| |
| |
| <!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.tools.utils — Apache Beam documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" /> |
| |
| |
| |
| |
| |
| <link rel="index" title="Index" |
| href="../../../genindex.html"/> |
| <link rel="search" title="Search" href="../../../search.html"/> |
| <link rel="top" title="Apache Beam documentation" href="../../../index.html"/> |
| <link rel="up" title="Module code" href="../../index.html"/> |
| |
| |
| <script src="../../../_static/js/modernizr.min.js"></script> |
| |
| </head> |
| |
| <body class="wy-body-for-nav" role="document"> |
| |
| |
| <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 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.internal.html">apache_beam.internal 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.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.tools.html">apache_beam.tools 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> |
| </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> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.version.html">apache_beam.version module</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" role="navigation" 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> »</li> |
| |
| <li><a href="../../index.html">Module code</a> »</li> |
| |
| <li>apache_beam.tools.utils</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.tools.utils</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 "License"); 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 "AS IS" 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">"""Utility functions for all microbenchmarks."""</span> |
| |
| <span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">absolute_import</span> |
| <span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">division</span> |
| <span class="kn">from</span> <span class="nn">__future__</span> <span class="k">import</span> <span class="n">print_function</span> |
| |
| <span class="kn">import</span> <span class="nn">collections</span> |
| <span class="kn">import</span> <span class="nn">gc</span> |
| <span class="kn">import</span> <span class="nn">os</span> |
| <span class="kn">import</span> <span class="nn">time</span> |
| |
| <span class="kn">import</span> <span class="nn">numpy</span> |
| |
| |
| <div class="viewcode-block" id="check_compiled"><a class="viewcode-back" href="../../../apache_beam.tools.utils.html#apache_beam.tools.utils.check_compiled">[docs]</a><span class="k">def</span> <span class="nf">check_compiled</span><span class="p">(</span><span class="n">module</span><span class="p">):</span> |
| <span class="sd">"""Check whether given module has been compiled.</span> |
| <span class="sd"> Args:</span> |
| <span class="sd"> module: string, module name</span> |
| <span class="sd"> """</span> |
| <span class="n">check_module</span> <span class="o">=</span> <span class="nb">__import__</span><span class="p">(</span><span class="n">module</span><span class="p">,</span> <span class="nb">globals</span><span class="p">(),</span> <span class="nb">locals</span><span class="p">(),</span> <span class="o">-</span><span class="mi">1</span><span class="p">)</span> |
| <span class="n">ext</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">splitext</span><span class="p">(</span><span class="n">check_module</span><span class="o">.</span><span class="vm">__file__</span><span class="p">)[</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> |
| <span class="k">if</span> <span class="n">ext</span> <span class="ow">in</span> <span class="p">(</span><span class="s1">'.py'</span><span class="p">,</span> <span class="s1">'.pyc'</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span> |
| <span class="s2">"Profiling uncompiled code.</span><span class="se">\n</span><span class="s2">"</span> |
| <span class="s2">"To compile beam, run "</span> |
| <span class="s2">"'pip install Cython; python setup.py build_ext --inplace'"</span><span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="BenchmarkConfig"><a class="viewcode-back" href="../../../apache_beam.tools.utils.html#apache_beam.tools.utils.BenchmarkConfig">[docs]</a><span class="k">class</span> <span class="nc">BenchmarkConfig</span><span class="p">(</span> |
| <span class="n">collections</span><span class="o">.</span><span class="n">namedtuple</span><span class="p">(</span> |
| <span class="s2">"BenchmarkConfig"</span><span class="p">,</span> <span class="p">[</span><span class="s2">"benchmark"</span><span class="p">,</span> <span class="s2">"size"</span><span class="p">,</span> <span class="s2">"num_runs"</span><span class="p">])):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Attributes:</span> |
