| |
| |
| |
| |
| <!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.operators.mlengine_operator — 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> |
| <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"> |
| 1.10.4 |
| </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</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">Experimental Rest API</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">API Reference</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><a href="../operators.html">airflow.contrib.operators</a> »</li> |
| |
| <li>airflow.contrib.operators.mlengine_operator</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.operators.mlengine_operator</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 'License'); 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 'AS IS' 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="kn">import</span> <span class="nn">re</span> |
| |
| <span class="kn">from</span> <span class="nn">googleapiclient.errors</span> <span class="k">import</span> <span class="n">HttpError</span> |
| |
| <span class="kn">from</span> <span class="nn">airflow.contrib.hooks.gcp_mlengine_hook</span> <span class="k">import</span> <span class="n">MLEngineHook</span> |
| <span class="kn">from</span> <span class="nn">airflow.exceptions</span> <span class="k">import</span> <span class="n">AirflowException</span> |
| <span class="kn">from</span> <span class="nn">airflow.operators</span> <span class="k">import</span> <span class="n">BaseOperator</span> |
| <span class="kn">from</span> <span class="nn">airflow.utils.decorators</span> <span class="k">import</span> <span class="n">apply_defaults</span> |
| <span class="kn">from</span> <span class="nn">airflow.utils.log.logging_mixin</span> <span class="k">import</span> <span class="n">LoggingMixin</span> |
| |
| <div class="viewcode-block" id="log"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/mlengine_operator/index.html#airflow.contrib.operators.mlengine_operator.log">[docs]</a><span class="n">log</span> <span class="o">=</span> <span class="n">LoggingMixin</span><span class="p">()</span><span class="o">.</span><span class="n">log</span></div> |
| |
| |
| <div class="viewcode-block" id="_normalize_mlengine_job_id"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/mlengine_operator/index.html#airflow.contrib.operators.mlengine_operator._normalize_mlengine_job_id">[docs]</a><span class="k">def</span> <span class="nf">_normalize_mlengine_job_id</span><span class="p">(</span><span class="n">job_id</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Replaces invalid MLEngine job_id characters with '_'.</span> |
| |
| <span class="sd"> This also adds a leading 'z' in case job_id starts with an invalid</span> |
| <span class="sd"> character.</span> |
| |
| <span class="sd"> Args:</span> |
| <span class="sd"> job_id: A job_id str that may have invalid characters.</span> |
| |
| <span class="sd"> Returns:</span> |
| <span class="sd"> A valid job_id representation.</span> |
| <span class="sd"> """</span> |
| |
| <span class="c1"># Add a prefix when a job_id starts with a digit or a template</span> |
| <span class="n">match</span> <span class="o">=</span> <span class="n">re</span><span class="o">.</span><span class="n">search</span><span class="p">(</span><span class="sa">r</span><span class="s1">'\d|\{{2}'</span><span class="p">,</span> <span class="n">job_id</span><span class="p">)</span> |
| <span class="k">if</span> <span class="n">match</span> <span class="ow">and</span> <span class="n">match</span><span class="o">.</span><span class="n">start</span><span class="p">()</span> <span class="o">==</span> <span class="mi">0</span><span class="p">:</span> |
| <span class="n">job</span> <span class="o">=</span> <span class="s1">'z_</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">job_id</span><span class="p">)</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">job</span> <span class="o">=</span> <span class="n">job_id</span> |
| |
| <span class="c1"># Clean up 'bad' characters except templates</span> |
| <span class="n">tracker</span> <span class="o">=</span> <span class="mi">0</span> |
| <span class="n">cleansed_job_id</span> <span class="o">=</span> <span class="s1">''</span> |
| <span class="k">for</span> <span class="n">m</span> <span class="ow">in</span> <span class="n">re</span><span class="o">.</span><span class="n">finditer</span><span class="p">(</span><span class="sa">r</span><span class="s1">'\{{2}.+?\}</span><span class="si">{2}</span><span class="s1">'</span><span class="p">,</span> <span class="n">job</span><span class="p">):</span> |
| <span class="n">cleansed_job_id</span> <span class="o">+=</span> <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="sa">r</span><span class="s1">'[^0-9a-zA-Z]+'</span><span class="p">,</span> <span class="s1">'_'</span><span class="p">,</span> |
| <span class="n">job</span><span class="p">[</span><span class="n">tracker</span><span class="p">:</span><span class="n">m</span><span class="o">.</span><span class="n">start</span><span class="p">()])</span> |
| <span class="n">cleansed_job_id</span> <span class="o">+=</span> <span class="n">job</span><span class="p">[</span><span class="n">m</span><span class="o">.</span><span class="n">start</span><span class="p">():</span><span class="n">m</span><span class="o">.</span><span class="n">end</span><span class="p">()]</span> |
| <span class="n">tracker</span> <span class="o">=</span> <span class="n">m</span><span class="o">.</span><span class="n">end</span><span class="p">()</span> |
| |
| <span class="c1"># Clean up last substring or the full string if no templates</span> |
| <span class="n">cleansed_job_id</span> <span class="o">+=</span> <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</span><span class="sa">r</span><span class="s1">'[^0-9a-zA-Z]+'</span><span class="p">,</span> <span class="s1">'_'</span><span class="p">,</span> <span class="n">job</span><span class="p">[</span><span class="n">tracker</span><span class="p">:])</span> |
| |
| <span class="k">return</span> <span class="n">cleansed_job_id</span></div> |
| |
| |
| <div class="viewcode-block" id="MLEngineBatchPredictionOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/mlengine_operator/index.html#airflow.contrib.operators.mlengine_operator.MLEngineBatchPredictionOperator">[docs]</a><span class="k">class</span> <span class="nc">MLEngineBatchPredictionOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Start a Google Cloud ML Engine prediction job.</span> |
| |
