pydoc/2.47.0/_modules/apache_beam/ml/inference/sklearn_inference.html - beam-site - Git at Google



 <!DOCTYPE html>
 <!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
 <!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
 <head>
   <meta charset="utf-8">

   <meta name="viewport" content="width=device-width, initial-scale=1.0">

   <title>apache_beam.ml.inference.sklearn_inference &mdash; Apache Beam 2.47.0 documentation</title>


   <script type="text/javascript" src="../../../../_static/js/modernizr.min.js"></script>


       <script type="text/javascript" id="documentation_options" data-url_root="../../../../" src="../../../../_static/documentation_options.js"></script>
         <script type="text/javascript" src="../../../../_static/jquery.js"></script>
         <script type="text/javascript" src="../../../../_static/underscore.js"></script>
         <script type="text/javascript" src="../../../../_static/doctools.js"></script>
         <script type="text/javascript" src="../../../../_static/language_data.js"></script>
         <script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script>

     <script type="text/javascript" src="../../../../_static/js/theme.js"></script>


   <link rel="stylesheet" href="../../../../_static/css/theme.css" type="text/css" />
   <link rel="stylesheet" href="../../../../_static/pygments.css" type="text/css" />
     <link rel="index" title="Index" href="../../../../genindex.html" />
     <link rel="search" title="Search" href="../../../../search.html" />
 </head>

 <body class="wy-body-for-nav">


   <div class="wy-grid-for-nav">

     <nav data-toggle="wy-nav-shift" class="wy-nav-side">
       <div class="wy-side-scroll">
         <div class="wy-side-nav-search" >


             <a href="../../../../index.html" class="icon icon-home"> Apache Beam


           </a>


               <div class="version">
                 2.47.0
               </div>


 <div role="search">
   <form id="rtd-search-form" class="wy-form" action="../../../../search.html" method="get">
     <input type="text" name="q" placeholder="Search docs" />
     <input type="hidden" name="check_keywords" value="yes" />
     <input type="hidden" name="area" value="default" />
   </form>
 </div>


         </div>

         <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation">


               <ul>
 <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.coders.html">apache_beam.coders package</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.dataframe.html">apache_beam.dataframe package</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.io.html">apache_beam.io package</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.metrics.html">apache_beam.metrics package</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.ml.html">apache_beam.ml package</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.options.html">apache_beam.options package</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.portability.html">apache_beam.portability package</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.runners.html">apache_beam.runners package</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.testing.html">apache_beam.testing package</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.transforms.html">apache_beam.transforms package</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.typehints.html">apache_beam.typehints package</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.utils.html">apache_beam.utils package</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.yaml.html">apache_beam.yaml package</a></li>
 </ul>
 <ul>
 <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.error.html">apache_beam.error module</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pipeline.html">apache_beam.pipeline module</a></li>
 <li class="toctree-l1"><a class="reference internal" href="../../../../apache_beam.pvalue.html">apache_beam.pvalue module</a></li>
 </ul>


         </div>
       </div>
     </nav>

     <section data-toggle="wy-nav-shift" class="wy-nav-content-wrap">


       <nav class="wy-nav-top" aria-label="top navigation">

           <i data-toggle="wy-nav-top" class="fa fa-bars"></i>
           <a href="../../../../index.html">Apache Beam</a>

       </nav>


       <div class="wy-nav-content">

         <div class="rst-content">


 <div role="navigation" aria-label="breadcrumbs navigation">

   <ul class="wy-breadcrumbs">

       <li><a href="../../../../index.html">Docs</a> &raquo;</li>

           <li><a href="../../../index.html">Module code</a> &raquo;</li>

       <li>apache_beam.ml.inference.sklearn_inference</li>


       <li class="wy-breadcrumbs-aside">

       </li>

   </ul>


   <hr/>
 </div>
           <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
            <div itemprop="articleBody">

