Google Git
Sign in
apache / beam-site / refs/heads/revert-643-revert-642-updates_release_2.47.0 / . / pydoc / 2.47.0 / _modules / apache_beam / dataframe / convert.html
blob: 44b4245ab8709c834541ffe9d387de0c0a5a4472 [file] [log] [blame]
<!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.convert &mdash; 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> &raquo;</li>
<li><a href="../../index.html">Module code</a> &raquo;</li>
<li>apache_beam.dataframe.convert</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.convert</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 &quot;License&quot;); 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 &quot;AS IS&quot; 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">inspect</span>
<span class="kn">import</span> <span class="nn">warnings</span>
<span class="kn">import</span> <span class="nn">weakref</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">TYPE_CHECKING</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">Dict</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Iterable</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Tuple</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">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">import</span> <span class="nn">apache_beam</span> <span class="k">as</span> <span class="nn">beam</span>
<span class="kn">from</span> <span class="nn">apache_beam</span> <span class="kn">import</span> <span class="n">pvalue</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">frame_base</span>
<span class="kn">from</span> <span class="nn">apache_beam.dataframe</span> <span class="kn">import</span> <span class="n">transforms</span>
<span class="kn">from</span> <span class="nn">apache_beam.dataframe.schemas</span> <span class="kn">import</span> <span class="n">element_typehint_from_dataframe_proxy</span>
<span class="kn">from</span> <span class="nn">apache_beam.dataframe.schemas</span> <span class="kn">import</span> <span class="n">generate_proxy</span>
<span class="kn">from</span> <span class="nn">apache_beam.typehints.pandas_type_compatibility</span> <span class="kn">import</span> <span class="n">dtype_to_fieldtype</span>
<span class="k">if</span> <span class="n">TYPE_CHECKING</span><span class="p">:</span>
<span class="c1"># pylint: disable=ungrouped-imports</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Optional</span>
<span class="c1"># TODO: Or should this be called as_dataframe?</span>
<div class="viewcode-block" id="to_dataframe"><a class="viewcode-back" href="../../../apache_beam.dataframe.convert.html#apache_beam.dataframe.convert.to_dataframe">[docs]</a><span class="k">def</span> <span class="nf">to_dataframe</span><span class="p">(</span>
<span class="n">pcoll</span><span class="p">,</span> <span class="c1"># type: pvalue.PCollection</span>
<span class="n">proxy</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="c1"># type: Optional[pd.core.generic.NDFrame]</span>
<span class="n">label</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="c1"># type: Optional[str]</span>
<span class="p">):</span>
<span class="c1"># type: (...) -&gt; frame_base.DeferredFrame</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Converts a PCollection to a deferred dataframe-like object, which can</span>
<span class="sd"> manipulated with pandas methods like `filter` and `groupby`.</span>
<span class="sd"> For example, one might write::</span>
<span class="sd"> pcoll = ...</span>
<span class="sd"> df = to_dataframe(pcoll, proxy=...)</span>
<span class="sd"> result = df.groupby(&#39;col&#39;).sum()</span>
<span class="sd"> pcoll_result = to_pcollection(result)</span>
<span class="sd"> A proxy object must be given if the schema for the PCollection is not known.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">proxy</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">if</span> <span class="n">pcoll</span><span class="o">.</span><span class="n">element_type</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">&quot;Cannot infer a proxy because the input PCollection does not have a &quot;</span>
<span class="s2">&quot;schema defined. Please make sure a schema type is specified for &quot;</span>
<span class="s2">&quot;the input PCollection, or provide a proxy.&quot;</span><span class="p">)</span>
<span class="c1"># If no proxy is given, assume this is an element-wise schema-aware</span>
<span class="c1"># PCollection that needs to be batched.</span>
<span class="k">if</span> <span class="n">label</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="c1"># Attempt to come up with a reasonable, stable label by retrieving</span>
<span class="c1"># the name of these variables in the calling context.</span>
