blob: 231b606dab6efc645aa80a7412c8185e7dc80c85 [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.interactive.interactive_environment &mdash; Apache Beam documentation</title>
<link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
<link rel="index" title="Index"
href="../../../../genindex.html"/>
<link rel="search" title="Search" href="../../../../search.html"/>
<link rel="top" title="Apache Beam documentation" href="../../../../index.html"/>
<link rel="up" title="Module code" href="../../../index.html"/>
<script src="../../../../_static/js/modernizr.min.js"></script>
</head>
<body class="wy-body-for-nav" role="document">
<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>
<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.internal.html">apache_beam.internal 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.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.tools.html">apache_beam.tools 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>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.version.html">apache_beam.version module</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" role="navigation" 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.interactive.interactive_environment</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.interactive.interactive_environment</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;Module of the current Interactive Beam environment.</span>
<span class="sd">For internal use only; no backwards-compatibility guarantees.</span>
<span class="sd">Provides interfaces to interact with existing Interactive Beam environment.</span>
<span class="sd">External Interactive Beam users please use interactive_beam module in</span>
<span class="sd">application code or notebook.</span>
<span class="sd">&quot;&quot;&quot;</span>
<span class="c1"># pytype: skip-file</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">absolute_import</span>
<span class="kn">import</span> <span class="nn">atexit</span>
<span class="kn">import</span> <span class="nn">importlib</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">import</span> <span class="nn">sys</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.runners</span> <span class="kn">import</span> <span class="n">runner</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_ipython</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>
<span class="c1"># Interactive Beam user flow is data-centric rather than pipeline-centric, so</span>
<span class="c1"># there is only one global interactive environment instance that manages</span>
<span class="c1"># implementation that enables interactivity.</span>
<span class="n">_interactive_beam_env</span> <span class="o">=</span> <span class="kc">None</span>
<span class="n">_LOGGER</span> <span class="o">=</span> <span class="n">logging</span><span class="o">.</span><span class="n">getLogger</span><span class="p">(</span><span class="vm">__name__</span><span class="p">)</span>
<div class="viewcode-block" id="current_env"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.interactive_environment.html#apache_beam.runners.interactive.interactive_environment.current_env">[docs]</a><span class="k">def</span> <span class="nf">current_env</span><span class="p">(</span><span class="n">cache_manager</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Gets current Interactive Beam environment.&quot;&quot;&quot;</span>
<span class="k">global</span> <span class="n">_interactive_beam_env</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">_interactive_beam_env</span><span class="p">:</span>
<span class="n">_interactive_beam_env</span> <span class="o">=</span> <span class="n">InteractiveEnvironment</span><span class="p">(</span><span class="n">cache_manager</span><span class="p">)</span>
<span class="k">return</span> <span class="n">_interactive_beam_env</span></div>
<div class="viewcode-block" id="new_env"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.interactive_environment.html#apache_beam.runners.interactive.interactive_environment.new_env">[docs]</a><span class="k">def</span> <span class="nf">new_env</span><span class="p">(</span><span class="n">cache_manager</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Creates a new Interactive Beam environment to replace current one.&quot;&quot;&quot;</span>
<span class="k">global</span> <span class="n">_interactive_beam_env</span>
<span class="k">if</span> <span class="n">_interactive_beam_env</span><span class="p">:</span>
<span class="n">_interactive_beam_env</span><span class="o">.</span><span class="n">cleanup</span><span class="p">()</span>
<span class="n">_interactive_beam_env</span> <span class="o">=</span> <span class="kc">None</span>
<span class="k">return</span> <span class="n">current_env</span><span class="p">(</span><span class="n">cache_manager</span><span class="p">)</span></div>
<div class="viewcode-block" id="InteractiveEnvironment"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.interactive_environment.html#apache_beam.runners.interactive.interactive_environment.InteractiveEnvironment">[docs]</a><span class="k">class</span> <span class="nc">InteractiveEnvironment</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;An interactive environment with cache and pipeline variable metadata.</span>
<span class="sd"> Interactive Beam will use the watched variable information to determine if a</span>
<span class="sd"> PCollection is assigned to a variable in user pipeline definition. When</span>
<span class="sd"> executing the pipeline, interactivity is applied with implicit cache</span>
<span class="sd"> mechanism for those PCollections if the pipeline is interactive. Users can</span>
<span class="sd"> also visualize and introspect those PCollections in user code since they have</span>
<span class="sd"> handles to the variables.</span>