| <span class="sd"> NOTE: For model origin, users should consider exactly one from the</span> |
| <span class="sd"> three options below:</span> |
| |
| <span class="sd"> 1. Populate ``uri`` field only, which should be a GCS location that</span> |
| <span class="sd"> points to a tensorflow savedModel directory.</span> |
| <span class="sd"> 2. Populate ``model_name`` field only, which refers to an existing</span> |
| <span class="sd"> model, and the default version of the model will be used.</span> |
| <span class="sd"> 3. Populate both ``model_name`` and ``version_name`` fields, which</span> |
| <span class="sd"> refers to a specific version of a specific model.</span> |
| |
| <span class="sd"> In options 2 and 3, both model and version name should contain the</span> |
| <span class="sd"> minimal identifier. For instance, call::</span> |
| |
| <span class="sd"> MLEngineBatchPredictionOperator(</span> |
| <span class="sd"> ...,</span> |
| <span class="sd"> model_name='my_model',</span> |
| <span class="sd"> version_name='my_version',</span> |
| <span class="sd"> ...)</span> |
| |
| <span class="sd"> if the desired model version is</span> |
| <span class="sd"> ``projects/my_project/models/my_model/versions/my_version``.</span> |
| |
| <span class="sd"> See https://cloud.google.com/ml-engine/reference/rest/v1/projects.jobs</span> |
| <span class="sd"> for further documentation on the parameters.</span> |
| |
| <span class="sd"> :param project_id: The Google Cloud project name where the</span> |
| <span class="sd"> prediction job is submitted. (templated)</span> |
| <span class="sd"> :type project_id: str</span> |
| |
| <span class="sd"> :param job_id: A unique id for the prediction job on Google Cloud</span> |
| <span class="sd"> ML Engine. (templated)</span> |
| <span class="sd"> :type job_id: str</span> |
| |
| <span class="sd"> :param data_format: The format of the input data.</span> |
| <span class="sd"> It will default to 'DATA_FORMAT_UNSPECIFIED' if is not provided</span> |
| <span class="sd"> or is not one of ["TEXT", "TF_RECORD", "TF_RECORD_GZIP"].</span> |
| <span class="sd"> :type data_format: str</span> |
| |
| <span class="sd"> :param input_paths: A list of GCS paths of input data for batch</span> |
| <span class="sd"> prediction. Accepting wildcard operator ``*``, but only at the end. (templated)</span> |
| <span class="sd"> :type input_paths: list[str]</span> |
| |
| <span class="sd"> :param output_path: The GCS path where the prediction results are</span> |
| <span class="sd"> written to. (templated)</span> |
| <span class="sd"> :type output_path: str</span> |
| |
| <span class="sd"> :param region: The Google Compute Engine region to run the</span> |
| <span class="sd"> prediction job in. (templated)</span> |
| <span class="sd"> :type region: str</span> |
| |
| <span class="sd"> :param model_name: The Google Cloud ML Engine model to use for prediction.</span> |
| <span class="sd"> If version_name is not provided, the default version of this</span> |
| <span class="sd"> model will be used.</span> |
| <span class="sd"> Should not be None if version_name is provided.</span> |
| <span class="sd"> Should be None if uri is provided. (templated)</span> |
| <span class="sd"> :type model_name: str</span> |
| |
| <span class="sd"> :param version_name: The Google Cloud ML Engine model version to use for</span> |
| <span class="sd"> prediction.</span> |
| <span class="sd"> Should be None if uri is provided. (templated)</span> |
| <span class="sd"> :type version_name: str</span> |
| |
| <span class="sd"> :param uri: The GCS path of the saved model to use for prediction.</span> |
| <span class="sd"> Should be None if model_name is provided.</span> |
| <span class="sd"> It should be a GCS path pointing to a tensorflow SavedModel. (templated)</span> |
| <span class="sd"> :type uri: str</span> |
| |
| <span class="sd"> :param max_worker_count: The maximum number of workers to be used</span> |
| <span class="sd"> for parallel processing. Defaults to 10 if not specified.</span> |
| <span class="sd"> :type max_worker_count: int</span> |
| |
| <span class="sd"> :param runtime_version: The Google Cloud ML Engine runtime version to use</span> |
| <span class="sd"> for batch prediction.</span> |
| <span class="sd"> :type runtime_version: str</span> |
| |
| <span class="sd"> :param signature_name: The name of the signature defined in the SavedModel</span> |
| <span class="sd"> to use for this job.</span> |
| <span class="sd"> :type signature_name: str</span> |
| |
| <span class="sd"> :param gcp_conn_id: The connection ID used for connection to Google</span> |
| <span class="sd"> Cloud Platform.</span> |
| <span class="sd"> :type gcp_conn_id: str</span> |
| |
| <span class="sd"> :param delegate_to: The account to impersonate, if any.</span> |
| <span class="sd"> For this to work, the service account making the request must</span> |
| <span class="sd"> have domain-wide delegation enabled.</span> |
| <span class="sd"> :type delegate_to: str</span> |
| |
| <span class="sd"> :raises: ``ValueError``: if a unique model/version origin cannot be</span> |
| <span class="sd"> determined.</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="MLEngineBatchPredictionOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/mlengine_operator/index.html#airflow.contrib.operators.mlengine_operator.MLEngineBatchPredictionOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="s1">'_project_id'</span><span class="p">,</span> |
| <span class="s1">'_job_id'</span><span class="p">,</span> |
| <span class="s1">'_region'</span><span class="p">,</span> |
| <span class="s1">'_input_paths'</span><span class="p">,</span> |
| <span class="s1">'_output_path'</span><span class="p">,</span> |
| <span class="s1">'_model_name'</span><span class="p">,</span> |
| <span class="s1">'_version_name'</span><span class="p">,</span> |
| <span class="s1">'_uri'</span><span class="p">,</span></div> |
| <span class="p">]</span> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="p">,</span> |
| <span class="n">job_id</span><span class="p">,</span> |
| <span class="n">region</span><span class="p">,</span> |
| <span class="n">data_format</span><span class="p">,</span> |
| <span class="n">input_paths</span><span class="p">,</span> |
| <span class="n">output_path</span><span class="p">,</span> |
