| |
| |
| <!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.frame_base — Apache Beam 2.47.0 documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="../../../_static/js/modernizr.min.js"></script> |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script> |
| <script type="text/javascript" src="../../../_static/jquery.js"></script> |
| <script type="text/javascript" src="../../../_static/underscore.js"></script> |
| <script type="text/javascript" src="../../../_static/doctools.js"></script> |
| <script type="text/javascript" src="../../../_static/language_data.js"></script> |
| <script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| |
| <script type="text/javascript" src="../../../_static/js/theme.js"></script> |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="index" title="Index" href="../../../genindex.html" /> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| </head> |
| |
| <body class="wy-body-for-nav"> |
| |
| |
| <div class="wy-grid-for-nav"> |
| |
| <nav data-toggle="wy-nav-shift" class="wy-nav-side"> |
| <div class="wy-side-scroll"> |
| <div class="wy-side-nav-search" > |
| |
| |
| |
| <a href="../../../index.html" class="icon icon-home"> Apache Beam |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| <div class="version"> |
| 2.47.0 |
| </div> |
| |
| |
| |
| |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="../../../search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| |
| |
| </div> |
| |
| <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
| |
| |
| |
| |
| |
| |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.coders.html">apache_beam.coders package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.dataframe.html">apache_beam.dataframe package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.io.html">apache_beam.io package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.metrics.html">apache_beam.metrics package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.ml.html">apache_beam.ml package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.options.html">apache_beam.options package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.portability.html">apache_beam.portability package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.runners.html">apache_beam.runners package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.testing.html">apache_beam.testing package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.transforms.html">apache_beam.transforms package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.typehints.html">apache_beam.typehints package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.utils.html">apache_beam.utils package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.yaml.html">apache_beam.yaml package</a></li> |
| </ul> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.error.html">apache_beam.error module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../apache_beam.pvalue.html">apache_beam.pvalue module</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="../../../index.html">Apache Beam</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="../../../index.html">Docs</a> »</li> |
| |
| <li><a href="../../index.html">Module code</a> »</li> |
| |
| <li>apache_beam.dataframe.frame_base</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.frame_base</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">functools</span> |
| <span class="kn">import</span> <span class="nn">operator</span> |
| <span class="kn">import</span> <span class="nn">re</span> |
| <span class="kn">from</span> <span class="nn">inspect</span> <span class="kn">import</span> <span class="n">cleandoc</span> |
| <span class="kn">from</span> <span class="nn">inspect</span> <span class="kn">import</span> <span class="n">getfullargspec</span> |
| <span class="kn">from</span> <span class="nn">inspect</span> <span class="kn">import</span> <span class="n">isclass</span> |
| <span class="kn">from</span> <span class="nn">inspect</span> <span class="kn">import</span> <span class="n">ismodule</span> |
| <span class="kn">from</span> <span class="nn">inspect</span> <span class="kn">import</span> <span class="n">unwrap</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Callable</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Dict</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">List</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Optional</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Tuple</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Union</span> |
| |
| <span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span> |
| |
| <span class="kn">from</span> <span class="nn">apache_beam.dataframe</span> <span class="kn">import</span> <span class="n">expressions</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.dataframe</span> <span class="kn">import</span> <span class="n">partitionings</span> |
| |
| |
| <div class="viewcode-block" id="DeferredBase"><a class="viewcode-back" href="../../../apache_beam.dataframe.frame_base.html#apache_beam.dataframe.frame_base.DeferredBase">[docs]</a><span class="k">class</span> <span class="nc">DeferredBase</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| |
| <span class="n">_pandas_type_map</span> <span class="o">=</span> <span class="p">{}</span> <span class="c1"># type: Dict[Union[type, None], type]</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">expr</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_expr</span> <span class="o">=</span> <span class="n">expr</span> |
| |
| <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">_register_for</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">pandas_type</span><span class="p">):</span> |
| <span class="k">def</span> <span class="nf">wrapper</span><span class="p">(</span><span class="n">deferred_type</span><span class="p">):</span> |
| <span class="bp">cls</span><span class="o">.</span><span class="n">_pandas_type_map</span><span class="p">[</span><span class="n">pandas_type</span><span class="p">]</span> <span class="o">=</span> <span class="n">deferred_type</span> |
| <span class="k">return</span> <span class="n">deferred_type</span> |
| |
| <span class="k">return</span> <span class="n">wrapper</span> |
| |
| <div class="viewcode-block" id="DeferredBase.wrap"><a class="viewcode-back" href="../../../apache_beam.dataframe.frame_base.html#apache_beam.dataframe.frame_base.DeferredBase.wrap">[docs]</a> <span class="nd">@classmethod</span> |
| <span class="k">def</span> <span class="nf">wrap</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">expr</span><span class="p">,</span> <span class="n">split_tuples</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span> |
| <span class="n">proxy_type</span> <span class="o">=</span> <span class="nb">type</span><span class="p">(</span><span class="n">expr</span><span class="o">.</span><span class="n">proxy</span><span class="p">())</span> |
| <span class="k">if</span> <span class="n">proxy_type</span> <span class="ow">is</span> <span class="nb">tuple</span> <span class="ow">and</span> <span class="n">split_tuples</span><span class="p">:</span> |
| |
| <span class="k">def</span> <span class="nf">get</span><span class="p">(</span><span class="n">ix</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">expressions</span><span class="o">.</span><span class="n">ComputedExpression</span><span class="p">(</span> |
| <span class="c1"># yapf: disable</span> |
| <span class="s1">'get_</span><span class="si">%d</span><span class="s1">'</span> <span class="o">%</span> <span class="n">ix</span><span class="p">,</span> |
| <span class="k">lambda</span> <span class="n">t</span><span class="p">:</span> <span class="n">t</span><span class="p">[</span><span class="n">ix</span><span class="p">],</span> |
| <span class="p">[</span><span class="n">expr</span><span class="p">],</span> |
| <span class="n">requires_partition_by</span><span class="o">=</span><span class="n">partitionings</span><span class="o">.</span><span class="n">Arbitrary</span><span class="p">(),</span> |
| <span class="n">preserves_partition_by</span><span class="o">=</span><span class="n">partitionings</span><span class="o">.</span><span class="n">Singleton</span><span class="p">())</span> |
| |
| <span class="k">return</span> <span class="nb">tuple</span><span class="p">(</span><span class="bp">cls</span><span class="o">.</span><span class="n">wrap</span><span class="p">(</span><span class="n">get</span><span class="p">(</span><span class="n">ix</span><span class="p">))</span> <span class="k">for</span> <span class="n">ix</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">expr</span><span class="o">.</span><span class="n">proxy</span><span class="p">())))</span> |
| <span class="k">elif</span> <span class="n">proxy_type</span> <span class="ow">in</span> <span class="bp">cls</span><span class="o">.</span><span class="n">_pandas_type_map</span><span class="p">:</span> |
| <span class="n">wrapper_type</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="n">_pandas_type_map</span><span class="p">[</span><span class="n">proxy_type</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">expr</span><span class="o">.</span><span class="n">requires_partition_by</span><span class="p">()</span> <span class="o">!=</span> <span class="n">partitionings</span><span class="o">.</span><span class="n">Singleton</span><span class="p">():</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span> |
| <span class="s1">'Scalar expression </span><span class="si">%s</span><span class="s1"> of type </span><span class="si">%s</span><span class="s1"> partitoned by non-singleton </span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> |