<span class="n">label</span> <span class="o">=</span> <span class="s1">&#39;BatchElements(</span><span class="si">%s</span><span class="s1">)&#39;</span> <span class="o">%</span> <span class="n">_var_name</span><span class="p">(</span><span class="n">pcoll</span><span class="p">,</span> <span class="mi">2</span><span class="p">)</span>
<span class="n">proxy</span> <span class="o">=</span> <span class="n">generate_proxy</span><span class="p">(</span><span class="n">pcoll</span><span class="o">.</span><span class="n">element_type</span><span class="p">)</span>
<span class="n">shim_dofn</span><span class="p">:</span> <span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">proxy</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">shim_dofn</span> <span class="o">=</span> <span class="n">RowsToDataFrameFn</span><span class="p">()</span>
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">proxy</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="n">shim_dofn</span> <span class="o">=</span> <span class="n">ElementsToSeriesFn</span><span class="p">()</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">AssertionError</span><span class="p">(</span><span class="s2">&quot;Unknown proxy type: </span><span class="si">%s</span><span class="s2">&quot;</span> <span class="o">%</span> <span class="n">proxy</span><span class="p">)</span>
<span class="n">pcoll</span> <span class="o">=</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">label</span> <span class="o">&gt;&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">ParDo</span><span class="p">(</span><span class="n">shim_dofn</span><span class="p">)</span>
<span class="k">return</span> <span class="n">frame_base</span><span class="o">.</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">PlaceholderExpression</span><span class="p">(</span><span class="n">proxy</span><span class="p">,</span> <span class="n">pcoll</span><span class="p">))</span></div>
<span class="c1"># PCollections generated by to_pcollection are memoized, keyed by expression id.</span>
<span class="c1"># WeakValueDictionary is used so the caches are cleaned up with the parent</span>
<span class="c1"># pipelines</span>
<span class="c1"># Note that the pipeline (indirectly) holds references to the transforms which</span>
<span class="c1"># keeps both the PCollections and expressions alive. This ensures the</span>
<span class="c1"># expression&#39;s ids are never accidentally re-used.</span>
<span class="n">TO_PCOLLECTION_CACHE</span> <span class="o">=</span> <span class="n">weakref</span><span class="o">.</span><span class="n">WeakValueDictionary</span><span class="p">(</span>
<span class="p">)</span> <span class="c1"># type: weakref.WeakValueDictionary[str, pvalue.PCollection]</span>
<span class="n">UNBATCHED_CACHE</span> <span class="o">=</span> <span class="n">weakref</span><span class="o">.</span><span class="n">WeakValueDictionary</span><span class="p">(</span>
<span class="p">)</span> <span class="c1"># type: weakref.WeakValueDictionary[str, pvalue.PCollection]</span>
<div class="viewcode-block" id="RowsToDataFrameFn"><a class="viewcode-back" href="../../../apache_beam.dataframe.convert.html#apache_beam.dataframe.convert.RowsToDataFrameFn">[docs]</a><span class="k">class</span> <span class="nc">RowsToDataFrameFn</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="p">):</span>
<div class="viewcode-block" id="RowsToDataFrameFn.process_batch"><a class="viewcode-back" href="../../../apache_beam.dataframe.convert.html#apache_beam.dataframe.convert.RowsToDataFrameFn.process_batch">[docs]</a> <span class="nd">@beam</span><span class="o">.</span><span class="n">DoFn</span><span class="o">.</span><span class="n">yields_elements</span>
<span class="k">def</span> <span class="nf">process_batch</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch</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="o">-&gt;</span> <span class="n">Iterable</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="k">yield</span> <span class="n">batch</span></div></div>
<div class="viewcode-block" id="ElementsToSeriesFn"><a class="viewcode-back" href="../../../apache_beam.dataframe.convert.html#apache_beam.dataframe.convert.ElementsToSeriesFn">[docs]</a><span class="k">class</span> <span class="nc">ElementsToSeriesFn</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="p">):</span>
<div class="viewcode-block" id="ElementsToSeriesFn.process_batch"><a class="viewcode-back" href="../../../apache_beam.dataframe.convert.html#apache_beam.dataframe.convert.ElementsToSeriesFn.process_batch">[docs]</a> <span class="nd">@beam</span><span class="o">.</span><span class="n">DoFn</span><span class="o">.</span><span class="n">yields_elements</span>
<span class="k">def</span> <span class="nf">process_batch</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch</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="o">-&gt;</span> <span class="n">Iterable</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">yield</span> <span class="n">batch</span></div></div>