   <h1>Source code for apache_beam.ml.inference.sklearn_inference</h1><div class="highlight"><pre>
 <span></span><span class="c1">#</span>
 <span class="c1"># Licensed to the Apache Software Foundation (ASF) under one or more</span>
 <span class="c1"># contributor license agreements.  See the NOTICE file distributed with</span>
 <span class="c1"># this work for additional information regarding copyright ownership.</span>
 <span class="c1"># The ASF licenses this file to You under the Apache License, Version 2.0</span>
 <span class="c1"># (the &quot;License&quot;); you may not use this file except in compliance with</span>
 <span class="c1"># the License.  You may obtain a copy of the License at</span>
 <span class="c1">#</span>
 <span class="c1">#    http://www.apache.org/licenses/LICENSE-2.0</span>
 <span class="c1">#</span>
 <span class="c1"># Unless required by applicable law or agreed to in writing, software</span>
 <span class="c1"># distributed under the License is distributed on an &quot;AS IS&quot; BASIS,</span>
 <span class="c1"># WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.</span>
 <span class="c1"># See the License for the specific language governing permissions and</span>
 <span class="c1"># limitations under the License.</span>
 <span class="c1">#</span>

 <span class="kn">import</span> <span class="nn">enum</span>
 <span class="kn">import</span> <span class="nn">pickle</span>
 <span class="kn">import</span> <span class="nn">sys</span>
 <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Any</span>
 <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Callable</span>
 <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Dict</span>
 <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Iterable</span>
 <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Optional</span>
 <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">Sequence</span>

 <span class="kn">import</span> <span class="nn">numpy</span>
 <span class="kn">import</span> <span class="nn">pandas</span>
 <span class="kn">from</span> <span class="nn">sklearn.base</span> <span class="kn">import</span> <span class="n">BaseEstimator</span>

 <span class="kn">from</span> <span class="nn">apache_beam.io.filesystems</span> <span class="kn">import</span> <span class="n">FileSystems</span>
 <span class="kn">from</span> <span class="nn">apache_beam.ml.inference</span> <span class="kn">import</span> <span class="n">utils</span>
 <span class="kn">from</span> <span class="nn">apache_beam.ml.inference.base</span> <span class="kn">import</span> <span class="n">ModelHandler</span>
 <span class="kn">from</span> <span class="nn">apache_beam.ml.inference.base</span> <span class="kn">import</span> <span class="n">PredictionResult</span>
 <span class="kn">from</span> <span class="nn">apache_beam.utils.annotations</span> <span class="kn">import</span> <span class="n">experimental</span>

 <span class="k">try</span><span class="p">:</span>
   <span class="kn">import</span> <span class="nn">joblib</span>
 <span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span>
   <span class="c1"># joblib is an optional dependency.</span>
   <span class="k">pass</span>

 <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span>
     <span class="s1">&#39;SklearnModelHandlerNumpy&#39;</span><span class="p">,</span>
     <span class="s1">&#39;SklearnModelHandlerPandas&#39;</span><span class="p">,</span>
 <span class="p">]</span>

 <span class="n">NumpyInferenceFn</span> <span class="o">=</span> <span class="n">Callable</span><span class="p">[</span>
     <span class="p">[</span><span class="n">BaseEstimator</span><span class="p">,</span> <span class="n">Sequence</span><span class="p">[</span><span class="n">numpy</span><span class="o">.</span><span class="n">ndarray</span><span class="p">],</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]],</span> <span class="n">Any</span><span class="p">]</span>


 <span class="k">class</span> <span class="nc">ModelFileType</span><span class="p">(</span><span class="n">enum</span><span class="o">.</span><span class="n">Enum</span><span class="p">):</span>
 <span class="w">  </span><span class="sd">&quot;&quot;&quot;Defines how a model file is serialized. Options are pickle or joblib.&quot;&quot;&quot;</span>
   <span class="n">PICKLE</span> <span class="o">=</span> <span class="mi">1</span>
   <span class="n">JOBLIB</span> <span class="o">=</span> <span class="mi">2</span>


