EVOLUTION-MANAGER
Edit File: speed.html
<!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>Speed of glue</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> <script>// Hide empty <a> tag within highlighted CodeBlock for screen reader accessibility (see https://github.com/jgm/pandoc/issues/6352#issuecomment-626106786) --> // v0.0.1 // Written by JooYoung Seo (jooyoung@psu.edu) and Atsushi Yasumoto on June 1st, 2020. document.addEventListener('DOMContentLoaded', function() { const codeList = document.getElementsByClassName("sourceCode"); for (var i = 0; i < codeList.length; i++) { var linkList = codeList[i].getElementsByTagName('a'); for (var j = 0; j < linkList.length; j++) { if (linkList[j].innerHTML === "") { linkList[j].setAttribute('aria-hidden', 'true'); } } } }); </script> <style type="text/css">code{white-space: pre;}</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; } 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; } /* Alert */ code span.an { color: #60a0b0; font-weight: bold; font-style: italic; } /* Annotation */ code span.at { color: #7d9029; } /* Attribute */ code span.bn { color: #40a070; } /* BaseN */ code span.bu { } /* BuiltIn */ code span.cf { color: #007020; font-weight: bold; } /* ControlFlow */ code span.ch { color: #4070a0; } /* Char */ code span.cn { color: #880000; } /* Constant */ code span.co { color: #60a0b0; font-style: italic; } /* Comment */ code span.cv { color: #60a0b0; font-weight: bold; font-style: italic; } /* CommentVar */ code span.do { color: #ba2121; font-style: italic; } /* Documentation */ code span.dt { color: #902000; } /* DataType */ code span.dv { color: #40a070; } /* DecVal */ code span.er { color: #ff0000; font-weight: bold; } /* Error */ code span.ex { } /* Extension */ code span.fl { color: #40a070; } /* Float */ code span.fu { color: #06287e; } /* Function */ code span.im { } /* Import */ code span.in { color: #60a0b0; font-weight: bold; font-style: italic; } /* Information */ code span.kw { color: #007020; font-weight: bold; } /* Keyword */ code span.op { color: #666666; } /* Operator */ code span.ot { color: #007020; } /* Other */ code span.pp { color: #bc7a00; } /* Preprocessor */ code span.sc { color: #4070a0; } /* SpecialChar */ code span.ss { color: #bb6688; } /* SpecialString */ code span.st { color: #4070a0; } /* String */ code span.va { color: #19177c; } /* Variable */ code span.vs { color: #4070a0; } /* VerbatimString */ code span.wa { color: #60a0b0; font-weight: bold; font-style: italic; } /* Warning */ </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; } for (var j = 0; j < rules.length; j++) { var rule = rules[j]; // check if there is a div.sourceCode rule if (rule.type !== rule.STYLE_RULE || rule.selectorText !== "div.sourceCode") continue; var style = rule.style.cssText; // check if color or background-color is set if (rule.style.color === '' && rule.style.backgroundColor === '') 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">Speed of glue</h1> <p>Glue is advertised as</p> <blockquote> <p>Fast, dependency free string literals</p> </blockquote> <p>So what do we mean when we say that glue is fast? This does not mean glue is the fastest thing to use in all cases, however for the features it provides we can confidently say it is fast.</p> <p>A good way to determine this is to compare it’s speed of execution to some alternatives.</p> <ul> <li><code>base::paste0()</code>, <code>base::sprintf()</code> - Functions in base R implemented in C that provide variable insertion (but not interpolation).</li> <li><code>R.utils::gstring()</code>, <code>stringr::str_interp()</code> - Provides a similar interface as glue, but using <code>${}</code> to delimit blocks to interpolate.</li> <li><code>pystr::pystr_format()</code><a href="#fn1" class="footnote-ref" id="fnref1"><sup>1</sup></a>, <code>rprintf::rprintf()</code> - Provide a interfaces similar to python string formatters with variable replacement, but not arbitrary interpolation.</li> </ul> <div id="simple-concatenation" class="section level2"> <h2>Simple concatenation</h2> <div class="sourceCode" id="cb1"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb1-1"><a href="#cb1-1"></a>bar <-<span class="st"> "baz"</span></span> <span id="cb1-2"><a href="#cb1-2"></a></span> <span id="cb1-3"><a href="#cb1-3"></a>simple <-</span> <span id="cb1-4"><a href="#cb1-4"></a><span class="st"> </span>microbenchmark<span class="op">::</span><span class="kw">microbenchmark</span>(</span> <span id="cb1-5"><a href="#cb1-5"></a> <span class="dt">glue =</span> glue<span class="op">::</span><span class="kw">glue</span>(<span class="st">"foo{bar}"</span>),</span> <span id="cb1-6"><a href="#cb1-6"></a> <span class="dt">gstring =</span> R.utils<span class="op">::</span><span class="kw">gstring</span>(<span