<span class="k">def</span> <span class="nf">_make_unbatched_pcoll</span><span class="p">(</span>
<span class="n">pc</span><span class="p">:</span> <span class="n">pvalue</span><span class="o">.</span><span class="n">PCollection</span><span class="p">,</span> <span class="n">expr</span><span class="p">:</span> <span class="n">expressions</span><span class="o">.</span><span class="n">Expression</span><span class="p">,</span>
<span class="n">include_indexes</span><span class="p">:</span> <span class="nb">bool</span><span class="p">):</span>
<span class="n">label</span> <span class="o">=</span> <span class="sa">f</span><span class="s2">&quot;Unbatch &#39;</span><span class="si">{</span><span class="n">expr</span><span class="o">.</span><span class="n">_id</span><span class="si">}</span><span class="s2">&#39;&quot;</span>
<span class="k">if</span> <span class="n">include_indexes</span><span class="p">:</span>
<span class="n">label</span> <span class="o">+=</span> <span class="s2">&quot; with indexes&quot;</span>
<span class="k">if</span> <span class="n">label</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">UNBATCHED_CACHE</span><span class="p">:</span>
<span class="n">proxy</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="n">shim_dofn</span><span class="p">:</span> <span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">proxy</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">shim_dofn</span> <span class="o">=</span> <span class="n">DataFrameToRowsFn</span><span class="p">(</span><span class="n">proxy</span><span class="p">,</span> <span class="n">include_indexes</span><span class="p">)</span>
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">proxy</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">if</span> <span class="n">include_indexes</span><span class="p">:</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span>
<span class="s2">&quot;Pipeline is converting a DeferredSeries to PCollection &quot;</span>
<span class="s2">&quot;with include_indexes=True. Note that this parameter is &quot;</span>
<span class="s2">&quot;_not_ respected for DeferredSeries conversion. To &quot;</span>
<span class="s2">&quot;include the index with your data, produce a&quot;</span>
<span class="s2">&quot;DeferredDataFrame instead.&quot;</span><span class="p">)</span>
<span class="n">shim_dofn</span> <span class="o">=</span> <span class="n">SeriesToElementsFn</span><span class="p">(</span><span class="n">proxy</span><span class="p">)</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="sa">f</span><span class="s2">&quot;Proxy &#39;</span><span class="si">{</span><span class="n">proxy</span><span class="si">}</span><span class="s2">&#39; has unsupported type &#39;</span><span class="si">{</span><span class="nb">type</span><span class="p">(</span><span class="n">proxy</span><span class="p">)</span><span class="si">}</span><span class="s2">&#39;&quot;</span><span class="p">)</span>
<span class="n">UNBATCHED_CACHE</span><span class="p">[</span><span class="n">label</span><span class="p">]</span> <span class="o">=</span> <span class="n">pc</span> <span class="o">|</span> <span class="n">label</span> <span class="o">&gt;&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">ParDo</span><span class="p">(</span><span class="n">shim_dofn</span><span class="p">)</span>
<span class="c1"># Note unbatched cache is keyed by the expression id as well as parameters</span>
<span class="c1"># for the unbatching (i.e. include_indexes)</span>
<span class="k">return</span> <span class="n">UNBATCHED_CACHE</span><span class="p">[</span><span class="n">label</span><span class="p">]</span>
<div class="viewcode-block" id="DataFrameToRowsFn"><a class="viewcode-back" href="../../../apache_beam.dataframe.convert.html#apache_beam.dataframe.convert.DataFrameToRowsFn">[docs]</a><span class="k">class</span> <span class="nc">DataFrameToRowsFn</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="p">):</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">proxy</span><span class="p">,</span> <span class="n">include_indexes</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_proxy</span> <span class="o">=</span> <span class="n">proxy</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_include_indexes</span> <span class="o">=</span> <span class="n">include_indexes</span>
<div class="viewcode-block" id="DataFrameToRowsFn.process"><a class="viewcode-back" href="../../../apache_beam.dataframe.convert.html#apache_beam.dataframe.convert.DataFrameToRowsFn.process">[docs]</a> <span class="nd">@beam</span><span class="o">.</span><span class="n">DoFn</span><span class="o">.</span><span class="n">yields_batches</span>
