| |
| |
| <!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.transforms.combiners — 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.transforms.combiners</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.transforms.combiners</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">"""A library of basic combiner PTransform subclasses."""</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">import</span> <span class="nn">operator</span> |
| <span class="kn">import</span> <span class="nn">random</span> |
| <span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">object</span> |
| <span class="kn">from</span> <span class="nn">builtins</span> <span class="k">import</span> <span class="nb">zip</span> |
| <span class="kn">from</span> <span class="nn">functools</span> <span class="k">import</span> <span class="n">cmp_to_key</span> |
| |
| <span class="kn">from</span> <span class="nn">past.builtins</span> <span class="k">import</span> <span class="n">long</span> |
| |
| <span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="k">import</span> <span class="n">core</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="k">import</span> <span class="n">cy_combiners</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.transforms</span> <span class="k">import</span> <span class="n">ptransform</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.transforms.display</span> <span class="k">import</span> <span class="n">DisplayDataItem</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints</span> <span class="k">import</span> <span class="n">KV</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints</span> <span class="k">import</span> <span class="n">Any</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints</span> <span class="k">import</span> <span class="n">Dict</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints</span> <span class="k">import</span> <span class="n">List</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints</span> <span class="k">import</span> <span class="n">Tuple</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints</span> <span class="k">import</span> <span class="n">TypeVariable</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints</span> <span class="k">import</span> <span class="n">Union</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints</span> <span class="k">import</span> <span class="n">with_input_types</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.typehints</span> <span class="k">import</span> <span class="n">with_output_types</span> |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="s1">'Count'</span><span class="p">,</span> |
| <span class="s1">'Mean'</span><span class="p">,</span> |
| <span class="s1">'Sample'</span><span class="p">,</span> |
| <span class="s1">'Top'</span><span class="p">,</span> |
| <span class="s1">'ToDict'</span><span class="p">,</span> |
| <span class="s1">'ToList'</span><span class="p">,</span> |
| <span class="p">]</span> |
| |
| <span class="c1"># Type variables</span> |
| <span class="n">T</span> <span class="o">=</span> <span class="n">TypeVariable</span><span class="p">(</span><span class="s1">'T'</span><span class="p">)</span> |
| <span class="n">K</span> <span class="o">=</span> <span class="n">TypeVariable</span><span class="p">(</span><span class="s1">'K'</span><span class="p">)</span> |
| <span class="n">V</span> <span class="o">=</span> <span class="n">TypeVariable</span><span class="p">(</span><span class="s1">'V'</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="Mean"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.Mean">[docs]</a><span class="k">class</span> <span class="nc">Mean</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""Combiners for computing arithmetic means of elements."""</span> |
| |
| <div class="viewcode-block" id="Mean.Globally"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.Mean.Globally">[docs]</a> <span class="k">class</span> <span class="nc">Globally</span><span class="p">(</span><span class="n">ptransform</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="sd">"""combiners.Mean.Globally computes the arithmetic mean of the elements."""</span> |
| |
| <div class="viewcode-block" id="Mean.Globally.expand"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.Mean.Globally.expand">[docs]</a> <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">core</span><span class="o">.</span><span class="n">CombineGlobally</span><span class="p">(</span><span class="n">MeanCombineFn</span><span class="p">())</span></div></div> |
| |
| <div class="viewcode-block" id="Mean.PerKey"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.Mean.PerKey">[docs]</a> <span class="k">class</span> <span class="nc">PerKey</span><span class="p">(</span><span class="n">ptransform</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="sd">"""combiners.Mean.PerKey finds the means of the values for each key."""</span> |
| |
| <div class="viewcode-block" id="Mean.PerKey.expand"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.Mean.PerKey.expand">[docs]</a> <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">core</span><span class="o">.</span><span class="n">CombinePerKey</span><span class="p">(</span><span class="n">MeanCombineFn</span><span class="p">())</span></div></div></div> |
| |
| |
| <span class="c1"># TODO(laolu): This type signature is overly restrictive. This should be</span> |
| <span class="c1"># more general.</span> |
| <span class="nd">@with_input_types</span><span class="p">(</span><span class="n">Union</span><span class="p">[</span><span class="nb">float</span><span class="p">,</span> <span class="nb">int</span><span class="p">,</span> <span class="n">long</span><span class="p">])</span> |
| <span class="nd">@with_output_types</span><span class="p">(</span><span class="nb">float</span><span class="p">)</span> |
| <span class="k">class</span> <span class="nc">MeanCombineFn</span><span class="p">(</span><span class="n">core</span><span class="o">.</span><span class="n">CombineFn</span><span class="p">):</span> |
| <span class="sd">"""CombineFn for computing an arithmetic mean."""</span> |
| |
| <span class="k">def</span> <span class="nf">create_accumulator</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="mi">0</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">add_input</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sum_count</span><span class="p">,</span> <span class="n">element</span><span class="p">):</span> |
| <span class="p">(</span><span class="n">sum_</span><span class="p">,</span> <span class="n">count</span><span class="p">)</span> <span class="o">=</span> <span class="n">sum_count</span> |
| <span class="k">return</span> <span class="n">sum_</span> <span class="o">+</span> <span class="n">element</span><span class="p">,</span> <span class="n">count</span> <span class="o">+</span> <span class="mi">1</span> |
| |
| <span class="k">def</span> <span class="nf">merge_accumulators</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulators</span><span class="p">):</span> |
| <span class="n">sums</span><span class="p">,</span> <span class="n">counts</span> <span class="o">=</span> <span class="nb">zip</span><span class="p">(</span><span class="o">*</span><span class="n">accumulators</span><span class="p">)</span> |
| <span class="k">return</span> <span class="nb">sum</span><span class="p">(</span><span class="n">sums</span><span class="p">),</span> <span class="nb">sum</span><span class="p">(</span><span class="n">counts</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">extract_output</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">sum_count</span><span class="p">):</span> |