<span class="sd"> &quot;&quot;&quot;</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">cache_manager</span><span class="o">=</span><span class="kc">None</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cache_manager</span> <span class="o">=</span> <span class="n">cache_manager</span>
<span class="c1"># Register a cleanup routine when kernel is restarted or terminated.</span>
<span class="k">if</span> <span class="n">cache_manager</span><span class="p">:</span>
<span class="n">atexit</span><span class="o">.</span><span class="n">register</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">cleanup</span><span class="p">)</span>
<span class="c1"># Holds class instances, module object, string of module names.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_watching_set</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
<span class="c1"># Holds variables list of (Dict[str, object]).</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_watching_dict_list</span> <span class="o">=</span> <span class="p">[]</span>
<span class="c1"># Holds results of main jobs as Dict[Pipeline, PipelineResult].</span>
<span class="c1"># Each key is a pipeline instance defined by the end user. The</span>
<span class="c1"># InteractiveRunner is responsible for populating this dictionary</span>
<span class="c1"># implicitly.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_main_pipeline_results</span> <span class="o">=</span> <span class="p">{}</span>
<span class="c1"># Holds results of background caching jobs as</span>
<span class="c1"># Dict[Pipeline, PipelineResult]. Each key is a pipeline instance defined by</span>
<span class="c1"># the end user. The InteractiveRunner is responsible for populating this</span>
<span class="c1"># dictionary implicitly when a background caching jobs is started.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_background_caching_pipeline_results</span> <span class="o">=</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cached_source_signature</span> <span class="o">=</span> <span class="p">{}</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_tracked_user_pipelines</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
<span class="c1"># Always watch __main__ module.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">watch</span><span class="p">(</span><span class="s1">&#39;__main__&#39;</span><span class="p">)</span>
<span class="c1"># Do a warning level logging if current python version is below 3.6.</span>
<span class="k">if</span> <span class="n">sys</span><span class="o">.</span><span class="n">version_info</span> <span class="o">&lt;</span> <span class="p">(</span><span class="mi">3</span><span class="p">,</span> <span class="mi">6</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_is_py_version_ready</span> <span class="o">=</span> <span class="kc">False</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s1">&#39;Interactive Beam requires Python 3.5.3+.&#39;</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">_is_py_version_ready</span> <span class="o">=</span> <span class="kc">True</span>
<span class="c1"># Check if [interactive] dependencies are installed.</span>
<span class="k">try</span><span class="p">:</span>
<span class="kn">import</span> <span class="nn">IPython</span> <span class="c1"># pylint: disable=unused-import</span>
<span class="kn">import</span> <span class="nn">jsons</span> <span class="c1"># pylint: disable=unused-import</span>
<span class="kn">import</span> <span class="nn">timeloop</span> <span class="c1"># pylint: disable=unused-import</span>
<span class="kn">from</span> <span class="nn">facets_overview.generic_feature_statistics_generator</span> <span class="kn">import</span> <span class="n">GenericFeatureStatisticsGenerator</span> <span class="c1"># pylint: disable=unused-import</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_is_interactive_ready</span> <span class="o">=</span> <span class="kc">True</span>
<span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_is_interactive_ready</span> <span class="o">=</span> <span class="kc">False</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s1">&#39;Dependencies required for Interactive Beam PCollection &#39;</span>
<span class="s1">&#39;visualization are not available, please use: `pip &#39;</span>
<span class="s1">&#39;install apache-beam[interactive]` to install necessary &#39;</span>
<span class="s1">&#39;dependencies to enable all data visualization features.&#39;</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_is_in_ipython</span> <span class="o">=</span> <span class="n">is_in_ipython</span><span class="p">()</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_is_in_notebook</span> <span class="o">=</span> <span class="n">is_in_notebook</span><span class="p">()</span>
<span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_is_in_ipython</span><span class="p">:</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s1">&#39;You cannot use Interactive Beam features when you are &#39;</span>
<span class="s1">&#39;not in an interactive environment such as a Jupyter &#39;</span>
<span class="s1">&#39;notebook or ipython terminal.&#39;</span><span class="p">)</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_is_in_ipython</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_is_in_notebook</span><span class="p">:</span>
<span class="n">_LOGGER</span><span class="o">.</span><span class="n">warning</span><span class="p">(</span><span class="s1">&#39;You have limited Interactive Beam features since your &#39;</span>
