blob: 12a655df09937838d378939e9b8f7101f3e22e18 [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.runners.dask.dask_runner &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.runners.dask.dask_runner</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.runners.dask.dask_runner</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="c1">#</span>
<span class="sd">&quot;&quot;&quot;DaskRunner, executing remote jobs on Dask.distributed.</span>
<span class="sd">The DaskRunner is a runner implementation that executes a graph of</span>
<span class="sd">transformations across processes and workers via Dask distributed&#39;s</span>
<span class="sd">scheduler.</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="kn">import</span> <span class="nn">argparse</span>
<span class="kn">import</span> <span class="nn">dataclasses</span>
<span class="kn">import</span> <span class="nn">typing</span> <span class="k">as</span> <span class="nn">t</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.options.pipeline_options</span> <span class="kn">import</span> <span class="n">PipelineOptions</span>
<span class="kn">from</span> <span class="nn">apache_beam.pipeline</span> <span class="kn">import</span> <span class="n">AppliedPTransform</span>
<span class="kn">from</span> <span class="nn">apache_beam.pipeline</span> <span class="kn">import</span> <span class="n">PipelineVisitor</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.dask.overrides</span> <span class="kn">import</span> <span class="n">dask_overrides</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.dask.transform_evaluator</span> <span class="kn">import</span> <span class="n">TRANSLATIONS</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.dask.transform_evaluator</span> <span class="kn">import</span> <span class="n">NoOp</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.direct.direct_runner</span> <span class="kn">import</span> <span class="n">BundleBasedDirectRunner</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.runner</span> <span class="kn">import</span> <span class="n">PipelineResult</span>
<span class="kn">from</span> <span class="nn">apache_beam.runners.runner</span> <span class="kn">import</span> <span class="n">PipelineState</span>
<span class="kn">from</span> <span class="nn">apache_beam.utils.interactive_utils</span> <span class="kn">import</span> <span class="n">is_in_notebook</span>
<div class="viewcode-block" id="DaskOptions"><a class="viewcode-back" href="../../../../apache_beam.runners.dask.dask_runner.html#apache_beam.runners.dask.dask_runner.DaskOptions">[docs]</a><span class="k">class</span> <span class="nc">DaskOptions</span><span class="p">(</span><span class="n">PipelineOptions</span><span class="p">):</span>
<span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">_parse_timeout</span><span class="p">(</span><span class="n">candidate</span><span class="p">):</span>
<span class="k">try</span><span class="p">:</span>
<span class="k">return</span> <span class="nb">int</span><span class="p">(</span><span class="n">candidate</span><span class="p">)</span>
<span class="k">except</span> <span class="p">(</span><span class="ne">TypeError</span><span class="p">,</span> <span class="ne">ValueError</span><span class="p">):</span>
<span class="kn">import</span> <span class="nn">dask</span>
<span class="k">return</span> <span class="n">dask</span><span class="o">.</span><span class="n">config</span><span class="o">.</span><span class="n">no_default</span>
<span class="nd">@classmethod</span>
<span class="k">def</span> <span class="nf">_add_argparse_args</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">parser</span><span class="p">:</span> <span class="n">argparse</span><span class="o">.</span><span class="n">ArgumentParser</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span>
<span class="s1">&#39;--dask_client_address&#39;</span><span class="p">,</span>
<span class="n">dest</span><span class="o">=</span><span class="s1">&#39;address&#39;</span><span class="p">,</span>
<span class="nb">type</span><span class="o">=</span><span class="nb">str</span><span class="p">,</span>
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s1">&#39;Address of a dask Scheduler server. Will default to a &#39;</span>
<span class="s1">&#39;`dask.LocalCluster()`.&#39;</span><span class="p">)</span>
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span>
<span class="s1">&#39;--dask_connection_timeout&#39;</span><span class="p">,</span>
<span class="n">dest</span><span class="o">=</span><span class="s1">&#39;timeout&#39;</span><span class="p">,</span>
<span class="nb">type</span><span class="o">=</span><span class="n">DaskOptions</span><span class="o">.</span><span class="n">_parse_timeout</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s1">&#39;Timeout duration for initial connection to the scheduler.&#39;</span><span class="p">)</span>