 <span class="k">def</span> <span class="nf">_load_model</span><span class="p">(</span><span class="n">model_uri</span><span class="p">,</span> <span class="n">file_type</span><span class="p">):</span>
   <span class="n">file</span> <span class="o">=</span> <span class="n">FileSystems</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">model_uri</span><span class="p">,</span> <span class="s1">&#39;rb&#39;</span><span class="p">)</span>
   <span class="k">if</span> <span class="n">file_type</span> <span class="o">==</span> <span class="n">ModelFileType</span><span class="o">.</span><span class="n">PICKLE</span><span class="p">:</span>
     <span class="k">return</span> <span class="n">pickle</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">file</span><span class="p">)</span>
   <span class="k">elif</span> <span class="n">file_type</span> <span class="o">==</span> <span class="n">ModelFileType</span><span class="o">.</span><span class="n">JOBLIB</span><span class="p">:</span>
     <span class="k">if</span> <span class="ow">not</span> <span class="n">joblib</span><span class="p">:</span>
       <span class="k">raise</span> <span class="ne">ImportError</span><span class="p">(</span>
           <span class="s1">&#39;Could not import joblib in this execution environment. &#39;</span>
           <span class="s1">&#39;For help with managing dependencies on Python workers.&#39;</span>
           <span class="s1">&#39;see https://beam.apache.org/documentation/sdks/python-pipeline-dependencies/&#39;</span>  <span class="c1"># pylint: disable=line-too-long</span>
       <span class="p">)</span>
     <span class="k">return</span> <span class="n">joblib</span><span class="o">.</span><span class="n">load</span><span class="p">(</span><span class="n">file</span><span class="p">)</span>
   <span class="k">raise</span> <span class="ne">AssertionError</span><span class="p">(</span><span class="s1">&#39;Unsupported serialization type.&#39;</span><span class="p">)</span>


 <span class="k">def</span> <span class="nf">_default_numpy_inference_fn</span><span class="p">(</span>
     <span class="n">model</span><span class="p">:</span> <span class="n">BaseEstimator</span><span class="p">,</span>
     <span class="n">batch</span><span class="p">:</span> <span class="n">Sequence</span><span class="p">[</span><span class="n">numpy</span><span class="o">.</span><span class="n">ndarray</span><span class="p">],</span>
     <span class="n">inference_args</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Any</span><span class="p">:</span>
   <span class="c1"># vectorize data for better performance</span>
   <span class="n">vectorized_batch</span> <span class="o">=</span> <span class="n">numpy</span><span class="o">.</span><span class="n">stack</span><span class="p">(</span><span class="n">batch</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
   <span class="k">return</span> <span class="n">model</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">vectorized_batch</span><span class="p">)</span>


 <div class="viewcode-block" id="SklearnModelHandlerNumpy"><a class="viewcode-back" href="../../../../apache_beam.ml.inference.sklearn_inference.html#apache_beam.ml.inference.sklearn_inference.SklearnModelHandlerNumpy">[docs]</a><span class="k">class</span> <span class="nc">SklearnModelHandlerNumpy</span><span class="p">(</span><span class="n">ModelHandler</span><span class="p">[</span><span class="n">numpy</span><span class="o">.</span><span class="n">ndarray</span><span class="p">,</span>
                                             <span class="n">PredictionResult</span><span class="p">,</span>
                                             <span class="n">BaseEstimator</span><span class="p">]):</span>
   <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
       <span class="bp">self</span><span class="p">,</span>
       <span class="n">model_uri</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
       <span class="n">model_file_type</span><span class="p">:</span> <span class="n">ModelFileType</span> <span class="o">=</span> <span class="n">ModelFileType</span><span class="o">.</span><span class="n">PICKLE</span><span class="p">,</span>
       <span class="o">*</span><span class="p">,</span>
       <span class="n">inference_fn</span><span class="p">:</span> <span class="n">NumpyInferenceFn</span> <span class="o">=</span> <span class="n">_default_numpy_inference_fn</span><span class="p">,</span>
       <span class="n">min_batch_size</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
       <span class="n">max_batch_size</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot; Implementation of the ModelHandler interface for scikit-learn</span>
 <span class="sd">    using numpy arrays as input.</span>

 <span class="sd">    Example Usage::</span>

 <span class="sd">      pcoll | RunInference(SklearnModelHandlerNumpy(model_uri=&quot;my_uri&quot;))</span>