| <span class="p">(</span><span class="n">sum_</span><span class="p">,</span> <span class="n">count</span><span class="p">)</span> <span class="o">=</span> <span class="n">sum_count</span> |
| <span class="k">if</span> <span class="n">count</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="k">return</span> <span class="nb">float</span><span class="p">(</span><span class="s1">'NaN'</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">sum_</span> <span class="o">/</span> <span class="nb">float</span><span class="p">(</span><span class="n">count</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">for_input_type</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_type</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">input_type</span> <span class="ow">is</span> <span class="nb">int</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">cy_combiners</span><span class="o">.</span><span class="n">MeanInt64Fn</span><span class="p">()</span> |
| <span class="k">elif</span> <span class="n">input_type</span> <span class="ow">is</span> <span class="nb">float</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">cy_combiners</span><span class="o">.</span><span class="n">MeanFloatFn</span><span class="p">()</span> |
| <span class="k">return</span> <span class="bp">self</span> |
| |
| |
| <div class="viewcode-block" id="Count"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.Count">[docs]</a><span class="k">class</span> <span class="nc">Count</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""Combiners for counting elements."""</span> |
| |
| <div class="viewcode-block" id="Count.Globally"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.Count.Globally">[docs]</a> <span class="k">class</span> <span class="nc">Globally</span><span class="p">(</span><span class="n">ptransform</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="sd">"""combiners.Count.Globally counts the total number of elements."""</span> |
| |
| <div class="viewcode-block" id="Count.Globally.expand"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.Count.Globally.expand">[docs]</a> <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">core</span><span class="o">.</span><span class="n">CombineGlobally</span><span class="p">(</span><span class="n">CountCombineFn</span><span class="p">())</span></div></div> |
| |
| <div class="viewcode-block" id="Count.PerKey"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.Count.PerKey">[docs]</a> <span class="k">class</span> <span class="nc">PerKey</span><span class="p">(</span><span class="n">ptransform</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="sd">"""combiners.Count.PerKey counts how many elements each unique key has."""</span> |
| |
| <div class="viewcode-block" id="Count.PerKey.expand"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.Count.PerKey.expand">[docs]</a> <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">core</span><span class="o">.</span><span class="n">CombinePerKey</span><span class="p">(</span><span class="n">CountCombineFn</span><span class="p">())</span></div></div> |
| |
| <div class="viewcode-block" id="Count.PerElement"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.Count.PerElement">[docs]</a> <span class="k">class</span> <span class="nc">PerElement</span><span class="p">(</span><span class="n">ptransform</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="sd">"""combiners.Count.PerElement counts how many times each element occurs."""</span> |
| |
| <div class="viewcode-block" id="Count.PerElement.expand"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.Count.PerElement.expand">[docs]</a> <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">):</span> |
| <span class="n">paired_with_void_type</span> <span class="o">=</span> <span class="n">KV</span><span class="p">[</span><span class="n">pcoll</span><span class="o">.</span><span class="n">element_type</span><span class="p">,</span> <span class="n">Any</span><span class="p">]</span> |
| <span class="k">return</span> <span class="p">(</span><span class="n">pcoll</span> |
| <span class="o">|</span> <span class="p">(</span><span class="s1">'</span><span class="si">%s</span><span class="s1">:PairWithVoid'</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">label</span> <span class="o">>></span> <span class="n">core</span><span class="o">.</span><span class="n">Map</span><span class="p">(</span><span class="k">lambda</span> <span class="n">x</span><span class="p">:</span> <span class="p">(</span><span class="n">x</span><span class="p">,</span> <span class="kc">None</span><span class="p">))</span> |
| <span class="o">.</span><span class="n">with_output_types</span><span class="p">(</span><span class="n">paired_with_void_type</span><span class="p">))</span> |
| <span class="o">|</span> <span class="n">core</span><span class="o">.</span><span class="n">CombinePerKey</span><span class="p">(</span><span class="n">CountCombineFn</span><span class="p">()))</span></div></div></div> |
| |
| |
| <span class="nd">@with_input_types</span><span class="p">(</span><span class="n">Any</span><span class="p">)</span> |
| <span class="nd">@with_output_types</span><span class="p">(</span><span class="nb">int</span><span class="p">)</span> |
| <span class="k">class</span> <span class="nc">CountCombineFn</span><span class="p">(</span><span class="n">core</span><span class="o">.</span><span class="n">CombineFn</span><span class="p">):</span> |
| <span class="sd">"""CombineFn for computing PCollection size."""</span> |
| |
| <span class="k">def</span> <span class="nf">create_accumulator</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="mi">0</span> |
| |
| <span class="k">def</span> <span class="nf">add_input</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">,</span> <span class="n">element</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">accumulator</span> <span class="o">+</span> <span class="mi">1</span> |
| |
| <span class="k">def</span> <span class="nf">add_inputs</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">,</span> <span class="n">elements</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">accumulator</span> <span class="o">+</span> <span class="nb">len</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="n">elements</span><span class="p">))</span> |
| |
| <span class="k">def</span> <span class="nf">merge_accumulators</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulators</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">sum</span><span class="p">(</span><span class="n">accumulators</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">extract_output</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">accumulator</span> |
| |
| |
| <div class="viewcode-block" id="Top"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.Top">[docs]</a><span class="k">class</span> <span class="nc">Top</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""Combiners for obtaining extremal elements."""</span> |
| <span class="c1"># pylint: disable=no-self-argument</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="nd">@ptransform</span><span class="o">.</span><span class="n">ptransform_fn</span> |
| <span class="k">def</span> <span class="nf">Of</span><span class="p">(</span><span class="n">pcoll</span><span class="p">,</span> <span class="n">n</span><span class="p">,</span> <span class="n">compare</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="sd">"""Obtain a list of the compare-most N elements in a PCollection.</span> |
| |
| <span class="sd"> This transform will retrieve the n greatest elements in the PCollection</span> |
| <span class="sd"> to which it is applied, where "greatest" is determined by the comparator</span> |
| <span class="sd"> function supplied as the compare argument.</span> |
| |
