Google Git
Sign in
apache / beam-site / refs/heads/revert-643-revert-642-updates_release_2.47.0 / . / pydoc / 2.47.0 / _modules / apache_beam / dataframe / expressions.html
blob: 20c4248e62f27f773e2bfa7793581e37d72509be [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.dataframe.expressions &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.dataframe.expressions</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.dataframe.expressions</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="kn">import</span> <span class="nn">contextlib</span>
<span class="kn">import</span> <span class="nn">random</span>
<span class="kn">import</span> <span class="nn">threading</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Callable</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Generic</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Iterable</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Optional</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">TypeVar</span>
<span class="kn">from</span> <span class="nn">apache_beam.dataframe</span> <span class="kn">import</span> <span class="n">partitionings</span>
<div class="viewcode-block" id="Session"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.Session">[docs]</a><span class="k">class</span> <span class="nc">Session</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;A session represents a mapping of expressions to concrete values.</span>
<span class="sd"> The bindings typically include required placeholders, but may be any</span>
<span class="sd"> intermediate expression as well.</span>
<span class="sd"> &quot;&quot;&quot;</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">bindings</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_bindings</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="n">bindings</span> <span class="ow">or</span> <span class="p">{})</span>
<div class="viewcode-block" id="Session.evaluate"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.Session.evaluate">[docs]</a> <span class="k">def</span> <span class="nf">evaluate</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="c1"># type: (Expression) -&gt; Any</span>
<span class="k">if</span> <span class="n">expr</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_bindings</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_bindings</span><span class="p">[</span><span class="n">expr</span><span class="p">]</span> <span class="o">=</span> <span class="n">expr</span><span class="o">.</span><span class="n">evaluate_at</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_bindings</span><span class="p">[</span><span class="n">expr</span><span class="p">]</span></div>
<div class="viewcode-block" id="Session.lookup"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.Session.lookup">[docs]</a> <span class="k">def</span> <span class="nf">lookup</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="c1"># type: (Expression) -&gt; Any</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_bindings</span><span class="p">[</span><span class="n">expr</span><span class="p">]</span></div></div>
<div class="viewcode-block" id="PartitioningSession"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.PartitioningSession">[docs]</a><span class="k">class</span> <span class="nc">PartitioningSession</span><span class="p">(</span><span class="n">Session</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;An extension of Session that enforces actual partitioning of inputs.</span>
<span class="sd"> Each expression is evaluated multiple times for various supported</span>
<span class="sd"> partitionings determined by its `requires_partition_by` specification. For</span>
<span class="sd"> each tested partitioning, the input is partitioned and the expression is</span>
<span class="sd"> evaluated on each partition separately, as if this were actually executed in</span>
<span class="sd"> a parallel manner.</span>
<span class="sd"> For each input partitioning, the results are verified to be partitioned</span>
<span class="sd"> appropriately according to the expression&#39;s `preserves_partition_by`</span>
<span class="sd"> specification.</span>
<span class="sd"> For testing only.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<div class="viewcode-block" id="PartitioningSession.evaluate"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.PartitioningSession.evaluate">[docs]</a> <span class="k">def</span> <span class="nf">evaluate</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="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span>
<span class="kn">import</span> <span class="nn">collections</span>
<span class="k">def</span> <span class="nf">is_scalar</span><span class="p">(</span><span class="n">expr</span><span class="p">):</span>
<span class="k">return</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">expr</span><span class="o">.</span><span class="n">proxy</span><span class="p">(),</span> <span class="n">pd</span><span class="o">.</span><span class="n">core</span><span class="o">.</span><span class="n">generic</span><span class="o">.</span><span class="n">NDFrame</span><span class="p">)</span>
