| |
| |
| <!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.partitionings — Apache Beam 2.38.0 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"> |
| 2.38.0 |
| </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.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> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="../../../index.html">Apache Beam</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="../../../index.html">Docs</a> »</li> |
| |
| <li><a href="../../index.html">Module code</a> »</li> |
| |
| <li>apache_beam.dataframe.partitionings</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.partitionings</h1><div class="highlight"><pre> |
| <span></span><span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span> |
| <span class="c1"># contributor license agreements. See the NOTICE file distributed with</span> |
| <span class="c1"># this work for additional information regarding copyright ownership.</span> |
| <span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span> |
| <span class="c1"># (the "License"); you may not use this file except in compliance with</span> |
| <span class="c1"># the License. You may obtain a copy of the License at</span> |
| <span class="c1">#</span> |
| <span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span> |
| <span class="c1">#</span> |
| <span class="c1"># Unless required by applicable law or agreed to in writing, software</span> |
| <span class="c1"># distributed under the License is distributed on an "AS IS" BASIS,</span> |
| <span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span> |
| <span class="c1"># See the License for the specific language governing permissions and</span> |
| <span class="c1"># limitations under the License.</span> |
| |
| <span class="kn">import</span> <span class="nn">random</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">Iterable</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Tuple</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">TypeVar</span> |
| |
| <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</span> |
| <span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span> |
| |
| <span class="n">Frame</span> <span class="o">=</span> <span class="n">TypeVar</span><span class="p">(</span><span class="s1">'Frame'</span><span class="p">,</span> <span class="n">bound</span><span class="o">=</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> |
| |
| |
| <div class="viewcode-block" id="Partitioning"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.Partitioning">[docs]</a><span class="k">class</span> <span class="nc">Partitioning</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="sd">"""A class representing a (consistent) partitioning of dataframe objects.</span> |
| <span class="sd"> """</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="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span> |
| |
| <div class="viewcode-block" id="Partitioning.is_subpartitioning_of"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.Partitioning.is_subpartitioning_of">[docs]</a> <span class="k">def</span> <span class="nf">is_subpartitioning_of</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="c1"># type: (Partitioning) -> bool</span> |
| |
| <span class="sd">"""Returns whether self is a sub-partition of other.</span> |
| |
| <span class="sd"> Specifically, returns whether something partitioned by self is necissarily</span> |
| <span class="sd"> also partitioned by other.</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span></div> |
| |
| <span class="k">def</span> <span class="fm">__lt__</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">other</span> <span class="ow">and</span> <span class="bp">self</span> <span class="o"><=</span> <span class="n">other</span> |
| |
| <span class="k">def</span> <span class="fm">__le__</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="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">is_subpartitioning_of</span><span class="p">(</span><span class="n">other</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="Partitioning.partition_fn"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.Partitioning.partition_fn">[docs]</a> <span class="k">def</span> <span class="nf">partition_fn</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">df</span><span class="p">,</span> <span class="n">num_partitions</span><span class="p">):</span> |
| <span class="c1"># type: (Frame, int) -> Iterable[Tuple[Any, Frame]]</span> |
| |
| <span class="sd">"""A callable that actually performs the partitioning of a Frame df.</span> |
| |
| <span class="sd"> This will be invoked via a FlatMap in conjunction with a GroupKey to</span> |
| <span class="sd"> achieve the desired partitioning.</span> |
| <span class="sd"> """</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span></div> |
| |
| <div class="viewcode-block" id="Partitioning.test_partition_fn"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.Partitioning.test_partition_fn">[docs]</a> <span class="k">def</span> <span class="nf">test_partition_fn</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">df</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">partition_fn</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="mi">5</span><span class="p">)</span></div></div> |
| |
| |
| <div class="viewcode-block" id="Index"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.Index">[docs]</a><span class="k">class</span> <span class="nc">Index</span><span class="p">(</span><span class="n">Partitioning</span><span class="p">):</span> |
| <span class="sd">"""A partitioning by index (either fully or partially).</span> |
| |
| <span class="sd"> If the set of "levels" of the index to consider is not specified, the entire</span> |
| <span class="sd"> index is used.</span> |
| |
| <span class="sd"> These form a partial order, given by</span> |
| |
| <span class="sd"> Singleton() < Index([i]) < Index([i, j]) < ... < Index() < Arbitrary()</span> |
| |
| <span class="sd"> The ordering is implemented via the is_subpartitioning_of method, where the</span> |