 <span class="sd">    Args:</span>
 <span class="sd">      model_uri: The URI to where the model is saved.</span>
 <span class="sd">      model_file_type: The method of serialization of the argument.</span>
 <span class="sd">        default=pickle</span>
 <span class="sd">      inference_fn: The inference function to use.</span>
 <span class="sd">        default=_default_numpy_inference_fn</span>
 <span class="sd">      min_batch_size: the minimum batch size to use when batching inputs. This</span>
 <span class="sd">        batch will be fed into the inference_fn as a Sequence of Numpy</span>
 <span class="sd">        ndarrays.</span>
 <span class="sd">      max_batch_size: the maximum batch size to use when batching inputs. This</span>
 <span class="sd">        batch will be fed into the inference_fn as a Sequence of Numpy</span>
 <span class="sd">        ndarrays.</span>
 <span class="sd">    &quot;&quot;&quot;</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">_model_uri</span> <span class="o">=</span> <span class="n">model_uri</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">_model_file_type</span> <span class="o">=</span> <span class="n">model_file_type</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">_model_inference_fn</span> <span class="o">=</span> <span class="n">inference_fn</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">_batching_kwargs</span> <span class="o">=</span> <span class="p">{}</span>
     <span class="k">if</span> <span class="n">min_batch_size</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
       <span class="bp">self</span><span class="o">.</span><span class="n">_batching_kwargs</span><span class="p">[</span><span class="s1">&#39;min_batch_size&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">min_batch_size</span>
     <span class="k">if</span> <span class="n">max_batch_size</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
       <span class="bp">self</span><span class="o">.</span><span class="n">_batching_kwargs</span><span class="p">[</span><span class="s1">&#39;max_batch_size&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">max_batch_size</span>

 <div class="viewcode-block" id="SklearnModelHandlerNumpy.load_model"><a class="viewcode-back" href="../../../../apache_beam.ml.inference.sklearn_inference.html#apache_beam.ml.inference.sklearn_inference.SklearnModelHandlerNumpy.load_model">[docs]</a>  <span class="k">def</span> <span class="nf">load_model</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">BaseEstimator</span><span class="p">:</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;Loads and initializes a model for processing.&quot;&quot;&quot;</span>
     <span class="k">return</span> <span class="n">_load_model</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_model_uri</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model_file_type</span><span class="p">)</span></div>

 <div class="viewcode-block" id="SklearnModelHandlerNumpy.update_model_path"><a class="viewcode-back" href="../../../../apache_beam.ml.inference.sklearn_inference.html#apache_beam.ml.inference.sklearn_inference.SklearnModelHandlerNumpy.update_model_path">[docs]</a>  <span class="k">def</span> <span class="nf">update_model_path</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">model_path</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">_model_uri</span> <span class="o">=</span> <span class="n">model_path</span> <span class="k">if</span> <span class="n">model_path</span> <span class="k">else</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model_uri</span></div>

 <div class="viewcode-block" id="SklearnModelHandlerNumpy.run_inference"><a class="viewcode-back" href="../../../../apache_beam.ml.inference.sklearn_inference.html#apache_beam.ml.inference.sklearn_inference.SklearnModelHandlerNumpy.run_inference">[docs]</a>  <span class="k">def</span> <span class="nf">run_inference</span><span class="p">(</span>
       <span class="bp">self</span><span class="p">,</span>
       <span class="n">batch</span><span class="p">:</span> <span class="n">Sequence</span><span class="p">[</span><span class="n">numpy</span><span class="o">.</span><span class="n">ndarray</span><span class="p">],</span>
       <span class="n">model</span><span class="p">:</span> <span class="n">BaseEstimator</span><span class="p">,</span>
       <span class="n">inference_args</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span>
   <span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Iterable</span><span class="p">[</span><span class="n">PredictionResult</span><span class="p">]:</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;Runs inferences on a batch of numpy arrays.</span>