<span class="k">if</span> <span class="n">expr</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_bindings</span><span class="p">:</span>
<span class="k">if</span> <span class="n">is_scalar</span><span class="p">(</span><span class="n">expr</span><span class="p">)</span> <span class="ow">or</span> <span class="ow">not</span> <span class="n">expr</span><span class="o">.</span><span class="n">args</span><span class="p">():</span>
<span class="n">result</span> <span class="o">=</span> <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="n">evaluate</span><span class="p">(</span><span class="n">expr</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">scaler_args</span> <span class="o">=</span> <span class="p">[</span><span class="n">arg</span> <span class="k">for</span> <span class="n">arg</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="k">if</span> <span class="n">is_scalar</span><span class="p">(</span><span class="n">arg</span><span class="p">)]</span>
<span class="k">def</span> <span class="nf">evaluate_with</span><span class="p">(</span><span class="n">input_partitioning</span><span class="p">):</span>
<span class="n">parts</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="k">lambda</span><span class="p">:</span> <span class="n">Session</span><span class="p">({</span><span class="n">arg</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">evaluate</span><span class="p">(</span><span class="n">arg</span><span class="p">)</span>
<span class="k">for</span> <span class="n">arg</span> <span class="ow">in</span> <span class="n">scaler_args</span><span class="p">}))</span>
<span class="k">for</span> <span class="n">arg</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="k">if</span> <span class="ow">not</span> <span class="n">is_scalar</span><span class="p">(</span><span class="n">arg</span><span class="p">):</span>
<span class="nb">input</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">evaluate</span><span class="p">(</span><span class="n">arg</span><span class="p">)</span>
<span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">part</span> <span class="ow">in</span> <span class="n">input_partitioning</span><span class="o">.</span><span class="n">test_partition_fn</span><span class="p">(</span><span class="nb">input</span><span class="p">):</span>
<span class="n">parts</span><span class="p">[</span><span class="n">key</span><span class="p">]</span><span class="o">.</span><span class="n">_bindings</span><span class="p">[</span><span class="n">arg</span><span class="p">]</span> <span class="o">=</span> <span class="n">part</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">parts</span><span class="p">:</span>
<span class="n">parts</span><span class="p">[</span><span class="kc">None</span><span class="p">]</span> <span class="c1"># Create at least one entry.</span>
<span class="n">results</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">session</span> <span class="ow">in</span> <span class="n">parts</span><span class="o">.</span><span class="n">values</span><span class="p">():</span>
<span class="k">if</span> <span class="nb">any</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">session</span><span class="o">.</span><span class="n">lookup</span><span class="p">(</span><span class="n">arg</span><span class="p">))</span> <span class="k">for</span> <span class="n">arg</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="k">if</span> <span class="ow">not</span> <span class="n">is_scalar</span><span class="p">(</span><span class="n">arg</span><span class="p">)):</span>
<span class="n">results</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">session</span><span class="o">.</span><span class="n">evaluate</span><span class="p">(</span><span class="n">expr</span><span class="p">))</span>
<span class="n">expected_output_partitioning</span> <span class="o">=</span> <span class="n">output_partitioning</span><span class="p">(</span>
<span class="n">expr</span><span class="p">,</span> <span class="n">input_partitioning</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">expected_output_partitioning</span><span class="o">.</span><span class="n">check</span><span class="p">(</span><span class="n">results</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">AssertionError</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;&quot;&quot;Expression does not preserve partitioning!</span>
<span class="s2"> Expression: </span><span class="si">{</span><span class="n">expr</span><span class="si">}</span>
<span class="s2"> Requires: </span><span class="si">{</span><span class="n">expr</span><span class="o">.</span><span class="n">requires_partition_by</span><span class="p">()</span><span class="si">}</span>
<span class="s2"> Preserves: </span><span class="si">{</span><span class="n">expr</span><span class="o">.</span><span class="n">preserves_partition_by</span><span class="p">()</span><span class="si">}</span>
<span class="s2"> Input partitioning: </span><span class="si">{</span><span class="n">input_partitioning</span><span class="si">}</span>
<span class="s2"> Expected output partitioning: </span><span class="si">{</span><span class="n">expected_output_partitioning</span><span class="si">}</span>