| <span class="sd"> examples on the right are subpartitionings of the examples on the left above.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">levels</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">_levels</span> <span class="o">=</span> <span class="n">levels</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">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_levels</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s1">'Index</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">_levels</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s1">'Index'</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="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">==</span> <span class="nb">type</span><span class="p">(</span><span class="n">other</span><span class="p">)</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_levels</span> <span class="o">==</span> <span class="n">other</span><span class="o">.</span><span class="n">_levels</span> |
| |
| <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">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_levels</span><span class="p">:</span> |
| <span class="k">return</span> <span class="nb">hash</span><span class="p">(</span><span class="nb">tuple</span><span class="p">(</span><span class="nb">sorted</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_levels</span><span class="p">)))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="nb">hash</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">))</span> |
| |
| <div class="viewcode-block" id="Index.is_subpartitioning_of"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.Index.is_subpartitioning_of">[docs]</a> <span class="k">def</span> <span class="nf">is_subpartitioning_of</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">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">Singleton</span><span class="p">):</span> |
| <span class="k">return</span> <span class="kc">True</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">Index</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_levels</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="kc">True</span> |
| <span class="k">elif</span> <span class="n">other</span><span class="o">.</span><span class="n">_levels</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="kc">False</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="nb">all</span><span class="p">(</span><span class="n">level</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_levels</span> <span class="k">for</span> <span class="n">level</span> <span class="ow">in</span> <span class="n">other</span><span class="o">.</span><span class="n">_levels</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="p">(</span><span class="n">Arbitrary</span><span class="p">,</span> <span class="n">JoinIndex</span><span class="p">)):</span> |
| <span class="k">return</span> <span class="kc">False</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="sa">f</span><span class="s2">"Encountered unknown type </span><span class="si">{</span><span class="n">other</span><span class="si">!r}</span><span class="s2">"</span><span class="p">)</span></div> |
| |
| <span class="k">def</span> <span class="nf">_hash_index</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">df</span><span class="p">):</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_levels</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">levels</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">index</span><span class="o">.</span><span class="n">nlevels</span><span class="p">))</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">levels</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_levels</span> |
| <span class="k">return</span> <span class="nb">sum</span><span class="p">(</span> |
| <span class="n">pd</span><span class="o">.</span><span class="n">util</span><span class="o">.</span><span class="n">hash_array</span><span class="p">(</span><span class="n">np</span><span class="o">.</span><span class="n">asarray</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">index</span><span class="o">.</span><span class="n">get_level_values</span><span class="p">(</span><span class="n">level</span><span class="p">)))</span> |
| <span class="k">for</span> <span class="n">level</span> <span class="ow">in</span> <span class="n">levels</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="Index.partition_fn"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.Index.partition_fn">[docs]</a> <span class="k">def</span> <span class="nf">partition_fn</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">df</span><span class="p">,</span> <span class="n">num_partitions</span><span class="p">):</span> |
| <span class="n">hashes</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_hash_index</span><span class="p">(</span><span class="n">df</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">num_partitions</span><span class="p">):</span> |
| <span class="k">yield</span> <span class="n">key</span><span class="p">,</span> <span class="n">df</span><span class="p">[</span><span class="n">hashes</span> <span class="o">%</span> <span class="n">num_partitions</span> <span class="o">==</span> <span class="n">key</span><span class="p">]</span></div> |
| |
| <div class="viewcode-block" id="Index.check"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.Index.check">[docs]</a> <span class="k">def</span> <span class="nf">check</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dfs</span><span class="p">):</span> |
| <span class="c1"># Drop empty DataFrames</span> |
| <span class="n">dfs</span> <span class="o">=</span> <span class="p">[</span><span class="n">df</span> <span class="k">for</span> <span class="n">df</span> <span class="ow">in</span> <span class="n">dfs</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">df</span><span class="p">)]</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="nb">len</span><span class="p">(</span><span class="n">dfs</span><span class="p">):</span> |
| <span class="k">return</span> <span class="kc">True</span> |
| |
| <span class="k">def</span> <span class="nf">apply_consistent_order</span><span class="p">(</span><span class="n">dfs</span><span class="p">):</span> |
| <span class="c1"># Apply consistent order between dataframes by using sum of the index's</span> |
| <span class="c1"># hash.</span> |