| <span class="p">(</span><span class="n">expr</span><span class="p">,</span> <span class="n">proxy_type</span><span class="p">,</span> <span class="n">expr</span><span class="o">.</span><span class="n">requires_partition_by</span><span class="p">()))</span> |
| <span class="n">wrapper_type</span> <span class="o">=</span> <span class="n">_DeferredScalar</span> |
| <span class="k">return</span> <span class="n">wrapper_type</span><span class="p">(</span><span class="n">expr</span><span class="p">)</span></div> |
| |
| <span class="k">def</span> <span class="nf">_elementwise</span><span class="p">(</span> |
| <span class="bp">self</span><span class="p">,</span> <span class="n">func</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">other_args</span><span class="o">=</span><span class="p">(),</span> <span class="n">other_kwargs</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">False</span><span class="p">):</span> |
| <span class="n">other_kwargs</span> <span class="o">=</span> <span class="n">other_kwargs</span> <span class="ow">or</span> <span class="p">{}</span> |
| <span class="k">return</span> <span class="n">_elementwise_function</span><span class="p">(</span> |
| <span class="n">func</span><span class="p">,</span> <span class="n">name</span><span class="p">,</span> <span class="n">inplace</span><span class="o">=</span><span class="n">inplace</span><span class="p">)(</span><span class="bp">self</span><span class="p">,</span> <span class="o">*</span><span class="n">other_args</span><span class="p">,</span> <span class="o">**</span><span class="n">other_kwargs</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">__reduce__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">UnusableUnpickledDeferredBase</span><span class="p">,</span> <span class="p">(</span><span class="nb">str</span><span class="p">(</span><span class="bp">self</span><span class="p">),</span> <span class="p">)</span></div> |
| |
| |
| <div class="viewcode-block" id="UnusableUnpickledDeferredBase"><a class="viewcode-back" href="../../../apache_beam.dataframe.frame_base.html#apache_beam.dataframe.frame_base.UnusableUnpickledDeferredBase">[docs]</a><span class="k">class</span> <span class="nc">UnusableUnpickledDeferredBase</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Placeholder object used to break the transitive pickling chain in case a</span> |
| <span class="sd"> DeferredBase accidentially gets pickled (e.g. as part of globals).</span> |
| |
| <span class="sd"> Trying to use this object after unpickling is a bug and will result in an</span> |
| <span class="sd"> error.</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">name</span><span class="p">):</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_name</span> <span class="o">=</span> <span class="n">name</span> |
| |
| <span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="k">return</span> <span class="s1">'UnusablePickledDeferredBase(</span><span class="si">%r</span><span class="s1">)'</span> <span class="o">%</span> <span class="bp">self</span><span class="o">.</span><span class="n">name</span></div> |
| |
| |
| <div class="viewcode-block" id="DeferredFrame"><a class="viewcode-back" href="../../../apache_beam.dataframe.frame_base.html#apache_beam.dataframe.frame_base.DeferredFrame">[docs]</a><span class="k">class</span> <span class="nc">DeferredFrame</span><span class="p">(</span><span class="n">DeferredBase</span><span class="p">):</span> |
| <span class="k">pass</span></div> |
| |
| |
| <span class="k">class</span> <span class="nc">_DeferredScalar</span><span class="p">(</span><span class="n">DeferredBase</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">func</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">args</span><span class="o">=</span><span class="p">()):</span> |
| <span class="k">if</span> <span class="n">name</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">name</span> <span class="o">=</span> <span class="n">func</span><span class="o">.</span><span class="vm">__name__</span> |
| <span class="k">with</span> <span class="n">expressions</span><span class="o">.</span><span class="n">allow_non_parallel_operations</span><span class="p">(</span> |
| <span class="nb">all</span><span class="p">(</span><span class="nb">isinstance</span><span class="p">(</span><span class="n">arg</span><span class="p">,</span> <span class="n">_DeferredScalar</span><span class="p">)</span> <span class="k">for</span> <span class="n">arg</span> <span class="ow">in</span> <span class="n">args</span><span class="p">)</span> <span class="ow">or</span> <span class="kc">None</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">DeferredFrame</span><span class="o">.</span><span class="n">wrap</span><span class="p">(</span> |
| <span class="n">expressions</span><span class="o">.</span><span class="n">ComputedExpression</span><span class="p">(</span> |
| <span class="n">name</span><span class="p">,</span> |
| <span class="n">func</span><span class="p">,</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">_expr</span><span class="p">]</span> <span class="o">+</span> <span class="p">[</span><span class="n">arg</span><span class="o">.</span><span class="n">_expr</span> <span class="k">for</span> <span class="n">arg</span> <span class="ow">in</span> <span class="n">args</span><span class="p">],</span> |
| <span class="n">requires_partition_by</span><span class="o">=</span><span class="n">partitionings</span><span class="o">.</span><span class="n">Singleton</span><span class="p">()))</span> |
| |
| <span class="k">def</span> <span class="fm">__neg__</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">apply</span><span class="p">(</span><span class="n">operator</span><span class="o">.</span><span class="n">neg</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__pos__</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">apply</span><span class="p">(</span><span class="n">operator</span><span class="o">.</span><span class="n">pos</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__invert__</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">apply</span><span class="p">(</span><span class="n">operator</span><span class="o">.</span><span class="n">invert</span><span class="p">)</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="sa">f</span><span class="s2">"DeferredScalar[type=</span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_expr</span><span class="o">.</span><span class="n">proxy</span><span class="p">())</span><span class="si">}</span><span class="s2">]"</span> |
| |
| <span class="k">def</span> <span class="fm">__bool__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span> |
| <span class="c1"># TODO(BEAM-11951): Link to documentation</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span> |
| <span class="s2">"Testing the truth value of a deferred scalar is not "</span> |
| <span class="s2">"allowed. It's not possible to branch on the result of "</span> |
| <span class="s2">"deferred operations."</span><span class="p">)</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_scalar_binop</span><span class="p">(</span><span class="n">op</span><span class="p">):</span> |
| <span class="k">def</span> <span class="nf">binop</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="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">other</span><span class="p">,</span> <span class="n">DeferredBase</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="k">lambda</span> <span class="n">left</span><span class="p">:</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">left</span><span class="p">,</span> <span class="n">op</span><span class="p">)(</span><span class="n">other</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="n">op</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="n">_DeferredScalar</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span> |
| <span class="k">lambda</span> <span class="n">left</span><span class="p">,</span> <span class="n">right</span><span class="p">:</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">left</span><span class="p">,</span> <span class="n">op</span><span class="p">)(</span><span class="n">right</span><span class="p">),</span> <span class="n">name</span><span class="o">=</span><span class="n">op</span><span class="p">,</span> <span class="n">args</span><span class="o">=</span><span class="p">[</span><span class="n">other</span><span class="p">])</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="bp">NotImplemented</span> |
| |
| <span class="k">return</span> <span class="n">binop</span> |
| |
| |
| <span class="k">for</span> <span class="n">op</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'__add__'</span><span class="p">,</span> |
| <span class="s1">'__sub__'</span><span class="p">,</span> |
| <span class="s1">'__mul__'</span><span class="p">,</span> |
| <span class="s1">'__div__'</span><span class="p">,</span> |
| <span class="s1">'__truediv__'</span><span class="p">,</span> |
| <span class="s1">'__floordiv__'</span><span class="p">,</span> |
| <span class="s1">'__mod__'</span><span class="p">,</span> |
| <span class="s1">'__divmod__'</span><span class="p">,</span> |
| <span class="s1">'__pow__'</span><span class="p">,</span> |
| <span class="s1">'__and__'</span><span class="p">,</span> |
| <span class="s1">'__or__'</span><span class="p">]:</span> |
| <span class="nb">setattr</span><span class="p">(</span><span class="n">_DeferredScalar</span><span class="p">,</span> <span class="n">op</span><span class="p">,</span> <span class="n">_scalar_binop</span><span class="p">(</span><span class="n">op</span><span class="p">))</span> |