<span class="s2"> &quot;&quot;&quot;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">results</span><span class="p">:</span>
<span class="k">return</span> <span class="n">pd</span><span class="o">.</span><span class="n">concat</span><span class="p">(</span><span class="n">results</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="c1"># Choose any single session.</span>
<span class="k">return</span> <span class="nb">next</span><span class="p">(</span><span class="nb">iter</span><span class="p">(</span><span class="n">parts</span><span class="o">.</span><span class="n">values</span><span class="p">()))</span><span class="o">.</span><span class="n">evaluate</span><span class="p">(</span><span class="n">expr</span><span class="p">)</span>
<span class="c1"># Store random state so it can be re-used for each execution, in case</span>
<span class="c1"># the expression is part of a test that relies on the random seed.</span>
<span class="n">random_state</span> <span class="o">=</span> <span class="n">random</span><span class="o">.</span><span class="n">getstate</span><span class="p">()</span>
<span class="n">result</span> <span class="o">=</span> <span class="kc">None</span>
<span class="c1"># Run with all supported partitionings s.t. the smallest subpartitioning</span>
<span class="c1"># is used last. This way the final result is computed with the most</span>
<span class="c1"># challenging partitioning. Avoids heisenbugs where sometimes the result</span>
<span class="c1"># is computed trivially with Singleton partitioning and passes.</span>
<span class="k">for</span> <span class="n">input_partitioning</span> <span class="ow">in</span> <span class="nb">sorted</span><span class="p">(</span><span class="nb">set</span><span class="p">([</span><span class="n">expr</span><span class="o">.</span><span class="n">requires_partition_by</span><span class="p">(),</span>
<span class="n">partitionings</span><span class="o">.</span><span class="n">Arbitrary</span><span class="p">(),</span>
<span class="n">partitionings</span><span class="o">.</span><span class="n">JoinIndex</span><span class="p">(),</span>
<span class="n">partitionings</span><span class="o">.</span><span class="n">Index</span><span class="p">(),</span>
<span class="n">partitionings</span><span class="o">.</span><span class="n">Singleton</span><span class="p">()])):</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">expr</span><span class="o">.</span><span class="n">requires_partition_by</span><span class="p">()</span><span class="o">.</span><span class="n">is_subpartitioning_of</span><span class="p">(</span>
<span class="n">input_partitioning</span><span class="p">):</span>
<span class="k">continue</span>
<span class="n">random</span><span class="o">.</span><span class="n">setstate</span><span class="p">(</span><span class="n">random_state</span><span class="p">)</span>
<span class="n">result</span> <span class="o">=</span> <span class="n">evaluate_with</span><span class="p">(</span><span class="n">input_partitioning</span><span class="p">)</span>
<span class="k">assert</span> <span class="n">result</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_bindings</span><span class="p">[</span><span class="n">expr</span><span class="p">]</span> <span class="o">=</span> <span class="n">result</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_bindings</span><span class="p">[</span><span class="n">expr</span><span class="p">]</span></div></div>
<span class="c1"># The return type of an Expression</span>
<span class="n">T</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s1">&#39;T&#39;</span><span class="p">)</span>
<div class="viewcode-block" id="output_partitioning"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.output_partitioning">[docs]</a><span class="k">def</span> <span class="nf">output_partitioning</span><span class="p">(</span><span class="n">expr</span><span class="p">,</span> <span class="n">input_partitioning</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot; Return the expected output partitioning for `expr` when it&#39;s input is</span>
<span class="sd"> partitioned by `input_partitioning`.</span>
<span class="sd"> For internal use only; No backward compatibility guarantees &quot;&quot;&quot;</span>
<span class="k">assert</span> <span class="n">expr</span><span class="o">.</span><span class="n">requires_partition_by</span><span class="p">()</span><span class="o">.</span><span class="n">is_subpartitioning_of</span><span class="p">(</span><span class="n">input_partitioning</span><span class="p">)</span>
<span class="k">if</span> <span class="n">expr</span><span class="o">.</span><span class="n">preserves_partition_by</span><span class="p">()</span><span class="o">.</span><span class="n">is_subpartitioning_of</span><span class="p">(</span><span class="n">input_partitioning</span><span class="p">):</span>
<span class="k">return</span> <span class="nb">min</span><span class="p">(</span><span class="n">input_partitioning</span><span class="p">,</span> <span class="n">expr</span><span class="o">.</span><span class="n">preserves_partition_by</span><span class="p">())</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="n">partitionings</span><span class="o">.</span><span class="n">Arbitrary</span><span class="p">()</span></div>
