| |
| |
| <!-- |
| Javascript to render AIRFLOW-XXX and PR references in text |
| as HTML links. |
| |
| Overrides extrahead block from sphinx_rtd_theme |
| https://www.sphinx-doc.org/en/master/templating.html |
| --> |
| |
| |
| <!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>Papermill — Airflow Documentation</title> |
| |
| |
| |
| |
| <link rel="shortcut icon" href="../../_static/pin_32.png"/> |
| |
| |
| |
| |
| |
| <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="stylesheet" href="../../_static/graphviz.css" type="text/css" /> |
| <link rel="index" title="Index" href="../../genindex.html" /> |
| <link rel="search" title="Search" href="../../search.html" /> |
| <link rel="next" title="PythonOperator" href="python.html" /> |
| <link rel="prev" title="Google Cloud Vision Operators" href="gcp/vision.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"> |
| 1.10.6 |
| </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 class="current"> |
| <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 current"><a class="reference internal" href="../index.html">How-to Guides</a><ul class="current"> |
| <li class="toctree-l2"><a class="reference internal" href="../set-config.html">Setting Configuration Options</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../initialize-database.html">Initializing a Database Backend</a></li> |
| <li class="toctree-l2 current"><a class="reference internal" href="index.html">Using Operators</a><ul class="current"> |
| <li class="toctree-l3"><a class="reference internal" href="bash.html">BashOperator</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="dingding.html">Dingding Operators</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="gcp/index.html">Google Cloud Operators</a></li> |
| <li class="toctree-l3 current"><a class="current reference internal" href="#">Papermill</a><ul> |
| <li class="toctree-l4"><a class="reference internal" href="#usage">Usage</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="python.html">PythonOperator</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l2"><a class="reference internal" href="../connection/index.html">Managing Connections</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../secure-connections.html">Securing Connections</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../secure-connections.html#rotating-encryption-keys">Rotating encryption keys</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../write-logs.html">Writing Logs</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../executor/use-celery.html">Celery Executor</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../executor/use-dask.html">Dask Executor</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../executor/use-mesos.html">Scaling Out with Mesos (community contributed)</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../run-behind-proxy.html">Running Airflow behind a reverse proxy</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../run-with-systemd.html">Running Airflow with systemd</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../run-with-upstart.html">Running Airflow with upstart</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../use-test-config.html">Using the Test Mode Configuration</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../check-health.html">Checking Airflow Health Status</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../define_extra_link.html">Define an operator extra link</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../tracking-user-activity.html">Tracking User Activity</a></li> |
| <li class="toctree-l2"><a class="reference internal" href="../cli-completion.html">Set Up Bash/Zsh Completion</a></li> |
| </ul> |
| </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="../../errors.html">Error Tracking</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> |
| <p class="caption"><span class="caption-text">References</span></p> |
| <ul> |
| <li class="toctree-l1"><a class="reference internal" href="../../_api/index.html">Python API</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">How-to Guides</a> »</li> |
| |
| <li><a href="index.html">Using Operators</a> »</li> |
| |
| <li>Papermill</li> |
| |
| |
| <li class="wy-breadcrumbs-aside"> |
| |
| |
| <a href="../../_sources/howto/operator/papermill.rst.txt" rel="nofollow"> View page source</a> |
| |
| |
| </li> |
| |
| </ul> |
| |
| |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <blockquote> |
| <div></div></blockquote> |
| <div class="section" id="papermill"> |
| <h1>Papermill<a class="headerlink" href="#papermill" title="Permalink to this headline">¶</a></h1> |
| <p>Apache Airflow supports integration with <a class="reference external" href="https://papermill.readthedocs.io/en/latest/">Papermill</a>. Papermill is a tool for |
| parameterizing and executing Jupyter Notebooks. Perhaps you have a financial |
| report that you wish to run with different values on the first or last day of |
| a month or at the beginning or end of the year. Using <em>parameters</em> in your |
| notebook and using the <em>PapermillOperator</em> makes this a breeze.</p> |
| <div class="section" id="usage"> |
| <h2>Usage<a class="headerlink" href="#usage" title="Permalink to this headline">¶</a></h2> |
| <div class="section" id="creating-a-notebook"> |
| <h3>Creating a notebook<a class="headerlink" href="#creating-a-notebook" title="Permalink to this headline">¶</a></h3> |
| <p>To parameterize your notebook designate a cell with the tag parameters. Papermill |
| looks for the parameters cell and treats this cell as defaults for the parameters |
| passed in at execution time. Papermill will add a new cell tagged with injected-parameters |
| with input parameters in order to overwrite the values in parameters. If no cell is |
| tagged with parameters the injected cell will be inserted at the top of the notebook.</p> |
| <p>Note that Jupyter notebook has out of the box support for tags but you need to install |
| the celltags extension for Jupyter Lab: <code class="docutils literal notranslate"><span class="pre">jupyter</span> <span class="pre">labextension</span> <span class="pre">install</span> <span class="pre">@jupyterlab/celltags</span></code></p> |
| <p>Make sure that you save your notebook somewhere so that Airflow can access it. Papermill |
| supports S3, GCS, Azure and Local. HDFS is <em>not</em> supported.</p> |
| </div> |
| <div class="section" id="example-dag"> |
| <h3>Example DAG<a class="headerlink" href="#example-dag" title="Permalink to this headline">¶</a></h3> |
| <p>Use the <code class="xref py py-class docutils literal notranslate"><span class="pre">PapermillOperator</span></code> |
| to execute a jupyter notebook:</p> |
| <div class="example-block-wrapper docutils container"> |
| <p class="example-header example-header--with-button"><span class="example-title">airflow/contrib/example_dags/example_papermill_operator.py</span><a class="example-header-button viewcode-button reference internal" href="../../_modules/airflow/contrib/example_dags/example_papermill_operator.html"><span>View Source</span></a></p> |
| <div class="highlight-python notranslate"><div class="highlight"><pre><span></span><span class="n">run_this</span> <span class="o">=</span> <span class="n">PapermillOperator</span><span class="p">(</span> |
| <span class="n">task_id</span><span class="o">=</span><span class="s2">"run_example_notebook"</span><span class="p">,</span> |
| <span class="n">input_nb</span><span class="o">=</span><span class="s2">"/tmp/hello_world.ipynb"</span><span class="p">,</span> |
| <span class="n">output_nb</span><span class="o">=</span><span class="s2">"/tmp/out-{{ execution_date }}.ipynb"</span><span class="p">,</span> |
| <span class="n">parameters</span><span class="o">=</span><span class="p">{</span><span class="s2">"msgs"</span><span class="p">:</span> <span class="s2">"Ran from Airflow at {{ execution_date }}!"</span><span class="p">}</span> |
| <span class="p">)</span> |
| </pre></div> |
| </div> |
| </div> |
| </div> |
| </div> |
| </div> |
| |
| |
| </div> |
| |
| </div> |
| |
| |
| <footer> |
| |
| <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> |
| |
| <a href="python.html" class="btn btn-neutral float-right" title="PythonOperator" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right"></span></a> |
| |
| |
| <a href="gcp/vision.html" class="btn btn-neutral float-left" title="Google Cloud Vision Operators" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left"></span> Previous</a> |
| |
| </div> |
| |
| |
| <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> |