<span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">element</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="o">-&gt;</span> <span class="n">Iterable</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="k">yield</span> <span class="n">element</span></div>
<div class="viewcode-block" id="DataFrameToRowsFn.infer_output_type"><a class="viewcode-back" href="../../../apache_beam.dataframe.convert.html#apache_beam.dataframe.convert.DataFrameToRowsFn.infer_output_type">[docs]</a> <span class="k">def</span> <span class="nf">infer_output_type</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_element_type</span><span class="p">):</span>
<span class="k">return</span> <span class="n">element_typehint_from_dataframe_proxy</span><span class="p">(</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_proxy</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_include_indexes</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="SeriesToElementsFn"><a class="viewcode-back" href="../../../apache_beam.dataframe.convert.html#apache_beam.dataframe.convert.SeriesToElementsFn">[docs]</a><span class="k">class</span> <span class="nc">SeriesToElementsFn</span><span class="p">(</span><span class="n">beam</span><span class="o">.</span><span class="n">DoFn</span><span class="p">):</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">proxy</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_proxy</span> <span class="o">=</span> <span class="n">proxy</span>
<div class="viewcode-block" id="SeriesToElementsFn.process"><a class="viewcode-back" href="../../../apache_beam.dataframe.convert.html#apache_beam.dataframe.convert.SeriesToElementsFn.process">[docs]</a> <span class="nd">@beam</span><span class="o">.</span><span class="n">DoFn</span><span class="o">.</span><span class="n">yields_batches</span>
<span class="k">def</span> <span class="nf">process</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">element</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="o">-&gt;</span> <span class="n">Iterable</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">yield</span> <span class="n">element</span></div>
<div class="viewcode-block" id="SeriesToElementsFn.infer_output_type"><a class="viewcode-back" href="../../../apache_beam.dataframe.convert.html#apache_beam.dataframe.convert.SeriesToElementsFn.infer_output_type">[docs]</a> <span class="k">def</span> <span class="nf">infer_output_type</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">input_element_type</span><span class="p">):</span>
<span class="k">return</span> <span class="n">dtype_to_fieldtype</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_proxy</span><span class="o">.</span><span class="n">dtype</span><span class="p">)</span></div></div>
<span class="c1"># TODO: Or should this be called from_dataframe?</span>
<div class="viewcode-block" id="to_pcollection"><a class="viewcode-back" href="../../../apache_beam.dataframe.convert.html#apache_beam.dataframe.convert.to_pcollection">[docs]</a><span class="k">def</span> <span class="nf">to_pcollection</span><span class="p">(</span>
<span class="o">*</span><span class="n">dataframes</span><span class="p">,</span> <span class="c1"># type: Union[frame_base.DeferredFrame, pd.DataFrame, pd.Series]</span>
<span class="n">label</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">always_return_tuple</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">yield_elements</span><span class="o">=</span><span class="s1">&#39;schemas&#39;</span><span class="p">,</span>
<span class="n">include_indexes</span><span class="o">=</span><span class="kc">False</span><span class="p">,</span>
<span class="n">pipeline</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Union</span><span class="p">[</span><span class="n">pvalue</span><span class="o">.</span><span class="n">PCollection</span><span class="p">,</span> <span class="n">Tuple</span><span class="p">[</span><span class="n">pvalue</span><span class="o">.</span><span class="n">PCollection</span><span class="p">,</span> <span class="o">...</span><span class="p">]]:</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Converts one or more deferred dataframe-like objects back to a PCollection.</span>
<span class="sd"> This method creates and applies the actual Beam operations that compute</span>
<span class="sd"> the given deferred dataframes, returning a PCollection of their results. By</span>
<span class="sd"> default the resulting PCollections are schema-aware PCollections where each</span>
<span class="sd"> element is one row from the output dataframes, excluding indexes. This</span>
<span class="sd"> behavior can be modified with the `yield_elements` and `include_indexes`</span>
<span class="sd"> arguments.</span>
<span class="sd"> Also accepts non-deferred pandas dataframes, which are converted to deferred,</span>
<span class="sd"> schema&#39;d PCollections. In this case the contents of the entire dataframe are</span>