<div class="viewcode-block" id="Expression"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.Expression">[docs]</a><span class="k">class</span> <span class="nc">Expression</span><span class="p">(</span><span class="n">Generic</span><span class="p">[</span><span class="n">T</span><span class="p">]):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;An expression is an operation bound to a set of arguments.</span>
<span class="sd"> An expression represents a deferred tree of operations, which can be</span>
<span class="sd"> evaluated at a specific bindings of root expressions to values.</span>
<span class="sd"> requires_partition_by indicates the upper bound of a set of partitionings that</span>
<span class="sd"> are acceptable inputs to this expression. The expression should be able to</span>
<span class="sd"> produce the correct result when given input(s) partitioned by its</span>
<span class="sd"> requires_partition_by attribute, or by any partitoning that is _not_</span>
<span class="sd"> a subpartitioning of it.</span>
<span class="sd"> preserves_partition_by indicates the upper bound of a set of partitionings</span>
<span class="sd"> that can be preserved by this expression. When the input(s) to this expression</span>
<span class="sd"> are partitioned by preserves_partition_by, or by any partitioning that is</span>
<span class="sd"> _not_ a subpartitioning of it, this expression should produce output(s)</span>
<span class="sd"> partitioned by the same partitioning.</span>
<span class="sd"> However, if the partitioning of an expression&#39;s input is a subpartitioning of</span>
<span class="sd"> the partitioning that it preserves, the output is presumed to have no</span>
<span class="sd"> particular partitioning (i.e. Arbitrary()).</span>
<span class="sd"> For example, let&#39;s look at an &quot;element-wise operation&quot;, that has no</span>
<span class="sd"> partitioning requirement, and preserves any partitioning given to it::</span>
<span class="sd"> requires_partition_by = Arbitrary() -----------------------------+</span>
<span class="sd"> |</span>
<span class="sd"> +-----------+-------------+---------- ... ----+---------|</span>
<span class="sd"> | | | | |</span>
<span class="sd"> Singleton() &lt; Index([i]) &lt; Index([i, j]) &lt; ... &lt; Index() &lt; Arbitrary()</span>
<span class="sd"> | | | | |</span>
<span class="sd"> +-----------+-------------+---------- ... ----+---------|</span>
<span class="sd"> |</span>
<span class="sd"> preserves_partition_by = Arbitrary() ----------------------------+</span>
<span class="sd"> As a more interesting example, consider this expression, which requires Index</span>
<span class="sd"> partitioning, and preserves just Singleton partitioning::</span>
<span class="sd"> requires_partition_by = Index() -----------------------+</span>
<span class="sd"> |</span>
<span class="sd"> +-----------+-------------+---------- ... ----|</span>
<span class="sd"> | | | |</span>
<span class="sd"> Singleton() &lt; Index([i]) &lt; Index([i, j]) &lt; ... &lt; Index() &lt; Arbitrary()</span>
<span class="sd"> |</span>
<span class="sd"> |</span>
<span class="sd"> preserves_partition_by = Singleton()</span>
<span class="sd"> Note that any non-Arbitrary partitioning is an acceptable input for this</span>
<span class="sd"> expression. However, unless the inputs are Singleton-partitioned, the</span>
<span class="sd"> expression makes no guarantees about the partitioning of the output.</span>
<span class="sd"> &quot;&quot;&quot;</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">name</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span> <span class="n">proxy</span><span class="p">:</span> <span class="n">T</span><span class="p">,</span> <span class="n">_id</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_name</span> <span class="o">=</span> <span class="n">name</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_proxy</span> <span class="o">=</span> <span class="n">proxy</span>
<span class="c1"># Store for preservation through pickling.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_id</span> <span class="o">=</span> <span class="n">_id</span> <span class="ow">or</span> <span class="s1">&#39;</span><span class="si">%s</span><span class="s1">_</span><span class="si">%s</span><span class="s1">_</span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="nb">type</span><span class="p">(</span><span class="n">proxy</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> <span class="nb">id</span><span class="p">(</span><span class="bp">self</span><span class="p">))</span>
<div class="viewcode-block" id="Expression.proxy"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.Expression.proxy">[docs]</a> <span class="k">def</span> <span class="nf">proxy</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">T</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_proxy</span></div>
<span class="k">def</span> <span class="fm">__hash__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="nb">hash</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_id</span><span class="p">)</span>
