blob: c246d4f10f0fab31a5cb21c54498b62e8685a9a3 [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.ml.gcp.naturallanguageml &mdash; Apache Beam 2.38.0 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">
2.38.0
</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.transforms.html">apache_beam.transforms package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.typehints.html">apache_beam.typehints package</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.utils.html">apache_beam.utils package</a></li>
</ul>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.error.html">apache_beam.error module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pvalue.html">apache_beam.pvalue module</a></li>
</ul>
</div>
</div>
</nav>
<section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">
<nav class="wy-nav-top" aria-label="top navigation">
<i data-toggle="wy-nav-top" class="fa fa-bars"></i>
<a href="../../../../index.html">Apache Beam</a>
</nav>
<div class="wy-nav-content">
<div class="rst-content">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../../../index.html">Docs</a> &raquo;</li>
<li><a href="../../../index.html">Module code</a> &raquo;</li>
<li>apache_beam.ml.gcp.naturallanguageml</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.ml.gcp.naturallanguageml</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="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Mapping</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Optional</span>
<span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Sequence</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">apache_beam</span> <span class="k">as</span> <span class="nn">beam</span>
<span class="kn">from</span> <span class="nn">apache_beam.metrics</span> <span class="kn">import</span> <span class="n">Metrics</span>
<span class="k">try</span><span class="p">:</span>
<span class="kn">from</span> <span class="nn">google.cloud</span> <span class="kn">import</span> <span class="n">language</span>
<span class="kn">from</span> <span class="nn">google.cloud.language</span> <span class="kn">import</span> <span class="n">enums</span> <span class="c1"># pylint: disable=unused-import</span>
<span class="kn">from</span> <span class="nn">google.cloud.language</span> <span class="kn">import</span> <span class="n">types</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;Google Cloud Natural Language API not supported for this execution &#39;</span>
<span class="s1">&#39;environment (could not import Natural Language API client).&#39;</span><span class="p">)</span>
<span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s1">&#39;Document&#39;</span><span class="p">,</span> <span class="s1">&#39;AnnotateText&#39;</span><span class="p">]</span>
<div class="viewcode-block" id="Document"><a class="viewcode-back" href="../../../../apache_beam.ml.gcp.naturallanguageml.html#apache_beam.ml.gcp.naturallanguageml.Document">[docs]</a><span class="k">class</span> <span class="nc">Document</span><span class="p">(</span><span class="nb">object</span><span class="p">):</span>
<span class="sd">&quot;&quot;&quot;Represents the input to :class:`AnnotateText` transform.</span>
<span class="sd"> Args:</span>
<span class="sd"> content (str): The content of the input or the Google Cloud Storage URI</span>
<span class="sd"> where the file is stored.</span>
<span class="sd"> type (`Union[str, google.cloud.language.enums.Document.Type]`): Text type.</span>
<span class="sd"> Possible values are `HTML`, `PLAIN_TEXT`. The default value is</span>
<span class="sd"> `PLAIN_TEXT`.</span>
<span class="sd"> language_hint (`Optional[str]`): The language of the text. If not specified,</span>
<span class="sd"> language will be automatically detected. Values should conform to</span>
<span class="sd"> ISO-639-1 standard.</span>
<span class="sd"> encoding (`Optional[str]`): Text encoding. Possible values are: `NONE`,</span>
<span class="sd"> `UTF8`, `UTF16`, `UTF32`. The default value is `UTF8`.</span>
<span class="sd"> from_gcs (bool): Whether the content should be interpret as a Google Cloud</span>
<span class="sd"> Storage URI. The default value is :data:`False`.</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">content</span><span class="p">,</span> <span class="c1"># type: str</span>
<span class="nb">type</span><span class="o">=</span><span class="s1">&#39;PLAIN_TEXT&#39;</span><span class="p">,</span> <span class="c1"># type: Union[str, enums.Document.Type]</span>
