p>If true, use what Gabriel (1971) refers to as a "principal component
biplot", with <code>lambda = 1</code> and observations scaled up by sqrt(n) and
variables scaled down by sqrt(n). Then inner products between
variables approximate covariances and distances between observations
approximate Mahalanobis distance.</p></td>
</tr>
<tr>
<th>labels</th>
<td><p>an optional vector of labels for the observations. If set, the labels will be placed below their respective points. When using the <code><a href='pca.html'>pca()</a></code> function as input for <code>x</code>, this will be determined automatically based on the attribute <code>non_numeric_cols</code>, see <code><a href='pca.html'>pca()</a></code>.</p></td>
</tr>
<tr>
<th>labels_textsize</th>
<td><p>the size of the text used for the labels</p></td>
</tr>
<tr>
<th>labels_text_placement</th>
<td><p>adjustment factor the placement of the variable names (<code>&gt;=1</code> means further away from the arrow head)</p></td>
</tr>
<tr>
<th>groups</th>
<td><p>an optional vector of groups for the labels, with the same length as <code>labels</code>. If set, the points and labels will be coloured according to these groups. When using the <code><a href='pca.html'>pca()</a></code> function as input for <code>x</code>, this will be determined automatically based on the attribute <code>non_numeric_cols</code>, see <code><a href='pca.html'>pca()</a></code>.</p></td>
</tr>
<tr>
<th>ellipse</th>
<td><p>a logical to indicate whether a normal data ellipse should be drawn for each group (set with <code>groups</code>)</p></td>
</tr>
<tr>
<th>ellipse_prob</th>
<td><p>statistical size of the ellipse in normal probability</p></td>
</tr>
<tr>
<th>ellipse_size</th>
<td><p>the size of the ellipse line</p></td>
</tr>
<tr>
<th>ellipse_alpha</th>
<td><p>the alpha (transparency) of the ellipse line</p></td>
</tr>
<tr>
<th>points_size</th>
<td><p>the size of the points</p></td>
</tr>
<tr>
<th>points_alpha</th>
<td><p>the alpha (transparency) of the points</p></td>
</tr>
<tr>
<th>arrows</th>
<td><p>a logical to indicate whether arrows should be drawn</p></td>
</tr>
<tr>
<th>arrows_colour</th>
<td><p>the colour of the arrow and their text</p></td>
</tr>
<tr>
<th>arrows_size</th>
<td><p>the size (thickness) of the arrow lines</p></td>
</tr>
<tr>
<th>arrows_textsize</th>
<td><p>the size of the text at the end of the arrows</p></td>
</tr>
<tr>
<th>arrows_textangled</th>
<td><p>a logical whether the text at the end of the arrows should be angled</p></td>
</tr>
<tr>
<th>arrows_alpha</th>
<td><p>the alpha (transparency) of the arrows and their text</p></td>
</tr>
<tr>
<th>base_textsize</th>
<td><p>the text size for all plot elements except the labels and arrows</p></td>
</tr>
<tr>
<th>...</th>
<td><p>Parameters passed on to functions</p></td>
</tr>
</table>
<h2 class="hasAnchor" id="source"><a class="anchor" href="#source"></a>Source</h2>
<p>The <code>ggplot_pca()</code> function is based on the <code>ggbiplot()</code> function from the <code>ggbiplot</code> package by Vince Vu, as found on GitHub: <a href='https://github.com/vqv/ggbiplot'>https://github.com/vqv/ggbiplot</a> (retrieved: 2 March 2020, their latest commit: <a href='https://github.com/vqv/ggbiplot/commit/7325e880485bea4c07465a0304c470608fffb5d9'><code>7325e88</code></a>; 12 February 2015).</p>
<p>As per their GPL-2 licence that demands documentation of code changes, the changes made based on the source code were:</p><ol>
<li><p>Rewritten code to remove the dependency on packages <code>plyr</code>, <code>scales</code> and <code>grid</code></p></li>
<li><p>Parametrised more options, like arrow and ellipse settings</p></li>
<li><p>Added total amount of explained variance as a caption in the plot</p></li>
<li><p>Cleaned all syntax based on the <code>lintr</code> package and added integrity checks</p></li>
<li><p>Updated documentation</p></li>
</ol>
<h2 class="hasAnchor" id="details"><a class="anchor" href="#details"></a>Details</h2>
