| |
| |
| <!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.schemas 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.dataframe.transforms module" href="apache_beam.dataframe.transforms.html" /> |
| <link rel="prev" title="apache_beam.dataframe.partitionings module" href="apache_beam.dataframe.partitionings.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 current"><a class="current reference internal" href="#">apache_beam.dataframe.schemas module</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.dataframe.transforms.html">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.schemas module</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| |
| <a href="_sources/apache_beam.dataframe.schemas.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.schemas"> |
| <span id="apache-beam-dataframe-schemas-module"></span><h1>apache_beam.dataframe.schemas module<a class="headerlink" href="#module-apache_beam.dataframe.schemas" title="Permalink to this headline">¶</a></h1> |
| <p>Utilities for relating schema-aware PCollections and dataframe transforms.</p> |
| <p>Imposes a mapping between native Python typings (specifically those compatible |
| with <a class="reference internal" href="apache_beam.typehints.schemas.html#module-apache_beam.typehints.schemas" title="apache_beam.typehints.schemas"><code class="xref py py-mod docutils literal notranslate"><span class="pre">apache_beam.typehints.schemas</span></code></a>), and common pandas dtypes:</p> |
| <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="n">pandas</span> <span class="n">dtype</span> <span class="n">Python</span> <span class="n">typing</span> |
| <span class="n">np</span><span class="o">.</span><span class="n">int</span><span class="p">{</span><span class="mi">8</span><span class="p">,</span><span class="mi">16</span><span class="p">,</span><span class="mi">32</span><span class="p">,</span><span class="mi">64</span><span class="p">}</span> <span class="o"><-----></span> <span class="n">np</span><span class="o">.</span><span class="n">int</span><span class="p">{</span><span class="mi">8</span><span class="p">,</span><span class="mi">16</span><span class="p">,</span><span class="mi">32</span><span class="p">,</span><span class="mi">64</span><span class="p">}</span><span class="o">*</span> |
| <span class="n">pd</span><span class="o">.</span><span class="n">Int</span><span class="p">{</span><span class="mi">8</span><span class="p">,</span><span class="mi">16</span><span class="p">,</span><span class="mi">32</span><span class="p">,</span><span class="mi">64</span><span class="p">}</span><span class="n">Dtype</span> <span class="o"><-----></span> <span class="n">Optional</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">int</span><span class="p">{</span><span class="mi">8</span><span class="p">,</span><span class="mi">16</span><span class="p">,</span><span class="mi">32</span><span class="p">,</span><span class="mi">64</span><span class="p">}]</span><span class="o">*</span> |
| <span class="n">np</span><span class="o">.</span><span class="n">float</span><span class="p">{</span><span class="mi">32</span><span class="p">,</span><span class="mi">64</span><span class="p">}</span> <span class="o"><-----></span> <span class="n">Optional</span><span class="p">[</span><span class="n">np</span><span class="o">.</span><span class="n">float</span><span class="p">{</span><span class="mi">32</span><span class="p">,</span><span class="mi">64</span><span class="p">}]</span> |
| \<span class="o">---</span> <span class="n">np</span><span class="o">.</span><span class="n">float</span><span class="p">{</span><span class="mi">32</span><span class="p">,</span><span class="mi">64</span><span class="p">}</span> |
| <span class="n">Not</span> <span class="n">supported</span> <span class="o"><------</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">bytes</span><span class="p">]</span> |
| <span class="n">np</span><span class="o">.</span><span class="n">bool</span> <span class="o"><-----></span> <span class="n">np</span><span class="o">.</span><span class="n">bool</span> |
| <span class="n">np</span><span class="o">.</span><span class="n">dtype</span><span class="p">(</span><span class="s1">'S'</span><span class="p">)</span> <span class="o"><-----></span> <span class="nb">bytes</span> |
| <span class="n">pd</span><span class="o">.</span><span class="n">BooleanDType</span><span class="p">()</span> <span class="o"><-----></span> <span class="n">Optional</span><span class="p">[</span><span class="nb">bool</span><span class="p">]</span> |
| <span class="n">pd</span><span class="o">.</span><span class="n">StringDType</span><span class="p">()</span> <span class="o"><-----></span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> |
| \<span class="o">---</span> <span class="nb">str</span> |
| <span class="n">np</span><span class="o">.</span><span class="n">object</span> <span class="o"><-----></span> <span class="n">Any</span> |
| |
| <span class="o">*</span> <span class="nb">int</span><span class="p">,</span> <span class="nb">float</span><span class="p">,</span> <span class="nb">bool</span> <span class="n">are</span> <span class="n">treated</span> <span class="n">the</span> <span class="n">same</span> <span class="k">as</span> <span class="n">np</span><span class="o">.</span><span class="n">int64</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span><span class="p">,</span> <span class="n">np</span><span class="o">.</span><span class="n">bool</span> |
| </pre></div> |
| </div> |
| <p>Note that when converting to pandas dtypes, any types not specified here are |