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span>
<span class="s1">&#39;--dask_scheduler_file&#39;</span><span class="p">,</span>
<span class="n">dest</span><span class="o">=</span><span class="s1">&#39;scheduler_file&#39;</span><span class="p">,</span>
<span class="nb">type</span><span class="o">=</span><span class="nb">str</span><span class="p">,</span>
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s1">&#39;Path to a file with scheduler information if available.&#39;</span><span class="p">)</span>
<span class="c1"># TODO(alxr): Add options for security.</span>
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span>
<span class="s1">&#39;--dask_client_name&#39;</span><span class="p">,</span>
<span class="n">dest</span><span class="o">=</span><span class="s1">&#39;name&#39;</span><span class="p">,</span>
<span class="nb">type</span><span class="o">=</span><span class="nb">str</span><span class="p">,</span>
<span class="n">default</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s1">&#39;Gives the client a name that will be included in logs generated &#39;</span>
<span class="s1">&#39;on the scheduler for matters relating to this client.&#39;</span><span class="p">)</span>
<span class="n">parser</span><span class="o">.</span><span class="n">add_argument</span><span class="p">(</span>
<span class="s1">&#39;--dask_connection_limit&#39;</span><span class="p">,</span>
<span class="n">dest</span><span class="o">=</span><span class="s1">&#39;connection_limit&#39;</span><span class="p">,</span>
<span class="nb">type</span><span class="o">=</span><span class="nb">int</span><span class="p">,</span>
<span class="n">default</span><span class="o">=</span><span class="mi">512</span><span class="p">,</span>
<span class="n">help</span><span class="o">=</span><span class="s1">&#39;The number of open comms to maintain at once in the connection &#39;</span>
<span class="s1">&#39;pool.&#39;</span><span class="p">)</span></div>
<div class="viewcode-block" id="DaskRunnerResult"><a class="viewcode-back" href="../../../../apache_beam.runners.dask.dask_runner.html#apache_beam.runners.dask.dask_runner.DaskRunnerResult">[docs]</a><span class="nd">@dataclasses</span><span class="o">.</span><span class="n">dataclass</span>
<span class="k">class</span> <span class="nc">DaskRunnerResult</span><span class="p">(</span><span class="n">PipelineResult</span><span class="p">):</span>
<span class="kn">from</span> <span class="nn">dask</span> <span class="kn">import</span> <span class="n">distributed</span>
<span class="n">client</span><span class="p">:</span> <span class="n">distributed</span><span class="o">.</span><span class="n">Client</span>
<span class="n">futures</span><span class="p">:</span> <span class="n">t</span><span class="o">.</span><span class="n">Sequence</span><span class="p">[</span><span class="n">distributed</span><span class="o">.</span><span class="n">Future</span><span class="p">]</span>
<span class="k">def</span> <span class="nf">__post_init__</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="nb">super</span><span class="p">()</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="n">PipelineState</span><span class="o">.</span><span class="n">RUNNING</span><span class="p">)</span>
<div class="viewcode-block" id="DaskRunnerResult.wait_until_finish"><a class="viewcode-back" href="../../../../apache_beam.runners.dask.dask_runner.html#apache_beam.runners.dask.dask_runner.DaskRunnerResult.wait_until_finish">[docs]</a> <span class="k">def</span> <span class="nf">wait_until_finish</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">duration</span><span class="o">=</span><span class="kc">None</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="k">try</span><span class="p">:</span>
<span class="k">if</span> <span class="n">duration</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
<span class="c1"># Convert milliseconds to seconds</span>
<span class="n">duration</span> <span class="o">/=</span> <span class="mi">1000</span>
<span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">wait_for_workers</span><span class="p">(</span><span class="n">timeout</span><span class="o">=</span><span class="n">duration</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">gather</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">futures</span><span class="p">,</span> <span class="n">errors</span><span class="o">=</span><span class="s1">&#39;raise&#39;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_state</span> <span class="o">=</span> <span class="n">PipelineState</span><span class="o">.</span><span class="n">DONE</span>
<span class="k">except</span><span class="p">:</span> <span class="c1"># pylint: disable=broad-except</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_state</span> <span class="o">=</span> <span class="n">PipelineState</span><span class="o">.</span><span class="n">FAILED</span>