<span class="k">def</span> <span class="fm">__eq__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">other</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_id</span> <span class="o">==</span> <span class="n">other</span><span class="o">.</span><span class="n">_id</span>
<span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="s1">&#39;</span><span class="si">%s</span><span class="s1">[</span><span class="si">%s</span><span class="s1">]&#39;</span> <span class="o">%</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_id</span><span class="p">)</span>
<div class="viewcode-block" id="Expression.placeholders"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.Expression.placeholders">[docs]</a> <span class="k">def</span> <span class="nf">placeholders</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns all the placeholders that self depends on.&quot;&quot;&quot;</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">))</span></div>
<div class="viewcode-block" id="Expression.evaluate_at"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.Expression.evaluate_at">[docs]</a> <span class="k">def</span> <span class="nf">evaluate_at</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">session</span><span class="p">:</span> <span class="n">Session</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">T</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns the result of self with the bindings given in session.&quot;&quot;&quot;</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">))</span></div>
<div class="viewcode-block" id="Expression.requires_partition_by"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.Expression.requires_partition_by">[docs]</a> <span class="k">def</span> <span class="nf">requires_partition_by</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">partitionings</span><span class="o">.</span><span class="n">Partitioning</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns the partitioning, if any, require to evaluate this expression.</span>
<span class="sd"> Returns partitioning.Arbitrary() to require no partitioning is required.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">))</span></div>
<div class="viewcode-block" id="Expression.preserves_partition_by"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.Expression.preserves_partition_by">[docs]</a> <span class="k">def</span> <span class="nf">preserves_partition_by</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">partitionings</span><span class="o">.</span><span class="n">Partitioning</span><span class="p">:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Returns the partitioning, if any, preserved by this expression.</span>
<span class="sd"> This gives an upper bound on the partitioning of its ouput. The actual</span>
<span class="sd"> partitioning of the output may be less strict (e.g. if the input was</span>
<span class="sd"> less partitioned).</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">))</span></div></div>
<div class="viewcode-block" id="PlaceholderExpression"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.PlaceholderExpression">[docs]</a><span class="k">class</span> <span class="nc">PlaceholderExpression</span><span class="p">(</span><span class="n">Expression</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;An expression whose value must be explicitly bound in the session.&quot;&quot;&quot;</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="c1"># type: PlaceholderExpression</span>
<span class="n">proxy</span><span class="p">,</span> <span class="c1"># type: T</span>
<span class="n">reference</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="c1"># type: Any</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Initialize a placeholder expression.</span>
<span class="sd"> Args:</span>
<span class="sd"> proxy: A proxy object with the type expected to be bound to this</span>
<span class="sd"> expression. Used for type checking at pipeline construction time.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="s1">&#39;placeholder&#39;</span><span class="p">,</span> <span class="n">proxy</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_reference</span> <span class="o">=</span> <span class="n">reference</span>
<div class="viewcode-block" id="PlaceholderExpression.placeholders"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.PlaceholderExpression.placeholders">[docs]</a> <span class="k">def</span> <span class="nf">placeholders</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="nb">frozenset</span><span class="p">([</span><span class="bp">self</span><span class="p">])</span></div>
<div class="viewcode-block" id="PlaceholderExpression.args"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.PlaceholderExpression.args">[docs]</a> <span class="k">def</span> <span class="nf">args</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="p">()</span></div>
<div class="viewcode-block" id="PlaceholderExpression.evaluate_at"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.PlaceholderExpression.evaluate_at">[docs]</a> <span class="k">def</span> <span class="nf">evaluate_at</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">session</span><span class="p">):</span>