| <span class="sd"> compare should be an implementation of "a < b" taking at least two arguments</span> |
| <span class="sd"> (a and b). Additional arguments and side inputs specified in the apply call</span> |
| <span class="sd"> become additional arguments to the comparator. Defaults to the natural</span> |
| <span class="sd"> ordering of the elements.</span> |
| |
| <span class="sd"> The arguments 'key' and 'reverse' may instead be passed as keyword</span> |
| <span class="sd"> arguments, and have the same meaning as for Python's sort functions.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> pcoll: PCollection to process.</span> |
| <span class="sd"> n: number of elements to extract from pcoll.</span> |
| <span class="sd"> compare: as described above.</span> |
| <span class="sd"> *args: as described above.</span> |
| <span class="sd"> **kwargs: as described above.</span> |
| <span class="sd"> """</span> |
| <span class="n">key</span> <span class="o">=</span> <span class="n">kwargs</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="s1">'key'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="n">reverse</span> <span class="o">=</span> <span class="n">kwargs</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="s1">'reverse'</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">core</span><span class="o">.</span><span class="n">CombineGlobally</span><span class="p">(</span> |
| <span class="n">TopCombineFn</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">compare</span><span class="p">,</span> <span class="n">key</span><span class="p">,</span> <span class="n">reverse</span><span class="p">),</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="nd">@ptransform</span><span class="o">.</span><span class="n">ptransform_fn</span> |
| <span class="k">def</span> <span class="nf">PerKey</span><span class="p">(</span><span class="n">pcoll</span><span class="p">,</span> <span class="n">n</span><span class="p">,</span> <span class="n">compare</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="sd">"""Identifies the compare-most N elements associated with each key.</span> |
| |
| <span class="sd"> This transform will produce a PCollection mapping unique keys in the input</span> |
| <span class="sd"> PCollection to the n greatest elements with which they are associated, where</span> |
| <span class="sd"> "greatest" is determined by the comparator function supplied as the compare</span> |
| <span class="sd"> argument.</span> |
| |
| <span class="sd"> compare should be an implementation of "a < b" taking at least two arguments</span> |
| <span class="sd"> (a and b). Additional arguments and side inputs specified in the apply call</span> |
| <span class="sd"> become additional arguments to the comparator. Defaults to the natural</span> |
| <span class="sd"> ordering of the elements.</span> |
| |
| <span class="sd"> The arguments 'key' and 'reverse' may instead be passed as keyword</span> |
| <span class="sd"> arguments, and have the same meaning as for Python's sort functions.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> pcoll: PCollection to process.</span> |
| <span class="sd"> n: number of elements to extract from pcoll.</span> |
| <span class="sd"> compare: as described above.</span> |
| <span class="sd"> *args: as described above.</span> |
| <span class="sd"> **kwargs: as described above.</span> |
| |
| <span class="sd"> Raises:</span> |
| <span class="sd"> TypeCheckError: If the output type of the input PCollection is not</span> |
| <span class="sd"> compatible with KV[A, B].</span> |
| <span class="sd"> """</span> |
| <span class="n">key</span> <span class="o">=</span> <span class="n">kwargs</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="s1">'key'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> |
| <span class="n">reverse</span> <span class="o">=</span> <span class="n">kwargs</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="s1">'reverse'</span><span class="p">,</span> <span class="kc">False</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">core</span><span class="o">.</span><span class="n">CombinePerKey</span><span class="p">(</span> |
| <span class="n">TopCombineFn</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">compare</span><span class="p">,</span> <span class="n">key</span><span class="p">,</span> <span class="n">reverse</span><span class="p">),</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="nd">@ptransform</span><span class="o">.</span><span class="n">ptransform_fn</span> |
| <span class="k">def</span> <span class="nf">Largest</span><span class="p">(</span><span class="n">pcoll</span><span class="p">,</span> <span class="n">n</span><span class="p">):</span> |
| <span class="sd">"""Obtain a list of the greatest N elements in a PCollection."""</span> |
| <span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">Top</span><span class="o">.</span><span class="n">Of</span><span class="p">(</span><span class="n">n</span><span class="p">)</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="nd">@ptransform</span><span class="o">.</span><span class="n">ptransform_fn</span> |
| <span class="k">def</span> <span class="nf">Smallest</span><span class="p">(</span><span class="n">pcoll</span><span class="p">,</span> <span class="n">n</span><span class="p">):</span> |
| <span class="sd">"""Obtain a list of the least N elements in a PCollection."""</span> |
| <span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">Top</span><span class="o">.</span><span class="n">Of</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">reverse</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="nd">@ptransform</span><span class="o">.</span><span class="n">ptransform_fn</span> |
| <span class="k">def</span> <span class="nf">LargestPerKey</span><span class="p">(</span><span class="n">pcoll</span><span class="p">,</span> <span class="n">n</span><span class="p">):</span> |
| <span class="sd">"""Identifies the N greatest elements associated with each key."""</span> |
| <span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">Top</span><span class="o">.</span><span class="n">PerKey</span><span class="p">(</span><span class="n">n</span><span class="p">)</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="nd">@ptransform</span><span class="o">.</span><span class="n">ptransform_fn</span> |
| <span class="k">def</span> <span class="nf">SmallestPerKey</span><span class="p">(</span><span class="n">pcoll</span><span class="p">,</span> <span class="n">n</span><span class="p">,</span> <span class="n">reverse</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span> |
| <span class="sd">"""Identifies the N least elements associated with each key."""</span> |
| <span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">Top</span><span class="o">.</span><span class="n">PerKey</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">reverse</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span></div> |
| |
| |
| <span class="nd">@with_input_types</span><span class="p">(</span><span class="n">T</span><span class="p">)</span> |
| <span class="nd">@with_output_types</span><span class="p">(</span><span class="n">List</span><span class="p">[</span><span class="n">T</span><span class="p">])</span> |
| <span class="k">class</span> <span class="nc">TopCombineFn</span><span class="p">(</span><span class="n">core</span><span class="o">.</span><span class="n">CombineFn</span><span class="p">):</span> |
| <span class="sd">"""CombineFn doing the combining for all of the Top transforms.</span> |
| |
| <span class="sd"> This CombineFn uses a key or comparison operator to rank the elements.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> compare: (optional) an implementation of "a < b" taking at least two</span> |
