P281424/AMR
1
0
Fork 0
mirror of https://github.com/msberends/AMR.git synced 2025-07-08 12:31:58 +02:00
Code Releases Activity

(v1.5.0.9021) improve speed of %like%

Browse Source
This commit is contained in:
dr. M.S. (Matthijs) Berends
2021-02-21 20:15:09 +01:00
parent daa12ced2c
commit 5ef8cb41a7
23 changed files with 137 additions and 126 deletions
Download Patch File Download Diff File Expand all files Collapse all files

123
docs/articles/benchmarks.html
View File

@ -39,7 +39,7 @@
</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">1.5.0</span>
<span class="version label label-default" data-toggle="tooltip" data-placement="bottom" title="Latest development version">1.5.0.9021</span>
</span>
</div>
@ -192,6 +192,7 @@
<div class="page-header toc-ignore">
<h1 data-toc-skip>Benchmarks</h1>
<h4 class="date">21 February 2021</h4>
<small class="dont-index">Source: <a href="https://github.com/msberends/AMR/blob/master/vignettes/benchmarks.Rmd"><code>vignettes/benchmarks.Rmd</code></a></small>
<div class="hidden name"><code>benchmarks.Rmd</code></div>
@ -225,36 +226,42 @@
<span class="fu"><a href="../reference/as.mo.html">as.mo</a></span><span class="op">(</span><span class="st">"VISA"</span><span class="op">)</span>, <span class="co"># Vancomycin Intermediate S. aureus</span>
<span class="fu"><a href="../reference/as.mo.html">as.mo</a></span><span class="op">(</span><span class="st">"VRSA"</span><span class="op">)</span>, <span class="co"># Vancomycin Resistant S. aureus</span>
times <span class="op">=</span> <span class="fl">10</span><span class="op">)</span>
<span class="fu"><a href="https://docs.ropensci.org/skimr/reference/print.html">print</a></span><span class="op">(</span><span class="va">S.aureus</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">2</span><span class="op">)</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="co"># [1] "^st.* au"</span>
<span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">S.aureus</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">2</span><span class="op">)</span>
<span class="co"># Unit: milliseconds</span>
<span class="co"># expr min lq mean median uq max</span>
<span class="co"># as.mo("sau") 13.0 14.0 25.0 15.0 44.0 65</span>
<span class="co"># as.mo("stau") 120.0 130.0 140.0 140.0 160.0 160</span>
<span class="co"># as.mo("STAU") 120.0 130.0 150.0 160.0 160.0 180</span>
<span class="co"># as.mo("staaur") 13.0 13.0 14.0 14.0 14.0 15</span>
<span class="co"># as.mo("STAAUR") 13.0 14.0 17.0 15.0 15.0 43</span>
<span class="co"># as.mo("S. aureus") 30.0 32.0 45.0 34.0 62.0 68</span>
<span class="co"># as.mo("S aureus") 31.0 34.0 42.0 35.0 61.0 63</span>
<span class="co"># as.mo("Staphylococcus aureus") 2.5 2.6 2.8 2.8 2.9 3</span>
<span class="co"># as.mo("Staphylococcus aureus (MRSA)") 1200.0 1200.0 1200.0 1200.0 1200.0 1200</span>
<span class="co"># as.mo("Sthafilokkockus aaureuz") 550.0 560.0 570.0 560.0 570.0 610</span>
<span class="co"># as.mo("MRSA") 13.0 13.0 17.0 15.0 15.0 42</span>
<span class="co"># as.mo("VISA") 21.0 22.0 26.0 23.0 23.0 52</span>
<span class="co"># as.mo("VRSA") 21.0 23.0 35.0 24.0 52.0 54</span>
<span class="co"># neval</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span>
<span class="co"># 10</span></code></pre></div>
<span class="co"># expr min lq mean median uq max neval</span>
<span class="co"># as.mo("sau") 12.0 12.0 13.0 14.0 14.0 16 10</span>
<span class="co"># as.mo("stau") 55.0 67.0 88.0 95.0 98.0 120 10</span>
<span class="co"># as.mo("STAU") 57.0 66.0 110.0 100.0 130.0 250 10</span>
<span class="co"># as.mo("staaur") 12.0 12.0 17.0 13.0 14.0 54 10</span>
<span class="co"># as.mo("STAAUR") 11.0 12.0 17.0 13.0 14.0 61 10</span>
<span class="co"># as.mo("S. aureus") 30.0 32.0 62.0 69.0 93.0 95 10</span>
<span class="co"># as.mo("S aureus") 29.0 33.0 43.0 37.0 53.0 71 10</span>
<span class="co"># as.mo("Staphylococcus aureus") 2.2 2.4 2.6 2.6 2.8 3 10</span>
<span class="co"># as.mo("Staphylococcus aureus (MRSA)") 270.0 290.0 330.0 310.0 380.0 430 10</span>
<span class="co"># as.mo("Sthafilokkockus aaureuz") 190.0 210.0 240.0 250.0 270.0 290 10</span>
<span class="co"># as.mo("MRSA") 12.0 12.0 14.0 13.0 15.0 16 10</span>
<span class="co"># as.mo("VISA") 21.0 22.0 29.0 24.0 25.0 79 10</span>
<span class="co"># as.mo("VRSA") 21.0 24.0 35.0 28.0 56.0 58 10</span></code></pre></div>
<p><img src="benchmarks_files/figure-html/unnamed-chunk-4-1.png" width="562.5"></p>