| <span class="c1"># Apply consistent order within dataframe with sort_index()</span> |
| <span class="c1"># Also drops any empty dataframes.</span> |
| <span class="k">return</span> <span class="nb">sorted</span><span class="p">((</span><span class="n">df</span><span class="o">.</span><span class="n">sort_index</span><span class="p">()</span> <span class="k">for</span> <span class="n">df</span> <span class="ow">in</span> <span class="n">dfs</span> <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">df</span><span class="p">)),</span> |
| <span class="n">key</span><span class="o">=</span><span class="k">lambda</span> <span class="n">df</span><span class="p">:</span> <span class="nb">sum</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_hash_index</span><span class="p">(</span><span class="n">df</span><span class="p">)))</span> |
| |
| <span class="n">dfs</span> <span class="o">=</span> <span class="n">apply_consistent_order</span><span class="p">(</span><span class="n">dfs</span><span class="p">)</span> |
| <span class="n">repartitioned_dfs</span> <span class="o">=</span> <span class="n">apply_consistent_order</span><span class="p">(</span> |
| <span class="n">df</span> <span class="k">for</span> <span class="n">_</span><span class="p">,</span> <span class="n">df</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">test_partition_fn</span><span class="p">(</span><span class="n">pd</span><span class="o">.</span><span class="n">concat</span><span class="p">(</span><span class="n">dfs</span><span class="p">)))</span> |
| |
| <span class="c1"># Assert that each index is identical</span> |
| <span class="k">for</span> <span class="n">df</span><span class="p">,</span> <span class="n">repartitioned_df</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">dfs</span><span class="p">,</span> <span class="n">repartitioned_dfs</span><span class="p">):</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">df</span><span class="o">.</span><span class="n">index</span><span class="o">.</span><span class="n">equals</span><span class="p">(</span><span class="n">repartitioned_df</span><span class="o">.</span><span class="n">index</span><span class="p">):</span> |
| <span class="k">return</span> <span class="kc">False</span> |
| |
| <span class="k">return</span> <span class="kc">True</span></div></div> |
| |
| |
| <div class="viewcode-block" id="Singleton"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.Singleton">[docs]</a><span class="k">class</span> <span class="nc">Singleton</span><span class="p">(</span><span class="n">Partitioning</span><span class="p">):</span> |
| <span class="sd">"""A partitioning of all the data into a single partition.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">reason</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">_reason</span> <span class="o">=</span> <span class="n">reason</span> |
| |
| <span class="nd">@property</span> |
| <span class="k">def</span> <span class="nf">reason</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">_reason</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="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">==</span> <span class="nb">type</span><span class="p">(</span><span class="n">other</span><span class="p">)</span> |
| |
| <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="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">))</span> |
| |
| <div class="viewcode-block" id="Singleton.is_subpartitioning_of"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.Singleton.is_subpartitioning_of">[docs]</a> <span class="k">def</span> <span class="nf">is_subpartitioning_of</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="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">Singleton</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="Singleton.partition_fn"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.Singleton.partition_fn">[docs]</a> <span class="k">def</span> <span class="nf">partition_fn</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">df</span><span class="p">,</span> <span class="n">num_partitions</span><span class="p">):</span> |
| <span class="k">yield</span> <span class="kc">None</span><span class="p">,</span> <span class="n">df</span></div> |
| |
| <div class="viewcode-block" id="Singleton.check"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.Singleton.check">[docs]</a> <span class="k">def</span> <span class="nf">check</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dfs</span><span class="p">):</span> |
| <span class="k">return</span> <span class="nb">len</span><span class="p">(</span><span class="n">dfs</span><span class="p">)</span> <span class="o"><=</span> <span class="mi">1</span></div></div> |
| |
| |
| <div class="viewcode-block" id="JoinIndex"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.JoinIndex">[docs]</a><span class="k">class</span> <span class="nc">JoinIndex</span><span class="p">(</span><span class="n">Partitioning</span><span class="p">):</span> |
| <span class="sd">"""A partitioning that lets two frames be joined.</span> |
| <span class="sd"> This can either be a hash partitioning on the full index, or a common</span> |
| <span class="sd"> ancestor with no intervening re-indexing/re-partitioning.</span> |
| |
| <span class="sd"> It fits into the partial ordering as</span> |
| |
| <span class="sd"> Index() < JoinIndex(x) < JoinIndex() < Arbitrary()</span> |
| |
| <span class="sd"> with</span> |
| |
| <span class="sd"> JoinIndex(x) and JoinIndex(y)</span> |
| |
| <span class="sd"> being incomparable for nontrivial x != y.</span> |
| |
| <span class="sd"> Expressions desiring to make use of this index should simply declare a</span> |
| <span class="sd"> requirement of JoinIndex().</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">ancestor</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">_ancestor</span> <span class="o">=</span> <span class="n">ancestor</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">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ancestor</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s1">'JoinIndex[</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">_ancestor</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s1">'JoinIndex'</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">if</span> <span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">!=</span> <span class="nb">type</span><span class="p">(</span><span class="n">other</span><span class="p">):</span> |
