| |
| |
| <!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.transforms module — Apache Beam 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" /> |
| <link rel="next" title="apache_beam.io package" href="apache_beam.io.html" /> |
| <link rel="prev" title="apache_beam.dataframe.schemas module" href="apache_beam.dataframe.schemas.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 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 class="current"> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.coders.html">apache_beam.coders package</a></li> |
| <li class="toctree-l1 current"><a class="reference internal" href="apache_beam.dataframe.html">apache_beam.dataframe package</a><ul class="current"> |
| <li class="toctree-l2 current"><a class="reference internal" href="apache_beam.dataframe.html#submodules">Submodules</a><ul class="current"> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.dataframe.convert.html">apache_beam.dataframe.convert module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.dataframe.doctests.html">apache_beam.dataframe.doctests module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.dataframe.expressions.html">apache_beam.dataframe.expressions module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.dataframe.frame_base.html">apache_beam.dataframe.frame_base module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.dataframe.frames.html">apache_beam.dataframe.frames module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.dataframe.io.html">apache_beam.dataframe.io module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.dataframe.pandas_top_level_functions.html">apache_beam.dataframe.pandas_top_level_functions module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.dataframe.partitionings.html">apache_beam.dataframe.partitionings module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.dataframe.schemas.html">apache_beam.dataframe.schemas module</a></li> |
| <li class="toctree-l3 current"><a class="current reference internal" href="#">apache_beam.dataframe.transforms module</a></li> |
| </ul> |
| </li> |
| </ul> |
| </li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.io.html">apache_beam.io package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.metrics.html">apache_beam.metrics package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.ml.html">apache_beam.ml package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.options.html">apache_beam.options package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.portability.html">apache_beam.portability package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.runners.html">apache_beam.runners package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.transforms.html">apache_beam.transforms package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.typehints.html">apache_beam.typehints package</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.utils.html">apache_beam.utils package</a></li> |
| </ul> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.error.html">apache_beam.error module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.pipeline.html">apache_beam.pipeline module</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="apache_beam.pvalue.html">apache_beam.pvalue module</a></li> |
| </ul> |
| |
| |
| |
| </div> |
| </div> |
| </nav> |
| |
| <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap"> |
| |
| |
| <nav class="wy-nav-top" aria-label="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="index.html">Apache Beam</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="index.html">Docs</a> »</li> |
| |
| <li><a href="apache_beam.dataframe.html">apache_beam.dataframe package</a> »</li> |
| |
| <li>apache_beam.dataframe.transforms module</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| |
| <a href="_sources/apache_beam.dataframe.transforms.rst.txt" rel="nofollow"> View page source</a> |
| |
| |
| </li> |
| |
| </ul> |
| |
| |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <div class="section" id="module-apache_beam.dataframe.transforms"> |
| <span id="apache-beam-dataframe-transforms-module"></span><h1>apache_beam.dataframe.transforms module<a class="headerlink" href="#module-apache_beam.dataframe.transforms" title="Permalink to this headline">¶</a></h1> |
| <dl class="class"> |
| <dt id="apache_beam.dataframe.transforms.DataframeTransform"> |
| <em class="property">class </em><code class="descclassname">apache_beam.dataframe.transforms.</code><code class="descname">DataframeTransform</code><span class="sig-paren">(</span><em>func</em>, <em>proxy=None</em>, <em>yield_elements='schemas'</em>, <em>include_indexes=False</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/dataframe/transforms.html#DataframeTransform"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.dataframe.transforms.DataframeTransform" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Bases: <a class="reference internal" href="apache_beam.transforms.ptransform.html#apache_beam.transforms.ptransform.PTransform" title="apache_beam.transforms.ptransform.PTransform"><code class="xref py py-class docutils literal notranslate"><span class="pre">apache_beam.transforms.ptransform.PTransform</span></code></a></p> |
| <p>A PTransform for applying function that takes and returns dataframes |
| to one or more PCollections.</p> |
| <p><a class="reference internal" href="#apache_beam.dataframe.transforms.DataframeTransform" title="apache_beam.dataframe.transforms.DataframeTransform"><code class="xref py py-class docutils literal notranslate"><span class="pre">DataframeTransform</span></code></a> will accept a PCollection with a <a class="reference external" href="https://beam.apache.org/documentation/programming-guide/#what-is-a-schema">schema</a> and |
| batch it into <a class="reference external" href="https://pandas.pydata.org/pandas-docs/dev/reference/api/pandas.DataFrame.html#pandas.DataFrame" title="(in pandas v1.4.0.dev0+828.g0eeda64521)"><code class="xref py py-class docutils literal notranslate"><span class="pre">DataFrame</span></code></a> instances if necessary:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="p">(</span><span class="n">pcoll</span> <span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">Select</span><span class="p">(</span><span class="n">key</span><span class="o">=...</span><span class="p">,</span> <span class="n">foo</span><span class="o">=...</span><span class="p">,</span> <span class="n">bar</span><span class="o">=...</span><span class="p">)</span> |