<span class="sd"> serialized into the graph, so for large amounts of data it is preferable to</span>
<span class="sd"> write them to disk and read them with one of the read methods.</span>
<span class="sd"> If more than one (related) result is desired, it can be more efficient to</span>
<span class="sd"> pass them all at the same time to this method.</span>
<span class="sd"> Args:</span>
<span class="sd"> label: (optional, default &quot;ToPCollection(...)&quot;&quot;) the label to use for the</span>
<span class="sd"> conversion transform.</span>
<span class="sd"> always_return_tuple: (optional, default: False) If true, always return</span>
<span class="sd"> a tuple of PCollections, even if there&#39;s only one output.</span>
<span class="sd"> yield_elements: (optional, default: &quot;schemas&quot;) If set to &quot;pandas&quot;, return</span>
<span class="sd"> PCollections containing the raw Pandas objects (DataFrames or Series),</span>
<span class="sd"> if set to &quot;schemas&quot;, return an element-wise PCollection, where DataFrame</span>
<span class="sd"> and Series instances are expanded to one element per row. DataFrames are</span>
<span class="sd"> converted to schema-aware PCollections, where column values can be</span>
<span class="sd"> accessed by attribute.</span>
<span class="sd"> include_indexes: (optional, default: False) When yield_elements=&quot;schemas&quot;,</span>
<span class="sd"> if include_indexes=True, attempt to include index columns in the output</span>
<span class="sd"> schema for expanded DataFrames. Raises an error if any of the index</span>
<span class="sd"> levels are unnamed (name=None), or if any of the names are not unique</span>
<span class="sd"> among all column and index names.</span>
<span class="sd"> pipeline: (optional, unless non-deferred dataframes are passed) Used when</span>
<span class="sd"> creating a PCollection from a non-deferred dataframe.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">yield_elements</span> <span class="ow">in</span> <span class="p">(</span><span class="s2">&quot;pandas&quot;</span><span class="p">,</span> <span class="s2">&quot;schemas&quot;</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span>
<span class="s2">&quot;Invalid value for yield_elements argument, &#39;</span><span class="si">%s</span><span class="s2">&#39;. &quot;</span>
<span class="s2">&quot;Allowed values are &#39;pandas&#39; and &#39;schemas&#39;&quot;</span> <span class="o">%</span> <span class="n">yield_elements</span><span class="p">)</span>
<span class="k">if</span> <span class="n">label</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="c1"># Attempt to come up with a reasonable, stable label by retrieving the name</span>
<span class="c1"># of these variables in the calling context.</span>
<span class="n">label</span> <span class="o">=</span> <span class="s1">&#39;ToPCollection(</span><span class="si">%s</span><span class="s1">)&#39;</span> <span class="o">%</span> <span class="s1">&#39;, &#39;</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">_var_name</span><span class="p">(</span><span class="n">e</span><span class="p">,</span> <span class="mi">3</span><span class="p">)</span> <span class="k">for</span> <span class="n">e</span> <span class="ow">in</span> <span class="n">dataframes</span><span class="p">)</span>
<span class="c1"># Support for non-deferred dataframes.</span>
<span class="n">deferred_dataframes</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">ix</span><span class="p">,</span> <span class="n">df</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">dataframes</span><span class="p">):</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">df</span><span class="p">,</span> <span class="n">frame_base</span><span class="o">.</span><span class="n">DeferredBase</span><span class="p">):</span>
<span class="c1"># TODO(robertwb): Maybe extract pipeline object?</span>
<span class="n">deferred_dataframes</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">df</span><span class="p">)</span>
<span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">df</span><span class="p">,</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="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">)):</span>
<span class="k">if</span> <span class="n">pipeline</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="s1">&#39;Pipeline keyword required for non-deferred dataframe conversion.&#39;</span><span class="p">)</span>
<span class="n">deferred</span> <span class="o">=</span> <span class="n">pipeline</span> <span class="o">|</span> <span class="s1">&#39;</span><span class="si">%s</span><span class="s1">_Defer</span><span class="si">%s</span><span class="s1">&#39;</span> <span class="o">%</span> <span class="p">(</span><span class="n">label</span><span class="p">,</span> <span class="n">ix</span><span class="p">)</span> <span class="o">&gt;&gt;</span> <span class="n">beam</span><span class="o">.</span><span class="n">Create</span><span class="p">([</span><span class="n">df</span><span class="p">])</span>
