| |
| |
| <!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.runners.interactive.caching.expression_cache — 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> »</li> |
| |
| <li><a href="../../../../index.html">Module code</a> »</li> |
| |
| <li>apache_beam.runners.interactive.caching.expression_cache</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.runners.interactive.caching.expression_cache</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="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="o">*</span> |
| |
| <span class="kn">import</span> <span class="nn">apache_beam</span> <span class="k">as</span> <span class="nn">beam</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.dataframe</span> <span class="kn">import</span> <span class="n">convert</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.dataframe</span> <span class="kn">import</span> <span class="n">expressions</span> |
| |
| |
| <div class="viewcode-block" id="ExpressionCache"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.caching.expression_cache.html#apache_beam.runners.interactive.caching.expression_cache.ExpressionCache">[docs]</a><span class="k">class</span> <span class="nc">ExpressionCache</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Utility class for caching deferred DataFrames expressions.</span> |
| |
| <span class="sd"> This is cache is currently a light-weight wrapper around the</span> |
| <span class="sd"> TO_PCOLLECTION_CACHE in the beam.dataframes.convert module and the</span> |
| <span class="sd"> computed_pcollections in the interactive module.</span> |
| |
| <span class="sd"> Example::</span> |
| |
| <span class="sd"> df : beam.dataframe.DeferredDataFrame = ...</span> |
| <span class="sd"> ...</span> |
| <span class="sd"> cache = ExpressionCache()</span> |
| <span class="sd"> cache.replace_with_cached(df._expr)</span> |
| |
| <span class="sd"> This will automatically link the instance to the existing caches. After it is</span> |
| <span class="sd"> created, the cache can then be used to modify an existing deferred dataframe</span> |
| <span class="sd"> expression tree to replace nodes with computed PCollections.</span> |
| |
| <span class="sd"> This object can be created and destroyed whenever. This class holds no state</span> |
| <span class="sd"> and the only side-effect is modifying the given expression.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcollection_cache</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">computed_cache</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.runners.interactive</span> <span class="kn">import</span> <span class="n">interactive_environment</span> <span class="k">as</span> <span class="n">ie</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_pcollection_cache</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">convert</span><span class="o">.</span><span class="n">TO_PCOLLECTION_CACHE</span> |
| <span class="k">if</span> <span class="n">pcollection_cache</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="n">pcollection_cache</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_computed_cache</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">ie</span><span class="o">.</span><span class="n">current_env</span><span class="p">()</span><span class="o">.</span><span class="n">computed_pcollections</span> |
| <span class="k">if</span> <span class="n">computed_cache</span> <span class="ow">is</span> <span class="kc">None</span> <span class="k">else</span> <span class="n">computed_cache</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="ExpressionCache.replace_with_cached"><a class="viewcode-back" href="../../../../../apache_beam.runners.interactive.caching.expression_cache.html#apache_beam.runners.interactive.caching.expression_cache.ExpressionCache.replace_with_cached">[docs]</a> <span class="k">def</span> <span class="nf">replace_with_cached</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">expr</span><span class="p">:</span> <span class="n">expressions</span><span class="o">.</span><span class="n">Expression</span><span class="p">)</span> <span class="o">-></span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">expressions</span><span class="o">.</span><span class="n">Expression</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""Replaces any previously computed expressions with PlaceholderExpressions.</span> |
| |
| <span class="sd"> This is used to correctly read any expressions that were cached in previous</span> |
| <span class="sd"> runs. This enables the InteractiveRunner to prune off old calculations from</span> |
| <span class="sd"> the expression tree.</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">replaced_inputs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">expressions</span><span class="o">.</span><span class="n">Expression</span><span class="p">]</span> <span class="o">=</span> <span class="p">{}</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_replace_with_cached_recur</span><span class="p">(</span><span class="n">expr</span><span class="p">,</span> <span class="n">replaced_inputs</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">replaced_inputs</span></div> |
| |
| <span class="k">def</span> <span class="nf">_replace_with_cached_recur</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> |
| <span class="n">expr</span><span class="p">:</span> <span class="n">expressions</span><span class="o">.</span><span class="n">Expression</span><span class="p">,</span> |
| <span class="n">replaced_inputs</span><span class="p">:</span> <span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">expressions</span><span class="o">.</span><span class="n">Expression</span><span class="p">])</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Recursive call for `replace_with_cached`.</span> |
| |
| <span class="sd"> Recurses through the expression tree and replaces any cached inputs with</span> |
| <span class="sd"> `PlaceholderExpression`s.</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">final_inputs</span> <span class="o">=</span> <span class="p">[]</span> |
| |
| <span class="k">for</span> <span class="nb">input</span> <span class="ow">in</span> <span class="n">expr</span><span class="o">.</span><span class="n">args</span><span class="p">():</span> |
| <span class="n">pc</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_get_cached</span><span class="p">(</span><span class="nb">input</span><span class="p">)</span> |
| |
| <span class="c1"># Only read from cache when there is the PCollection has been fully</span> |
| <span class="c1"># computed. This is so that no partial results are used.</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_is_computed</span><span class="p">(</span><span class="n">pc</span><span class="p">):</span> |
| |
| <span class="c1"># Reuse previously seen cached expressions. This is so that the same</span> |
| <span class="c1"># value isn't cached multiple times.</span> |
| <span class="k">if</span> <span class="nb">input</span><span class="o">.</span><span class="n">_id</span> <span class="ow">in</span> <span class="n">replaced_inputs</span><span class="p">:</span> |
| <span class="n">cached</span> <span class="o">=</span> <span class="n">replaced_inputs</span><span class="p">[</span><span class="nb">input</span><span class="o">.</span><span class="n">_id</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">cached</span> <span class="o">=</span> <span class="n">expressions</span><span class="o">.</span><span class="n">PlaceholderExpression</span><span class="p">(</span> |
| <span class="nb">input</span><span class="o">.</span><span class="n">proxy</span><span class="p">(),</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pcollection_cache</span><span class="p">[</span><span class="nb">input</span><span class="o">.</span><span class="n">_id</span><span class="p">])</span> |
| |
| <span class="n">replaced_inputs</span><span class="p">[</span><span class="nb">input</span><span class="o">.</span><span class="n">_id</span><span class="p">]</span> <span class="o">=</span> <span class="n">cached</span> |
| <span class="n">final_inputs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">cached</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">final_inputs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">input</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_replace_with_cached_recur</span><span class="p">(</span><span class="nb">input</span><span class="p">,</span> <span class="n">replaced_inputs</span><span class="p">)</span> |
| <span class="n">expr</span><span class="o">.</span><span class="n">_args</span> <span class="o">=</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">final_inputs</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_get_cached</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">expr</span><span class="p">:</span> <span class="n">expressions</span><span class="o">.</span><span class="n">Expression</span><span class="p">)</span> <span class="o">-></span> <span class="n">Optional</span><span class="p">[</span><span class="n">beam</span><span class="o">.</span><span class="n">PCollection</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""Returns the PCollection associated with the expression."""</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_pcollection_cache</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">expr</span><span class="o">.</span><span class="n">_id</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">_is_computed</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pc</span><span class="p">:</span> <span class="n">beam</span><span class="o">.</span><span class="n">PCollection</span><span class="p">)</span> <span class="o">-></span> <span class="nb">bool</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""Returns True if the PCollection has been run and computed."""</span> |
| <span class="k">return</span> <span class="n">pc</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="n">pc</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_computed_cache</span></div> |
| </pre></div> |
| |
| </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/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> |