 <span class="sd">    Args:</span>
 <span class="sd">      batch: A sequence of examples as numpy arrays. They should</span>
 <span class="sd">        be single examples.</span>
 <span class="sd">      model: A numpy model or pipeline. Must implement predict(X).</span>
 <span class="sd">        Where the parameter X is a numpy array.</span>
 <span class="sd">      inference_args: Any additional arguments for an inference.</span>

 <span class="sd">    Returns:</span>
 <span class="sd">      An Iterable of type PredictionResult.</span>
 <span class="sd">    &quot;&quot;&quot;</span>
     <span class="n">predictions</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model_inference_fn</span><span class="p">(</span>
         <span class="n">model</span><span class="p">,</span>
         <span class="n">batch</span><span class="p">,</span>
         <span class="n">inference_args</span><span class="p">,</span>
     <span class="p">)</span>

     <span class="k">return</span> <span class="n">utils</span><span class="o">.</span><span class="n">_convert_to_result</span><span class="p">(</span>
         <span class="n">batch</span><span class="p">,</span> <span class="n">predictions</span><span class="p">,</span> <span class="n">model_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_model_uri</span><span class="p">)</span></div>

 <div class="viewcode-block" id="SklearnModelHandlerNumpy.get_num_bytes"><a class="viewcode-back" href="../../../../apache_beam.ml.inference.sklearn_inference.html#apache_beam.ml.inference.sklearn_inference.SklearnModelHandlerNumpy.get_num_bytes">[docs]</a>  <span class="k">def</span> <span class="nf">get_num_bytes</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch</span><span class="p">:</span> <span class="n">Sequence</span><span class="p">[</span><span class="n">numpy</span><span class="o">.</span><span class="n">ndarray</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    Returns:</span>
 <span class="sd">      The number of bytes of data for a batch.</span>
 <span class="sd">    &quot;&quot;&quot;</span>
     <span class="k">return</span> <span class="nb">sum</span><span class="p">(</span><span class="n">sys</span><span class="o">.</span><span class="n">getsizeof</span><span class="p">(</span><span class="n">element</span><span class="p">)</span> <span class="k">for</span> <span class="n">element</span> <span class="ow">in</span> <span class="n">batch</span><span class="p">)</span></div>

 <div class="viewcode-block" id="SklearnModelHandlerNumpy.get_metrics_namespace"><a class="viewcode-back" href="../../../../apache_beam.ml.inference.sklearn_inference.html#apache_beam.ml.inference.sklearn_inference.SklearnModelHandlerNumpy.get_metrics_namespace">[docs]</a>  <span class="k">def</span> <span class="nf">get_metrics_namespace</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    Returns:</span>
 <span class="sd">       A namespace for metrics collected by the RunInference transform.</span>
 <span class="sd">    &quot;&quot;&quot;</span>
     <span class="k">return</span> <span class="s1">&#39;BeamML_Sklearn&#39;</span></div>

 <div class="viewcode-block" id="SklearnModelHandlerNumpy.batch_elements_kwargs"><a class="viewcode-back" href="../../../../apache_beam.ml.inference.sklearn_inference.html#apache_beam.ml.inference.sklearn_inference.SklearnModelHandlerNumpy.batch_elements_kwargs">[docs]</a>  <span class="k">def</span> <span class="nf">batch_elements_kwargs</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
     <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batching_kwargs</span></div></div>


 <span class="n">PandasInferenceFn</span> <span class="o">=</span> <span class="n">Callable</span><span class="p">[</span>
     <span class="p">[</span><span class="n">BaseEstimator</span><span class="p">,</span> <span class="n">Sequence</span><span class="p">[</span><span class="n">pandas</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">],</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]],</span> <span class="n">Any</span><span class="p">]</span>


