You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@airflow.apache.org by ka...@apache.org on 2018/08/27 16:26:48 UTC
[28/51] [partial] incubator-airflow-site git commit: 1.10.0
http://git-wip-us.apache.org/repos/asf/incubator-airflow-site/blob/11437c14/_modules/airflow/contrib/operators/mlengine_operator.html
----------------------------------------------------------------------
diff --git a/_modules/airflow/contrib/operators/mlengine_operator.html b/_modules/airflow/contrib/operators/mlengine_operator.html
index b322476..c7743c2 100644
--- a/_modules/airflow/contrib/operators/mlengine_operator.html
+++ b/_modules/airflow/contrib/operators/mlengine_operator.html
@@ -91,7 +91,7 @@
<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="../../../../configuration.html">Configuration</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>
@@ -99,8 +99,10 @@
<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="../../../../lineage.html">Lineage</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="../../../../code.html">API Reference</a></li>
</ul>
@@ -184,77 +186,17 @@
<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">airflow</span> <span class="k">import</span> <span class="n">settings</span>
+<span class="kn">from</span> <span class="nn">apiclient</span> <span class="k">import</span> <span class="n">errors</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">apiclient</span> <span class="k">import</span> <span class="n">errors</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>
<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>
-<span class="k">def</span> <span class="nf">_create_prediction_input</span><span class="p">(</span><span class="n">project_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="sd">"""</span>
-<span class="sd"> Create the batch prediction input from the given parameters.</span>
-
-<span class="sd"> Args:</span>
-<span class="sd"> A subset of arguments documented in __init__ method of class</span>
-<span class="sd"> MLEngineBatchPredictionOperator</span>
-
-<span class="sd"> Returns:</span>
-<span class="sd"> A dictionary representing the predictionInput object as documented</span>
-<span class="sd"> in https://cloud.google.com/ml-engine/reference/rest/v1/projects.jobs.</span>
-
-<span class="sd"> Raises:</span>
-<span class="sd"> ValueError: if a unique model/version origin cannot be determined.</span>
-<span class="sd"> """</span>
- <span class="n">prediction_input</span> <span class="o">=</span> <span class="p">{</span>
- <span class="s1">'dataFormat'</span><span class="p">:</span> <span class="n">data_format</span><span class="p">,</span>
- <span class="s1">'inputPaths'</span><span class="p">:</span> <span class="n">input_paths</span><span class="p">,</span>
- <span class="s1">'outputPath'</span><span class="p">:</span> <span class="n">output_path</span><span class="p">,</span>
- <span class="s1">'region'</span><span class="p">:</span> <span class="n">region</span>
- <span class="p">}</span>
-
- <span class="k">if</span> <span class="n">uri</span><span class="p">:</span>
- <span class="k">if</span> <span class="n">model_name</span> <span class="ow">or</span> <span class="n">version_name</span><span class="p">:</span>
- <span class="n">log</span><span class="o">.</span><span class="n">error</span><span class="p">(</span>
- <span class="s1">'Ambiguous model origin: Both uri and model/version name are provided.'</span>
- <span class="p">)</span>
- <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Ambiguous model origin.'</span><span class="p">)</span>
- <span class="n">prediction_input</span><span class="p">[</span><span class="s1">'uri'</span><span class="p">]</span> <span class="o">=</span> <span class="n">uri</span>
- <span class="k">elif</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="n">project_id</span><span class="p">,</span> <span class="n">model_name</span><span class="p">)</span>
- <span class="k">if</span> <span class="ow">not</span> <span class="n">version_name</span><span class="p">:</span>
- <span class="n">prediction_input</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_input</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="n">version_name</span><span class="p">)</span>
- <span class="k">else</span><span class="p">:</span>
- <span class="n">log</span><span class="o">.</span><span class="n">error</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 savedModel.'</span><span class="p">)</span>
- <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Missing model origin.'</span><span class="p">)</span>
-
- <span class="k">if</span> <span class="n">max_worker_count</span><span class="p">:</span>
- <span class="n">prediction_input</span><span class="p">[</span><span class="s1">'maxWorkerCount'</span><span class="p">]</span> <span class="o">=</span> <span class="n">max_worker_count</span>
- <span class="k">if</span> <span class="n">runtime_version</span><span class="p">:</span>
- <span class="n">prediction_input</span><span class="p">[</span><span class="s1">'runtimeVersion'</span><span class="p">]</span> <span class="o">=</span> <span class="n">runtime_version</span>
-
- <span class="k">return</span> <span class="n">prediction_input</span>
-
-
<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>
@@ -268,10 +210,27 @@
<span class="sd"> Returns:</span>
<span class="sd"> A valid job_id representation.</span>
<span class="sd"> """</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'</span><span class="p">,</span> <span class="n">job_id</span><span class="p">)</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="ow">is</span> <span class="mi">0</span><span class="p">:</span>
- <span class="n">job_id</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">return</span> <span class="n">re</span><span class="o">.</span><span class="n">sub</span><span class="p">(</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_id</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 class="viewcode-block" id="MLEngineBatchPredictionOperator"><a class="viewcode-back" href="../../../../integration.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>