| <span class="sd"> benchmark: a callable that takes an int argument - benchmark size,</span> |
| <span class="sd"> and returns a callable. A returned callable must run the code being</span> |
| <span class="sd"> benchmarked on an input of specified size.</span> |
| |
| <span class="sd"> For example, one can implement a benchmark as:</span> |
| |
| <span class="sd"> class MyBenchmark(object):</span> |
| <span class="sd"> def __init__(self, size):</span> |
| <span class="sd"> [do necessary initialization]</span> |
| <span class="sd"> def __call__(self):</span> |
| <span class="sd"> [run the code in question]</span> |
| |
| <span class="sd"> size: int, a size of the input. Aggregated per-element metrics</span> |
| <span class="sd"> are counted based on the size of the input.</span> |
| <span class="sd"> num_runs: int, number of times to run each benchmark.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="nf">__str__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="s2">"</span><span class="si">%s</span><span class="s2">, </span><span class="si">%s</span><span class="s2"> element(s)"</span> <span class="o">%</span> <span class="p">(</span> |
| <span class="nb">getattr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">benchmark</span><span class="p">,</span> <span class="s1">'__name__'</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">benchmark</span><span class="p">)),</span> |
| <span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">size</span><span class="p">))</span></div> |
| |
| |
| <div class="viewcode-block" id="run_benchmarks"><a class="viewcode-back" href="../../../apache_beam.tools.utils.html#apache_beam.tools.utils.run_benchmarks">[docs]</a><span class="k">def</span> <span class="nf">run_benchmarks</span><span class="p">(</span><span class="n">benchmark_suite</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="sd">"""Runs benchmarks, and collects execution times.</span> |
| |
| <span class="sd"> A simple instrumentation to run a callable several times, collect and print</span> |
| <span class="sd"> its execution times.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> benchmark_suite: A list of BenchmarkConfig.</span> |
| <span class="sd"> verbose: bool, whether to print benchmark results to stdout.</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> A dictionary of the form string -> list of floats. Keys of the dictionary</span> |
| <span class="sd"> are benchmark names, values are execution times in seconds for each run.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="nf">run</span><span class="p">(</span><span class="n">benchmark_fn</span><span class="p">,</span> <span class="n">size</span><span class="p">):</span> |
| <span class="c1"># Contain each run of a benchmark inside a function so that any temporary</span> |
| <span class="c1"># objects can be garbage-collected after the run.</span> |
| <span class="n">benchmark_instance_callable</span> <span class="o">=</span> <span class="n">benchmark_fn</span><span class="p">(</span><span class="n">size</span><span class="p">)</span> |
| <span class="n">start</span> <span class="o">=</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span> |
| <span class="n">_</span> <span class="o">=</span> <span class="n">benchmark_instance_callable</span><span class="p">()</span> |
| <span class="k">return</span> <span class="n">time</span><span class="o">.</span><span class="n">time</span><span class="p">()</span> <span class="o">-</span> <span class="n">start</span> |
| |
| <span class="n">cost_series</span> <span class="o">=</span> <span class="n">collections</span><span class="o">.</span><span class="n">defaultdict</span><span class="p">(</span><span class="nb">list</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">benchmark_config</span> <span class="ow">in</span> <span class="n">benchmark_suite</span><span class="p">:</span> |
| <span class="n">name</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">benchmark_config</span><span class="p">)</span> |
| <span class="n">num_runs</span> <span class="o">=</span> <span class="n">benchmark_config</span><span class="o">.</span><span class="n">num_runs</span> |
| <span class="n">size</span> <span class="o">=</span> <span class="n">benchmark_config</span><span class="o">.</span><span class="n">size</span> |
| <span class="k">for</span> <span class="n">run_id</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">num_runs</span><span class="p">):</span> |
| <span class="c1"># Do a proactive GC before each run to minimize side-effects of different</span> |
| <span class="c1"># runs.</span> |