| <span class="n">model_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">version_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">uri</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">max_worker_count</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">runtime_version</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">signature_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">gcp_conn_id</span><span class="o">=</span><span class="s1">'google_cloud_default'</span><span class="p">,</span> |
| <span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="o">*</span><span class="n">args</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">MLEngineBatchPredictionOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| |
| <span class="bp">self</span><span class="o">.</span><span class="n">_project_id</span> <span class="o">=</span> <span class="n">project_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_job_id</span> <span class="o">=</span> <span class="n">job_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_region</span> <span class="o">=</span> <span class="n">region</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_data_format</span> <span class="o">=</span> <span class="n">data_format</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_input_paths</span> <span class="o">=</span> <span class="n">input_paths</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_output_path</span> <span class="o">=</span> <span class="n">output_path</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_model_name</span> <span class="o">=</span> <span class="n">model_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_version_name</span> <span class="o">=</span> <span class="n">version_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_uri</span> <span class="o">=</span> <span class="n">uri</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_max_worker_count</span> <span class="o">=</span> <span class="n">max_worker_count</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_runtime_version</span> <span class="o">=</span> <span class="n">runtime_version</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_signature_name</span> <span class="o">=</span> <span class="n">signature_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_project_id</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'Google Cloud project id is required.'</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">_job_id</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span> |
| <span class="s1">'An unique job id is required for Google MLEngine prediction '</span> |
| <span class="s1">'job.'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_uri</span><span class="p">:</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model_name</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">_version_name</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'Ambiguous model origin: Both uri and '</span> |
| <span class="s1">'model/version name are provided.'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_version_name</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model_name</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span> |
| <span class="s1">'Missing model: Batch prediction expects '</span> |
| <span class="s1">'a model name when a version name is provided.'</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_uri</span> <span class="ow">or</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model_name</span><span class="p">):</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span> |
| <span class="s1">'Missing model origin: Batch prediction expects a model, '</span> |
| <span class="s1">'a model & version combination, or a URI to a savedModel.'</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="MLEngineBatchPredictionOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/mlengine_operator/index.html#airflow.contrib.operators.mlengine_operator.MLEngineBatchPredictionOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="n">job_id</span> <span class="o">=</span> <span class="n">_normalize_mlengine_job_id</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_job_id</span><span class="p">)</span> |
| <span class="n">prediction_request</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="s1">'jobId'</span><span class="p">:</span> <span class="n">job_id</span><span class="p">,</span> |
| <span class="s1">'predictionInput'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'dataFormat'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_data_format</span><span class="p">,</span> |
| <span class="s1">'inputPaths'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_input_paths</span><span class="p">,</span> |
| <span class="s1">'outputPath'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_output_path</span><span class="p">,</span> |
| <span class="s1">'region'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_region</span> |
| <span class="p">}</span> |
| <span class="p">}</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_uri</span><span class="p">:</span> |
| <span class="n">prediction_request</span><span class="p">[</span><span class="s1">'predictionInput'</span><span class="p">][</span><span class="s1">'uri'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_uri</span> |
| <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model_name</span><span class="p">:</span> |
| <span class="n">origin_name</span> <span class="o">=</span> <span class="s1">'projects/</span><span class="si">{}</span><span class="s1">/models/</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_project_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model_name</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">_version_name</span><span class="p">:</span> |
| <span class="n">prediction_request</span><span class="p">[</span><span class="s1">'predictionInput'</span><span class="p">][</span> |
| <span class="s1">'modelName'</span><span class="p">]</span> <span class="o">=</span> <span class="n">origin_name</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="n">prediction_request</span><span class="p">[</span><span class="s1">'predictionInput'</span><span class="p">][</span><span class="s1">'versionName'</span><span class="p">]</span> <span class="o">=</span> \ |
| <span class="n">origin_name</span> <span class="o">+</span> <span class="s1">'/versions/</span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_version_name</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_max_worker_count</span><span class="p">:</span> |
| <span class="n">prediction_request</span><span class="p">[</span><span class="s1">'predictionInput'</span><span class="p">][</span> |