<p>In the table above, all measurements are shown in milliseconds (thousands of seconds). A value of 5 milliseconds means it can determine 200 input values per second. It case of 100 milliseconds, this is only 10 input values per second. It is clear that accepted taxonomic names are extremely fast, but some variations can take up to 500-1000 times as much time.</p>
<p>To improve performance, two important calculations take almost no time at all: <strong>repetitive results</strong> and <strong>already precalculated results</strong>.</p>
@ -281,11 +288,11 @@
<span class="co"># now let's see:</span>
<span class="va">run_it</span> <span class="op">&lt;-</span> <span class="fu">microbenchmark</span><span class="op">(</span><span class="fu"><a href="../reference/mo_property.html">mo_name</a></span><span class="op">(</span><span class="va">x</span><span class="op">)</span>,
times <span class="op">=</span> <span class="fl">10</span><span class="op">)</span>
<span class="fu"><a href="https://docs.ropensci.org/skimr/reference/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
<span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
<span class="co"># Unit: milliseconds</span>
<span class="co"># expr min lq mean median uq max neval</span>
<span class="co"># mo_name(x) 141 180 218 207 245 312 10</span></code></pre></div>
<p>So getting official taxonomic names of 2,000,000 (!!) items consisting of 90 unique values only takes 0.207 seconds. You only lose time on your unique input values.</p>
<span class="co"># mo_name(x) 125 144 182 171 186 298 10</span></code></pre></div>
<p>So getting official taxonomic names of 2,000,000 (!!) items consisting of 90 unique values only takes 0.171 seconds. You only lose time on your unique input values.</p>
</div>
<div id="precalculated-results" class="section level3">
<h3 class="hasAnchor">
@ -296,13 +303,13 @@
B <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_name</a></span><span class="op">(</span><span class="st">"S. aureus"</span><span class="op">)</span>,
C <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_name</a></span><span class="op">(</span><span class="st">"Staphylococcus aureus"</span><span class="op">)</span>,
times <span class="op">=</span> <span class="fl">10</span><span class="op">)</span>
<span class="fu"><a href="https://docs.ropensci.org/skimr/reference/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
<span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
<span class="co"># Unit: milliseconds</span>
<span class="co"># expr min lq mean median uq max neval</span>
<span class="co"># A 8.76 8.96 9.39 9.31 9.86 10.10 10</span>
<span class="co"># B 27.60 28.20 33.00 28.90 29.40 71.20 10</span>
<span class="co"># C 2.28 2.32 2.47 2.45 2.48 2.85 10</span></code></pre></div>
<p>So going from <code><a href="../reference/mo_property.html">mo_name("Staphylococcus aureus")</a></code> to <code>"Staphylococcus aureus"</code> takes 0.0025 seconds - it doesn’t even start calculating <em>if the result would be the same as the expected resulting value</em>. That goes for all helper functions:</p>
<span class="co"># expr min lq mean median uq max neval</span>
<span class="co"># A 7.08 7.37 15.90 7.94 9.02 48.9 10</span>
<span class="co"># B 23.50 24.00 25.20 24.10 26.20 30.1 10</span>
<span class="co"># C 1.54 1.62 1.76 1.71 1.81 2.3 10</span></code></pre></div>
<p>So going from <code><a href="../reference/mo_property.html">mo_name("Staphylococcus aureus")</a></code> to <code>"Staphylococcus aureus"</code> takes 0.0017 seconds - it doesn’t even start calculating <em>if the result would be the same as the expected resulting value</em>. That goes for all helper functions:</p>
<div class="sourceCode" id="cb5"><pre class="downlit sourceCode r">
<code class="sourceCode R"><span class="va">run_it</span> <span class="op">&lt;-</span> <span class="fu">microbenchmark</span><span class="op">(</span>A <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_species</a></span><span class="op">(</span><span class="st">"aureus"</span><span class="op">)</span>,
B <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_genus</a></span><span class="op">(</span><span class="st">"Staphylococcus"</span><span class="op">)</span>,
@ -313,17 +320,17 @@
G <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_phylum</a></span><span class="op">(</span><span class="st">"Firmicutes"</span><span class="op">)</span>,