| <span class="sd"> arguments (a and b). Additional arguments and side inputs specified</span> |
| <span class="sd"> in the apply call become additional arguments to the comparator.</span> |
| <span class="sd"> key: (optional) a mapping of elements to a comparable key, similar to</span> |
| <span class="sd"> the key argument of Python's sorting methods.</span> |
| <span class="sd"> reverse: (optional) whether to order things smallest to largest, rather</span> |
| <span class="sd"> than largest to smallest</span> |
| <span class="sd"> """</span> |
| |
| <span class="n">_MIN_BUFFER_OVERSIZE</span> <span class="o">=</span> <span class="mi">100</span> |
| <span class="n">_MAX_BUFFER_OVERSIZE</span> <span class="o">=</span> <span class="mi">1000</span> |
| |
| <span class="c1"># TODO(robertwb): Allow taking a key rather than a compare.</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">n</span><span class="p">,</span> <span class="n">compare</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">key</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">reverse</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_n</span> <span class="o">=</span> <span class="n">n</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_buffer_size</span> <span class="o">=</span> <span class="nb">max</span><span class="p">(</span> |
| <span class="nb">min</span><span class="p">(</span><span class="mi">2</span> <span class="o">*</span> <span class="n">n</span><span class="p">,</span> <span class="n">n</span> <span class="o">+</span> <span class="n">TopCombineFn</span><span class="o">.</span><span class="n">_MAX_BUFFER_OVERSIZE</span><span class="p">),</span> |
| <span class="n">n</span> <span class="o">+</span> <span class="n">TopCombineFn</span><span class="o">.</span><span class="n">_MIN_BUFFER_OVERSIZE</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">compare</span> <span class="ow">is</span> <span class="n">operator</span><span class="o">.</span><span class="n">lt</span><span class="p">:</span> |
| <span class="n">compare</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="k">elif</span> <span class="n">compare</span> <span class="ow">is</span> <span class="n">operator</span><span class="o">.</span><span class="n">gt</span><span class="p">:</span> |
| <span class="n">compare</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="n">reverse</span> <span class="o">=</span> <span class="ow">not</span> <span class="n">reverse</span> |
| |
| <span class="k">if</span> <span class="n">compare</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_compare</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="p">(</span><span class="k">lambda</span> <span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">:</span> <span class="ow">not</span> <span class="n">compare</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">))</span> |
| <span class="k">if</span> <span class="n">reverse</span> |
| <span class="k">else</span> <span class="n">compare</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_compare</span> <span class="o">=</span> <span class="n">operator</span><span class="o">.</span><span class="n">gt</span> <span class="k">if</span> <span class="n">reverse</span> <span class="k">else</span> <span class="n">operator</span><span class="o">.</span><span class="n">lt</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_key_fn</span> <span class="o">=</span> <span class="n">key</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_reverse</span> <span class="o">=</span> <span class="n">reverse</span> |
| |
| <span class="k">def</span> <span class="nf">_sort_buffer</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">buffer</span><span class="p">,</span> <span class="n">lt</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">lt</span> <span class="ow">in</span> <span class="p">(</span><span class="n">operator</span><span class="o">.</span><span class="n">gt</span><span class="p">,</span> <span class="n">operator</span><span class="o">.</span><span class="n">lt</span><span class="p">):</span> |
| <span class="n">buffer</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="n">key</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_key_fn</span><span class="p">,</span> <span class="n">reverse</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_reverse</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">_key_fn</span><span class="p">:</span> |
| <span class="n">buffer</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="n">key</span><span class="o">=</span><span class="n">cmp_to_key</span><span class="p">(</span> |
| <span class="p">(</span><span class="k">lambda</span> <span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">:</span> <span class="p">(</span><span class="ow">not</span> <span class="n">lt</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_key_fn</span><span class="p">(</span><span class="n">a</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">_key_fn</span><span class="p">(</span><span class="n">b</span><span class="p">)))</span> |
| <span class="o">-</span> <span class="p">(</span><span class="ow">not</span> <span class="n">lt</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_key_fn</span><span class="p">(</span><span class="n">b</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">_key_fn</span><span class="p">(</span><span class="n">a</span><span class="p">))))))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">buffer</span><span class="o">.</span><span class="n">sort</span><span class="p">(</span><span class="n">key</span><span class="o">=</span><span class="n">cmp_to_key</span><span class="p">(</span><span class="k">lambda</span> <span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">:</span> <span class="p">(</span><span class="ow">not</span> <span class="n">lt</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">))</span> <span class="o">-</span> <span class="p">(</span><span class="ow">not</span> <span class="n">lt</span><span class="p">(</span><span class="n">b</span><span class="p">,</span> <span class="n">a</span><span class="p">))))</span> |
| |
| <span class="k">def</span> <span class="nf">display_data</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">{</span><span class="s1">'n'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_n</span><span class="p">,</span> |
| <span class="s1">'compare'</span><span class="p">:</span> <span class="n">DisplayDataItem</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_compare</span><span class="o">.</span><span class="vm">__name__</span> |
| <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_compare</span><span class="p">,</span> <span class="s1">'__name__'</span><span class="p">)</span> |
| <span class="k">else</span> <span class="bp">self</span><span class="o">.</span><span class="n">_compare</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="o">.</span><span class="n">drop_if_none</span><span class="p">()}</span> |
| |
| <span class="c1"># The accumulator type is a tuple (threshold, buffer), where threshold</span> |
| <span class="c1"># is the smallest element [key] that could possibly be in the top n based</span> |
| <span class="c1"># on the elements observed so far, and buffer is a (periodically sorted)</span> |
| <span class="c1"># list of candidates of bounded size.</span> |
| |
| <span class="k">def</span> <span class="nf">create_accumulator</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">return</span> <span class="kc">None</span><span class="p">,</span> <span class="p">[]</span> |
| |
| <span class="k">def</span> <span class="nf">add_input</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">,</span> <span class="n">element</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">args</span> <span class="ow">or</span> <span class="n">kwargs</span><span class="p">:</span> |