<p>The colours for labels and points can be changed by adding another scale layer for colour, like <code><a href='https://ggplot2.tidyverse.org/reference/scale_viridis.html'>scale_colour_viridis_d()</a></code> or <code><a href='https://ggplot2.tidyverse.org/reference/scale_brewer.html'>scale_colour_brewer()</a></code>.</p>
<h2 class="hasAnchor" id="maturing-lifecycle"><a class="anchor" href="#maturing-lifecycle"></a>Maturing lifecycle</h2>
<p><img src='figures/lifecycle_maturing.svg' style=margin-bottom:5px /> <br />
The <a href='lifecycle.html'>lifecycle</a> of this function is <strong>maturing</strong>. The unlying code of a maturing function has been roughed out, but finer details might still change. Since this function needs wider usage and more extensive testing, you are very welcome <a href='https://github.com/msberends/AMR/issues'>to suggest changes at our repository</a> or <a href='AMR.html'>write us an email (see section 'Contact Us')</a>.</p>
<h2 class="hasAnchor" id="examples"><a class="anchor" href="#examples"></a>Examples</h2>
<pre class="examples"><span class='co'># `example_isolates` is a dataset available in the AMR package.</span>
<span class='co'># See ?example_isolates.</span>
<span class='co'># See ?pca for more info about Principal Component Analysis (PCA).</span>
<span class='kw'>if</span> (<span class='fu'><a href='https://rdrr.io/r/base/library.html'>require</a></span>(<span class='st'>"dplyr"</span>)) {
<span class='no'>pca_model</span> <span class='kw'>&lt;-</span> <span class='no'>example_isolates</span> <span class='kw'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/filter.html'>filter</a></span>(<span class='fu'><a href='mo_property.html'>mo_genus</a></span>(<span class='no'>mo</span>) <span class='kw'>==</span> <span class='st'>"Staphylococcus"</span>) <span class='kw'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/group_by.html'>group_by</a></span>(<span class='kw'>species</span> <span class='kw'>=</span> <span class='fu'><a href='mo_property.html'>mo_shortname</a></span>(<span class='no'>mo</span>)) <span class='kw'>%&gt;%</span>
<span class='fu'><a href='https://dplyr.tidyverse.org/reference/summarise_all.html'>summarise_if</a></span> (<span class='no'>is.rsi</span>, <span class='no'>resistance</span>) <span class='kw'>%&gt;%</span>
<span class='fu'><a href='pca.html'>pca</a></span>(<span class='no'>FLC</span>, <span class='no'>AMC</span>, <span class='no'>CXM</span>, <span class='no'>GEN</span>, <span class='no'>TOB</span>, <span class='no'>TMP</span>, <span class='no'>SXT</span>, <span class='no'>CIP</span>, <span class='no'>TEC</span>, <span class='no'>TCY</span>, <span class='no'>ERY</span>)
<span class='co'># old (base R)</span>
<span class='fu'><a href='https://rdrr.io/r/stats/biplot.html'>biplot</a></span>(<span class='no'>pca_model</span>)
<span class='co'># new </span>
<span class='fu'>ggplot_pca</span>(<span class='no'>pca_model</span>)
<span class='kw'>if</span> (<span class='fu'><a href='https://rdrr.io/r/base/library.html'>require</a></span>(<span class='st'>"ggplot2"</span>)) {
<span class='fu'>ggplot_pca</span>(<span class='no'>pca_model</span>) +
<span class='fu'><a href='https://ggplot2.tidyverse.org/reference/scale_viridis.html'>scale_colour_viridis_d</a></span>() +
<span class='fu'><a href='https://ggplot2.tidyverse.org/reference/labs.html'>labs</a></span>(<span class='kw'>title</span> <span class='kw'>=</span> <span class='st'>"Title here"</span>)
}
}</pre>
</div>
<div class="col-md-3 hidden-xs hidden-sm" id="pkgdown-sidebar">
<nav id="toc" data-toggle="toc" class="sticky-top">
<h2 data-toc-skip>Contents</h2>
</nav>
</div>
</div>
<footer>
<div class="copyright">
<p>Developed by <a href='https://www.rug.nl/staff/m.s.berends/'>Matthijs S. Berends</a>, <a href='https://www.rug.nl/staff/c.f.luz/'>Christian F. Luz</a>, <a href='https://www.rug.nl/staff/a.w.friedrich/'>Alexander W. Friedrich</a>, <a href='https://www.rug.nl/staff/b.sinha/'>Bhanu N. M. Sinha</a>, <a href='https://www.rug.nl/staff/c.j.albers/'>Casper J. Albers</a>, <a href='https://www.rug.nl/staff/c.glasner/'>Corinna Glasner</a>.</p>
</div>
<div class="pkgdown">
<p>Site built with <a href="https://pkgdown.r-lib.org/">pkgdown</a> 1.5.1.</p>
</div>
</footer>
</div>
</body>
</html>