<span class="k">return</span> <span class="n">session</span><span class="o">.</span><span class="n">lookup</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span></div>
<div class="viewcode-block" id="PlaceholderExpression.requires_partition_by"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.PlaceholderExpression.requires_partition_by">[docs]</a> <span class="k">def</span> <span class="nf">requires_partition_by</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="n">partitionings</span><span class="o">.</span><span class="n">Arbitrary</span><span class="p">()</span></div>
<div class="viewcode-block" id="PlaceholderExpression.preserves_partition_by"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.PlaceholderExpression.preserves_partition_by">[docs]</a> <span class="k">def</span> <span class="nf">preserves_partition_by</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="n">partitionings</span><span class="o">.</span><span class="n">Index</span><span class="p">()</span></div></div>
<div class="viewcode-block" id="ConstantExpression"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.ConstantExpression">[docs]</a><span class="k">class</span> <span class="nc">ConstantExpression</span><span class="p">(</span><span class="n">Expression</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;An expression whose value is known at pipeline construction time.&quot;&quot;&quot;</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="c1"># type: ConstantExpression</span>
<span class="n">value</span><span class="p">,</span> <span class="c1"># type: T</span>
<span class="n">proxy</span><span class="o">=</span><span class="kc">None</span> <span class="c1"># type: Optional[T]</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Initialize a constant expression.</span>
<span class="sd"> Args:</span>
<span class="sd"> value: The constant value to be produced by this expression.</span>
<span class="sd"> proxy: (Optional) a proxy object with same type as `value` to use for</span>
<span class="sd"> rapid type checking at pipeline construction time. If not provided,</span>
<span class="sd"> `value` will be used directly.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">proxy</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">proxy</span> <span class="o">=</span> <span class="n">value</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="s1">&#39;constant&#39;</span><span class="p">,</span> <span class="n">proxy</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_value</span> <span class="o">=</span> <span class="n">value</span>
<div class="viewcode-block" id="ConstantExpression.placeholders"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.ConstantExpression.placeholders">[docs]</a> <span class="k">def</span> <span class="nf">placeholders</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="nb">frozenset</span><span class="p">()</span></div>
<div class="viewcode-block" id="ConstantExpression.args"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.ConstantExpression.args">[docs]</a> <span class="k">def</span> <span class="nf">args</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="p">()</span></div>
<div class="viewcode-block" id="ConstantExpression.evaluate_at"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.ConstantExpression.evaluate_at">[docs]</a> <span class="k">def</span> <span class="nf">evaluate_at</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">session</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_value</span></div>
<div class="viewcode-block" id="ConstantExpression.requires_partition_by"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.ConstantExpression.requires_partition_by">[docs]</a> <span class="k">def</span> <span class="nf">requires_partition_by</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="n">partitionings</span><span class="o">.</span><span class="n">Arbitrary</span><span class="p">()</span></div>
<div class="viewcode-block" id="ConstantExpression.preserves_partition_by"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.ConstantExpression.preserves_partition_by">[docs]</a> <span class="k">def</span> <span class="nf">preserves_partition_by</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="n">partitionings</span><span class="o">.</span><span class="n">Arbitrary</span><span class="p">()</span></div></div>
<div class="viewcode-block" id="ComputedExpression"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.ComputedExpression">[docs]</a><span class="k">class</span> <span class="nc">ComputedExpression</span><span class="p">(</span><span class="n">Expression</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;An expression whose value must be computed at pipeline execution time.&quot;&quot;&quot;</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="c1"># type: ComputedExpression</span>
<span class="n">name</span><span class="p">,</span> <span class="c1"># type: str</span>
<span class="n">func</span><span class="p">,</span> <span class="c1"># type: Callable[...,T]</span>