| |
| <span class="n">DeferredBase</span><span class="o">.</span><span class="n">_pandas_type_map</span><span class="p">[</span><span class="kc">None</span><span class="p">]</span> <span class="o">=</span> <span class="n">_DeferredScalar</span> |
| |
| |
| <div class="viewcode-block" id="name_and_func"><a class="viewcode-back" href="../../../apache_beam.dataframe.frame_base.html#apache_beam.dataframe.frame_base.name_and_func">[docs]</a><span class="k">def</span> <span class="nf">name_and_func</span><span class="p">(</span><span class="n">method</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Callable</span><span class="p">])</span> <span class="o">-></span> <span class="n">Tuple</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Callable</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""For the given method name or method, return the method name and the method</span> |
| <span class="sd"> itself.</span> |
| |
| <span class="sd"> For internal use only. No backwards compatibility guarantees."""</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">method</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="n">method_str</span> <span class="o">=</span> <span class="n">method</span> |
| <span class="n">func</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">df</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="nb">getattr</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="n">method_str</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="n">method</span><span class="p">,</span> <span class="n">func</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">method</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> <span class="n">method</span></div> |
| |
| |
| <span class="k">def</span> <span class="nf">_elementwise_method</span><span class="p">(</span> |
| <span class="n">func</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">restrictions</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">base</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">_proxy_method</span><span class="p">(</span> |
| <span class="n">func</span><span class="p">,</span> |
| <span class="n">name</span><span class="p">,</span> |
| <span class="n">restrictions</span><span class="p">,</span> |
| <span class="n">inplace</span><span class="p">,</span> |
| <span class="n">base</span><span class="p">,</span> |
| <span class="n">requires_partition_by</span><span class="o">=</span><span class="n">partitionings</span><span class="o">.</span><span class="n">Arbitrary</span><span class="p">(),</span> |
| <span class="n">preserves_partition_by</span><span class="o">=</span><span class="n">partitionings</span><span class="o">.</span><span class="n">Arbitrary</span><span class="p">())</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_proxy_method</span><span class="p">(</span> |
| <span class="n">func</span><span class="p">,</span> |
| <span class="n">name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">restrictions</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">inplace</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> |
| <span class="n">base</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="o">*</span><span class="p">,</span> |
| <span class="n">requires_partition_by</span><span class="p">,</span> <span class="c1"># type: partitionings.Partitioning</span> |
| <span class="n">preserves_partition_by</span><span class="p">,</span> <span class="c1"># type: partitionings.Partitioning</span> |
| <span class="p">):</span> |
| <span class="k">if</span> <span class="n">name</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">name</span><span class="p">,</span> <span class="n">func</span> <span class="o">=</span> <span class="n">name_and_func</span><span class="p">(</span><span class="n">func</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">base</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"base is required for _proxy_method"</span><span class="p">)</span> |
| <span class="k">return</span> <span class="n">_proxy_function</span><span class="p">(</span> |
| <span class="n">func</span><span class="p">,</span> |
| <span class="n">name</span><span class="p">,</span> |
| <span class="n">restrictions</span><span class="p">,</span> |
| <span class="n">inplace</span><span class="p">,</span> |
| <span class="n">base</span><span class="p">,</span> |
| <span class="n">requires_partition_by</span><span class="o">=</span><span class="n">requires_partition_by</span><span class="p">,</span> |
| <span class="n">preserves_partition_by</span><span class="o">=</span><span class="n">preserves_partition_by</span><span class="p">)</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_elementwise_function</span><span class="p">(</span> |
| <span class="n">func</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">restrictions</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="n">base</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">_proxy_function</span><span class="p">(</span> |
| <span class="n">func</span><span class="p">,</span> |
| <span class="n">name</span><span class="p">,</span> |
| <span class="n">restrictions</span><span class="p">,</span> |
| <span class="n">inplace</span><span class="p">,</span> |
| <span class="n">base</span><span class="p">,</span> |
| <span class="n">requires_partition_by</span><span class="o">=</span><span class="n">partitionings</span><span class="o">.</span><span class="n">Arbitrary</span><span class="p">(),</span> |
| <span class="n">preserves_partition_by</span><span class="o">=</span><span class="n">partitionings</span><span class="o">.</span><span class="n">Arbitrary</span><span class="p">())</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_proxy_function</span><span class="p">(</span> |
| <span class="n">func</span><span class="p">,</span> <span class="c1"># type: Union[Callable, str]</span> |
| <span class="n">name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="c1"># type: Optional[str]</span> |
| <span class="n">restrictions</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="c1"># type: Optional[Dict[str, Union[Any, List[Any]]]]</span> |
| <span class="n">inplace</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="c1"># type: bool</span> |
| <span class="n">base</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="c1"># type: Optional[type]</span> |
| <span class="o">*</span><span class="p">,</span> |
| <span class="n">requires_partition_by</span><span class="p">,</span> <span class="c1"># type: partitionings.Partitioning</span> |
| <span class="n">preserves_partition_by</span><span class="p">,</span> <span class="c1"># type: partitionings.Partitioning</span> |
| <span class="p">):</span> |
| |
| <span class="k">if</span> <span class="n">name</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">func</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span> |
| <span class="n">name</span> <span class="o">=</span> <span class="n">func</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">name</span> <span class="o">=</span> <span class="n">func</span><span class="o">.</span><span class="vm">__name__</span> |
| <span class="k">if</span> <span class="n">restrictions</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">restrictions</span> <span class="o">=</span> <span class="p">{}</span> |
| |
| <span class="k">def</span> <span class="nf">wrapper</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">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">values</span> <span class="ow">in</span> <span class="n">restrictions</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="k">if</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">kwargs</span><span class="p">:</span> |
| <span class="n">value</span> <span class="o">=</span> <span class="n">kwargs</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">ix</span> <span class="o">=</span> <span class="n">getfullargspec</span><span class="p">(</span><span class="n">func</span><span class="p">)</span><span class="o">.</span><span class="n">args</span><span class="o">.</span><span class="n">index</span><span class="p">(</span><span class="n">key</span><span class="p">)</span> |
| <span class="k">except</span> <span class="ne">ValueError</span><span class="p">:</span> |
| <span class="c1"># TODO: fix for delegation?</span> |
| <span class="k">continue</span> |
| <span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">args</span><span class="p">)</span> <span class="o"><=</span> <span class="n">ix</span><span class="p">:</span> |
| <span class="k">continue</span> |
| <span class="n">value</span> <span class="o">=</span> <span class="n">args</span><span class="p">[</span><span class="n">ix</span><span class="p">]</span> |
| <span class="k">if</span> <span class="nb">callable</span><span class="p">(</span><span class="n">values</span><span class="p">):</span> |
| <span class="n">check</span> <span class="o">=</span> <span class="n">values</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">values</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span> |
| <span class="n">check</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">x</span><span class="p">,</span> <span class="n">values</span><span class="o">=</span><span class="n">values</span><span class="p">:</span> <span class="n">x</span> <span class="ow">in</span> <span class="n">values</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">check</span> <span class="o">=</span> <span class="k">lambda</span> <span class="n">x</span><span class="p">,</span> <span class="n">value</span><span class="o">=</span><span class="n">value</span><span class="p">:</span> <span class="n">x</span> <span class="o">==</span> <span class="n">value</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">check</span><span class="p">(</span><span class="n">value</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span> |