<span class="n">language_hint</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="c1"># type: Optional[str]</span>
<span class="n">encoding</span><span class="o">=</span><span class="s1">&#39;UTF8&#39;</span><span class="p">,</span> <span class="c1"># type: Optional[str]</span>
<span class="n">from_gcs</span><span class="o">=</span><span class="kc">False</span> <span class="c1"># type: bool</span>
<span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">content</span> <span class="o">=</span> <span class="n">content</span>
<span class="bp">self</span><span class="o">.</span><span class="n">type</span> <span class="o">=</span> <span class="nb">type</span>
<span class="bp">self</span><span class="o">.</span><span class="n">encoding</span> <span class="o">=</span> <span class="n">encoding</span>
<span class="bp">self</span><span class="o">.</span><span class="n">language_hint</span> <span class="o">=</span> <span class="n">language_hint</span>
<span class="bp">self</span><span class="o">.</span><span class="n">from_gcs</span> <span class="o">=</span> <span class="n">from_gcs</span>
<div class="viewcode-block" id="Document.to_dict"><a class="viewcode-back" href="../../../../apache_beam.ml.gcp.naturallanguageml.html#apache_beam.ml.gcp.naturallanguageml.Document.to_dict">[docs]</a> <span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">to_dict</span><span class="p">(</span><span class="n">document</span><span class="p">):</span>
<span class="c1"># type: (Document) -&gt; Mapping[str, Optional[str]]</span>
<span class="k">if</span> <span class="n">document</span><span class="o">.</span><span class="n">from_gcs</span><span class="p">:</span>
<span class="n">dict_repr</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;gcs_content_uri&#39;</span><span class="p">:</span> <span class="n">document</span><span class="o">.</span><span class="n">content</span><span class="p">}</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">dict_repr</span> <span class="o">=</span> <span class="p">{</span><span class="s1">&#39;content&#39;</span><span class="p">:</span> <span class="n">document</span><span class="o">.</span><span class="n">content</span><span class="p">}</span>
<span class="n">dict_repr</span><span class="o">.</span><span class="n">update</span><span class="p">({</span>
<span class="s1">&#39;type&#39;</span><span class="p">:</span> <span class="n">document</span><span class="o">.</span><span class="n">type</span><span class="p">,</span> <span class="s1">&#39;language&#39;</span><span class="p">:</span> <span class="n">document</span><span class="o">.</span><span class="n">language_hint</span>
<span class="p">})</span>
<span class="k">return</span> <span class="n">dict_repr</span></div></div>
<div class="viewcode-block" id="AnnotateText"><a class="viewcode-back" href="../../../../apache_beam.ml.gcp.naturallanguageml.html#apache_beam.ml.gcp.naturallanguageml.AnnotateText">[docs]</a><span class="nd">@beam</span><span class="o">.</span><span class="n">ptransform_fn</span>
<span class="k">def</span> <span class="nf">AnnotateText</span><span class="p">(</span>
<span class="n">pcoll</span><span class="p">,</span> <span class="c1"># type: beam.pvalue.PCollection</span>
<span class="n">features</span><span class="p">,</span> <span class="c1"># type: Union[Mapping[str, bool], types.AnnotateTextRequest.Features]</span>
<span class="n">timeout</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="c1"># type: Optional[float]</span>
<span class="n">metadata</span><span class="o">=</span><span class="kc">None</span> <span class="c1"># type: Optional[Sequence[Tuple[str, str]]]</span>
<span class="p">):</span>
<span class="sd">&quot;&quot;&quot;A :class:`~apache_beam.transforms.ptransform.PTransform`</span>
<span class="sd"> for annotating text using the Google Cloud Natural Language API:</span>
<span class="sd"> https://cloud.google.com/natural-language/docs.</span>
<span class="sd"> Args:</span>
<span class="sd"> pcoll (:class:`~apache_beam.pvalue.PCollection`): An input PCollection of</span>
<span class="sd"> :class:`Document` objects.</span>
<span class="sd"> features (`Union[Mapping[str, bool], types.AnnotateTextRequest.Features]`):</span>
<span class="sd"> A dictionary of natural language operations to be performed on given</span>
<span class="sd"> text in the following format::</span>
<span class="sd"> {&#39;extact_syntax&#39;=True, &#39;extract_entities&#39;=True}</span>
<span class="sd"> timeout (`Optional[float]`): The amount of time, in seconds, to wait</span>