 <span class="k">def</span> <span class="nf">_default_pandas_inference_fn</span><span class="p">(</span>
     <span class="n">model</span><span class="p">:</span> <span class="n">BaseEstimator</span><span class="p">,</span>
     <span class="n">batch</span><span class="p">:</span> <span class="n">Sequence</span><span class="p">[</span><span class="n">pandas</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">],</span>
     <span class="n">inference_args</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Any</span><span class="p">:</span>
   <span class="c1"># vectorize data for better performance</span>
   <span class="n">vectorized_batch</span> <span class="o">=</span> <span class="n">pandas</span><span class="o">.</span><span class="n">concat</span><span class="p">(</span><span class="n">batch</span><span class="p">,</span> <span class="n">axis</span><span class="o">=</span><span class="mi">0</span><span class="p">)</span>
   <span class="n">predictions</span> <span class="o">=</span> <span class="n">model</span><span class="o">.</span><span class="n">predict</span><span class="p">(</span><span class="n">vectorized_batch</span><span class="p">)</span>
   <span class="n">splits</span> <span class="o">=</span> <span class="p">[</span>
       <span class="n">vectorized_batch</span><span class="o">.</span><span class="n">iloc</span><span class="p">[[</span><span class="n">i</span><span class="p">]]</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="nb">range</span><span class="p">(</span><span class="n">vectorized_batch</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">])</span>
   <span class="p">]</span>
   <span class="k">return</span> <span class="n">predictions</span><span class="p">,</span> <span class="n">splits</span>


 <div class="viewcode-block" id="SklearnModelHandlerPandas"><a class="viewcode-back" href="../../../../apache_beam.ml.inference.sklearn_inference.html#apache_beam.ml.inference.sklearn_inference.SklearnModelHandlerPandas">[docs]</a><span class="nd">@experimental</span><span class="p">(</span><span class="n">extra_message</span><span class="o">=</span><span class="s2">&quot;No backwards-compatibility guarantees.&quot;</span><span class="p">)</span>
 <span class="k">class</span> <span class="nc">SklearnModelHandlerPandas</span><span class="p">(</span><span class="n">ModelHandler</span><span class="p">[</span><span class="n">pandas</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">,</span>
                                              <span class="n">PredictionResult</span><span class="p">,</span>
                                              <span class="n">BaseEstimator</span><span class="p">]):</span>
   <span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span>
       <span class="bp">self</span><span class="p">,</span>
       <span class="n">model_uri</span><span class="p">:</span> <span class="nb">str</span><span class="p">,</span>
       <span class="n">model_file_type</span><span class="p">:</span> <span class="n">ModelFileType</span> <span class="o">=</span> <span class="n">ModelFileType</span><span class="o">.</span><span class="n">PICKLE</span><span class="p">,</span>
       <span class="o">*</span><span class="p">,</span>
       <span class="n">inference_fn</span><span class="p">:</span> <span class="n">PandasInferenceFn</span> <span class="o">=</span> <span class="n">_default_pandas_inference_fn</span><span class="p">,</span>
       <span class="n">min_batch_size</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">,</span>
       <span class="n">max_batch_size</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">int</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;Implementation of the ModelHandler interface for scikit-learn that</span>
 <span class="sd">    supports pandas dataframes.</span>

 <span class="sd">    Example Usage::</span>

 <span class="sd">      pcoll | RunInference(SklearnModelHandlerPandas(model_uri=&quot;my_uri&quot;))</span>

 <span class="sd">    **NOTE:** This API and its implementation are under development and</span>
 <span class="sd">    do not provide backward compatibility guarantees.</span>

 <span class="sd">    Args:</span>
 <span class="sd">      model_uri: The URI to where the model is saved.</span>
 <span class="sd">      model_file_type: The method of serialization of the argument.</span>
 <span class="sd">        default=pickle</span>
 <span class="sd">      inference_fn: The inference function to use.</span>
 <span class="sd">        default=_default_pandas_inference_fn</span>
 <span class="sd">      min_batch_size: the minimum batch size to use when batching inputs. This</span>
 <span class="sd">        batch will be fed into the inference_fn as a Sequence of Pandas</span>
 <span class="sd">        Dataframes.</span>
 <span class="sd">      max_batch_size: the maximum batch size to use when batching inputs. This</span>
 <span class="sd">        batch will be fed into the inference_fn as a Sequence of Pandas</span>
 <span class="sd">        Dataframes.</span>