| <span class="s1">'maxWorkerCount'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_max_worker_count</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_runtime_version</span><span class="p">:</span> |
| <span class="n">prediction_request</span><span class="p">[</span><span class="s1">'predictionInput'</span><span class="p">][</span> |
| <span class="s1">'runtimeVersion'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_runtime_version</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_signature_name</span><span class="p">:</span> |
| <span class="n">prediction_request</span><span class="p">[</span><span class="s1">'predictionInput'</span><span class="p">][</span> |
| <span class="s1">'signatureName'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_signature_name</span> |
| |
| <span class="n">hook</span> <span class="o">=</span> <span class="n">MLEngineHook</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_gcp_conn_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_delegate_to</span><span class="p">)</span> |
| |
| <span class="c1"># Helper method to check if the existing job's prediction input is the</span> |
| <span class="c1"># same as the request we get here.</span> |
| <span class="k">def</span> <span class="nf">check_existing_job</span><span class="p">(</span><span class="n">existing_job</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">existing_job</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'predictionInput'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> <span class="o">==</span> \ |
| <span class="n">prediction_request</span><span class="p">[</span><span class="s1">'predictionInput'</span><span class="p">]</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">finished_prediction_job</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">create_job</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_project_id</span><span class="p">,</span> <span class="n">prediction_request</span><span class="p">,</span> <span class="n">check_existing_job</span><span class="p">)</span> |
| <span class="k">except</span> <span class="n">HttpError</span><span class="p">:</span> |
| <span class="k">raise</span> |
| |
| <span class="k">if</span> <span class="n">finished_prediction_job</span><span class="p">[</span><span class="s1">'state'</span><span class="p">]</span> <span class="o">!=</span> <span class="s1">'SUCCEEDED'</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">error</span><span class="p">(</span> |
| <span class="s1">'MLEngine batch prediction job failed: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">finished_prediction_job</span><span class="p">)</span> |
| <span class="p">)</span> |
| <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="n">finished_prediction_job</span><span class="p">[</span><span class="s1">'errorMessage'</span><span class="p">])</span> |
| |
| <span class="k">return</span> <span class="n">finished_prediction_job</span><span class="p">[</span><span class="s1">'predictionOutput'</span><span class="p">]</span></div></div> |
| |
| |
| <div class="viewcode-block" id="MLEngineModelOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/mlengine_operator/index.html#airflow.contrib.operators.mlengine_operator.MLEngineModelOperator">[docs]</a><span class="k">class</span> <span class="nc">MLEngineModelOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Operator for managing a Google Cloud ML Engine model.</span> |
| |
| <span class="sd"> :param project_id: The Google Cloud project name to which MLEngine</span> |
| <span class="sd"> model belongs. (templated)</span> |
| <span class="sd"> :type project_id: str</span> |
| <span class="sd"> :param model: A dictionary containing the information about the model.</span> |
| <span class="sd"> If the `operation` is `create`, then the `model` parameter should</span> |
| <span class="sd"> contain all the information about this model such as `name`.</span> |
| |
| <span class="sd"> If the `operation` is `get`, the `model` parameter</span> |
| <span class="sd"> should contain the `name` of the model.</span> |
| <span class="sd"> :type model: dict</span> |
| <span class="sd"> :param operation: The operation to perform. Available operations are:</span> |
| |
| <span class="sd"> * ``create``: Creates a new model as provided by the `model` parameter.</span> |
| <span class="sd"> * ``get``: Gets a particular model where the name is specified in `model`.</span> |
| <span class="sd"> :type operation: str</span> |
| <span class="sd"> :param gcp_conn_id: The connection ID to use when fetching connection info.</span> |
| <span class="sd"> :type gcp_conn_id: str</span> |
| <span class="sd"> :param delegate_to: The account to impersonate, if any.</span> |
| <span class="sd"> For this to work, the service account making the request must have</span> |
| <span class="sd"> domain-wide delegation enabled.</span> |
| <span class="sd"> :type delegate_to: str</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="MLEngineModelOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/mlengine_operator/index.html#airflow.contrib.operators.mlengine_operator.MLEngineModelOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="s1">'_model'</span><span class="p">,</span></div> |
| <span class="p">]</span> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="p">,</span> |
| <span class="n">model</span><span class="p">,</span> |
| <span class="n">operation</span><span class="o">=</span><span class="s1">'create'</span><span class="p">,</span> |
| <span class="n">gcp_conn_id</span><span class="o">=</span><span class="s1">'google_cloud_default'</span><span class="p">,</span> |
| <span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="o">*</span><span class="n">args</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">MLEngineModelOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_project_id</span> <span class="o">=</span> <span class="n">project_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_model</span> <span class="o">=</span> <span class="n">model</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_operation</span> <span class="o">=</span> <span class="n">operation</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> |
| |
| <div class="viewcode-block" id="MLEngineModelOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/mlengine_operator/index.html#airflow.contrib.operators.mlengine_operator.MLEngineModelOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="n">hook</span> <span class="o">=</span> <span class="n">MLEngineHook</span><span class="p">(</span> |