<span class="sd"> for the request to complete. The timeout applies to each individual</span>
<span class="sd"> retry attempt.</span>
<span class="sd"> metadata (`Optional[Sequence[Tuple[str, str]]]`): Additional metadata</span>
<span class="sd"> that is provided to the method.</span>
<span class="sd"> &quot;&quot;&quot;</span>
<span class="k">return</span> <span class="n">pcoll</span> <span class="o">|</span> <span class="n">beam</span><span class="o">.</span><span class="n">ParDo</span><span class="p">(</span><span class="n">_AnnotateTextFn</span><span class="p">(</span><span class="n">features</span><span class="p">,</span> <span class="n">timeout</span><span class="p">,</span> <span class="n">metadata</span><span class="p">))</span></div>
<span class="nd">@beam</span><span class="o">.</span><span class="n">typehints</span><span class="o">.</span><span class="n">with_input_types</span><span class="p">(</span><span class="n">Document</span><span class="p">)</span>
<span class="nd">@beam</span><span class="o">.</span><span class="n">typehints</span><span class="o">.</span><span class="n">with_output_types</span><span class="p">(</span><span class="n">types</span><span class="o">.</span><span class="n">AnnotateTextResponse</span><span class="p">)</span>
<span class="k">class</span> <span class="nc">_AnnotateTextFn</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">features</span><span class="p">,</span> <span class="c1"># type: Union[Mapping[str, bool], types.AnnotateTextRequest.Features]</span>
<span class="n">timeout</span><span class="p">,</span> <span class="c1"># type: Optional[float]</span>
<span class="n">metadata</span><span class="o">=</span><span class="kc">None</span> <span class="c1"># type: Optional[Sequence[Tuple[str, str]]]</span>
<span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">features</span> <span class="o">=</span> <span class="n">features</span>
<span class="bp">self</span><span class="o">.</span><span class="n">timeout</span> <span class="o">=</span> <span class="n">timeout</span>
<span class="bp">self</span><span class="o">.</span><span class="n">metadata</span> <span class="o">=</span> <span class="n">metadata</span>
<span class="bp">self</span><span class="o">.</span><span class="n">api_calls</span> <span class="o">=</span> <span class="n">Metrics</span><span class="o">.</span><span class="n">counter</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="vm">__class__</span><span class="o">.</span><span class="vm">__name__</span><span class="p">,</span> <span class="s1">&#39;api_calls&#39;</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="kc">None</span>
<span class="k">def</span> <span class="nf">setup</span><span class="p">(</span><span class="bp">self</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="bp">self</span><span class="o">.</span><span class="n">_get_api_client</span><span class="p">()</span>
<span class="nd">@staticmethod</span>
<span class="k">def</span> <span class="nf">_get_api_client</span><span class="p">():</span>
<span class="c1"># type: () -&gt; language.LanguageServiceClient</span>
<span class="k">return</span> <span class="n">language</span><span class="o">.</span><span class="n">LanguageServiceClient</span><span class="p">()</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">response</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">client</span><span class="o">.</span><span class="n">annotate_text</span><span class="p">(</span>
<span class="n">document</span><span class="o">=</span><span class="n">Document</span><span class="o">.</span><span class="n">to_dict</span><span class="p">(</span><span class="n">element</span><span class="p">),</span>
<span class="n">features</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">features</span><span class="p">,</span>
<span class="n">encoding_type</span><span class="o">=</span><span class="n">element</span><span class="o">.</span><span class="n">encoding</span><span class="p">,</span>
<span class="n">timeout</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">timeout</span><span class="p">,</span>
<span class="n">metadata</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">metadata</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">api_calls</span><span class="o">.</span><span class="n">inc</span><span class="p">()</span>
<span class="k">yield</span> <span class="n">response</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>