<span class="s1">&#39;ipython kernel is not connected any notebook frontend.&#39;</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">is_py_version_ready</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;If Python version is above the minimum requirement.&quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_is_py_version_ready</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">is_interactive_ready</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;If the [interactive] dependencies are installed.&quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_is_interactive_ready</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">is_in_ipython</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;If the runtime is within an IPython kernel.&quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_is_in_ipython</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">is_in_notebook</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;If the kernel is connected to a notebook frontend.</span>
<span class="sd"> If not, it could be that the user is using kernel in a terminal or a unit</span>
<span class="sd"> test.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_is_in_notebook</span>
<div class="viewcode-block" id="InteractiveEnvironment.cleanup"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.interactive_environment.html#apache_beam.runners.interactive.interactive_environment.InteractiveEnvironment.cleanup">[docs]</a> <span class="k">def</span> <span class="nf">cleanup</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="c1"># Utilizes cache manager to clean up cache from everywhere.</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">cache_manager</span><span class="p">():</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cache_manager</span><span class="p">()</span><span class="o">.</span><span class="n">cleanup</span><span class="p">()</span></div>
<div class="viewcode-block" id="InteractiveEnvironment.watch"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.interactive_environment.html#apache_beam.runners.interactive.interactive_environment.InteractiveEnvironment.watch">[docs]</a> <span class="k">def</span> <span class="nf">watch</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">watchable</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Watches a watchable.</span>
<span class="sd"> A watchable can be a dictionary of variable metadata such as locals(), a str</span>
<span class="sd"> name of a module, a module object or an instance of a class. The variable</span>
<span class="sd"> can come from any scope even local. Duplicated variable naming doesn&#39;t</span>
<span class="sd"> matter since they are different instances. Duplicated variables are also</span>
<span class="sd"> allowed when watching.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">watchable</span><span class="p">,</span> <span class="nb">dict</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_watching_dict_list</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">watchable</span><span class="o">.</span><span class="n">items</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">_watching_set</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">watchable</span><span class="p">)</span></div>
<div class="viewcode-block" id="InteractiveEnvironment.watching"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.interactive_environment.html#apache_beam.runners.interactive.interactive_environment.InteractiveEnvironment.watching">[docs]</a> <span class="k">def</span> <span class="nf">watching</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Analyzes and returns a list of pair lists referring to variable names and</span>
<span class="sd"> values from watched scopes.</span>
<span class="sd"> Each entry in the list represents the variable defined within a watched</span>
<span class="sd"> watchable. Currently, each entry holds a list of pairs. The format might</span>
<span class="sd"> change in the future to hold more metadata. Duplicated pairs are allowed.</span>
<span class="sd"> And multiple paris can have the same variable name as the &quot;first&quot; while</span>
<span class="sd"> having different variable values as the &quot;second&quot; since variables in</span>
<span class="sd"> different scopes can have the same name.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="n">watching</span> <span class="o">=</span> <span class="nb">list</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_watching_dict_list</span><span class="p">)</span>
<span class="k">for</span> <span class="n">watchable</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_watching_set</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">watchable</span><span class="p">,</span> <span class="nb">str</span><span class="p">):</span>
<span class="n">module</span> <span class="o">=</span> <span class="n">importlib</span><span class="o">.</span><span class="n">import_module</span><span class="p">(</span><span class="n">watchable</span><span class="p">)</span>
<span class="n">watching</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">vars</span><span class="p">(</span><span class="n">module</span><span class="p">)</span><span class="o">.</span><span class="n">items</span><span class="p">())</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">watching</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="nb">vars</span><span class="p">(</span><span class="n">watchable</span><span class="p">)</span><span class="o">.</span><span class="n">items</span><span class="p">())</span>
<span class="k">return</span> <span class="n">watching</span></div>
<div class="viewcode-block" id="InteractiveEnvironment.set_cache_manager"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.interactive_environment.html#apache_beam.runners.interactive.interactive_environment.InteractiveEnvironment.set_cache_manager">[docs]</a> <span class="k">def</span> <span class="nf">set_cache_manager</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">cache_manager</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Sets the cache manager held by current Interactive Environment.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cache_manager</span> <span class="ow">is</span> <span class="n">cache_manager</span><span class="p">:</span>