| <span class="s1">'</span><span class="si">%s</span><span class="s1">=</span><span class="si">%s</span><span class="s1"> not supported for </span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span> <span class="p">(</span><span class="n">key</span><span class="p">,</span> <span class="n">value</span><span class="p">,</span> <span class="n">name</span><span class="p">))</span> |
| <span class="n">deferred_arg_indices</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">deferred_arg_exprs</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">constant_args</span> <span class="o">=</span> <span class="p">[</span><span class="kc">None</span><span class="p">]</span> <span class="o">*</span> <span class="nb">len</span><span class="p">(</span><span class="n">args</span><span class="p">)</span> |
| <span class="kn">from</span> <span class="nn">apache_beam.dataframe.frames</span> <span class="kn">import</span> <span class="n">_DeferredIndex</span> |
| <span class="k">for</span> <span class="n">ix</span><span class="p">,</span> <span class="n">arg</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">args</span><span class="p">):</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">arg</span><span class="p">,</span> <span class="n">DeferredBase</span><span class="p">):</span> |
| <span class="n">deferred_arg_indices</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">ix</span><span class="p">)</span> |
| <span class="n">deferred_arg_exprs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">arg</span><span class="o">.</span><span class="n">_expr</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">arg</span><span class="p">,</span> <span class="n">_DeferredIndex</span><span class="p">):</span> |
| <span class="c1"># TODO(robertwb): Consider letting indices pass through as indices.</span> |
| <span class="c1"># This would require updating the partitioning code, as indices don't</span> |
| <span class="c1"># have indices.</span> |
| <span class="n">deferred_arg_indices</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">ix</span><span class="p">)</span> |
| <span class="n">deferred_arg_exprs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span> |
| <span class="n">expressions</span><span class="o">.</span><span class="n">ComputedExpression</span><span class="p">(</span> |
| <span class="s1">'index_as_series'</span><span class="p">,</span> |
| <span class="k">lambda</span> <span class="n">ix</span><span class="p">:</span> <span class="n">ix</span><span class="o">.</span><span class="n">index</span><span class="o">.</span><span class="n">to_series</span><span class="p">(),</span> <span class="c1"># yapf break</span> |
| <span class="p">[</span><span class="n">arg</span><span class="o">.</span><span class="n">_frame</span><span class="o">.</span><span class="n">_expr</span><span class="p">],</span> |
| <span class="n">preserves_partition_by</span><span class="o">=</span><span class="n">partitionings</span><span class="o">.</span><span class="n">Singleton</span><span class="p">(),</span> |
| <span class="n">requires_partition_by</span><span class="o">=</span><span class="n">partitionings</span><span class="o">.</span><span class="n">Arbitrary</span><span class="p">()))</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">arg</span><span class="p">,</span> <span class="n">pd</span><span class="o">.</span><span class="n">core</span><span class="o">.</span><span class="n">generic</span><span class="o">.</span><span class="n">NDFrame</span><span class="p">):</span> |
| <span class="n">deferred_arg_indices</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">ix</span><span class="p">)</span> |
| <span class="n">deferred_arg_exprs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">expressions</span><span class="o">.</span><span class="n">ConstantExpression</span><span class="p">(</span><span class="n">arg</span><span class="p">,</span> <span class="n">arg</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">else</span><span class="p">:</span> |
| <span class="n">constant_args</span><span class="p">[</span><span class="n">ix</span><span class="p">]</span> <span class="o">=</span> <span class="n">arg</span> |
| |
| <span class="n">deferred_kwarg_keys</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">deferred_kwarg_exprs</span> <span class="o">=</span> <span class="p">[]</span> |
| <span class="n">constant_kwargs</span> <span class="o">=</span> <span class="p">{</span><span class="n">key</span><span class="p">:</span> <span class="kc">None</span> <span class="k">for</span> <span class="n">key</span> <span class="ow">in</span> <span class="n">kwargs</span><span class="p">}</span> |
| <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">arg</span> <span class="ow">in</span> <span class="n">kwargs</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">arg</span><span class="p">,</span> <span class="n">DeferredBase</span><span class="p">):</span> |
| <span class="n">deferred_kwarg_keys</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">key</span><span class="p">)</span> |
| <span class="n">deferred_kwarg_exprs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">arg</span><span class="o">.</span><span class="n">_expr</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">arg</span><span class="p">,</span> <span class="n">pd</span><span class="o">.</span><span class="n">core</span><span class="o">.</span><span class="n">generic</span><span class="o">.</span><span class="n">NDFrame</span><span class="p">):</span> |
| <span class="n">deferred_kwarg_keys</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">key</span><span class="p">)</span> |
| <span class="n">deferred_kwarg_exprs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span> |
| <span class="n">expressions</span><span class="o">.</span><span class="n">ConstantExpression</span><span class="p">(</span><span class="n">arg</span><span class="p">,</span> <span class="n">arg</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">else</span><span class="p">:</span> |
| <span class="n">constant_kwargs</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="o">=</span> <span class="n">arg</span> |
| |
| <span class="n">deferred_exprs</span> <span class="o">=</span> <span class="n">deferred_arg_exprs</span> <span class="o">+</span> <span class="n">deferred_kwarg_exprs</span> |
| |
| <span class="k">if</span> <span class="n">inplace</span><span class="p">:</span> |
| <span class="n">actual_func</span> <span class="o">=</span> <span class="n">_copy_and_mutate</span><span class="p">(</span><span class="n">func</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">actual_func</span> <span class="o">=</span> <span class="n">func</span> |
| |
| <span class="k">def</span> <span class="nf">apply</span><span class="p">(</span><span class="o">*</span><span class="n">actual_args</span><span class="p">):</span> |
| <span class="n">actual_args</span><span class="p">,</span> <span class="n">actual_kwargs</span> <span class="o">=</span> <span class="p">(</span><span class="n">actual_args</span><span class="p">[:</span><span class="nb">len</span><span class="p">(</span><span class="n">deferred_arg_exprs</span><span class="p">)],</span> |
| <span class="n">actual_args</span><span class="p">[</span><span class="nb">len</span><span class="p">(</span><span class="n">deferred_arg_exprs</span><span class="p">):])</span> |
| |
| <span class="n">full_args</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">constant_args</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">ix</span><span class="p">,</span> <span class="n">arg</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">deferred_arg_indices</span><span class="p">,</span> <span class="n">actual_args</span><span class="p">):</span> |
| <span class="n">full_args</span><span class="p">[</span><span class="n">ix</span><span class="p">]</span> <span class="o">=</span> <span class="n">arg</span> |
| |
| <span class="n">full_kwargs</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="n">constant_kwargs</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">arg</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">deferred_kwarg_keys</span><span class="p">,</span> <span class="n">actual_kwargs</span><span class="p">):</span> |
| <span class="n">full_kwargs</span><span class="p">[</span><span class="n">key</span><span class="p">]</span> <span class="o">=</span> <span class="n">arg</span> |
| |
| <span class="k">return</span> <span class="n">actual_func</span><span class="p">(</span><span class="o">*</span><span class="n">full_args</span><span class="p">,</span> <span class="o">**</span><span class="n">full_kwargs</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="p">(</span><span class="n">requires_partition_by</span><span class="o">.</span><span class="n">is_subpartitioning_of</span><span class="p">(</span><span class="n">partitionings</span><span class="o">.</span><span class="n">Index</span><span class="p">())</span> <span class="ow">and</span> |
| <span class="nb">sum</span><span class="p">(</span><span class="nb">isinstance</span><span class="p">(</span><span class="n">arg</span><span class="o">.</span><span class="n">proxy</span><span class="p">(),</span> <span class="n">pd</span><span class="o">.</span><span class="n">core</span><span class="o">.</span><span class="n">generic</span><span class="o">.</span><span class="n">NDFrame</span><span class="p">)</span> |