 <span class="sd">    &quot;&quot;&quot;</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">_model_uri</span> <span class="o">=</span> <span class="n">model_uri</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">_model_file_type</span> <span class="o">=</span> <span class="n">model_file_type</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">_model_inference_fn</span> <span class="o">=</span> <span class="n">inference_fn</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">_batching_kwargs</span> <span class="o">=</span> <span class="p">{}</span>
     <span class="k">if</span> <span class="n">min_batch_size</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
       <span class="bp">self</span><span class="o">.</span><span class="n">_batching_kwargs</span><span class="p">[</span><span class="s1">&#39;min_batch_size&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">min_batch_size</span>
     <span class="k">if</span> <span class="n">max_batch_size</span> <span class="ow">is</span> <span class="ow">not</span> <span class="kc">None</span><span class="p">:</span>
       <span class="bp">self</span><span class="o">.</span><span class="n">_batching_kwargs</span><span class="p">[</span><span class="s1">&#39;max_batch_size&#39;</span><span class="p">]</span> <span class="o">=</span> <span class="n">max_batch_size</span>

 <div class="viewcode-block" id="SklearnModelHandlerPandas.load_model"><a class="viewcode-back" href="../../../../apache_beam.ml.inference.sklearn_inference.html#apache_beam.ml.inference.sklearn_inference.SklearnModelHandlerPandas.load_model">[docs]</a>  <span class="k">def</span> <span class="nf">load_model</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="n">BaseEstimator</span><span class="p">:</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;Loads and initializes a model for processing.&quot;&quot;&quot;</span>
     <span class="k">return</span> <span class="n">_load_model</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_model_uri</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model_file_type</span><span class="p">)</span></div>

 <div class="viewcode-block" id="SklearnModelHandlerPandas.update_model_path"><a class="viewcode-back" href="../../../../apache_beam.ml.inference.sklearn_inference.html#apache_beam.ml.inference.sklearn_inference.SklearnModelHandlerPandas.update_model_path">[docs]</a>  <span class="k">def</span> <span class="nf">update_model_path</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">model_path</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="nb">str</span><span class="p">]</span> <span class="o">=</span> <span class="kc">None</span><span class="p">):</span>
     <span class="bp">self</span><span class="o">.</span><span class="n">_model_uri</span> <span class="o">=</span> <span class="n">model_path</span> <span class="k">if</span> <span class="n">model_path</span> <span class="k">else</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model_uri</span></div>

 <div class="viewcode-block" id="SklearnModelHandlerPandas.run_inference"><a class="viewcode-back" href="../../../../apache_beam.ml.inference.sklearn_inference.html#apache_beam.ml.inference.sklearn_inference.SklearnModelHandlerPandas.run_inference">[docs]</a>  <span class="k">def</span> <span class="nf">run_inference</span><span class="p">(</span>
       <span class="bp">self</span><span class="p">,</span>
       <span class="n">batch</span><span class="p">:</span> <span class="n">Sequence</span><span class="p">[</span><span class="n">pandas</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">],</span>
       <span class="n">model</span><span class="p">:</span> <span class="n">BaseEstimator</span><span class="p">,</span>
       <span class="n">inference_args</span><span class="p">:</span> <span class="n">Optional</span><span class="p">[</span><span class="n">Dict</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="n">Any</span><span class="p">]]</span> <span class="o">=</span> <span class="kc">None</span>
   <span class="p">)</span> <span class="o">-&gt;</span> <span class="n">Iterable</span><span class="p">[</span><span class="n">PredictionResult</span><span class="p">]:</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    Runs inferences on a batch of pandas dataframes.</span>

 <span class="sd">    Args:</span>
 <span class="sd">      batch: A sequence of examples as numpy arrays. They should</span>
 <span class="sd">        be single examples.</span>
 <span class="sd">      model: A dataframe model or pipeline. Must implement predict(X).</span>
 <span class="sd">        Where the parameter X is a pandas dataframe.</span>
 <span class="sd">      inference_args: Any additional arguments for an inference.</span>