<span class="n">args</span><span class="p">,</span> <span class="c1"># type: Iterable[Expression]</span>
<span class="n">proxy</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="c1"># type: Optional[T]</span>
<span class="n">_id</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="c1"># type: Optional[str]</span>
<span class="n">requires_partition_by</span><span class="o">=</span><span class="n">partitionings</span><span class="o">.</span><span class="n">Index</span><span class="p">(),</span> <span class="c1"># type: partitionings.Partitioning</span>
<span class="n">preserves_partition_by</span><span class="o">=</span><span class="n">partitionings</span><span class="o">.</span><span class="n">Singleton</span><span class="p">(),</span> <span class="c1"># type: partitionings.Partitioning</span>
<span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Initialize a computed expression.</span>
<span class="sd"> Args:</span>
<span class="sd"> name: The name of this expression.</span>
<span class="sd"> func: The function that will be used to compute the value of this</span>
<span class="sd"> expression. Should accept arguments of the types returned when</span>
<span class="sd"> evaluating the `args` expressions.</span>
<span class="sd"> args: The list of expressions that will be used to produce inputs to</span>
<span class="sd"> `func`.</span>
<span class="sd"> proxy: (Optional) a proxy object with same type as the objects that this</span>
<span class="sd"> ComputedExpression will produce at execution time. If not provided, a</span>
<span class="sd"> proxy will be generated using `func` and the proxies of `args`.</span>
<span class="sd"> _id: (Optional) a string to uniquely identify this expression.</span>
<span class="sd"> requires_partition_by: The required (common) partitioning of the args.</span>
<span class="sd"> preserves_partition_by: The level of partitioning preserved.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="p">(</span><span class="ow">not</span> <span class="n">_get_allow_non_parallel</span><span class="p">()</span> <span class="ow">and</span>
<span class="nb">isinstance</span><span class="p">(</span><span class="n">requires_partition_by</span><span class="p">,</span> <span class="n">partitionings</span><span class="o">.</span><span class="n">Singleton</span><span class="p">)):</span>
<span class="n">reason</span> <span class="o">=</span> <span class="n">requires_partition_by</span><span class="o">.</span><span class="n">reason</span> <span class="ow">or</span> <span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;Encountered non-parallelizable form of </span><span class="si">{</span><span class="n">name</span><span class="si">!r}</span><span class="s2">.&quot;</span><span class="p">)</span>
<span class="k">raise</span> <span class="n">NonParallelOperation</span><span class="p">(</span>
<span class="sa">f</span><span class="s2">&quot;</span><span class="si">{</span><span class="n">reason</span><span class="si">}</span><span class="se">\n</span><span class="s2">&quot;</span>
<span class="s2">&quot;Consider using an allow_non_parallel_operations block if you&#39;re &quot;</span>
<span class="s2">&quot;sure you want to do this. See &quot;</span>
<span class="s2">&quot;https://s.apache.org/dataframe-non-parallel-operations for more &quot;</span>
<span class="s2">&quot;information.&quot;</span><span class="p">)</span>
<span class="n">args</span> <span class="o">=</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">args</span><span class="p">)</span>
<span class="k">if</span> <span class="n">proxy</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">proxy</span> <span class="o">=</span> <span class="n">func</span><span class="p">(</span><span class="o">*</span><span class="p">(</span><span class="n">arg</span><span class="o">.</span><span class="n">proxy</span><span class="p">()</span> <span class="k">for</span> <span class="n">arg</span> <span class="ow">in</span> <span class="n">args</span><span class="p">))</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">proxy</span><span class="p">,</span> <span class="n">_id</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_func</span> <span class="o">=</span> <span class="n">func</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_args</span> <span class="o">=</span> <span class="n">args</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_requires_partition_by</span> <span class="o">=</span> <span class="n">requires_partition_by</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_preserves_partition_by</span> <span class="o">=</span> <span class="n">preserves_partition_by</span>
<div class="viewcode-block" id="ComputedExpression.placeholders"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.ComputedExpression.placeholders">[docs]</a> <span class="k">def</span> <span class="nf">placeholders</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="nb">frozenset</span><span class="o">.</span><span class="n">union</span><span class="p">(</span>
