blob: 6009406c2126e61b8efa3003813e4447487e6755 [file] [log] [blame]
<!DOCTYPE html>
<html class="writer-html5" lang="en" data-content_root="./">
<head>
<meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>apache_beam.transforms.deduplicate module &mdash; Apache Beam 2.67.0 documentation</title>
<link rel="stylesheet" type="text/css" href="_static/pygments.css?v=b86133f3" />
<link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=e59714d7" />
<script src="_static/jquery.js?v=5d32c60e"></script>
<script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script>
<script src="_static/documentation_options.js?v=959b4fbe"></script>
<script src="_static/doctools.js?v=9a2dae69"></script>
<script src="_static/sphinx_highlight.js?v=dc90522c"></script>
<script src="_static/js/theme.js"></script>
<link rel="index" title="Index" href="genindex.html" />
<link rel="search" title="Search" href="search.html" />
<link rel="next" title="apache_beam.transforms.display module" href="apache_beam.transforms.display.html" />
<link rel="prev" title="apache_beam.transforms.create_source module" href="apache_beam.transforms.create_source.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" aria-label="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="Navigation menu">
<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"><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 current"><a class="reference internal" href="apache_beam.transforms.html">apache_beam.transforms package</a><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="apache_beam.transforms.html#subpackages">Subpackages</a></li>
<li class="toctree-l2 current"><a class="reference internal" href="apache_beam.transforms.html#submodules">Submodules</a><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.async_dofn.html">apache_beam.transforms.async_dofn module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.combinefn_lifecycle_pipeline.html">apache_beam.transforms.combinefn_lifecycle_pipeline module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.combiners.html">apache_beam.transforms.combiners module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.core.html">apache_beam.transforms.core module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.create_source.html">apache_beam.transforms.create_source module</a></li>
<li class="toctree-l3 current"><a class="current reference internal" href="#">apache_beam.transforms.deduplicate module</a><ul>
<li class="toctree-l4"><a class="reference internal" href="#apache_beam.transforms.deduplicate.Deduplicate"><code class="docutils literal notranslate"><span class="pre">Deduplicate</span></code></a></li>
<li class="toctree-l4"><a class="reference internal" href="#apache_beam.transforms.deduplicate.DeduplicatePerKey"><code class="docutils literal notranslate"><span class="pre">DeduplicatePerKey</span></code></a></li>
</ul>
</li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.display.html">apache_beam.transforms.display module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.enrichment.html">apache_beam.transforms.enrichment module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.environments.html">apache_beam.transforms.environments module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.error_handling.html">apache_beam.transforms.error_handling module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.external.html">apache_beam.transforms.external module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.external_java.html">apache_beam.transforms.external_java module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.external_transform_provider.html">apache_beam.transforms.external_transform_provider module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.fully_qualified_named_transform.html">apache_beam.transforms.fully_qualified_named_transform module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.managed.html">apache_beam.transforms.managed module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.periodicsequence.html">apache_beam.transforms.periodicsequence module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.ptransform.html">apache_beam.transforms.ptransform module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.resources.html">apache_beam.transforms.resources module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.sideinputs.html">apache_beam.transforms.sideinputs module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.sql.html">apache_beam.transforms.sql module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.stats.html">apache_beam.transforms.stats module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.timeutil.html">apache_beam.transforms.timeutil module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.trigger.html">apache_beam.transforms.trigger module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.userstate.html">apache_beam.transforms.userstate module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.util.html">apache_beam.transforms.util module</a></li>
<li class="toctree-l3"><a class="reference internal" href="apache_beam.transforms.window.html">apache_beam.transforms.window module</a></li>
</ul>
</li>
</ul>
</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="Mobile navigation menu" >
<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="Page navigation">
<ul class="wy-breadcrumbs">
<li><a href="index.html" class="icon icon-home" aria-label="Home"></a></li>
<li class="breadcrumb-item"><a href="apache_beam.transforms.html">apache_beam.transforms package</a></li>
<li class="breadcrumb-item active">apache_beam.transforms.deduplicate module</li>
<li class="wy-breadcrumbs-aside">
<a href="_sources/apache_beam.transforms.deduplicate.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">
<section id="module-apache_beam.transforms.deduplicate">
<span id="apache-beam-transforms-deduplicate-module"></span><h1>apache_beam.transforms.deduplicate module<a class="headerlink" href="#module-apache_beam.transforms.deduplicate" title="Link to this heading"></a></h1>
<p>a collection of ptransforms for deduplicating elements.</p>
<dl class="py class">
<dt class="sig sig-object py" id="apache_beam.transforms.deduplicate.Deduplicate">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.transforms.deduplicate.</span></span><span class="sig-name descname"><span class="pre">Deduplicate</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">processing_time_duration</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">event_time_duration</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/transforms/deduplicate.html#Deduplicate"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.transforms.deduplicate.Deduplicate" title="Link 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">PTransform</span></code></a></p>
<p>Similar to DeduplicatePerKey, the Deduplicate transform takes any arbitrary
value as input and uses value as key to deduplicate among certain amount of
time duration.</p>
<dl class="py method">
<dt class="sig sig-object py" id="apache_beam.transforms.deduplicate.Deduplicate.expand">
<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pcoll</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/transforms/deduplicate.html#Deduplicate.expand"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.transforms.deduplicate.Deduplicate.expand" title="Link to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="apache_beam.transforms.deduplicate.DeduplicatePerKey">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.transforms.deduplicate.</span></span><span class="sig-name descname"><span class="pre">DeduplicatePerKey</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">processing_time_duration</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">event_time_duration</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/transforms/deduplicate.html#DeduplicatePerKey"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.transforms.deduplicate.DeduplicatePerKey" title="Link 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">PTransform</span></code></a></p>
<p>A PTransform which deduplicates &lt;key, value&gt; pair over a time domain and
threshold. Values in different windows will NOT be considered duplicates of
each other. Deduplication is guaranteed with respect of time domain and
duration.</p>
<p>Time durations are required so as to avoid unbounded memory and/or storage
requirements within a runner and care might need to be used to ensure that the
deduplication time limit is long enough to remove duplicates but short enough
to not cause performance problems within a runner. Each runner may provide an
optimized implementation of their choice using the deduplication time domain
and threshold specified.</p>
<p>Does not preserve any order the input PCollection might have had.</p>
<dl class="py method">
<dt class="sig sig-object py" id="apache_beam.transforms.deduplicate.DeduplicatePerKey.expand">
<span class="sig-name descname"><span class="pre">expand</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">pcoll</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/transforms/deduplicate.html#DeduplicatePerKey.expand"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.transforms.deduplicate.DeduplicatePerKey.expand" title="Link to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
</section>
</div>
</div>
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
<a href="apache_beam.transforms.create_source.html" class="btn btn-neutral float-left" title="apache_beam.transforms.create_source module" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
<a href="apache_beam.transforms.display.html" class="btn btn-neutral float-right" title="apache_beam.transforms.display module" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
</div>
<hr/>
<div role="contentinfo">
<p>&#169; Copyright %Y, Apache Beam.</p>
</div>
Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a
<a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a>
provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script>
jQuery(function () {
SphinxRtdTheme.Navigation.enable(true);
});
</script>
</body>
</html>