| <span class="o">|</span> <span class="n">DataframeTransform</span><span class="p">(</span><span class="k">lambda</span> <span class="n">df</span><span class="p">:</span> <span class="n">df</span><span class="o">.</span><span class="n">group_by</span><span class="p">(</span><span class="s1">'key'</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">()))</span> |
| </pre></div> |
| </div> |
| <p>It is also possible to process a PCollection of <a class="reference external" href="https://pandas.pydata.org/pandas-docs/dev/reference/api/pandas.DataFrame.html#pandas.DataFrame" title="(in pandas v1.4.0.dev0+828.g0eeda64521)"><code class="xref py py-class docutils literal notranslate"><span class="pre">DataFrame</span></code></a> |
| instances directly, in this case a “proxy” must be provided. For example, if |
| <code class="docutils literal notranslate"><span class="pre">pcoll</span></code> is a PCollection of DataFrames, one could write:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">pcoll</span> <span class="o">|</span> <span class="n">DataframeTransform</span><span class="p">(</span><span class="k">lambda</span> <span class="n">df</span><span class="p">:</span> <span class="n">df</span><span class="o">.</span><span class="n">group_by</span><span class="p">(</span><span class="s1">'key'</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">(),</span> <span class="n">proxy</span><span class="o">=...</span><span class="p">)</span> |
| </pre></div> |
| </div> |
| <p>To pass multiple PCollections, pass a tuple of PCollections wich will be |
| passed to the callable as positional arguments, or a dictionary of |
| PCollections, in which case they will be passed as keyword arguments.</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name" /> |
| <col class="field-body" /> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>yield_elements</strong> – (optional, default: “schemas”) If set to <code class="docutils literal notranslate"><span class="pre">"pandas"</span></code>, |
| return PCollection(s) containing the raw Pandas objects |
| (<a class="reference external" href="https://pandas.pydata.org/pandas-docs/dev/reference/api/pandas.DataFrame.html#pandas.DataFrame" title="(in pandas v1.4.0.dev0+828.g0eeda64521)"><code class="xref py py-class docutils literal notranslate"><span class="pre">DataFrame</span></code></a> or <a class="reference external" href="https://pandas.pydata.org/pandas-docs/dev/reference/api/pandas.Series.html#pandas.Series" title="(in pandas v1.4.0.dev0+828.g0eeda64521)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Series</span></code></a> as appropriate). |
| If set to <code class="docutils literal notranslate"><span class="pre">"schemas"</span></code>, return an element-wise PCollection, where |
| DataFrame and Series instances are expanded to one element per row. |
| DataFrames are converted to <a class="reference external" href="https://beam.apache.org/documentation/programming-guide/#what-is-a-schema">schema-aware</a> PCollections, where column |
| values can be accessed by attribute.</li> |
| <li><strong>include_indexes</strong> – (optional, default: False) When |
| <code class="docutils literal notranslate"><span class="pre">yield_elements="schemas"</span></code>, if <code class="docutils literal notranslate"><span class="pre">include_indexes=True</span></code>, attempt to |
| include index columns in the output schema for expanded DataFrames. |
| Raises an error if any of the index levels are unnamed (name=None), or if |
| any of the names are not unique among all column and index names.</li> |
| <li><strong>proxy</strong> – (optional) An empty <a class="reference external" href="https://pandas.pydata.org/pandas-docs/dev/reference/api/pandas.DataFrame.html#pandas.DataFrame" title="(in pandas v1.4.0.dev0+828.g0eeda64521)"><code class="xref py py-class docutils literal notranslate"><span class="pre">DataFrame</span></code></a> or |
| <a class="reference external" href="https://pandas.pydata.org/pandas-docs/dev/reference/api/pandas.Series.html#pandas.Series" title="(in pandas v1.4.0.dev0+828.g0eeda64521)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Series</span></code></a> instance with the same <code class="docutils literal notranslate"><span class="pre">dtype</span></code> and <code class="docutils literal notranslate"><span class="pre">name</span></code> |
| as the elements of the input PCollection. Required when input |
| PCollection <a class="reference external" href="https://pandas.pydata.org/pandas-docs/dev/reference/api/pandas.DataFrame.html#pandas.DataFrame" title="(in pandas v1.4.0.dev0+828.g0eeda64521)"><code class="xref py py-class docutils literal notranslate"><span class="pre">DataFrame</span></code></a> or <a class="reference external" href="https://pandas.pydata.org/pandas-docs/dev/reference/api/pandas.Series.html#pandas.Series" title="(in pandas v1.4.0.dev0+828.g0eeda64521)"><code class="xref py py-class docutils literal notranslate"><span class="pre">Series</span></code></a> |
| elements. Ignored when input PCollection has a <a class="reference external" href="https://beam.apache.org/documentation/programming-guide/#what-is-a-schema">schema</a>.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="apache_beam.dataframe.transforms.DataframeTransform.expand"> |
| <code class="descname">expand</code><span class="sig-paren">(</span><em>input_pcolls</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/dataframe/transforms.html#DataframeTransform.expand"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.dataframe.transforms.DataframeTransform.expand" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| </div> |
| |
| |
| </div> |
| |
| </div> |
| <footer> |
| |
| <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> |
| |
| <a href="apache_beam.io.html" class="btn btn-neutral float-right" title="apache_beam.io package" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a> |
| |
| |
| <a href="apache_beam.dataframe.schemas.html" class="btn btn-neutral float-left" title="apache_beam.dataframe.schemas module" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a> |
| |
| </div> |
| |
| |
| <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> |