@@ -289,14 +248,20 @@
<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"> ::</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.</span>
@@ -358,11 +323,18 @@
<span class="sd"> :type delegate_to: string</span>
<span class="sd"> Raises:</span>
-<span class="sd"> ValueError: if a unique model/version origin cannot be determined.</span>
+<span class="sd"> ``ValueError``: if a unique model/version origin cannot be determined.</span>
<span class="sd"> """</span>
<span class="n">template_fields</span> <span class="o">=</span> <span class="p">[</span>
- <span class="s2">"prediction_job_request"</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>
<span class="p">]</span>
<span class="nd">@apply_defaults</span>
@@ -384,45 +356,91 @@
<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">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">_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">_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">try</span><span class="p">:</span>
- <span class="n">prediction_input</span> <span class="o">=</span> <span class="n">_create_prediction_input</span><span class="p">(</span>
- <span class="n">project_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="p">,</span> <span class="n">version_name</span><span class="p">,</span> <span class="n">uri</span><span class="p">,</span> <span class="n">max_worker_count</span><span class="p">,</span>
- <span class="n">runtime_version</span><span class="p">)</span>
- <span class="k">except</span> <span class="ne">ValueError</span> <span class="k">as</span> <span class="n">e</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">'Cannot create batch prediction job request due to: </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span>
- <span class="n">e</span>
- <span class="p">)</span>
- <span class="k">raise</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="bp">self</span><span class="o">.</span><span class="n">prediction_job_request</span> <span class="o">=</span> <span class="p">{</span>
- <span class="s1">'jobId'</span><span class="p">:</span> <span class="n">_normalize_mlengine_job_id</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="n">prediction_input</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>
<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="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="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="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="bp">self</span><span class="o">.</span><span class="n">prediction_job_request</span><span class="p">[</span><span class="s1">'predictionInput'</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="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="bp">self</span><span class="o">.</span><span class="n">prediction_job_request</span><span class="p">,</span>
- <span class="n">check_existing_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">errors</span><span class="o">.</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">'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="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">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</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="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>
@@ -445,8 +463,9 @@
<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"> * ``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"> :param gcp_conn_id: The connection ID to use when fetching connection info.</span>
<span class="sd"> :type gcp_conn_id: string</span>
@@ -515,23 +534,25 @@
<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"> * ``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"> * ``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"> * ``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"> * ``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: string</span>
+<span class="sd"> :type operation: string</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: string</span>
@@ -581,9 +602,8 @@
<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">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>
@@ -625,6 +645,16 @@
<span class="sd"> :param scale_tier: Resource tier for MLEngine training job.</span>
<span class="sd"> :type scale_tier: string</span>
+<span class="sd"> :param runtime_version: The Google Cloud ML runtime version to use for training.</span>
+<span class="sd"> :type runtime_version: string</span>
+
+<span class="sd"> :param python_version: The version of Python used in training.</span>
+<span class="sd"> :type python_version: string</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.</span>
+<span class="sd"> :type job_dir: string</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: string</span>
@@ -648,6 +678,9 @@
<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">'_runtime_version'</span><span class="p">,</span>
+ <span class="s1">'_python_version'</span><span class="p">,</span>
+ <span class="s1">'_job_dir'</span>
<span class="p">]</span>
<span class="nd">@apply_defaults</span>
@@ -659,6 +692,9 @@
<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">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>
@@ -672,6 +708,9 @@
<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">_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>
@@ -706,9 +745,19 @@
<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">_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">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">training_request</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">{}</span><span class="s1">'</span><span class="o">.</span><span class="n">format</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>
@@ -719,6 +768,7 @@
<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>