<span class="c1"># NOOP if setting to the same cache_manager.</span>
<span class="k">return</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cache_manager</span><span class="p">:</span>
<span class="c1"># Invoke cleanup routine when a new cache_manager is forcefully set and</span>
<span class="c1"># current cache_manager is not None.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">cleanup</span><span class="p">()</span>
<span class="n">atexit</span><span class="o">.</span><span class="n">unregister</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">cleanup</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cache_manager</span> <span class="o">=</span> <span class="n">cache_manager</span>
<span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cache_manager</span><span class="p">:</span>
<span class="c1"># Re-register cleanup routine for the new cache_manager if it&#39;s not None.</span>
<span class="n">atexit</span><span class="o">.</span><span class="n">register</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">cleanup</span><span class="p">)</span></div>
<div class="viewcode-block" id="InteractiveEnvironment.cache_manager"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.interactive_environment.html#apache_beam.runners.interactive.interactive_environment.InteractiveEnvironment.cache_manager">[docs]</a> <span class="k">def</span> <span class="nf">cache_manager</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Gets the cache manager held by current Interactive Environment.&quot;&quot;&quot;</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cache_manager</span></div>
<div class="viewcode-block" id="InteractiveEnvironment.set_pipeline_result"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.interactive_environment.html#apache_beam.runners.interactive.interactive_environment.InteractiveEnvironment.set_pipeline_result">[docs]</a> <span class="k">def</span> <span class="nf">set_pipeline_result</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">result</span><span class="p">,</span> <span class="n">is_main_job</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Sets the pipeline run result. Adds one if absent. Otherwise, replace.</span>
<span class="sd"> When is_main_job is True, set the result for the main job; otherwise, set</span>
<span class="sd"> the result for the background caching job.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">assert</span> <span class="nb">issubclass</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">pipeline</span><span class="p">),</span> <span class="n">beam</span><span class="o">.</span><span class="n">Pipeline</span><span class="p">),</span> <span class="p">(</span>
<span class="s1">&#39;pipeline must be an instance of apache_beam.Pipeline or its subclass&#39;</span><span class="p">)</span>
<span class="k">assert</span> <span class="nb">issubclass</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">result</span><span class="p">),</span> <span class="n">runner</span><span class="o">.</span><span class="n">PipelineResult</span><span class="p">),</span> <span class="p">(</span>
<span class="s1">&#39;result must be an instance of &#39;</span>
<span class="s1">&#39;apache_beam.runners.runner.PipelineResult or its subclass&#39;</span><span class="p">)</span>
<span class="k">if</span> <span class="n">is_main_job</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_main_pipeline_results</span><span class="p">[</span><span class="n">pipeline</span><span class="p">]</span> <span class="o">=</span> <span class="n">result</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_background_caching_pipeline_results</span><span class="p">[</span><span class="n">pipeline</span><span class="p">]</span> <span class="o">=</span> <span class="n">result</span></div>
<div class="viewcode-block" id="InteractiveEnvironment.evict_pipeline_result"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.interactive_environment.html#apache_beam.runners.interactive.interactive_environment.InteractiveEnvironment.evict_pipeline_result">[docs]</a> <span class="k">def</span> <span class="nf">evict_pipeline_result</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">is_main_job</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Evicts the tracking of given pipeline run. Noop if absent.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">is_main_job</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_main_pipeline_results</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="n">pipeline</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_background_caching_pipeline_results</span><span class="o">.</span><span class="n">pop</span><span class="p">(</span><span class="n">pipeline</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span></div>
<div class="viewcode-block" id="InteractiveEnvironment.pipeline_result"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.interactive_environment.html#apache_beam.runners.interactive.interactive_environment.InteractiveEnvironment.pipeline_result">[docs]</a> <span class="k">def</span> <span class="nf">pipeline_result</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">is_main_job</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Gets the pipeline run result. None if absent.&quot;&quot;&quot;</span>
<span class="k">if</span> <span class="n">is_main_job</span><span class="p">:</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_main_pipeline_results</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">pipeline</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_background_caching_pipeline_results</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">pipeline</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span></div>