| <span class="k">for</span> <span class="n">arg</span> <span class="ow">in</span> <span class="n">deferred_exprs</span><span class="p">)</span> <span class="o">></span> <span class="mi">1</span><span class="p">):</span> |
| <span class="c1"># Implicit join on index if there is more than one indexed input.</span> |
| <span class="n">actual_requires_partition_by</span> <span class="o">=</span> <span class="n">partitionings</span><span class="o">.</span><span class="n">JoinIndex</span><span class="p">()</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">actual_requires_partition_by</span> <span class="o">=</span> <span class="n">requires_partition_by</span> |
| |
| <span class="n">result_expr</span> <span class="o">=</span> <span class="n">expressions</span><span class="o">.</span><span class="n">ComputedExpression</span><span class="p">(</span> |
| <span class="n">name</span><span class="p">,</span> |
| <span class="n">apply</span><span class="p">,</span> |
| <span class="n">deferred_exprs</span><span class="p">,</span> |
| <span class="n">requires_partition_by</span><span class="o">=</span><span class="n">actual_requires_partition_by</span><span class="p">,</span> |
| <span class="n">preserves_partition_by</span><span class="o">=</span><span class="n">preserves_partition_by</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">inplace</span><span class="p">:</span> |
| <span class="n">args</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">_expr</span> <span class="o">=</span> <span class="n">result_expr</span> |
| |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">DeferredFrame</span><span class="o">.</span><span class="n">wrap</span><span class="p">(</span><span class="n">result_expr</span><span class="p">)</span> |
| |
| <span class="n">wrapper</span><span class="o">.</span><span class="vm">__name__</span> <span class="o">=</span> <span class="n">name</span> |
| <span class="k">if</span> <span class="n">restrictions</span><span class="p">:</span> |
| <span class="n">wrapper</span><span class="o">.</span><span class="vm">__doc__</span> <span class="o">=</span> <span class="s2">"</span><span class="se">\n</span><span class="s2">"</span><span class="o">.</span><span class="n">join</span><span class="p">(</span> |
| <span class="sa">f</span><span class="s2">"Only </span><span class="si">{</span><span class="n">kw</span><span class="si">}</span><span class="s2">=</span><span class="si">{</span><span class="n">value</span><span class="si">!r}</span><span class="s2"> is supported"</span> |
| <span class="k">for</span> <span class="p">(</span><span class="n">kw</span><span class="p">,</span> <span class="n">value</span><span class="p">)</span> <span class="ow">in</span> <span class="n">restrictions</span><span class="o">.</span><span class="n">items</span><span class="p">())</span> |
| |
| <span class="k">if</span> <span class="n">base</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">with_docs_from</span><span class="p">(</span><span class="n">base</span><span class="p">)(</span><span class="n">wrapper</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">wrapper</span> |
| |
| |
| <span class="k">def</span> <span class="nf">_prettify_pandas_type</span><span class="p">(</span><span class="n">pandas_type</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">pandas_type</span> <span class="ow">in</span> <span class="p">(</span><span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">,</span> <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">):</span> |
| <span class="k">return</span> <span class="sa">f</span><span class="s1">'pandas.</span><span class="si">{</span><span class="n">pandas_type</span><span class="o">.</span><span class="vm">__name__</span><span class="si">}</span><span class="s1">'</span> |
| <span class="k">elif</span> <span class="n">isclass</span><span class="p">(</span><span class="n">pandas_type</span><span class="p">):</span> |
| <span class="k">return</span> <span class="sa">f</span><span class="s1">'</span><span class="si">{</span><span class="n">pandas_type</span><span class="o">.</span><span class="vm">__module__</span><span class="si">}</span><span class="s1">.</span><span class="si">{</span><span class="n">pandas_type</span><span class="o">.</span><span class="vm">__name__</span><span class="si">}</span><span class="s1">'</span> |
| <span class="k">elif</span> <span class="n">ismodule</span><span class="p">(</span><span class="n">pandas_type</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">pandas_type</span><span class="o">.</span><span class="vm">__name__</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span><span class="n">pandas_type</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="wont_implement_method"><a class="viewcode-back" href="../../../apache_beam.dataframe.frame_base.html#apache_beam.dataframe.frame_base.wont_implement_method">[docs]</a><span class="k">def</span> <span class="nf">wont_implement_method</span><span class="p">(</span><span class="n">base_type</span><span class="p">,</span> <span class="n">name</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="n">explanation</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Generate a stub method that raises WontImplementError.</span> |
| |
| <span class="sd"> Note either reason or explanation must be specified. If both are specified,</span> |
| <span class="sd"> explanation is ignored.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> base_type: The pandas type of the method that this is trying to replicate.</span> |
| <span class="sd"> name: The name of the method that this is aiming to replicate.</span> |
| <span class="sd"> reason: If specified, use data from the corresponding entry in</span> |
| <span class="sd"> ``_WONT_IMPLEMENT_REASONS`` to generate a helpful exception message</span> |
| <span class="sd"> and docstring for the method.</span> |
| <span class="sd"> explanation: If specified, use this string as an explanation for why</span> |
| <span class="sd"> this operation is not supported when generating an exception message</span> |
| <span class="sd"> and docstring.</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="n">reason</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">reason</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">_WONT_IMPLEMENT_REASONS</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">AssertionError</span><span class="p">(</span> |
| <span class="sa">f</span><span class="s2">"reason must be one of </span><span class="si">{</span><span class="nb">list</span><span class="p">(</span><span class="n">_WONT_IMPLEMENT_REASONS</span><span class="o">.</span><span class="n">keys</span><span class="p">())</span><span class="si">}</span><span class="s2">, "</span> |
| <span class="sa">f</span><span class="s2">"got </span><span class="si">{</span><span class="n">reason</span><span class="si">!r}</span><span class="s2">"</span><span class="p">)</span> |
| <span class="n">reason_data</span> <span class="o">=</span> <span class="n">_WONT_IMPLEMENT_REASONS</span><span class="p">[</span><span class="n">reason</span><span class="p">]</span> |
| <span class="k">elif</span> <span class="n">explanation</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="n">reason_data</span> <span class="o">=</span> <span class="p">{</span><span class="s1">'explanation'</span><span class="p">:</span> <span class="n">explanation</span><span class="p">}</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="s2">"One of (reason, explanation) must be specified"</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">wrapper</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">raise</span> <span class="n">WontImplementError</span><span class="p">(</span> |
| <span class="sa">f</span><span class="s2">"'</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">' is not yet supported </span><span class="si">{</span><span class="n">reason_data</span><span class="p">[</span><span class="s1">'explanation'</span><span class="p">]</span><span class="si">}</span><span class="s2">"</span><span class="p">,</span> |
| <span class="n">reason</span><span class="o">=</span><span class="n">reason</span><span class="p">)</span> |
| |
| <span class="n">wrapper</span><span class="o">.</span><span class="vm">__name__</span> <span class="o">=</span> <span class="n">name</span> |
| <span class="n">wrapper</span><span class="o">.</span><span class="vm">__doc__</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="sa">f</span><span class="s2">":meth:`</span><span class="si">{</span><span class="n">_prettify_pandas_type</span><span class="p">(</span><span class="n">base_type</span><span class="p">)</span><span class="si">}</span><span class="s2">.</span><span class="si">{</span><span class="n">name</span><span class="si">}</span><span class="s2">` is not yet supported "</span> |
| <span class="sa">f</span><span class="s2">"in the Beam DataFrame API </span><span class="si">{</span><span class="n">reason_data</span><span class="p">[</span><span class="s1">'explanation'</span><span class="p">]</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="s1">'url'</span> <span class="ow">in</span> <span class="n">reason_data</span><span class="p">:</span> |
| <span class="n">wrapper</span><span class="o">.</span><span class="vm">__doc__</span> <span class="o">+=</span> <span class="sa">f</span><span class="s2">"</span><span class="se">\n\n</span><span class="s2"> For more information see </span><span class="si">{</span><span class="n">reason_data</span><span class="p">[</span><span class="s1">'url'</span><span class="p">]</span><span class="si">}</span><span class="s2">."</span> |