<span class="n">deferred_dataframes</span><span class="o">.</span><span class="n">append</span><span class="p">(</span>
<span class="n">frame_base</span><span class="o">.</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">PlaceholderExpression</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">iloc</span><span class="p">[:</span><span class="mi">0</span><span class="p">],</span> <span class="n">deferred</span><span class="p">)))</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="s1">&#39;Unable to convert objects of type </span><span class="si">%s</span><span class="s1"> to a PCollection&#39;</span> <span class="o">%</span> <span class="nb">type</span><span class="p">(</span><span class="n">df</span><span class="p">))</span>
<span class="n">dataframes</span> <span class="o">=</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">deferred_dataframes</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">extract_input</span><span class="p">(</span><span class="n">placeholder</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">placeholder</span><span class="o">.</span><span class="n">_reference</span><span class="p">,</span> <span class="n">pvalue</span><span class="o">.</span><span class="n">PCollection</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">TypeError</span><span class="p">(</span>
<span class="s1">&#39;Expression roots must have been created with to_dataframe.&#39;</span><span class="p">)</span>
<span class="k">return</span> <span class="n">placeholder</span><span class="o">.</span><span class="n">_reference</span>
<span class="n">placeholders</span> <span class="o">=</span> <span class="nb">frozenset</span><span class="o">.</span><span class="n">union</span><span class="p">(</span>
<span class="nb">frozenset</span><span class="p">(),</span> <span class="o">*</span><span class="p">[</span><span class="n">df</span><span class="o">.</span><span class="n">_expr</span><span class="o">.</span><span class="n">placeholders</span><span class="p">()</span> <span class="k">for</span> <span class="n">df</span> <span class="ow">in</span> <span class="n">dataframes</span><span class="p">])</span>
<span class="c1"># Exclude any dataframes that have already been converted to PCollections.</span>
<span class="c1"># We only want to convert each DF expression once, then re-use.</span>
<span class="n">new_dataframes</span> <span class="o">=</span> <span class="p">[</span>
<span class="n">df</span> <span class="k">for</span> <span class="n">df</span> <span class="ow">in</span> <span class="n">dataframes</span> <span class="k">if</span> <span class="n">df</span><span class="o">.</span><span class="n">_expr</span><span class="o">.</span><span class="n">_id</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">TO_PCOLLECTION_CACHE</span>
<span class="p">]</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">new_dataframes</span><span class="p">):</span>
<span class="n">new_results</span> <span class="o">=</span> <span class="p">{</span><span class="n">p</span><span class="p">:</span> <span class="n">extract_input</span><span class="p">(</span><span class="n">p</span><span class="p">)</span>
<span class="k">for</span> <span class="n">p</span> <span class="ow">in</span> <span class="n">placeholders</span>
<span class="p">}</span> <span class="o">|</span> <span class="n">label</span> <span class="o">&gt;&gt;</span> <span class="n">transforms</span><span class="o">.</span><span class="n">_DataframeExpressionsTransform</span><span class="p">({</span>
<span class="n">ix</span><span class="p">:</span> <span class="n">df</span><span class="o">.</span><span class="n">_expr</span>
<span class="k">for</span> <span class="p">(</span><span class="n">ix</span><span class="p">,</span> <span class="n">df</span><span class="p">)</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">new_dataframes</span><span class="p">)</span>
<span class="p">})</span> <span class="c1"># type: Dict[Any, pvalue.PCollection]</span>
<span class="n">TO_PCOLLECTION_CACHE</span><span class="o">.</span><span class="n">update</span><span class="p">(</span>
<span class="p">{</span><span class="n">new_dataframes</span><span class="p">[</span><span class="n">ix</span><span class="p">]</span><span class="o">.</span><span class="n">_expr</span><span class="o">.</span><span class="n">_id</span><span class="p">:</span> <span class="n">pc</span>
<span class="k">for</span> <span class="n">ix</span><span class="p">,</span> <span class="n">pc</span> <span class="ow">in</span> <span class="n">new_results</span><span class="o">.</span><span class="n">items</span><span class="p">()})</span>