<div class="viewcode-block" id="InteractiveEnvironment.is_terminated"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.interactive_environment.html#apache_beam.runners.interactive.interactive_environment.InteractiveEnvironment.is_terminated">[docs]</a> <span class="k">def</span> <span class="nf">is_terminated</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">is_main_job</span><span class="o">=</span><span class="kc">True</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Queries if the most recent job (by executing the given pipeline) state</span>
<span class="sd"> is in a terminal state. True if absent.&quot;&quot;&quot;</span>
<span class="n">result</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">pipeline_result</span><span class="p">(</span><span class="n">pipeline</span><span class="p">,</span> <span class="n">is_main_job</span><span class="o">=</span><span class="n">is_main_job</span><span class="p">)</span>
<span class="k">if</span> <span class="n">result</span><span class="p">:</span>
<span class="k">return</span> <span class="n">runner</span><span class="o">.</span><span class="n">PipelineState</span><span class="o">.</span><span class="n">is_terminal</span><span class="p">(</span><span class="n">result</span><span class="o">.</span><span class="n">state</span><span class="p">)</span>
<span class="k">return</span> <span class="kc">True</span></div>
<div class="viewcode-block" id="InteractiveEnvironment.set_cached_source_signature"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.interactive_environment.html#apache_beam.runners.interactive.interactive_environment.InteractiveEnvironment.set_cached_source_signature">[docs]</a> <span class="k">def</span> <span class="nf">set_cached_source_signature</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">signature</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_cached_source_signature</span><span class="p">[</span><span class="n">pipeline</span><span class="p">]</span> <span class="o">=</span> <span class="n">signature</span></div>
<div class="viewcode-block" id="InteractiveEnvironment.get_cached_source_signature"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.interactive_environment.html#apache_beam.runners.interactive.interactive_environment.InteractiveEnvironment.get_cached_source_signature">[docs]</a> <span class="k">def</span> <span class="nf">get_cached_source_signature</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="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_cached_source_signature</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">pipeline</span><span class="p">,</span> <span class="nb">set</span><span class="p">())</span></div>
<div class="viewcode-block" id="InteractiveEnvironment.track_user_pipelines"><a class="viewcode-back" href="../../../../apache_beam.runners.interactive.interactive_environment.html#apache_beam.runners.interactive.interactive_environment.InteractiveEnvironment.track_user_pipelines">[docs]</a> <span class="k">def</span> <span class="nf">track_user_pipelines</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Record references to all user-defined pipeline instances watched in</span>
<span class="sd"> current environment.</span>
<span class="sd"> Current static global singleton interactive environment holds references to</span>
<span class="sd"> a set of pipeline instances defined by the user in the watched scope.</span>
<span class="sd"> Interactive Beam features could use the references to determine if a given</span>
<span class="sd"> pipeline is defined by user or implicitly created by Beam SDK or runners,</span>
<span class="sd"> then handle them differently.</span>
<span class="sd"> This is invoked every time a PTransform is to be applied if the current</span>
<span class="sd"> code execution is under ipython due to the possibility that any user-defined</span>
<span class="sd"> pipeline can be re-evaluated through notebook cell re-execution at any time.</span>
<span class="sd"> Each time this is invoked, the tracked user pipelines are refreshed to</span>
<span class="sd"> remove any pipeline instances that are no longer in watched scope. For</span>
<span class="sd"> example, after a notebook cell re-execution re-evaluating a pipeline</span>
<span class="sd"> creation, the last pipeline reference created by last evaluation will not be</span>
<span class="sd"> in watched scope anymore.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_tracked_user_pipelines</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
<span class="k">for</span> <span class="n">watching</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">watching</span><span class="p">():</span>
<span class="k">for</span> <span class="n">_</span><span class="p">,</span> <span class="n">val</span> <span class="ow">in</span> <span class="n">watching</span><span class="p">:</span>
<span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">val</span><span class="p">,</span> <span class="n">beam</span><span class="o">.</span><span class="n">pipeline</span><span class="o">.</span><span class="n">Pipeline</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_tracked_user_pipelines</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">val</span><span class="p">)</span></div>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">tracked_user_pipelines</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_tracked_user_pipelines</span></div>
</pre></div>
</div>
<div class="articleComments">
</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/snide/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">
var DOCUMENTATION_OPTIONS = {
URL_ROOT:'../../../../',
VERSION:'',
COLLAPSE_INDEX:false,
FILE_SUFFIX:'.html',
HAS_SOURCE: true,
SOURCELINK_SUFFIX: '.txt'
};
</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/js/theme.js"></script>
<script type="text/javascript">
jQuery(function () {
SphinxRtdTheme.StickyNav.enable();
});
</script>
</body>
</html>