| <span class="n">lt</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_compare</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">lt</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_compare</span> |
| |
| <span class="n">threshold</span><span class="p">,</span> <span class="n">buffer</span> <span class="o">=</span> <span class="n">accumulator</span> |
| <span class="n">element_key</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_key_fn</span><span class="p">(</span><span class="n">element</span><span class="p">)</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_key_fn</span> <span class="k">else</span> <span class="n">element</span> |
| |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">buffer</span><span class="p">)</span> <span class="o"><</span> <span class="bp">self</span><span class="o">.</span><span class="n">_n</span><span class="p">:</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">buffer</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">element_key</span><span class="p">,</span> <span class="p">[</span><span class="n">element</span><span class="p">]</span> |
| <span class="n">buffer</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">element</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">lt</span><span class="p">(</span><span class="n">element_key</span><span class="p">,</span> <span class="n">threshold</span><span class="p">):</span> <span class="c1"># element_key < threshold</span> |
| <span class="k">return</span> <span class="n">element_key</span><span class="p">,</span> <span class="n">buffer</span> |
| <span class="k">return</span> <span class="n">accumulator</span> <span class="c1"># with mutated buffer</span> |
| <span class="k">elif</span> <span class="n">lt</span><span class="p">(</span><span class="n">threshold</span><span class="p">,</span> <span class="n">element_key</span><span class="p">):</span> <span class="c1"># threshold < element_key</span> |
| <span class="n">buffer</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">element</span><span class="p">)</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">buffer</span><span class="p">)</span> <span class="o"><</span> <span class="bp">self</span><span class="o">.</span><span class="n">_buffer_size</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">accumulator</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_sort_buffer</span><span class="p">(</span><span class="n">buffer</span><span class="p">,</span> <span class="n">lt</span><span class="p">)</span> |
| <span class="n">min_element</span> <span class="o">=</span> <span class="n">buffer</span><span class="p">[</span><span class="o">-</span><span class="bp">self</span><span class="o">.</span><span class="n">_n</span><span class="p">]</span> |
| <span class="n">threshold</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_key_fn</span><span class="p">(</span><span class="n">min_element</span><span class="p">)</span> <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_key_fn</span> <span class="k">else</span> <span class="n">min_element</span> |
| <span class="k">return</span> <span class="n">threshold</span><span class="p">,</span> <span class="n">buffer</span><span class="p">[</span><span class="o">-</span><span class="bp">self</span><span class="o">.</span><span class="n">_n</span><span class="p">:]</span> |
| <span class="k">return</span> <span class="n">accumulator</span> |
| |
| <span class="k">def</span> <span class="nf">merge_accumulators</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulators</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="n">accumulators</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">accumulators</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">args</span> <span class="ow">or</span> <span class="n">kwargs</span><span class="p">:</span> |
| <span class="n">add_input</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">accumulator</span><span class="p">,</span> <span class="n">element</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">add_input</span><span class="p">(</span> |
| <span class="n">accumulator</span><span class="p">,</span> <span class="n">element</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">add_input</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">add_input</span> |
| |
| <span class="n">total_accumulator</span> <span class="o">=</span> <span class="kc">None</span> |
| <span class="k">for</span> <span class="n">accumulator</span> <span class="ow">in</span> <span class="n">accumulators</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">total_accumulator</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">total_accumulator</span> <span class="o">=</span> <span class="n">accumulator</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">for</span> <span class="n">element</span> <span class="ow">in</span> <span class="n">accumulator</span><span class="p">[</span><span class="mi">1</span><span class="p">]:</span> |
| <span class="n">total_accumulator</span> <span class="o">=</span> <span class="n">add_input</span><span class="p">(</span><span class="n">total_accumulator</span><span class="p">,</span> <span class="n">element</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">total_accumulator</span> |
| |
| <span class="k">def</span> <span class="nf">extract_output</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">args</span> <span class="ow">or</span> <span class="n">kwargs</span><span class="p">:</span> |
| <span class="n">lt</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_compare</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">b</span><span class="p">,</span> <span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">lt</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_compare</span> |
| |
| <span class="n">_</span><span class="p">,</span> <span class="n">buffer</span> <span class="o">=</span> <span class="n">accumulator</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_sort_buffer</span><span class="p">(</span><span class="n">buffer</span><span class="p">,</span> <span class="n">lt</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">buffer</span><span class="p">[:</span><span class="o">-</span><span class="bp">self</span><span class="o">.</span><span class="n">_n</span><span class="o">-</span><span class="mi">1</span><span class="p">:</span><span class="o">-</span><span class="mi">1</span><span class="p">]</span> <span class="c1"># tail, reversed</span> |
| |
| |
| <span class="k">class</span> <span class="nc">Largest</span><span class="p">(</span><span class="n">TopCombineFn</span><span class="p">):</span> |
| <span class="k">def</span> <span class="nf">default_label</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="s1">'Largest(</span><span class="si">%s</span><span class="s1">)'</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">_n</span> |
| |
| |
| <span class="k">class</span> <span class="nc">Smallest</span><span class="p">(</span><span class="n">TopCombineFn</span><span class="p">):</span> |
| |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">n</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">Smallest</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">n</span><span class="p">,</span> <span class="n">reverse</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">default_label</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="s1">'Smallest(</span><span class="si">%s</span><span class="s1">)'</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">_n</span> |
| |
| |