| <span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_gcp_conn_id</span><span class="p">,</span> <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_delegate_to</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_operation</span> <span class="o">==</span> <span class="s1">'create'</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">hook</span><span class="o">.</span><span class="n">create_model</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_project_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">_operation</span> <span class="o">==</span> <span class="s1">'get'</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">hook</span><span class="o">.</span><span class="n">get_model</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_project_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="p">[</span><span class="s1">'name'</span><span class="p">])</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Unknown operation: </span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_operation</span><span class="p">))</span></div></div> |
| |
| |
| <div class="viewcode-block" id="MLEngineVersionOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/mlengine_operator/index.html#airflow.contrib.operators.mlengine_operator.MLEngineVersionOperator">[docs]</a><span class="k">class</span> <span class="nc">MLEngineVersionOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Operator for managing a Google Cloud ML Engine version.</span> |
| |
| <span class="sd"> :param project_id: The Google Cloud project name to which MLEngine</span> |
| <span class="sd"> model belongs.</span> |
| <span class="sd"> :type project_id: str</span> |
| |
| <span class="sd"> :param model_name: The name of the Google Cloud ML Engine model that the version</span> |
| <span class="sd"> belongs to. (templated)</span> |
| <span class="sd"> :type model_name: str</span> |
| |
| <span class="sd"> :param version_name: A name to use for the version being operated upon.</span> |
| <span class="sd"> If not None and the `version` argument is None or does not have a value for</span> |
| <span class="sd"> the `name` key, then this will be populated in the payload for the</span> |
| <span class="sd"> `name` key. (templated)</span> |
| <span class="sd"> :type version_name: str</span> |
| |
| <span class="sd"> :param version: A dictionary containing the information about the version.</span> |
| <span class="sd"> If the `operation` is `create`, `version` should contain all the</span> |
| <span class="sd"> information about this version such as name, and deploymentUrl.</span> |
| <span class="sd"> If the `operation` is `get` or `delete`, the `version` parameter</span> |
| <span class="sd"> should contain the `name` of the version.</span> |
| <span class="sd"> If it is None, the only `operation` possible would be `list`. (templated)</span> |
| <span class="sd"> :type version: dict</span> |
| |
| <span class="sd"> :param operation: The operation to perform. Available operations are:</span> |
| |
| <span class="sd"> * ``create``: Creates a new version in the model specified by `model_name`,</span> |
| <span class="sd"> in which case the `version` parameter should contain all the</span> |
| <span class="sd"> information to create that version</span> |
| <span class="sd"> (e.g. `name`, `deploymentUrl`).</span> |
| |
| <span class="sd"> * ``get``: Gets full information of a particular version in the model</span> |
| <span class="sd"> specified by `model_name`.</span> |
| <span class="sd"> The name of the version should be specified in the `version`</span> |
| <span class="sd"> parameter.</span> |
| |
| <span class="sd"> * ``list``: Lists all available versions of the model specified</span> |
| <span class="sd"> by `model_name`.</span> |
| |
| <span class="sd"> * ``delete``: Deletes the version specified in `version` parameter from the</span> |
| <span class="sd"> model specified by `model_name`).</span> |
| <span class="sd"> The name of the version should be specified in the `version`</span> |
| <span class="sd"> parameter.</span> |
| <span class="sd"> :type operation: str</span> |
| |
| <span class="sd"> :param gcp_conn_id: The connection ID to use when fetching connection info.</span> |
| <span class="sd"> :type gcp_conn_id: str</span> |
| |
| <span class="sd"> :param delegate_to: The account to impersonate, if any.</span> |
| <span class="sd"> For this to work, the service account making the request must have</span> |
| <span class="sd"> domain-wide delegation enabled.</span> |
| <span class="sd"> :type delegate_to: str</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="MLEngineVersionOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/mlengine_operator/index.html#airflow.contrib.operators.mlengine_operator.MLEngineVersionOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="s1">'_model_name'</span><span class="p">,</span> |
| <span class="s1">'_version_name'</span><span class="p">,</span> |
| <span class="s1">'_version'</span><span class="p">,</span></div> |
| <span class="p">]</span> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="p">,</span> |
| <span class="n">model_name</span><span class="p">,</span> |
| <span class="n">version_name</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">version</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">operation</span><span class="o">=</span><span class="s1">'create'</span><span class="p">,</span> |
| <span class="n">gcp_conn_id</span><span class="o">=</span><span class="s1">'google_cloud_default'</span><span class="p">,</span> |
| <span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="o">*</span><span class="n">args</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| |
| <span class="nb">super</span><span class="p">(</span><span class="n">MLEngineVersionOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_project_id</span> <span class="o">=</span> <span class="n">project_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_model_name</span> <span class="o">=</span> <span class="n">model_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_version_name</span> <span class="o">=</span> <span class="n">version_name</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_version</span> <span class="o">=</span> <span class="n">version</span> <span class="ow">or</span> <span class="p">{}</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_operation</span> <span class="o">=</span> <span class="n">operation</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> |
| |