<span class="k">raise</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_state</span></div>
<div class="viewcode-block" id="DaskRunnerResult.cancel"><a class="viewcode-back" href="../../../../apache_beam.runners.dask.dask_runner.html#apache_beam.runners.dask.dask_runner.DaskRunnerResult.cancel">[docs]</a> <span class="k">def</span> <span class="nf">cancel</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_state</span> <span class="o">=</span> <span class="n">PipelineState</span><span class="o">.</span><span class="n">CANCELLING</span>
<span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">cancel</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">futures</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_state</span> <span class="o">=</span> <span class="n">PipelineState</span><span class="o">.</span><span class="n">CANCELLED</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_state</span></div>
<div class="viewcode-block" id="DaskRunnerResult.metrics"><a class="viewcode-back" href="../../../../apache_beam.runners.dask.dask_runner.html#apache_beam.runners.dask.dask_runner.DaskRunnerResult.metrics">[docs]</a> <span class="k">def</span> <span class="nf">metrics</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="c1"># TODO(alxr): Collect and return metrics...</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="s1">&#39;collecting metrics will come later!&#39;</span><span class="p">)</span></div></div>
<div class="viewcode-block" id="DaskRunner"><a class="viewcode-back" href="../../../../apache_beam.runners.dask.dask_runner.html#apache_beam.runners.dask.dask_runner.DaskRunner">[docs]</a><span class="k">class</span> <span class="nc">DaskRunner</span><span class="p">(</span><span class="n">BundleBasedDirectRunner</span><span class="p">):</span>
<span class="w"> </span><span class="sd">&quot;&quot;&quot;Executes a pipeline on a Dask distributed client.&quot;&quot;&quot;</span>
<div class="viewcode-block" id="DaskRunner.to_dask_bag_visitor"><a class="viewcode-back" href="../../../../apache_beam.runners.dask.dask_runner.html#apache_beam.runners.dask.dask_runner.DaskRunner.to_dask_bag_visitor">[docs]</a> <span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">to_dask_bag_visitor</span><span class="p">()</span> <span class="o">-&gt;</span> <span class="n">PipelineVisitor</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">dask</span> <span class="kn">import</span> <span class="n">bag</span> <span class="k">as</span> <span class="n">db</span>
<span class="nd">@dataclasses</span><span class="o">.</span><span class="n">dataclass</span>
<span class="k">class</span> <span class="nc">DaskBagVisitor</span><span class="p">(</span><span class="n">PipelineVisitor</span><span class="p">):</span>
<span class="n">bags</span><span class="p">:</span> <span class="n">t</span><span class="o">.</span><span class="n">Dict</span><span class="p">[</span><span class="n">AppliedPTransform</span><span class="p">,</span>
<span class="n">db</span><span class="o">.</span><span class="n">Bag</span><span class="p">]</span> <span class="o">=</span> <span class="n">dataclasses</span><span class="o">.</span><span class="n">field</span><span class="p">(</span><span class="n">default_factory</span><span class="o">=</span><span class="nb">dict</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">visit_transform</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">transform_node</span><span class="p">:</span> <span class="n">AppliedPTransform</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="kc">None</span><span class="p">:</span>
<span class="n">op_class</span> <span class="o">=</span> <span class="n">TRANSLATIONS</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">transform_node</span><span class="o">.</span><span class="n">transform</span><span class="o">.</span><span class="vm">__class__</span><span class="p">,</span> <span class="n">NoOp</span><span class="p">)</span>
<span class="n">op</span> <span class="o">=</span> <span class="n">op_class</span><span class="p">(</span><span class="n">transform_node</span><span class="p">)</span>
<span class="n">inputs</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="n">transform_node</span><span class="o">.</span><span class="n">inputs</span><span class="p">)</span>
<span class="k">if</span> <span class="n">inputs</span><span class="p">:</span>
<span class="n">bag_inputs</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">input_value</span> <span class="ow">in</span> <span class="n">inputs</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">input_value</span><span class="p">,</span> <span class="n">pvalue</span><span class="o">.</span><span class="n">PBegin</span><span class="p">):</span>
<span class="n">bag_inputs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="kc">None</span><span class="p">)</span>