| <div class="viewcode-block" id="Sample"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.Sample">[docs]</a><span class="k">class</span> <span class="nc">Sample</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""Combiners for sampling n elements without replacement."""</span> |
| <span class="c1"># pylint: disable=no-self-argument</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="nd">@ptransform</span><span class="o">.</span><span class="n">ptransform_fn</span> |
| <span class="k">def</span> <span class="nf">FixedSizeGlobally</span><span class="p">(</span><span class="n">pcoll</span><span class="p">,</span> <span class="n">n</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">core</span><span class="o">.</span><span class="n">CombineGlobally</span><span class="p">(</span><span class="n">SampleCombineFn</span><span class="p">(</span><span class="n">n</span><span class="p">))</span> |
| |
| <span class="nd">@staticmethod</span> |
| <span class="nd">@ptransform</span><span class="o">.</span><span class="n">ptransform_fn</span> |
| <span class="k">def</span> <span class="nf">FixedSizePerKey</span><span class="p">(</span><span class="n">pcoll</span><span class="p">,</span> <span class="n">n</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">core</span><span class="o">.</span><span class="n">CombinePerKey</span><span class="p">(</span><span class="n">SampleCombineFn</span><span class="p">(</span><span class="n">n</span><span class="p">))</span></div> |
| |
| |
| <span class="nd">@with_input_types</span><span class="p">(</span><span class="n">T</span><span class="p">)</span> |
| <span class="nd">@with_output_types</span><span class="p">(</span><span class="n">List</span><span class="p">[</span><span class="n">T</span><span class="p">])</span> |
| <span class="k">class</span> <span class="nc">SampleCombineFn</span><span class="p">(</span><span class="n">core</span><span class="o">.</span><span class="n">CombineFn</span><span class="p">):</span> |
| <span class="sd">"""CombineFn for all Sample transforms."""</span> |
| |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">n</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">SampleCombineFn</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">()</span> |
| <span class="c1"># Most of this combiner's work is done by a TopCombineFn. We could just</span> |
| <span class="c1"># subclass TopCombineFn to make this class, but since sampling is not</span> |
| <span class="c1"># really a kind of Top operation, we use a TopCombineFn instance as a</span> |
| <span class="c1"># helper instead.</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_top_combiner</span> <span class="o">=</span> <span class="n">TopCombineFn</span><span class="p">(</span><span class="n">n</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">create_accumulator</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">_top_combiner</span><span class="o">.</span><span class="n">create_accumulator</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">add_input</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">heap</span><span class="p">,</span> <span class="n">element</span><span class="p">):</span> |
| <span class="c1"># Before passing elements to the Top combiner, we pair them with random</span> |
| <span class="c1"># numbers. The elements with the n largest random number "keys" will be</span> |
| <span class="c1"># selected for the output.</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_top_combiner</span><span class="o">.</span><span class="n">add_input</span><span class="p">(</span><span class="n">heap</span><span class="p">,</span> <span class="p">(</span><span class="n">random</span><span class="o">.</span><span class="n">random</span><span class="p">(),</span> <span class="n">element</span><span class="p">))</span> |
| |
| <span class="k">def</span> <span class="nf">merge_accumulators</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">heaps</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_top_combiner</span><span class="o">.</span><span class="n">merge_accumulators</span><span class="p">(</span><span class="n">heaps</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">extract_output</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">heap</span><span class="p">):</span> |
| <span class="c1"># Here we strip off the random number keys we added in add_input.</span> |
| <span class="k">return</span> <span class="p">[</span><span class="n">e</span> <span class="k">for</span> <span class="n">_</span><span class="p">,</span> <span class="n">e</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_top_combiner</span><span class="o">.</span><span class="n">extract_output</span><span class="p">(</span><span class="n">heap</span><span class="p">)]</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_TupleCombineFnBase</span><span class="p">(</span><span class="n">core</span><span class="o">.</span><span class="n">CombineFn</span><span class="p">):</span> |
| |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">combiners</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_combiners</span> <span class="o">=</span> <span class="p">[</span><span class="n">core</span><span class="o">.</span><span class="n">CombineFn</span><span class="o">.</span><span class="n">maybe_from_callable</span><span class="p">(</span><span class="n">c</span><span class="p">)</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="n">combiners</span><span class="p">]</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_named_combiners</span> <span class="o">=</span> <span class="n">combiners</span> |
| |
| <span class="k">def</span> <span class="nf">display_data</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="n">combiners</span> <span class="o">=</span> <span class="p">[</span><span class="n">c</span><span class="o">.</span><span class="vm">__name__</span> <span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="n">c</span><span class="p">,</span> <span class="s1">'__name__'</span><span class="p">)</span> <span class="k">else</span> <span class="n">c</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span> |
| <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_named_combiners</span><span class="p">]</span> |
| <span class="k">return</span> <span class="p">{</span><span class="s1">'combiners'</span><span class="p">:</span> <span class="nb">str</span><span class="p">(</span><span class="n">combiners</span><span class="p">)}</span> |
| |
| <span class="k">def</span> <span class="nf">create_accumulator</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">[</span><span class="n">c</span><span class="o">.</span><span class="n">create_accumulator</span><span class="p">()</span> <span class="k">for</span> <span class="n">c</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_combiners</span><span class="p">]</span> |
| |
| <span class="k">def</span> <span class="nf">merge_accumulators</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulators</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">[</span><span class="n">c</span><span class="o">.</span><span class="n">merge_accumulators</span><span class="p">(</span><span class="n">a</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">c</span><span class="p">,</span> <span class="n">a</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_combiners</span><span class="p">,</span> <span class="nb">zip</span><span class="p">(</span><span class="o">*</span><span class="n">accumulators</span><span class="p">))]</span> |
| |
| <span class="k">def</span> <span class="nf">extract_output</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">tuple</span><span class="p">([</span><span class="n">c</span><span class="o">.</span><span class="n">extract_output</span><span class="p">(</span><span class="n">a</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">c</span><span class="p">,</span> <span class="n">a</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_combiners</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">)])</span> |
