blob: b01b85c04c7eb69f13203d75fc6db95ebc32e603 [file] [log] [blame]
<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>apache_beam.typehints.arrow_batching_microbenchmark &mdash; Apache Beam 2.47.0 documentation</title>
<script type="text/javascript" src="../../../_static/js/modernizr.min.js"></script>
<script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script>
<script type="text/javascript" src="../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../_static/doctools.js"></script>
<script type="text/javascript" src="../../../_static/language_data.js"></script>
<script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" />
<link rel="index" title="Index" href="../../../genindex.html" />
<link rel="search" title="Search" href="../../../search.html" />
</head>
<body class="wy-body-for-nav">
<div class="wy-grid-for-nav">
<nav data-toggle="wy-nav-shift" class="wy-nav-side">
<div class="wy-side-scroll">
<div class="wy-side-nav-search" >
<a href="../../../index.html" class="icon icon-home"> Apache Beam
</a>
<div class="version">
2.47.0
</div>
<div role="search">
<form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get">
<input type="text" name="q" placeholder="Search docs" />
<input type="hidden" name="check_keywords" value="yes" />
<input type="hidden" name="area" value="default" />
</form>
</div>
</div>
<div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.coders.html">apache_beam.coders package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.dataframe.html">apache_beam.dataframe package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.io.html">apache_beam.io package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.metrics.html">apache_beam.metrics package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.ml.html">apache_beam.ml package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.options.html">apache_beam.options package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.portability.html">apache_beam.portability package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.runners.html">apache_beam.runners package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.testing.html">apache_beam.testing package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.transforms.html">apache_beam.transforms package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.typehints.html">apache_beam.typehints package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.utils.html">apache_beam.utils package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.yaml.html">apache_beam.yaml package</a></li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.error.html">apache_beam.error module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.pvalue.html">apache_beam.pvalue module</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../index.html">Apache Beam</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../../index.html">Docs</a> &raquo;</li>
<li><a href="../../index.html">Module code</a> &raquo;</li>
<li>apache_beam.typehints.arrow_batching_microbenchmark</li>
<li class="wy-breadcrumbs-aside">
</li>
</ul>
<hr/>
</div>
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<h1>Source code for apache_beam.typehints.arrow_batching_microbenchmark</h1><div class="highlight"><pre>
<span></span><span class="c1">#</span>
<span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span>
<span class="c1"># contributor license agreements. See the NOTICE file distributed with</span>
<span class="c1"># this work for additional information regarding copyright ownership.</span>
<span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span>
<span class="c1"># (the &quot;License&quot;); you may not use this file except in compliance with</span>
<span class="c1"># the License. You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
<span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
<span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
<span class="c1"># See the License for the specific language governing permissions and</span>
<span class="c1"># limitations under the License.</span>
<span class="c1">#</span>
<span class="sd">&quot;&quot;&quot;A microbenchmark for pyarrow batch creation.</span>
<span class="sd">This microbenchmark exercises the PyarrowBatchConverter.produce_batch method</span>
<span class="sd">for different batch sizes.</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="kn">import</span> <span class="nn">argparse</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">import</span> <span class="nn">pyarrow</span> <span class="k">as</span> <span class="nn">pa</span>
<span class="kn">from</span> <span class="nn">apache_beam.portability.api</span> <span class="kn">import</span> <span class="n">schema_pb2</span>
<span class="kn">from</span> <span class="nn">apache_beam.tools</span> <span class="kn">import</span> <span class="n">utils</span>
<span class="kn">from</span> <span class="nn">apache_beam.typehints.arrow_type_compatibility</span> <span class="kn">import</span> <span class="n">PyarrowBatchConverter</span>
<span class="kn">from</span> <span class="nn">apache_beam.typehints.arrow_type_compatibility</span> <span class="kn">import</span> <span class="n">beam_schema_from_arrow_schema</span>
<span class="kn">from</span> <span class="nn">apache_beam.typehints.schemas</span> <span class="kn">import</span> <span class="n">typing_from_runner_api</span>
<div class="viewcode-block" id="benchmark_produce_batch"><a class="viewcode-back" href="../../../apache_beam.typehints.arrow_batching_microbenchmark.html#apache_beam.typehints.arrow_batching_microbenchmark.benchmark_produce_batch">[docs]</a><span class="k">def</span> <span class="nf">benchmark_produce_batch</span><span class="p">(</span><span class="n">size</span><span class="p">):</span>
<span class="n">batch</span> <span class="o">=</span> <span class="n">pa</span><span class="o">.</span><span class="n">Table</span><span class="o">.</span><span class="n">from_pydict</span><span class="p">({</span>
<span class="s1">&#39;foo&#39;</span><span class="p">:</span> <span class="n">pa</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="n">size</span><span class="p">),</span> <span class="nb">type</span><span class="o">=</span><span class="n">pa</span><span class="o">.</span><span class="n">int64</span><span class="p">()),</span>