H <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_kingdom</a></span><span class="op">(</span><span class="st">"Bacteria"</span><span class="op">)</span>,
times <span class="op">=</span> <span class="fl">10</span><span class="op">)</span>
<span class="fu"><a href="https://docs.ropensci.org/skimr/reference/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
<span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">3</span><span class="op">)</span>
<span class="co"># Unit: milliseconds</span>
<span class="co"># expr min lq mean median uq max neval</span>
<span class="co"># A 1.91 1.95 2.06 1.99 2.09 2.62 10</span>
<span class="co"># B 1.83 1.91 2.09 2.04 2.20 2.45 10</span>
<span class="co"># C 1.79 1.90 2.03 1.99 2.22 2.30 10</span>
<span class="co"># D 1.90 2.01 2.18 2.12 2.25 2.71 10</span>
<span class="co"># E 1.91 2.02 2.14 2.08 2.15 2.81 10</span>
<span class="co"># F 1.86 1.92 2.00 2.01 2.06 2.16 10</span>
<span class="co"># G 1.81 1.96 2.09 2.08 2.22 2.41 10</span>
<span class="co"># H 1.90 1.93 2.05 2.00 2.22 2.29 10</span></code></pre></div>
<span class="co"># expr min lq mean median uq max neval</span>
<span class="co"># A 1.63 1.92 1.99 2.01 2.11 2.29 10</span>
<span class="co"># B 1.67 1.89 2.01 1.96 2.12 2.62 10</span>
<span class="co"># C 1.86 1.87 1.96 1.97 2.04 2.13 10</span>
<span class="co"># D 1.63 1.82 1.90 1.94 2.00 2.06 10</span>
<span class="co"># E 1.60 1.94 3.05 1.97 2.24 12.60 10</span>
<span class="co"># F 1.66 1.90 2.18 1.95 2.01 4.33 10</span>
<span class="co"># G 1.84 1.89 1.99 1.98 2.02 2.24 10</span>
<span class="co"># H 1.79 1.95 2.08 2.06 2.25 2.36 10</span></code></pre></div>
<p>Of course, when running <code><a href="../reference/mo_property.html">mo_phylum("Firmicutes")</a></code> the function has zero knowledge about the actual microorganism, namely <em>S. aureus</em>. But since the result would be <code>"Firmicutes"</code> anyway, there is no point in calculating the result. And because this package ‘knows’ all phyla of all known bacteria (according to the Catalogue of Life), it can just return the initial value immediately.</p>
</div>
<div id="results-in-other-languages" class="section level3">
@ -348,16 +355,16 @@
fr <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_name</a></span><span class="op">(</span><span class="st">"CoNS"</span>, language <span class="op">=</span> <span class="st">"fr"</span><span class="op">)</span>,
pt <span class="op">=</span> <span class="fu"><a href="../reference/mo_property.html">mo_name</a></span><span class="op">(</span><span class="st">"CoNS"</span>, language <span class="op">=</span> <span class="st">"pt"</span><span class="op">)</span>,
times <span class="op">=</span> <span class="fl">100</span><span class="op">)</span>
<span class="fu"><a href="https://docs.ropensci.org/skimr/reference/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">4</span><span class="op">)</span>
<span class="fu"><a href="https://rdrr.io/r/base/print.html">print</a></span><span class="op">(</span><span class="va">run_it</span>, unit <span class="op">=</span> <span class="st">"ms"</span>, signif <span class="op">=</span> <span class="fl">4</span><span class="op">)</span>
<span class="co"># Unit: milliseconds</span>
<span class="co"># expr min lq mean median uq max neval</span>
<span class="co"># en 17.45 18.01 19.69 18.53 19.14 55.30 100</span>
<span class="co"># de 20.58 21.54 26.69 22.08 23.96 67.16 100</span>
<span class="co"># nl 33.79 34.67 39.13 35.39 36.72 74.60 100</span>
<span class="co"># es 20.71 21.42 24.36 21.88 22.65 58.57 100</span>
<span class="co"># it 20.65 21.18 26.50 21.53 22.68 61.96 100</span>
<span class="co"># fr 20.68 21.27 25.05 21.64 22.37 58.82 100</span>
<span class="co"># pt 20.69 21.44 24.36 21.94 22.99 59.66 100</span></code></pre></div>
<span class="co"># expr min lq mean median uq max neval</span>
<span class="co"># en 17.21 17.88 21.68 18.14 19.20 71.64 100</span>
<span class="co"># de 20.08 20.74 26.58 21.26 22.41 159.80 100</span>
<span class="co"># nl 24.88 25.81 31.01 26.32 27.03 74.57 100</span>
<span class="co"># es 19.91 20.80 26.33 21.28 22.60 80.34 100</span>
<span class="co"># it 19.96 20.63 25.21 21.20 22.25 76.35 100</span>
<span class="co"># fr 19.61 20.38 26.62 21.15 22.59 80.90 100</span>
<span class="co"># pt 19.87 20.58 27.65 20.92 23.22 80.73 100</span></code></pre></div>
<p>Currently supported are German, Dutch, Spanish, Italian, French and Portuguese.</p>
</div>
</div>