| |
| |
| <span class="k">class</span> <span class="nc">TupleCombineFn</span><span class="p">(</span><span class="n">_TupleCombineFnBase</span><span class="p">):</span> |
| <span class="sd">"""A combiner for combining tuples via a tuple of combiners.</span> |
| |
| <span class="sd"> Takes as input a tuple of N CombineFns and combines N-tuples by</span> |
| <span class="sd"> combining the k-th element of each tuple with the k-th CombineFn,</span> |
| <span class="sd"> outputting a new N-tuple of combined values.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="nf">add_input</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">,</span> <span class="n">element</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">[</span><span class="n">c</span><span class="o">.</span><span class="n">add_input</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">e</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">c</span><span class="p">,</span> <span class="n">a</span><span class="p">,</span> <span class="n">e</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_combiners</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">,</span> <span class="n">element</span><span class="p">)]</span> |
| |
| <span class="k">def</span> <span class="nf">with_common_input</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">SingleInputTupleCombineFn</span><span class="p">(</span><span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">_combiners</span><span class="p">)</span> |
| |
| |
| <span class="k">class</span> <span class="nc">SingleInputTupleCombineFn</span><span class="p">(</span><span class="n">_TupleCombineFnBase</span><span class="p">):</span> |
| <span class="sd">"""A combiner for combining a single value via a tuple of combiners.</span> |
| |
| <span class="sd"> Takes as input a tuple of N CombineFns and combines elements by</span> |
| <span class="sd"> applying each CombineFn to each input, producing an N-tuple of</span> |
| <span class="sd"> the outputs corresponding to each of the N CombineFn's outputs.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="nf">add_input</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">,</span> <span class="n">element</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">[</span><span class="n">c</span><span class="o">.</span><span class="n">add_input</span><span class="p">(</span><span class="n">a</span><span class="p">,</span> <span class="n">element</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">c</span><span class="p">,</span> <span class="n">a</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_combiners</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">)]</span> |
| |
| |
| <div class="viewcode-block" id="ToList"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.ToList">[docs]</a><span class="k">class</span> <span class="nc">ToList</span><span class="p">(</span><span class="n">ptransform</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="sd">"""A global CombineFn that condenses a PCollection into a single list."""</span> |
| |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s1">'ToList'</span><span class="p">):</span> <span class="c1"># pylint: disable=useless-super-delegation</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">ToList</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">label</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="ToList.expand"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.ToList.expand">[docs]</a> <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">label</span> <span class="o">>></span> <span class="n">core</span><span class="o">.</span><span class="n">CombineGlobally</span><span class="p">(</span><span class="n">ToListCombineFn</span><span class="p">())</span></div></div> |
| |
| |
| <span class="nd">@with_input_types</span><span class="p">(</span><span class="n">T</span><span class="p">)</span> |
| <span class="nd">@with_output_types</span><span class="p">(</span><span class="n">List</span><span class="p">[</span><span class="n">T</span><span class="p">])</span> |
| <span class="k">class</span> <span class="nc">ToListCombineFn</span><span class="p">(</span><span class="n">core</span><span class="o">.</span><span class="n">CombineFn</span><span class="p">):</span> |
| <span class="sd">"""CombineFn for to_list."""</span> |
| |
| <span class="k">def</span> <span class="nf">create_accumulator</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="p">[]</span> |
| |
| <span class="k">def</span> <span class="nf">add_input</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">,</span> <span class="n">element</span><span class="p">):</span> |
| <span class="n">accumulator</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">element</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">accumulator</span> |
| |
| <span class="k">def</span> <span class="nf">merge_accumulators</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulators</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">sum</span><span class="p">(</span><span class="n">accumulators</span><span class="p">,</span> <span class="p">[])</span> |
| |
| <span class="k">def</span> <span class="nf">extract_output</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">accumulator</span> |
| |
| |
| <div class="viewcode-block" id="ToDict"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.ToDict">[docs]</a><span class="k">class</span> <span class="nc">ToDict</span><span class="p">(</span><span class="n">ptransform</span><span class="o">.</span><span class="n">PTransform</span><span class="p">):</span> |
| <span class="sd">"""A global CombineFn that condenses a PCollection into a single dict.</span> |
| |
| <span class="sd"> PCollections should consist of 2-tuples, notionally (key, value) pairs.</span> |
| <span class="sd"> If multiple values are associated with the same key, only one of the values</span> |
| <span class="sd"> will be present in the resulting dict.</span> |
| <span class="sd"> """</span> |
| |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">label</span><span class="o">=</span><span class="s1">'ToDict'</span><span class="p">):</span> <span class="c1"># pylint: disable=useless-super-delegation</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">ToDict</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">label</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="ToDict.expand"><a class="viewcode-back" href="../../../apache_beam.transforms.combiners.html#apache_beam.transforms.combiners.ToDict.expand">[docs]</a> <span class="k">def</span> <span class="nf">expand</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="bp">self</span><span class="o">.</span><span class="n">label</span> <span class="o">>></span> <span class="n">core</span><span class="o">.</span><span class="n">CombineGlobally</span><span class="p">(</span><span class="n">ToDictCombineFn</span><span class="p">())</span></div></div> |
| |
| |
| <span class="nd">@with_input_types</span><span class="p">(</span><span class="n">Tuple</span><span class="p">[</span><span class="n">K</span><span class="p">,</span> <span class="n">V</span><span class="p">])</span> |
| <span class="nd">@with_output_types</span><span class="p">(</span><span class="n">Dict</span><span class="p">[</span><span class="n">K</span><span class="p">,</span> <span class="n">V</span><span class="p">])</span> |
| <span class="k">class</span> <span class="nc">ToDictCombineFn</span><span class="p">(</span><span class="n">core</span><span class="o">.</span><span class="n">CombineFn</span><span class="p">):</span> |