<span class="n">raw_results</span> <span class="o">=</span> <span class="p">{</span>
<span class="n">ix</span><span class="p">:</span> <span class="n">TO_PCOLLECTION_CACHE</span><span class="p">[</span><span class="n">df</span><span class="o">.</span><span class="n">_expr</span><span class="o">.</span><span class="n">_id</span><span class="p">]</span>
<span class="k">for</span> <span class="n">ix</span><span class="p">,</span>
<span class="n">df</span> <span class="ow">in</span> <span class="nb">enumerate</span><span class="p">(</span><span class="n">dataframes</span><span class="p">)</span>
<span class="p">}</span>
<span class="k">if</span> <span class="n">yield_elements</span> <span class="o">==</span> <span class="s2">&quot;schemas&quot;</span><span class="p">:</span>
<span class="k">def</span> <span class="nf">maybe_unbatch</span><span class="p">(</span><span class="n">pc</span><span class="p">,</span> <span class="n">value</span><span class="p">):</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">value</span><span class="p">,</span> <span class="n">frame_base</span><span class="o">.</span><span class="n">_DeferredScalar</span><span class="p">):</span>
<span class="k">return</span> <span class="n">pc</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="n">_make_unbatched_pcoll</span><span class="p">(</span><span class="n">pc</span><span class="p">,</span> <span class="n">value</span><span class="o">.</span><span class="n">_expr</span><span class="p">,</span> <span class="n">include_indexes</span><span class="p">)</span>
<span class="n">results</span> <span class="o">=</span> <span class="p">{</span>
<span class="n">ix</span><span class="p">:</span> <span class="n">maybe_unbatch</span><span class="p">(</span><span class="n">pc</span><span class="p">,</span> <span class="n">dataframes</span><span class="p">[</span><span class="n">ix</span><span class="p">])</span>
<span class="k">for</span> <span class="p">(</span><span class="n">ix</span><span class="p">,</span> <span class="n">pc</span><span class="p">)</span> <span class="ow">in</span> <span class="n">raw_results</span><span class="o">.</span><span class="n">items</span><span class="p">()</span>
<span class="p">}</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">results</span> <span class="o">=</span> <span class="n">raw_results</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">results</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span> <span class="ow">and</span> <span class="ow">not</span> <span class="n">always_return_tuple</span><span class="p">:</span>
<span class="k">return</span> <span class="n">results</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="k">return</span> <span class="nb">tuple</span><span class="p">(</span><span class="n">value</span> <span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="nb">sorted</span><span class="p">(</span><span class="n">results</span><span class="o">.</span><span class="n">items</span><span class="p">()))</span></div>
<span class="k">def</span> <span class="nf">_var_name</span><span class="p">(</span><span class="n">obj</span><span class="p">,</span> <span class="n">level</span><span class="p">):</span>
<span class="n">frame</span> <span class="o">=</span> <span class="n">inspect</span><span class="o">.</span><span class="n">currentframe</span><span class="p">()</span>
<span class="k">for</span> <span class="n">_</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">level</span><span class="p">):</span>
<span class="k">if</span> <span class="n">frame</span> <span class="ow">is</span> <span class="kc">None</span><span class="p">:</span>
<span class="k">return</span> <span class="s1">&#39;...&#39;</span>
<span class="n">frame</span> <span class="o">=</span> <span class="n">frame</span><span class="o">.</span><span class="n">f_back</span>
<span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">frame</span><span class="o">.</span><span class="n">f_locals</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
<span class="k">if</span> <span class="n">obj</span> <span class="ow">is</span> <span class="n">value</span><span class="p">:</span>
<span class="k">return</span> <span class="n">key</span>
<span class="k">for</span> <span class="n">key</span><span class="p">,</span> <span class="n">value</span> <span class="ow">in</span> <span class="n">frame</span><span class="o">.</span><span class="n">f_globals</span><span class="o">.</span><span class="n">items</span><span class="p">():</span>
<span class="k">if</span> <span class="n">obj</span> <span class="ow">is</span> <span class="n">value</span><span class="p">:</span>
<span class="k">return</span> <span class="n">key</span>
<span class="k">return</span> <span class="s1">&#39;...&#39;</span>
</pre></div>
</div>
</div>
<footer>
<hr/>
<div role="contentinfo">
<p>
&copy; 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>