| <div class="viewcode-block" id="MLEngineVersionOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/mlengine_operator/index.html#airflow.contrib.operators.mlengine_operator.MLEngineVersionOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="k">if</span> <span class="s1">'name'</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">_version</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_version</span><span class="p">[</span><span class="s1">'name'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_version_name</span> |
| |
| <span class="n">hook</span> <span class="o">=</span> <span class="n">MLEngineHook</span><span class="p">(</span> |
| <span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_gcp_conn_id</span><span class="p">,</span> <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_delegate_to</span><span class="p">)</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_operation</span> <span class="o">==</span> <span class="s1">'create'</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">_version</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s2">"version attribute of </span><span class="si">{}</span><span class="s2"> could not "</span> |
| <span class="s2">"be empty"</span><span class="o">.</span><span class="n">format</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="k">return</span> <span class="n">hook</span><span class="o">.</span><span class="n">create_version</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_project_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model_name</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_version</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">_operation</span> <span class="o">==</span> <span class="s1">'set_default'</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">hook</span><span class="o">.</span><span class="n">set_default_version</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_project_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model_name</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_version</span><span class="p">[</span><span class="s1">'name'</span><span class="p">])</span> |
| <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">_operation</span> <span class="o">==</span> <span class="s1">'list'</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">hook</span><span class="o">.</span><span class="n">list_versions</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_project_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model_name</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="bp">self</span><span class="o">.</span><span class="n">_operation</span> <span class="o">==</span> <span class="s1">'delete'</span><span class="p">:</span> |
| <span class="k">return</span> <span class="n">hook</span><span class="o">.</span><span class="n">delete_version</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_project_id</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model_name</span><span class="p">,</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_version</span><span class="p">[</span><span class="s1">'name'</span><span class="p">])</span> |
| <span class="k">else</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Unknown operation: </span><span class="si">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_operation</span><span class="p">))</span></div></div> |
| |
| |
| <div class="viewcode-block" id="MLEngineTrainingOperator"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/mlengine_operator/index.html#airflow.contrib.operators.mlengine_operator.MLEngineTrainingOperator">[docs]</a><span class="k">class</span> <span class="nc">MLEngineTrainingOperator</span><span class="p">(</span><span class="n">BaseOperator</span><span class="p">):</span> |
| <span class="sd">"""</span> |
| <span class="sd"> Operator for launching a MLEngine training job.</span> |
| |
| <span class="sd"> :param project_id: The Google Cloud project name within which MLEngine</span> |
| <span class="sd"> training job should run (templated).</span> |
| <span class="sd"> :type project_id: str</span> |
| |
| <span class="sd"> :param job_id: A unique templated id for the submitted Google MLEngine</span> |
| <span class="sd"> training job. (templated)</span> |
| <span class="sd"> :type job_id: str</span> |
| |
| <span class="sd"> :param package_uris: A list of package locations for MLEngine training job,</span> |
| <span class="sd"> which should include the main training program + any additional</span> |
| <span class="sd"> dependencies. (templated)</span> |
| <span class="sd"> :type package_uris: str</span> |
| |
| <span class="sd"> :param training_python_module: The Python module name to run within MLEngine</span> |
| <span class="sd"> training job after installing 'package_uris' packages. (templated)</span> |
| <span class="sd"> :type training_python_module: str</span> |
| |
| <span class="sd"> :param training_args: A list of templated command line arguments to pass to</span> |
| <span class="sd"> the MLEngine training program. (templated)</span> |
| <span class="sd"> :type training_args: str</span> |
| |
| <span class="sd"> :param region: The Google Compute Engine region to run the MLEngine training</span> |
| <span class="sd"> job in (templated).</span> |
| <span class="sd"> :type region: str</span> |
| |
| <span class="sd"> :param scale_tier: Resource tier for MLEngine training job. (templated)</span> |
| <span class="sd"> :type scale_tier: str</span> |
| |
| <span class="sd"> :param master_type: Cloud ML Engine machine name.</span> |
| <span class="sd"> Must be set when scale_tier is CUSTOM. (templated)</span> |
| <span class="sd"> :type master_type: str</span> |
| |
| <span class="sd"> :param runtime_version: The Google Cloud ML runtime version to use for</span> |
| <span class="sd"> training. (templated)</span> |
| <span class="sd"> :type runtime_version: str</span> |
| |
| <span class="sd"> :param python_version: The version of Python used in training. (templated)</span> |
| <span class="sd"> :type python_version: str</span> |
| |
| <span class="sd"> :param job_dir: A Google Cloud Storage path in which to store training</span> |
| <span class="sd"> outputs and other data needed for training. (templated)</span> |
| <span class="sd"> :type job_dir: str</span> |
| |
| <span class="sd"> :param gcp_conn_id: The connection ID to use when fetching connection info.</span> |
| <span class="sd"> :type gcp_conn_id: str</span> |
| |
| <span class="sd"> :param delegate_to: The account to impersonate, if any.</span> |
| <span class="sd"> For this to work, the service account making the request must have</span> |