| |
| <span class="k">return</span> <span class="n">wrapper</span></div> |
| |
| |
| <div class="viewcode-block" id="not_implemented_method"><a class="viewcode-back" href="../../../apache_beam.dataframe.frame_base.html#apache_beam.dataframe.frame_base.not_implemented_method">[docs]</a><span class="k">def</span> <span class="nf">not_implemented_method</span><span class="p">(</span><span class="n">op</span><span class="p">,</span> <span class="n">issue</span><span class="o">=</span><span class="s1">'20318'</span><span class="p">,</span> <span class="n">base_type</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Generate a stub method for ``op`` that simply raises a NotImplementedError.</span> |
| |
| <span class="sd"> For internal use only. No backwards compatibility guarantees."""</span> |
| <span class="k">assert</span> <span class="n">base_type</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">,</span> <span class="s2">"base_type must be specified"</span> |
| <span class="n">issue_url</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"https://issues.apache.org/jira/</span><span class="si">{</span><span class="n">issue</span><span class="si">}</span><span class="s2">."</span> <span class="k">if</span> <span class="n">issue</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span> |
| <span class="s2">"BEAM-"</span><span class="p">)</span> <span class="k">else</span> <span class="sa">f</span><span class="s2">"https://github.com/apache/beam/issues/</span><span class="si">{</span><span class="n">issue</span><span class="si">}</span><span class="s2">"</span> |
| |
| <span class="k">def</span> <span class="nf">wrapper</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">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span> |
| <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">op</span><span class="si">!r}</span><span class="s2"> is not implemented yet. "</span> |
| <span class="sa">f</span><span class="s2">"If support for </span><span class="si">{</span><span class="n">op</span><span class="si">!r}</span><span class="s2"> is important to you, please let the Beam "</span> |
| <span class="s2">"community know by writing to user@beam.apache.org "</span> |
| <span class="s2">"(see https://beam.apache.org/community/contact-us/) or commenting on "</span> |
| <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">issue_url</span><span class="si">}</span><span class="s2">"</span><span class="p">)</span> |
| |
| <span class="n">wrapper</span><span class="o">.</span><span class="vm">__name__</span> <span class="o">=</span> <span class="n">op</span> |
| <span class="n">wrapper</span><span class="o">.</span><span class="vm">__doc__</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="sa">f</span><span class="s2">":meth:`</span><span class="si">{</span><span class="n">_prettify_pandas_type</span><span class="p">(</span><span class="n">base_type</span><span class="p">)</span><span class="si">}</span><span class="s2">.</span><span class="si">{</span><span class="n">op</span><span class="si">}</span><span class="s2">` is not implemented yet "</span> |
| <span class="s2">"in the Beam DataFrame API.</span><span class="se">\n\n</span><span class="s2">"</span> |
| <span class="sa">f</span><span class="s2">"If support for </span><span class="si">{</span><span class="n">op</span><span class="si">!r}</span><span class="s2"> is important to you, please let the Beam "</span> |
| <span class="s2">"community know by `writing to user@beam.apache.org "</span> |
| <span class="s2">"<https://beam.apache.org/community/contact-us/>`_ or commenting on "</span> |
| <span class="sa">f</span><span class="s2">"`</span><span class="si">{</span><span class="n">issue</span><span class="si">}</span><span class="s2"> <</span><span class="si">{</span><span class="n">issue_url</span><span class="si">}</span><span class="s2">>`_."</span><span class="p">)</span> |
| |
| <span class="k">return</span> <span class="n">wrapper</span></div> |
| |
| |
| <span class="k">def</span> <span class="nf">_copy_and_mutate</span><span class="p">(</span><span class="n">func</span><span class="p">):</span> |
| <span class="k">def</span> <span class="nf">wrapper</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="n">copy</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span> |
| <span class="n">func</span><span class="p">(</span><span class="n">copy</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="n">copy</span> |
| |
| <span class="k">return</span> <span class="n">wrapper</span> |
| |
| |
| <div class="viewcode-block" id="maybe_inplace"><a class="viewcode-back" href="../../../apache_beam.dataframe.frame_base.html#apache_beam.dataframe.frame_base.maybe_inplace">[docs]</a><span class="k">def</span> <span class="nf">maybe_inplace</span><span class="p">(</span><span class="n">func</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Handles the inplace= kwarg available in many pandas operations.</span> |
| |
| <span class="sd"> This decorator produces a new function handles the inplace kwarg. When</span> |
| <span class="sd"> `inplace=False`, the new function simply yields the result of `func`</span> |
| <span class="sd"> directly.</span> |
| |
| <span class="sd"> When `inplace=True`, the output of `func` is used to replace this instances</span> |
| <span class="sd"> expression. The result is that any operations applied to this instance after</span> |
| <span class="sd"> the inplace operation will refernce the updated expression.</span> |
| |
| <span class="sd"> For internal use only. No backwards compatibility guarantees."""</span> |
| <span class="nd">@functools</span><span class="o">.</span><span class="n">wraps</span><span class="p">(</span><span class="n">func</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">wrapper</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">inplace</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="n">result</span> <span class="o">=</span> <span class="n">func</span><span class="p">(</span><span class="bp">self</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">inplace</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_expr</span> <span class="o">=</span> <span class="n">result</span><span class="o">.</span><span class="n">_expr</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">result</span> |
| |
| <span class="k">return</span> <span class="n">wrapper</span></div> |
| |
| |
| <div class="viewcode-block" id="args_to_kwargs"><a class="viewcode-back" href="../../../apache_beam.dataframe.frame_base.html#apache_beam.dataframe.frame_base.args_to_kwargs">[docs]</a><span class="k">def</span> <span class="nf">args_to_kwargs</span><span class="p">(</span><span class="n">base_type</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Convert all args to kwargs before calling the decorated function.</span> |
| |
| <span class="sd"> When applied to a function, this decorator creates a new function</span> |
| <span class="sd"> that always calls the wrapped function with *only* keyword arguments. It</span> |
| <span class="sd"> inspects the argspec for the identically-named method on `base_type` to</span> |
| <span class="sd"> determine the name to use for arguments that are converted to keyword</span> |
| <span class="sd"> arguments.</span> |
| |
| <span class="sd"> For internal use only. No backwards compatibility guarantees."""</span> |
| <span class="k">def</span> <span class="nf">wrap</span><span class="p">(</span><span class="n">func</span><span class="p">):</span> |
| <span class="n">arg_names</span> <span class="o">=</span> <span class="n">getfullargspec</span><span class="p">(</span><span class="n">unwrap</span><span class="p">(</span><span class="nb">getattr</span><span class="p">(</span><span class="n">base_type</span><span class="p">,</span> <span class="n">func</span><span class="o">.</span><span class="vm">__name__</span><span class="p">)))</span><span class="o">.</span><span class="n">args</span> |
| |
| <span class="nd">@functools</span><span class="o">.</span><span class="n">wraps</span><span class="p">(</span><span class="n">func</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">wrapper</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">for</span> <span class="n">name</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="nb">zip</span><span class="p">(</span><span class="n">arg_names</span><span class="p">,</span> <span class="n">args</span><span class="p">):</span> |
| <span class="k">if</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">kwargs</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span> |
| <span class="s2">"</span><span class="si">%s</span><span class="s2">() got multiple values for argument '</span><span class="si">%s</span><span class="s2">'"</span> <span class="o">%</span> |
| <span class="p">(</span><span class="n">func</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> <span class="n">name</span><span class="p">))</span> |
| <span class="n">kwargs</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="n">value</span> |
| <span class="k">return</span> <span class="n">func</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="n">wrapper</span> |
| |
| <span class="k">return</span> <span class="n">wrap</span></div> |
| |
| |
| <span class="n">BEAM_SPECIFIC</span> <span class="o">=</span> <span class="s2">"Differences from pandas"</span> |
| |
| <span class="n">SECTION_ORDER</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="s1">'Parameters'</span><span class="p">,</span> |
| <span class="s1">'Returns'</span><span class="p">,</span> |
| <span class="s1">'Raises'</span><span class="p">,</span> |