<span class="nb">frozenset</span><span class="p">(),</span> <span class="o">*</span><span class="p">[</span><span class="n">arg</span><span class="o">.</span><span class="n">placeholders</span><span class="p">()</span> <span class="k">for</span> <span class="n">arg</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">args</span><span class="p">()])</span></div>
<div class="viewcode-block" id="ComputedExpression.args"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.ComputedExpression.args">[docs]</a> <span class="k">def</span> <span class="nf">args</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_args</span></div>
<div class="viewcode-block" id="ComputedExpression.evaluate_at"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.ComputedExpression.evaluate_at">[docs]</a> <span class="k">def</span> <span class="nf">evaluate_at</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">session</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_func</span><span class="p">(</span><span class="o">*</span><span class="p">(</span><span class="n">session</span><span class="o">.</span><span class="n">evaluate</span><span class="p">(</span><span class="n">arg</span><span class="p">)</span> <span class="k">for</span> <span class="n">arg</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_args</span><span class="p">))</span></div>
<div class="viewcode-block" id="ComputedExpression.requires_partition_by"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.ComputedExpression.requires_partition_by">[docs]</a> <span class="k">def</span> <span class="nf">requires_partition_by</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_requires_partition_by</span></div>
<div class="viewcode-block" id="ComputedExpression.preserves_partition_by"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.ComputedExpression.preserves_partition_by">[docs]</a> <span class="k">def</span> <span class="nf">preserves_partition_by</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_preserves_partition_by</span></div></div>
<div class="viewcode-block" id="elementwise_expression"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.elementwise_expression">[docs]</a><span class="k">def</span> <span class="nf">elementwise_expression</span><span class="p">(</span><span class="n">name</span><span class="p">,</span> <span class="n">func</span><span class="p">,</span> <span class="n">args</span><span class="p">):</span>
<span class="k">return</span> <span class="n">ComputedExpression</span><span class="p">(</span>
<span class="n">name</span><span class="p">,</span>
<span class="n">func</span><span class="p">,</span>
<span class="n">args</span><span class="p">,</span>
<span class="n">requires_partition_by</span><span class="o">=</span><span class="n">partitionings</span><span class="o">.</span><span class="n">Arbitrary</span><span class="p">(),</span>
<span class="n">preserves_partition_by</span><span class="o">=</span><span class="n">partitionings</span><span class="o">.</span><span class="n">Arbitrary</span><span class="p">())</span></div>
<span class="n">_ALLOW_NON_PARALLEL</span> <span class="o">=</span> <span class="n">threading</span><span class="o">.</span><span class="n">local</span><span class="p">()</span>
<span class="n">_ALLOW_NON_PARALLEL</span><span class="o">.</span><span class="n">value</span> <span class="o">=</span> <span class="kc">False</span>
<span class="k">def</span> <span class="nf">_get_allow_non_parallel</span><span class="p">():</span>
<span class="k">return</span> <span class="n">_ALLOW_NON_PARALLEL</span><span class="o">.</span><span class="n">value</span>
<div class="viewcode-block" id="allow_non_parallel_operations"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.allow_non_parallel_operations">[docs]</a><span class="nd">@contextlib</span><span class="o">.</span><span class="n">contextmanager</span>
<span class="k">def</span> <span class="nf">allow_non_parallel_operations</span><span class="p">(</span><span class="n">allow</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="k">if</span> <span class="n">allow</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">yield</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">old_value</span><span class="p">,</span> <span class="n">_ALLOW_NON_PARALLEL</span><span class="o">.</span><span class="n">value</span> <span class="o">=</span> <span class="n">_ALLOW_NON_PARALLEL</span><span class="o">.</span><span class="n">value</span><span class="p">,</span> <span class="n">allow</span>
<span class="k">yield</span>
<span class="n">_ALLOW_NON_PARALLEL</span><span class="o">.</span><span class="n">value</span> <span class="o">=</span> <span class="n">old_value</span></div>
<div class="viewcode-block" id="NonParallelOperation"><a class="viewcode-back" href="../../../apache_beam.dataframe.expressions.html#apache_beam.dataframe.expressions.NonParallelOperation">[docs]</a><span class="k">class</span> <span class="nc">NonParallelOperation</span><span class="p">(</span><span class="ne">Exception</span><span class="p">):</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">msg</span><span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">msg</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">msg</span> <span class="o">=</span> <span class="n">msg</span></div>
</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>