| |
| |
| |
| |
| |
| <!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>airflow.contrib.example_dags.example_gcp_natural_language — Airflow 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 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" /> |
| |
| <script> |
| document.addEventListener('DOMContentLoaded', function() { |
| var el = document.getElementById('changelog'); |
| if (el !== null ) { |
| // [AIRFLOW-...] |
| el.innerHTML = el.innerHTML.replace( |
| /\[(AIRFLOW-[\d]+)\]/g, |
| `<a href="https://issues.apache.org/jira/browse/$1">[$1]</a>` |
| ); |
| // (#...) |
| el.innerHTML = el.innerHTML.replace( |
| /\(#([\d]+)\)/g, |
| `<a href="https://github.com/apache/airflow/pull/$1">(#$1)</a>` |
| ); |
| }; |
| }) |
| </script> |
| <script type="text/javascript"> |
| var _gaq = _gaq || []; |
| _gaq.push(['_setAccount', 'UA-140539454-1']); |
| _gaq.push(['_trackPageview']); |
| </script> |
| <style> |
| .example-header { |
| position: relative; |
| background: #9AAA7A; |
| padding: 8px 16px; |
| margin-bottom: 0; |
| } |
| .example-header--with-button { |
| padding-right: 166px; |
| } |
| .example-header:after{ |
| content: ''; |
| display: table; |
| clear: both; |
| } |
| .example-title { |
| display:block; |
| padding: 4px; |
| margin-right: 16px; |
| color: white; |
| overflow-x: auto; |
| } |
| .example-header-button { |
| top: 8px; |
| right: 16px; |
| position: absolute; |
| } |
| .example-header + .highlight-python { |
| margin-top: 0 !important; |
| } |
| .viewcode-button { |
| display: inline-block; |
| padding: 8px 16px; |
| border: 0; |
| margin: 0; |
| outline: 0; |
| border-radius: 2px; |
| -webkit-box-shadow: 0 3px 5px 0 rgba(0,0,0,.3); |
| box-shadow: 0 3px 6px 0 rgba(0,0,0,.3); |
| color: #404040; |
| background-color: #e7e7e7; |
| cursor: pointer; |
| font-size: 16px; |
| font-weight: 500; |
| line-height: 1; |
| text-decoration: none; |
| text-overflow: ellipsis; |
| overflow: hidden; |
| text-transform: uppercase; |
| -webkit-transition: background-color .2s; |
| transition: background-color .2s; |
| vertical-align: middle; |
| white-space: nowrap; |
| } |
| .viewcode-button:visited { |
| color: #404040; |
| } |
| .viewcode-button:hover, .viewcode-button:focus { |
| color: #404040; |
| background-color: #d6d6d6; |
| } |
| </style> |
| |
| </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"> Airflow |
| |
| |
| |
| </a> |
| |
| |
| |
| |
| <div class="version"> |
| 1.10.5 |
| </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="../../../../project.html">Project</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../license.html">License</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../start.html">Quick Start</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../installation.html">Installation</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../tutorial.html">Tutorial</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../howto/index.html">How-to Guides</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../ui.html">UI / Screenshots</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../concepts.html">Concepts</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../profiling.html">Data Profiling</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../cli.html">Command Line Interface Reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../scheduler.html">Scheduling & Triggers</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../plugins.html">Plugins</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../security.html">Security</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../timezone.html">Time zones</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../api.html">REST API Reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../integration.html">Integration</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../metrics.html">Metrics</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../kubernetes.html">Kubernetes</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../lineage.html">Lineage</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../changelog.html">Changelog</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../faq.html">FAQ</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../macros.html">Macros reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../_api/index.html">Python API Reference</a></li> |
| <li class="toctree-l1"><a class="reference internal" href="../../../../privacy_notice.html">Privacy Notice</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">Airflow</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> »</li> |
| |
| <li><a href="../../../index.html">Module code</a> »</li> |
| |
| <li>airflow.contrib.example_dags.example_gcp_natural_language</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 airflow.contrib.example_dags.example_gcp_natural_language</h1><div class="highlight"><pre> |
| <span></span><span class="c1"># -*- coding: utf-8 -*-</span> |
| <span class="c1">#</span> |
| <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span> |
| <span class="c1"># or more contributor license agreements. See the NOTICE file</span> |
| <span class="c1"># distributed with this work for additional information</span> |
| <span class="c1"># regarding copyright ownership. The ASF licenses this file</span> |
| <span class="c1"># to you under the Apache License, Version 2.0 (the</span> |
| <span class="c1"># "License"); you may not use this file except in compliance</span> |
| <span class="c1"># with 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,</span> |