| <span class="n">BEAM_SPECIFIC</span><span class="p">,</span> |
| <span class="s1">'See Also'</span><span class="p">,</span> |
| <span class="s1">'Notes'</span><span class="p">,</span> |
| <span class="s1">'Examples'</span> |
| <span class="p">]</span> |
| |
| <span class="n">EXAMPLES_DISCLAIMER</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="s2">"**NOTE:** These examples are pulled directly from the pandas "</span> |
| <span class="s2">"documentation for convenience. Usage of the Beam DataFrame API will look "</span> |
| <span class="s2">"different because it is a deferred API."</span><span class="p">)</span> |
| <span class="n">EXAMPLES_DIFFERENCES</span> <span class="o">=</span> <span class="n">EXAMPLES_DISCLAIMER</span> <span class="o">+</span> <span class="p">(</span> |
| <span class="s2">" In addition, some arguments shown here may not be supported, see "</span> |
| <span class="sa">f</span><span class="s2">"**</span><span class="si">{</span><span class="n">BEAM_SPECIFIC</span><span class="si">!r}</span><span class="s2">** for details."</span><span class="p">)</span> |
| |
| |
| <div class="viewcode-block" id="with_docs_from"><a class="viewcode-back" href="../../../apache_beam.dataframe.frame_base.html#apache_beam.dataframe.frame_base.with_docs_from">[docs]</a><span class="k">def</span> <span class="nf">with_docs_from</span><span class="p">(</span><span class="n">base_type</span><span class="p">,</span> <span class="n">name</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Decorator that updates the documentation from the wrapped function to</span> |
| <span class="sd"> duplicate the documentation from the identically-named method in `base_type`.</span> |
| |
| <span class="sd"> Any docstring on the original function will be included in the new function</span> |
| <span class="sd"> under a "Differences from pandas" heading.</span> |
| <span class="sd"> """</span> |
| <span class="k">def</span> <span class="nf">wrap</span><span class="p">(</span><span class="n">func</span><span class="p">):</span> |
| <span class="n">fn_name</span> <span class="o">=</span> <span class="n">name</span> <span class="ow">or</span> <span class="n">func</span><span class="o">.</span><span class="vm">__name__</span> |
| <span class="n">orig_doc</span> <span class="o">=</span> <span class="nb">getattr</span><span class="p">(</span><span class="n">base_type</span><span class="p">,</span> <span class="n">fn_name</span><span class="p">)</span><span class="o">.</span><span class="vm">__doc__</span> |
| <span class="k">if</span> <span class="n">orig_doc</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">func</span> |
| |
| <span class="n">orig_doc</span> <span class="o">=</span> <span class="n">cleandoc</span><span class="p">(</span><span class="n">orig_doc</span><span class="p">)</span> |
| |
| <span class="n">section_splits</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="sa">r</span><span class="s1">'^(.*)$\n^-+$\n'</span><span class="p">,</span> <span class="n">orig_doc</span><span class="p">,</span> <span class="n">flags</span><span class="o">=</span><span class="n">re</span><span class="o">.</span><span class="n">MULTILINE</span><span class="p">)</span> |
| <span class="n">intro</span> <span class="o">=</span> <span class="n">section_splits</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span> |
| <span class="n">sections</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span><span class="nb">zip</span><span class="p">(</span><span class="n">section_splits</span><span class="p">[</span><span class="mi">1</span><span class="p">::</span><span class="mi">2</span><span class="p">],</span> <span class="n">section_splits</span><span class="p">[</span><span class="mi">2</span><span class="p">::</span><span class="mi">2</span><span class="p">]))</span> |
| |
| <span class="n">beam_has_differences</span> <span class="o">=</span> <span class="nb">bool</span><span class="p">(</span><span class="n">func</span><span class="o">.</span><span class="vm">__doc__</span><span class="p">)</span> |
| |
| <span class="k">for</span> <span class="n">header</span><span class="p">,</span> <span class="n">content</span> <span class="ow">in</span> <span class="n">sections</span><span class="o">.</span><span class="n">items</span><span class="p">():</span> |
| <span class="n">content</span> <span class="o">=</span> <span class="n">content</span><span class="o">.</span><span class="n">strip</span><span class="p">()</span> |
| |
| <span class="c1"># Replace references to version numbers so its clear they reference</span> |
| <span class="c1"># *pandas* versions</span> |
| <span class="n">content</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="sa">r</span><span class="s1">'([Vv]ersion\s+[\d\.]+)'</span><span class="p">,</span> <span class="sa">r</span><span class="s1">'pandas \1'</span><span class="p">,</span> <span class="n">content</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="n">header</span> <span class="o">==</span> <span class="s2">"Examples"</span><span class="p">:</span> |
| <span class="n">content</span> <span class="o">=</span> <span class="s1">'</span><span class="se">\n\n</span><span class="s1">'</span><span class="o">.</span><span class="n">join</span><span class="p">([</span> |
| <span class="p">(</span> |
| <span class="n">EXAMPLES_DIFFERENCES</span> |
| <span class="k">if</span> <span class="n">beam_has_differences</span> <span class="k">else</span> <span class="n">EXAMPLES_DISCLAIMER</span><span class="p">),</span> |
| <span class="c1"># Indent the examples under a doctest heading,</span> |
| <span class="c1"># add skipif option. This makes sure our doctest</span> |
| <span class="c1"># framework doesn't run these pandas tests.</span> |
| <span class="p">(</span><span class="s2">".. doctest::</span><span class="se">\n</span><span class="s2">"</span> |
| <span class="s2">" :skipif: True"</span><span class="p">),</span> |
| <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="sa">r</span><span class="s2">"^"</span><span class="p">,</span> <span class="s2">" "</span><span class="p">,</span> <span class="n">content</span><span class="p">,</span> <span class="n">flags</span><span class="o">=</span><span class="n">re</span><span class="o">.</span><span class="n">MULTILINE</span><span class="p">),</span> |
| <span class="p">])</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">content</span> <span class="o">=</span> <span class="n">content</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span><span class="s1">'DataFrame'</span><span class="p">,</span> <span class="s1">'DeferredDataFrame'</span><span class="p">)</span><span class="o">.</span><span class="n">replace</span><span class="p">(</span> |
| <span class="s1">'Series'</span><span class="p">,</span> <span class="s1">'DeferredSeries'</span><span class="p">)</span> |
| <span class="n">sections</span><span class="p">[</span><span class="n">header</span><span class="p">]</span> <span class="o">=</span> <span class="n">content</span> |
| |
| <span class="k">if</span> <span class="n">beam_has_differences</span><span class="p">:</span> |
| <span class="n">sections</span><span class="p">[</span><span class="n">BEAM_SPECIFIC</span><span class="p">]</span> <span class="o">=</span> <span class="n">cleandoc</span><span class="p">(</span><span class="n">func</span><span class="o">.</span><span class="vm">__doc__</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">sections</span><span class="p">[</span><span class="n">BEAM_SPECIFIC</span><span class="p">]</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="s2">"This operation has no known divergences from the "</span> |
| <span class="s2">"pandas API."</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="nf">format_section</span><span class="p">(</span><span class="n">header</span><span class="p">):</span> |
| <span class="k">return</span> <span class="s1">'</span><span class="se">\n</span><span class="s1">'</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">header</span><span class="p">,</span> <span class="s1">''</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="s1">'-'</span> <span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="n">header</span><span class="p">),</span> <span class="n">sections</span><span class="p">[</span><span class="n">header</span><span class="p">]])</span> |
| |
| <span class="n">func</span><span class="o">.</span><span class="vm">__doc__</span> <span class="o">=</span> <span class="s1">'</span><span class="se">\n\n</span><span class="s1">'</span><span class="o">.</span><span class="n">join</span><span class="p">([</span><span class="n">intro</span><span class="p">]</span> <span class="o">+</span> <span class="p">[</span> |
| <span class="n">format_section</span><span class="p">(</span><span class="n">header</span><span class="p">)</span> <span class="k">for</span> <span class="n">header</span> <span class="ow">in</span> <span class="n">SECTION_ORDER</span> <span class="k">if</span> <span class="n">header</span> <span class="ow">in</span> <span class="n">sections</span> |
| <span class="p">])</span> |
| |
| <span class="k">return</span> <span class="n">func</span> |
| |
| <span class="k">return</span> <span class="n">wrap</span></div> |
| |
| |
| <div class="viewcode-block" id="populate_defaults"><a class="viewcode-back" href="../../../apache_beam.dataframe.frame_base.html#apache_beam.dataframe.frame_base.populate_defaults">[docs]</a><span class="k">def</span> <span class="nf">populate_defaults</span><span class="p">(</span><span class="n">base_type</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""Populate default values for keyword arguments in decorated function.</span> |