| <span class="k">return</span> <span class="kc">False</span> |
| <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ancestor</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">other</span><span class="o">.</span><span class="n">_ancestor</span> <span class="ow">is</span> <span class="kc">None</span> |
| <span class="k">elif</span> <span class="n">other</span><span class="o">.</span><span class="n">_ancestor</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="kc">False</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ancestor</span> <span class="o">==</span> <span class="n">other</span><span class="o">.</span><span class="n">_ancestor</span> |
| |
| <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="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ancestor</span><span class="p">))</span> |
| |
| <div class="viewcode-block" id="JoinIndex.is_subpartitioning_of"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.JoinIndex.is_subpartitioning_of">[docs]</a> <span class="k">def</span> <span class="nf">is_subpartitioning_of</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">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">Arbitrary</span><span class="p">):</span> |
| <span class="k">return</span> <span class="kc">False</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">JoinIndex</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_ancestor</span> <span class="ow">is</span> <span class="kc">None</span> <span class="ow">or</span> <span class="bp">self</span> <span class="o">==</span> <span class="n">other</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="kc">True</span></div> |
| |
| <div class="viewcode-block" id="JoinIndex.test_partition_fn"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.JoinIndex.test_partition_fn">[docs]</a> <span class="k">def</span> <span class="nf">test_partition_fn</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">df</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">Index</span><span class="p">()</span><span class="o">.</span><span class="n">test_partition_fn</span><span class="p">(</span><span class="n">df</span><span class="p">)</span></div> |
| |
| <div class="viewcode-block" id="JoinIndex.check"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.JoinIndex.check">[docs]</a> <span class="k">def</span> <span class="nf">check</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dfs</span><span class="p">):</span> |
| <span class="k">return</span> <span class="kc">True</span></div></div> |
| |
| |
| <div class="viewcode-block" id="Arbitrary"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.Arbitrary">[docs]</a><span class="k">class</span> <span class="nc">Arbitrary</span><span class="p">(</span><span class="n">Partitioning</span><span class="p">):</span> |
| <span class="sd">"""A partitioning imposing no constraints on the actual partitioning.</span> |
| <span class="sd"> """</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="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">==</span> <span class="nb">type</span><span class="p">(</span><span class="n">other</span><span class="p">)</span> |
| |
| <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="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="p">))</span> |
| |
| <div class="viewcode-block" id="Arbitrary.is_subpartitioning_of"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.Arbitrary.is_subpartitioning_of">[docs]</a> <span class="k">def</span> <span class="nf">is_subpartitioning_of</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="kc">True</span></div> |
| |
| <div class="viewcode-block" id="Arbitrary.test_partition_fn"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.Arbitrary.test_partition_fn">[docs]</a> <span class="k">def</span> <span class="nf">test_partition_fn</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">df</span><span class="p">):</span> |
| <span class="n">num_partitions</span> <span class="o">=</span> <span class="mi">10</span> |
| |
| <span class="k">def</span> <span class="nf">shuffled</span><span class="p">(</span><span class="n">seq</span><span class="p">):</span> |
| <span class="n">seq</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">seq</span><span class="p">)</span> |
| <span class="n">random</span><span class="o">.</span><span class="n">shuffle</span><span class="p">(</span><span class="n">seq</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">seq</span> |
| |
| <span class="n">part</span> <span class="o">=</span> <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">(</span><span class="n">shuffled</span><span class="p">(</span><span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">df</span><span class="p">))),</span> <span class="n">index</span><span class="o">=</span><span class="n">df</span><span class="o">.</span><span class="n">index</span><span class="p">)</span> <span class="o">%</span> <span class="n">num_partitions</span> |
| <span class="k">for</span> <span class="n">k</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">num_partitions</span><span class="p">):</span> |
| <span class="k">yield</span> <span class="n">k</span><span class="p">,</span> <span class="n">df</span><span class="p">[</span><span class="n">part</span> <span class="o">==</span> <span class="n">k</span><span class="p">]</span></div> |
| |
| <div class="viewcode-block" id="Arbitrary.check"><a class="viewcode-back" href="../../../apache_beam.dataframe.partitionings.html#apache_beam.dataframe.partitionings.Arbitrary.check">[docs]</a> <span class="k">def</span> <span class="nf">check</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">dfs</span><span class="p">):</span> |
| <span class="k">return</span> <span class="kc">True</span></div></div> |
| </pre></div> |
| |
| </div> |
| |
| </div> |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| © Copyright |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| </body> |
| </html> |