 <span class="sd">    Returns:</span>
 <span class="sd">      An Iterable of type PredictionResult.</span>
 <span class="sd">    &quot;&quot;&quot;</span>
     <span class="c1"># sklearn_inference currently only supports single rowed dataframes.</span>
     <span class="k">for</span> <span class="n">dataframe</span> <span class="ow">in</span> <span class="nb">iter</span><span class="p">(</span><span class="n">batch</span><span class="p">):</span>
       <span class="k">if</span> <span class="n">dataframe</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="o">!=</span> <span class="mi">1</span><span class="p">:</span>
         <span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">&#39;Only dataframes with single rows are supported.&#39;</span><span class="p">)</span>

     <span class="n">predictions</span><span class="p">,</span> <span class="n">splits</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model_inference_fn</span><span class="p">(</span><span class="n">model</span><span class="p">,</span> <span class="n">batch</span><span class="p">,</span> <span class="n">inference_args</span><span class="p">)</span>

     <span class="k">return</span> <span class="n">utils</span><span class="o">.</span><span class="n">_convert_to_result</span><span class="p">(</span>
         <span class="n">splits</span><span class="p">,</span> <span class="n">predictions</span><span class="p">,</span> <span class="n">model_id</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_model_uri</span><span class="p">)</span></div>

 <div class="viewcode-block" id="SklearnModelHandlerPandas.get_num_bytes"><a class="viewcode-back" href="../../../../apache_beam.ml.inference.sklearn_inference.html#apache_beam.ml.inference.sklearn_inference.SklearnModelHandlerPandas.get_num_bytes">[docs]</a>  <span class="k">def</span> <span class="nf">get_num_bytes</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">batch</span><span class="p">:</span> <span class="n">Sequence</span><span class="p">[</span><span class="n">pandas</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">])</span> <span class="o">-&gt;</span> <span class="nb">int</span><span class="p">:</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    Returns:</span>
 <span class="sd">      The number of bytes of data for a batch.</span>
 <span class="sd">    &quot;&quot;&quot;</span>
     <span class="k">return</span> <span class="nb">sum</span><span class="p">(</span><span class="n">df</span><span class="o">.</span><span class="n">memory_usage</span><span class="p">(</span><span class="n">deep</span><span class="o">=</span><span class="kc">True</span><span class="p">)</span><span class="o">.</span><span class="n">sum</span><span class="p">()</span> <span class="k">for</span> <span class="n">df</span> <span class="ow">in</span> <span class="n">batch</span><span class="p">)</span></div>

 <div class="viewcode-block" id="SklearnModelHandlerPandas.get_metrics_namespace"><a class="viewcode-back" href="../../../../apache_beam.ml.inference.sklearn_inference.html#apache_beam.ml.inference.sklearn_inference.SklearnModelHandlerPandas.get_metrics_namespace">[docs]</a>  <span class="k">def</span> <span class="nf">get_metrics_namespace</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-&gt;</span> <span class="nb">str</span><span class="p">:</span>
 <span class="w">    </span><span class="sd">&quot;&quot;&quot;</span>
 <span class="sd">    Returns:</span>
 <span class="sd">       A namespace for metrics collected by the RunInference transform.</span>
 <span class="sd">    &quot;&quot;&quot;</span>
     <span class="k">return</span> <span class="s1">&#39;BeamML_Sklearn&#39;</span></div>

 <div class="viewcode-block" id="SklearnModelHandlerPandas.batch_elements_kwargs"><a class="viewcode-back" href="../../../../apache_beam.ml.inference.sklearn_inference.html#apache_beam.ml.inference.sklearn_inference.SklearnModelHandlerPandas.batch_elements_kwargs">[docs]</a>  <span class="k">def</span> <span class="nf">batch_elements_kwargs</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
     <span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_batching_kwargs</span></div></div>
 </pre></div>

            </div>

           </div>
           <footer>


   <hr/>

   <div role="contentinfo">
     <p>
         &copy; Copyright

     </p>
   </div>
   Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.

 </footer>

         </div>
       </div>

     </section>

   </div>


   <script type="text/javascript">
       jQuery(function () {
           SphinxRtdTheme.Navigation.enable(true);
       });
   </script>


 </body>
 </html>