<span class="n">prev_op</span> <span class="o">=</span> <span class="n">input_value</span><span class="o">.</span><span class="n">producer</span>
<span class="k">if</span> <span class="n">prev_op</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">bags</span><span class="p">:</span>
<span class="n">bag_inputs</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">bags</span><span class="p">[</span><span class="n">prev_op</span><span class="p">])</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">bag_inputs</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bags</span><span class="p">[</span><span class="n">transform_node</span><span class="p">]</span> <span class="o">=</span> <span class="n">op</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">bag_inputs</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="bp">self</span><span class="o">.</span><span class="n">bags</span><span class="p">[</span><span class="n">transform_node</span><span class="p">]</span> <span class="o">=</span> <span class="n">op</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="n">bag_inputs</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">bags</span><span class="p">[</span><span class="n">transform_node</span><span class="p">]</span> <span class="o">=</span> <span class="n">op</span><span class="o">.</span><span class="n">apply</span><span class="p">(</span><span class="kc">None</span><span class="p">)</span>
<span class="k">return</span> <span class="n">DaskBagVisitor</span><span class="p">()</span></div>
<div class="viewcode-block" id="DaskRunner.is_fnapi_compatible"><a class="viewcode-back" href="../../../../apache_beam.runners.dask.dask_runner.html#apache_beam.runners.dask.dask_runner.DaskRunner.is_fnapi_compatible">[docs]</a> <span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">is_fnapi_compatible</span><span class="p">():</span>
<span class="k">return</span> <span class="kc">False</span></div>
<div class="viewcode-block" id="DaskRunner.run_pipeline"><a class="viewcode-back" href="../../../../apache_beam.runners.dask.dask_runner.html#apache_beam.runners.dask.dask_runner.DaskRunner.run_pipeline">[docs]</a> <span class="k">def</span> <span class="nf">run_pipeline</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pipeline</span><span class="p">,</span> <span class="n">options</span><span class="p">):</span>
<span class="c1"># TODO(alxr): Create interactive notebook support.</span>
<span class="k">if</span> <span class="n">is_in_notebook</span><span class="p">():</span>
<span class="k">raise</span> <span class="ne">NotImplementedError</span><span class="p">(</span><span class="s1">&#39;interactive support will come later!&#39;</span><span class="p">)</span>
<span class="k">try</span><span class="p">:</span>
<span class="kn">import</span> <span class="nn">dask.distributed</span> <span class="k">as</span> <span class="nn">ddist</span>
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ImportError</span><span class="p">(</span>
<span class="s1">&#39;DaskRunner is not available. Please install apache_beam[dask].&#39;</span><span class="p">)</span>
<span class="n">dask_options</span> <span class="o">=</span> <span class="n">options</span><span class="o">.</span><span class="n">view_as</span><span class="p">(</span><span class="n">DaskOptions</span><span class="p">)</span><span class="o">.</span><span class="n">get_all_options</span><span class="p">(</span>
<span class="n">drop_default</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span>
<span class="n">client</span> <span class="o">=</span> <span class="n">ddist</span><span class="o">.</span><span class="n">Client</span><span class="p">(</span><span class="o">**</span><span class="n">dask_options</span><span class="p">)</span>
<span class="n">pipeline</span><span class="o">.</span><span class="n">replace_all</span><span class="p">(</span><span class="n">dask_overrides</span><span class="p">())</span>
<span class="n">dask_visitor</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">to_dask_bag_visitor</span><span class="p">()</span>
<span class="n">pipeline</span><span class="o">.</span><span class="n">visit</span><span class="p">(</span><span class="n">dask_visitor</span><span class="p">)</span>
<span class="n">futures</span> <span class="o">=</span> <span class="n">client</span><span class="o">.</span><span class="n">compute</span><span class="p">(</span><span class="nb">list</span><span class="p">(</span><span class="n">dask_visitor</span><span class="o">.</span><span class="n">bags</span><span class="o">.</span><span class="n">values</span><span class="p">()))</span>
<span class="k">return</span> <span class="n">DaskRunnerResult</span><span class="p">(</span><span class="n">client</span><span class="p">,</span> <span class="n">futures</span><span class="p">)</span></div></div>
</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>