| |
| <span class="sd"> When applied to a function, this decorator creates a new function</span> |
| <span class="sd"> with default values for all keyword arguments, based on the default values</span> |
| <span class="sd"> for the identically-named method on `base_type`.</span> |
| |
| <span class="sd"> For internal use only. No backwards compatibility guarantees."""</span> |
| <span class="k">def</span> <span class="nf">wrap</span><span class="p">(</span><span class="n">func</span><span class="p">):</span> |
| <span class="n">base_argspec</span> <span class="o">=</span> <span class="n">getfullargspec</span><span class="p">(</span><span class="n">unwrap</span><span class="p">(</span><span class="nb">getattr</span><span class="p">(</span><span class="n">base_type</span><span class="p">,</span> <span class="n">func</span><span class="o">.</span><span class="vm">__name__</span><span class="p">)))</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">base_argspec</span><span class="o">.</span><span class="n">defaults</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">func</span> |
| |
| <span class="n">arg_to_default</span> <span class="o">=</span> <span class="nb">dict</span><span class="p">(</span> |
| <span class="nb">zip</span><span class="p">(</span> |
| <span class="n">base_argspec</span><span class="o">.</span><span class="n">args</span><span class="p">[</span><span class="o">-</span><span class="nb">len</span><span class="p">(</span><span class="n">base_argspec</span><span class="o">.</span><span class="n">defaults</span><span class="p">):],</span> |
| <span class="n">base_argspec</span><span class="o">.</span><span class="n">defaults</span><span class="p">))</span> |
| |
| <span class="n">unwrapped_func</span> <span class="o">=</span> <span class="n">unwrap</span><span class="p">(</span><span class="n">func</span><span class="p">)</span> |
| <span class="c1"># args that do not have defaults in func, but do have defaults in base</span> |
| <span class="n">func_argspec</span> <span class="o">=</span> <span class="n">getfullargspec</span><span class="p">(</span><span class="n">unwrapped_func</span><span class="p">)</span> |
| <span class="n">num_non_defaults</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">func_argspec</span><span class="o">.</span><span class="n">args</span><span class="p">)</span> <span class="o">-</span> <span class="nb">len</span><span class="p">(</span><span class="n">func_argspec</span><span class="o">.</span><span class="n">defaults</span> <span class="ow">or</span> <span class="p">())</span> |
| <span class="n">defaults_to_populate</span> <span class="o">=</span> <span class="nb">set</span><span class="p">(</span> |
| <span class="n">func_argspec</span><span class="o">.</span><span class="n">args</span><span class="p">[:</span><span class="n">num_non_defaults</span><span class="p">])</span><span class="o">.</span><span class="n">intersection</span><span class="p">(</span> |
| <span class="n">arg_to_default</span><span class="o">.</span><span class="n">keys</span><span class="p">())</span> |
| |
| <span class="nd">@functools</span><span class="o">.</span><span class="n">wraps</span><span class="p">(</span><span class="n">func</span><span class="p">)</span> |
| <span class="k">def</span> <span class="nf">wrapper</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="k">for</span> <span class="n">name</span> <span class="ow">in</span> <span class="n">defaults_to_populate</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">name</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">kwargs</span><span class="p">:</span> |
| <span class="n">kwargs</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> <span class="o">=</span> <span class="n">arg_to_default</span><span class="p">[</span><span class="n">name</span><span class="p">]</span> |
| <span class="k">return</span> <span class="n">func</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="n">wrapper</span> |
| |
| <span class="k">return</span> <span class="n">wrap</span></div> |
| |
| |
| <span class="n">_WONT_IMPLEMENT_REASONS</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="s1">'order-sensitive'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'explanation'</span><span class="p">:</span> <span class="s2">"because it is sensitive to the order of the data."</span><span class="p">,</span> |
| <span class="s1">'url'</span><span class="p">:</span> <span class="s1">'https://s.apache.org/dataframe-order-sensitive-operations'</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="s1">'non-deferred-columns'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'explanation'</span><span class="p">:</span> <span class="p">(</span> |
| <span class="s2">"because the columns in the output DataFrame depend "</span> |
| <span class="s2">"on the data."</span><span class="p">),</span> |
| <span class="s1">'url'</span><span class="p">:</span> <span class="s1">'https://s.apache.org/dataframe-non-deferred-columns'</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="s1">'non-deferred-result'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'explanation'</span><span class="p">:</span> <span class="p">(</span> |
| <span class="s2">"because it produces an output type that is not "</span> |
| <span class="s2">"deferred."</span><span class="p">),</span> |
| <span class="s1">'url'</span><span class="p">:</span> <span class="s1">'https://s.apache.org/dataframe-non-deferred-result'</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="s1">'plotting-tools'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'explanation'</span><span class="p">:</span> <span class="s2">"because it is a plotting tool."</span><span class="p">,</span> |
| <span class="s1">'url'</span><span class="p">:</span> <span class="s1">'https://s.apache.org/dataframe-plotting-tools'</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="s1">'event-time-semantics'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'explanation'</span><span class="p">:</span> <span class="p">(</span> |
| <span class="s2">"because implementing it would require integrating with Beam "</span> |
| <span class="s2">"event-time semantics"</span><span class="p">),</span> |
| <span class="s1">'url'</span><span class="p">:</span> <span class="s1">'https://s.apache.org/dataframe-event-time-semantics'</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="s1">'deprecated'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'explanation'</span><span class="p">:</span> <span class="s2">"because it is deprecated in pandas."</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="s1">'experimental'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'explanation'</span><span class="p">:</span> <span class="s2">"because it is experimental in pandas."</span><span class="p">,</span> |
| <span class="p">},</span> |
| <span class="p">}</span> |
| |
| |
| <div class="viewcode-block" id="WontImplementError"><a class="viewcode-back" href="../../../apache_beam.dataframe.frame_base.html#apache_beam.dataframe.frame_base.WontImplementError">[docs]</a><span class="k">class</span> <span class="nc">WontImplementError</span><span class="p">(</span><span class="ne">NotImplementedError</span><span class="p">):</span> |
| <span class="w"> </span><span class="sd">"""An subclass of NotImplementedError to raise indicating that implementing</span> |
| <span class="sd"> the given method is not planned.</span> |
| |
| <span class="sd"> Raising this error will also prevent this doctests from being validated</span> |
| <span class="sd"> when run with the beam dataframe validation doctest runner.</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">msg</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="k">if</span> <span class="n">reason</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span> |
| <span class="k">if</span> <span class="n">reason</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">_WONT_IMPLEMENT_REASONS</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">AssertionError</span><span class="p">(</span> |
| <span class="sa">f</span><span class="s2">"reason must be one of </span><span class="si">{</span><span class="nb">list</span><span class="p">(</span><span class="n">_WONT_IMPLEMENT_REASONS</span><span class="o">.</span><span class="n">keys</span><span class="p">())</span><span class="si">}</span><span class="s2">, "</span> |
| <span class="sa">f</span><span class="s2">"got </span><span class="si">{</span><span class="n">reason</span><span class="si">!r}</span><span class="s2">"</span><span class="p">)</span> |
| |
| <span class="n">reason_data</span> <span class="o">=</span> <span class="n">_WONT_IMPLEMENT_REASONS</span><span class="p">[</span><span class="n">reason</span><span class="p">]</span> |
| <span class="k">if</span> <span class="s1">'url'</span> <span class="ow">in</span> <span class="n">reason_data</span><span class="p">:</span> |
| <span class="n">msg</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">"</span><span class="si">{</span><span class="n">msg</span><span class="si">}</span><span class="se">\n</span><span class="s2">For more information see </span><span class="si">{</span><span class="n">reason_data</span><span class="p">[</span><span class="s1">'url'</span><span class="p">]</span><span class="si">}</span><span class="s2">."</span> |
| |
| <span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">msg</span><span class="p">)</span></div> |
| </pre></div> |
| |
| </div> |
| |
| </div> |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| © Copyright |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| </body> |
| </html> |