| <span class="sd"> domain-wide delegation enabled.</span> |
| <span class="sd"> :type delegate_to: str</span> |
| |
| <span class="sd"> :param mode: Can be one of 'DRY_RUN'/'CLOUD'. In 'DRY_RUN' mode, no real</span> |
| <span class="sd"> training job will be launched, but the MLEngine training job request</span> |
| <span class="sd"> will be printed out. In 'CLOUD' mode, a real MLEngine training job</span> |
| <span class="sd"> creation request will be issued.</span> |
| <span class="sd"> :type mode: str</span> |
| <span class="sd"> """</span> |
| |
| <div class="viewcode-block" id="MLEngineTrainingOperator.template_fields"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/mlengine_operator/index.html#airflow.contrib.operators.mlengine_operator.MLEngineTrainingOperator.template_fields">[docs]</a> <span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="s1">'_project_id'</span><span class="p">,</span> |
| <span class="s1">'_job_id'</span><span class="p">,</span> |
| <span class="s1">'_package_uris'</span><span class="p">,</span> |
| <span class="s1">'_training_python_module'</span><span class="p">,</span> |
| <span class="s1">'_training_args'</span><span class="p">,</span> |
| <span class="s1">'_region'</span><span class="p">,</span> |
| <span class="s1">'_scale_tier'</span><span class="p">,</span> |
| <span class="s1">'_master_type'</span><span class="p">,</span> |
| <span class="s1">'_runtime_version'</span><span class="p">,</span> |
| <span class="s1">'_python_version'</span><span class="p">,</span> |
| <span class="s1">'_job_dir'</span></div> |
| <span class="p">]</span> |
| |
| <span class="nd">@apply_defaults</span> |
| <span class="k">def</span> <span class="nf">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> |
| <span class="n">project_id</span><span class="p">,</span> |
| <span class="n">job_id</span><span class="p">,</span> |
| <span class="n">package_uris</span><span class="p">,</span> |
| <span class="n">training_python_module</span><span class="p">,</span> |
| <span class="n">training_args</span><span class="p">,</span> |
| <span class="n">region</span><span class="p">,</span> |
| <span class="n">scale_tier</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">master_type</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">runtime_version</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">python_version</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">job_dir</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">gcp_conn_id</span><span class="o">=</span><span class="s1">'google_cloud_default'</span><span class="p">,</span> |
| <span class="n">delegate_to</span><span class="o">=</span><span class="kc">None</span><span class="p">,</span> |
| <span class="n">mode</span><span class="o">=</span><span class="s1">'PRODUCTION'</span><span class="p">,</span> |
| <span class="o">*</span><span class="n">args</span><span class="p">,</span> |
| <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span> |
| <span class="nb">super</span><span class="p">(</span><span class="n">MLEngineTrainingOperator</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">*</span><span class="n">args</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_project_id</span> <span class="o">=</span> <span class="n">project_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_job_id</span> <span class="o">=</span> <span class="n">job_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_package_uris</span> <span class="o">=</span> <span class="n">package_uris</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_training_python_module</span> <span class="o">=</span> <span class="n">training_python_module</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_training_args</span> <span class="o">=</span> <span class="n">training_args</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_region</span> <span class="o">=</span> <span class="n">region</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_scale_tier</span> <span class="o">=</span> <span class="n">scale_tier</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_master_type</span> <span class="o">=</span> <span class="n">master_type</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_runtime_version</span> <span class="o">=</span> <span class="n">runtime_version</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_python_version</span> <span class="o">=</span> <span class="n">python_version</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_job_dir</span> <span class="o">=</span> <span class="n">job_dir</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_gcp_conn_id</span> <span class="o">=</span> <span class="n">gcp_conn_id</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_delegate_to</span> <span class="o">=</span> <span class="n">delegate_to</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_mode</span> <span class="o">=</span> <span class="n">mode</span> |
| |
| <span class="k">if</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_project_id</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'Google Cloud project id is required.'</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">_job_id</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span> |
| <span class="s1">'An unique job id is required for Google MLEngine training '</span> |
| <span class="s1">'job.'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">package_uris</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span> |
| <span class="s1">'At least one python package is required for MLEngine '</span> |
| <span class="s1">'Training job.'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="ow">not</span> <span class="n">training_python_module</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span> |
| <span class="s1">'Python module name to run after installing required '</span> |
| <span class="s1">'packages is required.'</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">_region</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span><span class="s1">'Google Compute Engine region is required.'</span><span class="p">)</span> |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_scale_tier</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_scale_tier</span><span class="o">.</span><span class="n">upper</span><span class="p">()</span> <span class="o">==</span> <span class="s2">"CUSTOM"</span> <span class="ow">and</span> <span class="ow">not</span> <span class="bp">self</span><span class="o">.</span><span class="n">_master_type</span><span class="p">:</span> |