<span class="s1">&#39;bar&#39;</span><span class="p">:</span> <span class="n">pa</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="n">i</span> <span class="o">/</span> <span class="n">size</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">size</span><span class="p">)],</span> <span class="nb">type</span><span class="o">=</span><span class="n">pa</span><span class="o">.</span><span class="n">float64</span><span class="p">()),</span>
<span class="s1">&#39;baz&#39;</span><span class="p">:</span> <span class="n">pa</span><span class="o">.</span><span class="n">array</span><span class="p">([</span><span class="nb">str</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">size</span><span class="p">)],</span> <span class="nb">type</span><span class="o">=</span><span class="n">pa</span><span class="o">.</span><span class="n">string</span><span class="p">()),</span>
<span class="p">})</span>
<span class="n">beam_schema</span> <span class="o">=</span> <span class="n">beam_schema_from_arrow_schema</span><span class="p">(</span><span class="n">batch</span><span class="o">.</span><span class="n">schema</span><span class="p">)</span>
<span class="n">element_type</span> <span class="o">=</span> <span class="n">typing_from_runner_api</span><span class="p">(</span>
<span class="n">schema_pb2</span><span class="o">.</span><span class="n">FieldType</span><span class="p">(</span><span class="n">row_type</span><span class="o">=</span><span class="n">schema_pb2</span><span class="o">.</span><span class="n">RowType</span><span class="p">(</span><span class="n">schema</span><span class="o">=</span><span class="n">beam_schema</span><span class="p">)))</span>
<span class="n">batch_converter</span> <span class="o">=</span> <span class="n">PyarrowBatchConverter</span><span class="o">.</span><span class="n">from_typehints</span><span class="p">(</span><span class="n">element_type</span><span class="p">,</span> <span class="n">pa</span><span class="o">.</span><span class="n">Table</span><span class="p">)</span>
<span class="n">elements</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">batch_converter</span><span class="o">.</span><span class="n">explode_batch</span><span class="p">(</span><span class="n">batch</span><span class="p">))</span>
<span class="k">def</span> <span class="nf">_do_benchmark</span><span class="p">():</span>
<span class="n">_</span> <span class="o">=</span> <span class="n">batch_converter</span><span class="o">.</span><span class="n">produce_batch</span><span class="p">(</span><span class="n">elements</span><span class="p">)</span>
<span class="k">return</span> <span class="n">_do_benchmark</span></div>
<div class="viewcode-block" id="run_benchmark"><a class="viewcode-back" href="../../../apache_beam.typehints.arrow_batching_microbenchmark.html#apache_beam.typehints.arrow_batching_microbenchmark.run_benchmark">[docs]</a><span class="k">def</span> <span class="nf">run_benchmark</span><span class="p">(</span>
<span class="n">starting_point</span><span class="o">=</span><span class="mi">1</span><span class="p">,</span> <span class="n">num_runs</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="n">num_elements_step</span><span class="o">=</span><span class="mi">300</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="n">suite</span> <span class="o">=</span> <span class="p">[</span>
<span class="n">utils</span><span class="o">.</span><span class="n">LinearRegressionBenchmarkConfig</span><span class="p">(</span>
<span class="n">benchmark_produce_batch</span><span class="p">,</span> <span class="n">starting_point</span><span class="p">,</span> <span class="n">num_elements_step</span><span class="p">,</span> <span class="n">num_runs</span><span class="p">)</span>
<span class="p">]</span>
<span class="k">return</span> <span class="n">utils</span><span class="o">.</span><span class="n">run_benchmarks</span><span class="p">(</span><span class="n">suite</span><span class="p">,</span> <span class="n">verbose</span><span class="o">=</span><span class="n">verbose</span><span class="p">)</span></div>
<span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s1">&#39;__main__&#39;</span><span class="p">:</span>
<span class="n">logging</span><span class="o">.</span><span class="n">basicConfig</span><span class="p">()</span>
<span class="n">parser</span> <span class="o">=</span> <span class="n">argparse</span><span class="o">.</span><span class="n">ArgumentParser</span><span class="p">()</span>
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s1">&#39;--num_runs&#39;</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="mi">10</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">)</span>
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s1">&#39;--starting_point&#39;</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="mi">50</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">)</span>
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s1">&#39;--increment&#39;</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="mi">1000</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">)</span>
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span><span class="s1">&#39;--verbose&#39;</span><span class="p">,</span> <span class="n">default</span><span class="o">=</span><span class="kc">True</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="nb">bool</span><span class="p">)</span>
<span class="n">options</span> <span class="o">=</span> <span class="n">parser</span><span class="o">.</span><span class="n">parse_args</span><span class="p">()</span>
<span class="n">run_benchmark</span><span class="p">(</span>
<span class="n">options</span><span class="o">.</span><span class="n">starting_point</span><span class="p">,</span>
<span class="n">options</span><span class="o">.</span><span class="n">num_runs</span><span class="p">,</span>
<span class="n">options</span><span class="o">.</span><span class="n">increment</span><span class="p">,</span>
<span class="n">options</span><span class="o">.</span><span class="n">verbose</span><span class="p">)</span>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
&copy; Copyright
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>