| <span class="c1"># software distributed under the License is distributed on an</span> |
| <span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span> |
| <span class="c1"># KIND, either express or implied. See the License for the</span> |
| <span class="c1"># specific language governing permissions and limitations</span> |
| <span class="c1"># under the License.</span> |
| |
| <span class="sd">"""</span> |
| <span class="sd">Example Airflow DAG for Google Cloud Natural Language service</span> |
| <span class="sd">"""</span> |
| |
| |
| <span class="kn">from</span> <span class="nn">google.cloud.language_v1.proto.language_service_pb2</span> <span class="k">import</span> <span class="n">Document</span> |
| |
| <span class="kn">import</span> <span class="nn">airflow</span> |
| <span class="kn">from</span> <span class="nn">airflow</span> <span class="k">import</span> <span class="n">models</span> |
| <span class="kn">from</span> <span class="nn">airflow.contrib.operators.gcp_natural_language_operator</span> <span class="k">import</span> <span class="p">(</span> |
| <span class="n">CloudLanguageAnalyzeEntitiesOperator</span><span class="p">,</span> |
| <span class="n">CloudLanguageAnalyzeEntitySentimentOperator</span><span class="p">,</span> |
| <span class="n">CloudLanguageAnalyzeSentimentOperator</span><span class="p">,</span> |
| <span class="n">CloudLanguageClassifyTextOperator</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="kn">from</span> <span class="nn">airflow.operators.bash_operator</span> <span class="k">import</span> <span class="n">BashOperator</span> |
| |
| <span class="c1"># [START howto_operator_gcp_natural_language_document_text]</span> |
| <span class="n">TEXT</span> <span class="o">=</span> <span class="s2">"""</span> |
| <span class="s2">Airflow is a platform to programmatically author, schedule and monitor workflows.</span> |
| |
| <span class="s2">Use Airflow to author workflows as Directed Acyclic Graphs (DAGs) of tasks. The Airflow scheduler executes</span> |
| <span class="s2"> your tasks on an array of workers while following the specified dependencies. Rich command line utilities</span> |
| <span class="s2"> make performing complex surgeries on DAGs a snap. The rich user interface makes it easy to visualize</span> |
| <span class="s2"> pipelines running in production, monitor progress, and troubleshoot issues when needed.</span> |
| <span class="s2">"""</span> |
| <span class="n">document</span> <span class="o">=</span> <span class="n">Document</span><span class="p">(</span><span class="n">content</span><span class="o">=</span><span class="n">TEXT</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="s2">"PLAIN_TEXT"</span><span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_natural_language_document_text]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_natural_language_document_gcs]</span> |
| <span class="n">GCS_CONTENT_URI</span> <span class="o">=</span> <span class="s2">"gs://my-text-bucket/sentiment-me.txt"</span> |
| <span class="n">document_gcs</span> <span class="o">=</span> <span class="n">Document</span><span class="p">(</span><span class="n">gcs_content_uri</span><span class="o">=</span><span class="n">GCS_CONTENT_URI</span><span class="p">,</span> <span class="nb">type</span><span class="o">=</span><span class="s2">"PLAIN_TEXT"</span><span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_natural_language_document_gcs]</span> |
| |
| |
| <span class="n">default_args</span> <span class="o">=</span> <span class="p">{</span><span class="s2">"start_date"</span><span class="p">:</span> <span class="n">airflow</span><span class="o">.</span><span class="n">utils</span><span class="o">.</span><span class="n">dates</span><span class="o">.</span><span class="n">days_ago</span><span class="p">(</span><span class="mi">1</span><span class="p">)}</span> |
| |
| <span class="k">with</span> <span class="n">models</span><span class="o">.</span><span class="n">DAG</span><span class="p">(</span> |
| <span class="s2">"example_gcp_natural_language"</span><span class="p">,</span> |
| <span class="n">default_args</span><span class="o">=</span><span class="n">default_args</span><span class="p">,</span> |
| <span class="n">schedule_interval</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> <span class="c1"># Override to match your needs</span> |
| <span class="p">)</span> <span class="k">as</span> <span class="n">dag</span><span class="p">:</span> |
| |
| <span class="c1"># [START howto_operator_gcp_natural_language_analyze_entities]</span> |
| <span class="n">analyze_entities</span> <span class="o">=</span> <span class="n">CloudLanguageAnalyzeEntitiesOperator</span><span class="p">(</span><span class="n">document</span><span class="o">=</span><span class="n">document</span><span class="p">,</span> <span class="n">task_id</span><span class="o">=</span><span class="s2">"analyze_entities"</span><span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_natural_language_analyze_entities]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_natural_language_analyze_entities_result]</span> |
| <span class="n">analyze_entities_result</span> <span class="o">=</span> <span class="n">BashOperator</span><span class="p">(</span> |
| <span class="n">bash_command</span><span class="o">=</span><span class="s2">"echo </span><span class="se">\"</span><span class="s2">{{ task_instance.xcom_pull('analyze_entities') }}</span><span class="se">\"</span><span class="s2">"</span><span class="p">,</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"analyze_entities_result"</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_natural_language_analyze_entities_result]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_natural_language_analyze_entity_sentiment]</span> |