| shunted to <code class="docutils literal notranslate"><span class="pre">np.object</span></code>.</p> |
| <p>Similarly when converting from pandas to Python types, types that aren’t |
| otherwise specified here are shunted to <code class="docutils literal notranslate"><span class="pre">Any</span></code>. Notably, this includes |
| <code class="docutils literal notranslate"><span class="pre">np.datetime64</span></code>.</p> |
| <p>Pandas does not support hierarchical data natively. Currently, all structured |
| types (<code class="docutils literal notranslate"><span class="pre">Sequence</span></code>, <code class="docutils literal notranslate"><span class="pre">Mapping</span></code>, nested <code class="docutils literal notranslate"><span class="pre">NamedTuple</span></code> types), are |
| shunted to <code class="docutils literal notranslate"><span class="pre">np.object</span></code> like all other unknown types. In the future these |
| types may be given special consideration.</p> |
| <dl class="class"> |
| <dt id="apache_beam.dataframe.schemas.BatchRowsAsDataFrame"> |
| <em class="property">class </em><code class="descclassname">apache_beam.dataframe.schemas.</code><code class="descname">BatchRowsAsDataFrame</code><span class="sig-paren">(</span><em>*args</em>, <em>proxy=None</em>, <em>**kwargs</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/dataframe/schemas.html#BatchRowsAsDataFrame"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.dataframe.schemas.BatchRowsAsDataFrame" 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 transform that batches schema-aware PCollection elements into DataFrames</p> |
| <p>Batching parameters are inherited from |
| <a class="reference internal" href="apache_beam.transforms.util.html#apache_beam.transforms.util.BatchElements" title="apache_beam.transforms.util.BatchElements"><code class="xref py py-class docutils literal notranslate"><span class="pre">BatchElements</span></code></a>.</p> |
| <dl class="method"> |
| <dt id="apache_beam.dataframe.schemas.BatchRowsAsDataFrame.expand"> |
| <code class="descname">expand</code><span class="sig-paren">(</span><em>pcoll</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/dataframe/schemas.html#BatchRowsAsDataFrame.expand"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.dataframe.schemas.BatchRowsAsDataFrame.expand" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="apache_beam.dataframe.schemas.generate_proxy"> |
| <code class="descclassname">apache_beam.dataframe.schemas.</code><code class="descname">generate_proxy</code><span class="sig-paren">(</span><em>element_type</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/dataframe/schemas.html#generate_proxy"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.dataframe.schemas.generate_proxy" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Generate a proxy pandas object for the given PCollection element_type.</p> |
| <p>Currently only supports generating a DataFrame proxy from a schema-aware |
| PCollection or a Series proxy from a primitively typed PCollection.</p> |
| </dd></dl> |
| |
| <dl class="function"> |
| <dt id="apache_beam.dataframe.schemas.element_type_from_dataframe"> |
| <code class="descclassname">apache_beam.dataframe.schemas.</code><code class="descname">element_type_from_dataframe</code><span class="sig-paren">(</span><em>proxy</em>, <em>include_indexes=False</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/dataframe/schemas.html#element_type_from_dataframe"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.dataframe.schemas.element_type_from_dataframe" title="Permalink to this definition">¶</a></dt> |
| <dd><p>Generate an element_type for an element-wise PCollection from a proxy |
| pandas object. Currently only supports converting the element_type for |
| a schema-aware PCollection to a proxy DataFrame.</p> |
| <p>Currently only supports generating a DataFrame proxy from a schema-aware |
| PCollection.</p> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.dataframe.schemas.UnbatchPandas"> |
| <em class="property">class </em><code class="descclassname">apache_beam.dataframe.schemas.</code><code class="descname">UnbatchPandas</code><span class="sig-paren">(</span><em>proxy</em>, <em>include_indexes=False</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/dataframe/schemas.html#UnbatchPandas"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.dataframe.schemas.UnbatchPandas" 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 transform that explodes a PCollection of DataFrame or Series. DataFrame |
| is converterd to a schema-aware PCollection, while Series is converted to its |
| underlying type.</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"><strong>include_indexes</strong> – (optional, default: False) When unbatching a DataFrame |
| if include_indexes=True, 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.</td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="apache_beam.dataframe.schemas.UnbatchPandas.expand"> |
| <code class="descname">expand</code><span class="sig-paren">(</span><em>pcoll</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/dataframe/schemas.html#UnbatchPandas.expand"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.dataframe.schemas.UnbatchPandas.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.dataframe.transforms.html" class="btn btn-neutral float-right" title="apache_beam.dataframe.transforms module" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a> |
| |
| |
| <a href="apache_beam.dataframe.partitionings.html" class="btn btn-neutral float-left" title="apache_beam.dataframe.partitionings 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> |