| <span class="n">gc</span><span class="o">.</span><span class="n">collect</span><span class="p">()</span> |
| <span class="n">time_cost</span> <span class="o">=</span> <span class="n">run</span><span class="p">(</span><span class="n">benchmark_config</span><span class="o">.</span><span class="n">benchmark</span><span class="p">,</span> <span class="n">size</span><span class="p">)</span> |
| <span class="n">cost_series</span><span class="p">[</span><span class="n">name</span><span class="p">]</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">time_cost</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">verbose</span><span class="p">:</span> |
| <span class="n">per_element_cost</span> <span class="o">=</span> <span class="n">time_cost</span> <span class="o">/</span> <span class="n">size</span> |
| <span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%s</span><span class="s2">: run </span><span class="si">%d</span><span class="s2"> of </span><span class="si">%d</span><span class="s2">, per element time cost: </span><span class="si">%g</span><span class="s2"> sec"</span> <span class="o">%</span> <span class="p">(</span> |
| <span class="n">name</span><span class="p">,</span> <span class="n">run_id</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="n">num_runs</span><span class="p">,</span> <span class="n">per_element_cost</span><span class="p">))</span> |
| <span class="k">if</span> <span class="n">verbose</span><span class="p">:</span> |
| <span class="nb">print</span><span class="p">(</span><span class="s2">""</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">verbose</span><span class="p">:</span> |
| <span class="n">pad_length</span> <span class="o">=</span> <span class="nb">max</span><span class="p">([</span><span class="nb">len</span><span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="n">bc</span><span class="p">))</span> <span class="k">for</span> <span class="n">bc</span> <span class="ow">in</span> <span class="n">benchmark_suite</span><span class="p">])</span> |
| |
| <span class="k">for</span> <span class="n">benchmark_config</span> <span class="ow">in</span> <span class="n">benchmark_suite</span><span class="p">:</span> |
| <span class="n">name</span> <span class="o">=</span> <span class="nb">str</span><span class="p">(</span><span class="n">benchmark_config</span><span class="p">)</span> |
| <span class="n">per_element_median_cost</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">numpy</span><span class="o">.</span><span class="n">median</span><span class="p">(</span><span class="n">cost_series</span><span class="p">[</span><span class="n">name</span><span class="p">])</span> <span class="o">/</span> <span class="n">benchmark_config</span><span class="o">.</span><span class="n">size</span><span class="p">)</span> |
| <span class="n">std</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">std</span><span class="p">(</span><span class="n">cost_series</span><span class="p">[</span><span class="n">name</span><span class="p">])</span> <span class="o">/</span> <span class="n">benchmark_config</span><span class="o">.</span><span class="n">size</span> |
| |
| <span class="nb">print</span><span class="p">(</span><span class="s2">"</span><span class="si">%s</span><span class="s2">: per element median time cost: </span><span class="si">%g</span><span class="s2"> sec, relative std: </span><span class="si">%.2f%%</span><span class="s2">"</span> <span class="o">%</span> <span class="p">(</span> |
| <span class="n">name</span><span class="o">.</span><span class="n">ljust</span><span class="p">(</span><span class="n">pad_length</span><span class="p">,</span> <span class="s2">" "</span><span class="p">),</span> <span class="n">per_element_median_cost</span><span class="p">,</span> |
| <span class="n">std</span> <span class="o">*</span> <span class="mi">100</span> <span class="o">/</span> <span class="n">per_element_median_cost</span><span class="p">))</span> |
| |
| <span class="k">return</span> <span class="n">cost_series</span></div> |
| </pre></div> |
| |
| </div> |
| <div class="articleComments"> |
| |
| </div> |
| </div> |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| © Copyright . |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/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"> |
| var DOCUMENTATION_OPTIONS = { |
| URL_ROOT:'../../../', |
| VERSION:'', |
| COLLAPSE_INDEX:false, |
| FILE_SUFFIX:'.html', |
| HAS_SOURCE: true, |
| SOURCELINK_SUFFIX: '.txt' |
| }; |
| </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/js/theme.js"></script> |
| |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.StickyNav.enable(); |
| }); |
| </script> |
| |
| |
| </body> |
| </html> |