| <span class="k">raise</span> <span class="n">AirflowException</span><span class="p">(</span> |
| <span class="s1">'master_type must be set when scale_tier is CUSTOM'</span><span class="p">)</span> |
| |
| <div class="viewcode-block" id="MLEngineTrainingOperator.execute"><a class="viewcode-back" href="../../../../_api/airflow/contrib/operators/mlengine_operator/index.html#airflow.contrib.operators.mlengine_operator.MLEngineTrainingOperator.execute">[docs]</a> <span class="k">def</span> <span class="nf">execute</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">context</span><span class="p">):</span> |
| <span class="n">job_id</span> <span class="o">=</span> <span class="n">_normalize_mlengine_job_id</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_job_id</span><span class="p">)</span> |
| <span class="n">training_request</span> <span class="o">=</span> <span class="p">{</span> |
| <span class="s1">'jobId'</span><span class="p">:</span> <span class="n">job_id</span><span class="p">,</span> |
| <span class="s1">'trainingInput'</span><span class="p">:</span> <span class="p">{</span> |
| <span class="s1">'scaleTier'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_scale_tier</span><span class="p">,</span> |
| <span class="s1">'packageUris'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_package_uris</span><span class="p">,</span> |
| <span class="s1">'pythonModule'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_training_python_module</span><span class="p">,</span> |
| <span class="s1">'region'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_region</span><span class="p">,</span> |
| <span class="s1">'args'</span><span class="p">:</span> <span class="bp">self</span><span class="o">.</span><span class="n">_training_args</span><span class="p">,</span> |
| <span class="p">}</span> |
| <span class="p">}</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_runtime_version</span><span class="p">:</span> |
| <span class="n">training_request</span><span class="p">[</span><span class="s1">'trainingInput'</span><span class="p">][</span><span class="s1">'runtimeVersion'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_runtime_version</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_python_version</span><span class="p">:</span> |
| <span class="n">training_request</span><span class="p">[</span><span class="s1">'trainingInput'</span><span class="p">][</span><span class="s1">'pythonVersion'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_python_version</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job_dir</span><span class="p">:</span> |
| <span class="n">training_request</span><span class="p">[</span><span class="s1">'trainingInput'</span><span class="p">][</span><span class="s1">'jobDir'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_job_dir</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_scale_tier</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span> <span class="ow">and</span> <span class="bp">self</span><span class="o">.</span><span class="n">_scale_tier</span><span class="o">.</span><span class="n">upper</span><span class="p">()</span> <span class="o">==</span> <span class="s2">"CUSTOM"</span><span class="p">:</span> |
| <span class="n">training_request</span><span class="p">[</span><span class="s1">'trainingInput'</span><span class="p">][</span><span class="s1">'masterType'</span><span class="p">]</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_master_type</span> |
| |
| <span class="k">if</span> <span class="bp">self</span><span class="o">.</span><span class="n">_mode</span> <span class="o">==</span> <span class="s1">'DRY_RUN'</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'In dry_run mode.'</span><span class="p">)</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'MLEngine Training job request is: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">training_request</span><span class="p">)</span> |
| <span class="k">return</span> |
| |
| <span class="n">hook</span> <span class="o">=</span> <span class="n">MLEngineHook</span><span class="p">(</span> |
| <span class="n">gcp_conn_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_gcp_conn_id</span><span class="p">,</span> <span class="n">delegate_to</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_delegate_to</span><span class="p">)</span> |
| |
| <span class="c1"># Helper method to check if the existing job's training input is the</span> |
| <span class="c1"># same as the request we get here.</span> |
| <span class="k">def</span> <span class="nf">check_existing_job</span><span class="p">(</span><span class="n">existing_job</span><span class="p">):</span> |
| <span class="k">return</span> <span class="n">existing_job</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'trainingInput'</span><span class="p">,</span> <span class="kc">None</span><span class="p">)</span> <span class="o">==</span> \ |
| <span class="n">training_request</span><span class="p">[</span><span class="s1">'trainingInput'</span><span class="p">]</span> |
| |
| <span class="k">try</span><span class="p">:</span> |
| <span class="n">finished_training_job</span> <span class="o">=</span> <span class="n">hook</span><span class="o">.</span><span class="n">create_job</span><span class="p">(</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_project_id</span><span class="p">,</span> <span class="n">training_request</span><span class="p">,</span> <span class="n">check_existing_job</span><span class="p">)</span> |
| <span class="k">except</span> <span class="n">HttpError</span><span class="p">:</span> |
| <span class="k">raise</span> |
| |
| <span class="k">if</span> <span class="n">finished_training_job</span><span class="p">[</span><span class="s1">'state'</span><span class="p">]</span> <span class="o">!=</span> <span class="s1">'SUCCEEDED'</span><span class="p">:</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">log</span><span class="o">.</span><span class="n">error</span><span class="p">(</span><span class="s1">'MLEngine training job failed: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="nb">str</span><span class="p">(</span><span class="n">finished_training_job</span><span class="p">))</span> |
| <span class="k">raise</span> <span class="ne">RuntimeError</span><span class="p">(</span><span class="n">finished_training_job</span><span class="p">[</span><span class="s1">'errorMessage'</span><span class="p">])</span></div></div> |
| </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>. |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| </body> |
| </html> |