class="st">"foo${bar}"</span>),</span> <span id="cb1-7"><a href="#cb1-7"></a> <span class="dt">paste0 =</span> <span class="kw">paste0</span>(<span class="st">"foo"</span>, bar),</span> <span id="cb1-8"><a href="#cb1-8"></a> <span class="dt">sprintf =</span> <span class="kw">sprintf</span>(<span class="st">"foo%s"</span>, bar),</span> <span id="cb1-9"><a href="#cb1-9"></a> <span class="dt">str_interp =</span> stringr<span class="op">::</span><span class="kw">str_interp</span>(<span class="st">"foo${bar}"</span>),</span> <span id="cb1-10"><a href="#cb1-10"></a> <span class="dt">rprintf =</span> rprintf<span class="op">::</span><span class="kw">rprintf</span>(<span class="st">"foo$bar"</span>, <span class="dt">bar =</span> bar)</span> <span id="cb1-11"><a href="#cb1-11"></a>)</span> <span id="cb1-12"><a href="#cb1-12"></a></span> <span id="cb1-13"><a href="#cb1-13"></a><span class="kw">print</span>(<span class="dt">unit =</span> <span class="st">"eps"</span>, <span class="dt">order =</span> <span class="st">"median"</span>, <span class="dt">signif =</span> <span class="dv">4</span>, simple)</span> <span id="cb1-14"><a href="#cb1-14"></a></span> <span id="cb1-15"><a href="#cb1-15"></a><span class="kw">plot_comparison</span>(simple)</span></code></pre></div> <p>While <code>glue()</code> is slower than <code>paste0</code>,<code>sprintf()</code> it is twice as fast as <code>str_interp()</code> and <code>gstring()</code>, and on par with <code>rprintf()</code>.</p> <p>Although <code>paste0()</code>, <code>sprintf()</code> don’t do string interpolation and will likely always be significantly faster than glue, glue was never meant to be a direct replacement for them.</p> <p><code>rprintf()</code> does only variable interpolation, not arbitrary expressions, which was one of the explicit goals of writing glue.</p> <p>So glue is ~2x as fast as the two functions (<code>str_interp()</code>, <code>gstring()</code>), which do have roughly equivalent functionality.</p> <p>It also is still quite fast, with over 6000 evaluations per second on this machine.</p> </div> <div id="vectorized-performance" class="section level2"> <h2>Vectorized performance</h2> <p>Taking advantage of glue’s vectorization is the best way to avoid performance. For instance the vectorized form of the previous benchmark is able to generate 100,000 strings in only 22ms with performance much closer to that of <code>paste0()</code> and <code>sprintf()</code>. NB: <code>str_interp()</code> does not support vectorization, and so was removed.</p> <div class="sourceCode" id="cb2"><pre class="sourceCode r"><code class="sourceCode r"><span id="cb2-1"><a href="#cb2-1"></a>bar <-<span class="st"> </span><span class="kw">rep</span>(<span class="st">"bar"</span>, <span class="fl">1e5</span>)</span> <span id="cb2-2"><a href="#cb2-2"></a></span> <span id="cb2-3"><a href="#cb2-3"></a>vectorized <-</span> <span id="cb2-4"><a href="#cb2-4"></a><span class="st"> </span>microbenchmark<span class="op">::</span><span class="kw">microbenchmark</span>(</span> <span id="cb2-5"><a href="#cb2-5"></a> <span class="dt">glue =</span> glue<span class="op">::</span><span class="kw">glue</span>(<span class="st">"foo{bar}"</span>),</span> <span id="cb2-6"><a href="#cb2-6"></a> <span class="dt">gstring =</span> R.utils<span class="op">::</span><span class="kw">gstring</span>(<span class="st">"foo${bar}"</span>),</span> <span id="cb2-7"><a href="#cb2-7"></a> <span class="dt">paste0 =</span> <span class="kw">paste0</span>(<span class="st">"foo"</span>, bar),</span> <span id="cb2-8"><a href="#cb2-8"></a> <span class="dt">sprintf =</span> <span class="kw">sprintf</span>(<span class="st">"foo%s"</span>, bar),</span> <span id="cb2-9"><a href="#cb2-9"></a> <span class="dt">rprintf =</span> rprintf<span class="op">::</span><span class="kw">rprintf</span>(<span class="st">"foo$bar"</span>, <span class="dt">bar =</span> bar)</span> <span id="cb2-10"><a href="#cb2-10"></a>)</span> <span id="cb2-11"><a href="#cb2-11"></a></span> <span id="cb2-12"><a href="#cb2-12"></a><span class="kw">print</span>(<span class="dt">unit =</span> <span class="st">"ms"</span>, <span class="dt">order =</span> <span class="st">"median"</span>, <span class="dt">signif =</span> <span class="dv">4</span>, vectorized)</span> <span id="cb2-13"><a href="#cb2-13"></a></span> <span id="cb2-14"><a href="#cb2-14"></a><span class="kw">plot_comparison</span>(vectorized, <span class="dt">log =</span> <span class="ot">FALSE</span>)</span></code></pre></div> </div> <div class="footnotes"> <hr /> <ol> <li id="fn1"><p>pystr is no longer available from CRAN due to failure to correct installation errors and was therefore removed from further testing.<a href="#fnref1" class="footnote-back">↩︎</a></p></li> </ol> </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>