| <span class="sd">"""CombineFn for to_dict."""</span> |
| |
| <span class="k">def</span> <span class="nf">create_accumulator</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">dict</span><span class="p">()</span> |
| |
| <span class="k">def</span> <span class="nf">add_input</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">,</span> <span class="n">element</span><span class="p">):</span> |
| <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="o">=</span> <span class="n">element</span> |
| <span class="n">accumulator</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span> |
| <span class="k">return</span> <span class="n">accumulator</span> |
| |
| <span class="k">def</span> <span class="nf">merge_accumulators</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulators</span><span class="p">):</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">()</span> |
| <span class="k">for</span> <span class="n">a</span> <span class="ow">in</span> <span class="n">accumulators</span><span class="p">:</span> |
| <span class="n">result</span><span class="o">.</span><span class="n">update</span><span class="p">(</span><span class="n">a</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">result</span> |
| |
| <span class="k">def</span> <span class="nf">extract_output</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">accumulator</span> |
| |
| |
| <span class="k">class</span> <span class="nc">_CurriedFn</span><span class="p">(</span><span class="n">core</span><span class="o">.</span><span class="n">CombineFn</span><span class="p">):</span> |
| <span class="sd">"""Wrapped CombineFn with extra arguments."""</span> |
| |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">fn</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">fn</span> <span class="o">=</span> <span class="n">fn</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">kwargs</span> <span class="o">=</span> <span class="n">kwargs</span> |
| |
| <span class="k">def</span> <span class="nf">create_accumulator</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">fn</span><span class="o">.</span><span class="n">create_accumulator</span><span class="p">(</span><span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">add_input</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">,</span> <span class="n">element</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">fn</span><span class="o">.</span><span class="n">add_input</span><span class="p">(</span><span class="n">accumulator</span><span class="p">,</span> <span class="n">element</span><span class="p">,</span> <span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">merge_accumulators</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulators</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">fn</span><span class="o">.</span><span class="n">merge_accumulators</span><span class="p">(</span><span class="n">accumulators</span><span class="p">,</span> <span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">extract_output</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">fn</span><span class="o">.</span><span class="n">extract_output</span><span class="p">(</span><span class="n">accumulator</span><span class="p">,</span> <span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">apply</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">elements</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">fn</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">elements</span><span class="p">,</span> <span class="o">*</span><span class="bp">self</span><span class="o">.</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="bp">self</span><span class="o">.</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| |
| <span class="k">def</span> <span class="nf">curry_combine_fn</span><span class="p">(</span><span class="n">fn</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">args</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">kwargs</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">fn</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">_CurriedFn</span><span class="p">(</span><span class="n">fn</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> |
| |
| |
| <span class="k">class</span> <span class="nc">PhasedCombineFnExecutor</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""Executor for phases of combine operations."""</span> |
| |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">phase</span><span class="p">,</span> <span class="n">fn</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">):</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">combine_fn</span> <span class="o">=</span> <span class="n">curry_combine_fn</span><span class="p">(</span><span class="n">fn</span><span class="p">,</span> <span class="n">args</span><span class="p">,</span> <span class="n">kwargs</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">phase</span> <span class="o">==</span> <span class="s1">'all'</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">apply</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">full_combine</span> |
| <span class="k">elif</span> <span class="n">phase</span> <span class="o">==</span> <span class="s1">'add'</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">apply</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">add_only</span> |
| <span class="k">elif</span> <span class="n">phase</span> <span class="o">==</span> <span class="s1">'merge'</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">apply</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">merge_only</span> |
| <span class="k">elif</span> <span class="n">phase</span> <span class="o">==</span> <span class="s1">'extract'</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">apply</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">extract_only</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Unexpected phase: </span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="n">phase</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">full_combine</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">elements</span><span class="p">):</span> <span class="c1"># pylint: disable=invalid-name</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">combine_fn</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">elements</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">add_only</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">elements</span><span class="p">):</span> <span class="c1"># pylint: disable=invalid-name</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">combine_fn</span><span class="o">.</span><span class="n">add_inputs</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">combine_fn</span><span class="o">.</span><span class="n">create_accumulator</span><span class="p">(),</span> <span class="n">elements</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">merge_only</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulators</span><span class="p">):</span> <span class="c1"># pylint: disable=invalid-name</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">combine_fn</span><span class="o">.</span><span class="n">merge_accumulators</span><span class="p">(</span><span class="n">accumulators</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">extract_only</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">accumulator</span><span class="p">):</span> <span class="c1"># pylint: disable=invalid-name</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">combine_fn</span><span class="o">.</span><span class="n">extract_output</span><span class="p">(</span><span class="n">accumulator</span><span class="p">)</span> |
| </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> |