| <span class="n">analyze_entity_sentiment</span> <span class="o">=</span> <span class="n">CloudLanguageAnalyzeEntitySentimentOperator</span><span class="p">(</span> |
| <span class="n">document</span><span class="o">=</span><span class="n">document</span><span class="p">,</span> <span class="n">task_id</span><span class="o">=</span><span class="s2">"analyze_entity_sentiment"</span> |
| <span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_natural_language_analyze_entity_sentiment]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_natural_language_analyze_entity_sentiment_result]</span> |
| <span class="n">analyze_entity_sentiment_result</span> <span class="o">=</span> <span class="n">BashOperator</span><span class="p">(</span> |
| <span class="n">bash_command</span><span class="o">=</span><span class="s2">"echo </span><span class="se">\"</span><span class="s2">{{ task_instance.xcom_pull('analyze_entity_sentiment') }}</span><span class="se">\"</span><span class="s2">"</span><span class="p">,</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"analyze_entity_sentiment_result"</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_natural_language_analyze_entity_sentiment_result]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_natural_language_analyze_sentiment]</span> |
| <span class="n">analyze_sentiment</span> <span class="o">=</span> <span class="n">CloudLanguageAnalyzeSentimentOperator</span><span class="p">(</span><span class="n">document</span><span class="o">=</span><span class="n">document</span><span class="p">,</span> <span class="n">task_id</span><span class="o">=</span><span class="s2">"analyze_sentiment"</span><span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_natural_language_analyze_sentiment]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_natural_language_analyze_sentiment_result]</span> |
| <span class="n">analyze_sentiment_result</span> <span class="o">=</span> <span class="n">BashOperator</span><span class="p">(</span> |
| <span class="n">bash_command</span><span class="o">=</span><span class="s2">"echo </span><span class="se">\"</span><span class="s2">{{ task_instance.xcom_pull('analyze_sentiment') }}</span><span class="se">\"</span><span class="s2">"</span><span class="p">,</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"analyze_sentiment_result"</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_natural_language_analyze_sentiment_result]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_natural_language_analyze_classify_text]</span> |
| <span class="n">analyze_classify_text</span> <span class="o">=</span> <span class="n">CloudLanguageClassifyTextOperator</span><span class="p">(</span> |
| <span class="n">document</span><span class="o">=</span><span class="n">document</span><span class="p">,</span> <span class="n">task_id</span><span class="o">=</span><span class="s2">"analyze_classify_text"</span> |
| <span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_natural_language_analyze_classify_text]</span> |
| |
| <span class="c1"># [START howto_operator_gcp_natural_language_analyze_classify_text_result]</span> |
| <span class="n">analyze_classify_text_result</span> <span class="o">=</span> <span class="n">BashOperator</span><span class="p">(</span> |
| <span class="n">bash_command</span><span class="o">=</span><span class="s2">"echo </span><span class="se">\"</span><span class="s2">{{ task_instance.xcom_pull('analyze_classify_text') }}</span><span class="se">\"</span><span class="s2">"</span><span class="p">,</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"analyze_classify_text_result"</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="c1"># [END howto_operator_gcp_natural_language_analyze_classify_text_result]</span> |
| |
| <span class="n">analyze_entities</span> <span class="o">>></span> <span class="n">analyze_entities_result</span> |
| <span class="n">analyze_entity_sentiment</span> <span class="o">>></span> <span class="n">analyze_entity_sentiment_result</span> |
| <span class="n">analyze_sentiment</span> <span class="o">>></span> <span class="n">analyze_sentiment_result</span> |
| <span class="n">analyze_classify_text</span> <span class="o">>></span> <span class="n">analyze_classify_text_result</span> |
| </pre></div> |
| |
| </div> |
| |
| </div> |
| |
| |
| <footer> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| |
| </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>. |
| <div class="footer">This page uses <a href="https://analytics.google.com/"> |
| Google Analytics</a> to collect statistics. You can disable it by blocking |
| the JavaScript coming from www.google-analytics.com. Check our |
| <a href="../../../../privacy_notice.html">Privacy Policy</a> |
| for more details. |
| <script type="text/javascript"> |
| (function() { |
| var ga = document.createElement('script'); |
| ga.src = ('https:' == document.location.protocol ? |
| 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; |
| ga.setAttribute('async', 'true'); |
| var nodes = document.documentElement.childNodes; |
| var i = -1; |
| var node; |
| do { |
| i++; |
| node = nodes[i] |
| } while(node.nodeType !== Node.ELEMENT_NODE); |
| node.appendChild(ga); |
| })(); |
| </script> |
| </div> |
| |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| </body> |
| </html> |