| |
| <!DOCTYPE html> |
| |
| <html> |
| <head> |
| <meta charset="utf-8" /> |
| <title>pyspark.pandas.mlflow — PySpark master documentation</title> |
| |
| <link href="../../../_static/styles/theme.css?digest=1999514e3f237ded88cf" rel="stylesheet"> |
| <link href="../../../_static/styles/pydata-sphinx-theme.css?digest=1999514e3f237ded88cf" rel="stylesheet"> |
| |
| |
| <link rel="stylesheet" |
| href="../../../_static/vendor/fontawesome/5.13.0/css/all.min.css"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-solid-900.woff2"> |
| <link rel="preload" as="font" type="font/woff2" crossorigin |
| href="../../../_static/vendor/fontawesome/5.13.0/webfonts/fa-brands-400.woff2"> |
| |
| |
| |
| |
| |
| <link rel="stylesheet" href="../../../_static/styles/pydata-sphinx-theme.css" type="text/css" /> |
| <link rel="stylesheet" href="../../../_static/pygments.css" type="text/css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/copybutton.css" /> |
| <link rel="stylesheet" type="text/css" href="../../../_static/css/pyspark.css" /> |
| |
| <link rel="preload" as="script" href="../../../_static/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf"> |
| |
| <script id="documentation_options" data-url_root="../../../" src="../../../_static/documentation_options.js"></script> |
| <script src="../../../_static/jquery.js"></script> |
| <script src="../../../_static/underscore.js"></script> |
| <script src="../../../_static/doctools.js"></script> |
| <script src="../../../_static/language_data.js"></script> |
| <script src="../../../_static/clipboard.min.js"></script> |
| <script src="../../../_static/copybutton.js"></script> |
| <script crossorigin="anonymous" integrity="sha256-Ae2Vz/4ePdIu6ZyI/5ZGsYnb+m0JlOmKPjt6XZ9JJkA=" src="https://cdnjs.cloudflare.com/ajax/libs/require.js/2.3.4/require.min.js"></script> |
| <script async="async" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| <script type="text/x-mathjax-config">MathJax.Hub.Config({"tex2jax": {"inlineMath": [["$", "$"], ["\\(", "\\)"]], "processEscapes": true, "ignoreClass": "tex2jax_ignore|mathjax_ignore|document", "processClass": "tex2jax_process|mathjax_process|math|output_area"}})</script> |
| <link rel="canonical" href="https://spark.apache.org/docs/latest/api/python/_modules/pyspark/pandas/mlflow.html" /> |
| <link rel="search" title="Search" href="../../../search.html" /> |
| <meta name="viewport" content="width=device-width, initial-scale=1" /> |
| <meta name="docsearch:language" content="None"> |
| |
| |
| <!-- Google Analytics --> |
| |
| </head> |
| <body data-spy="scroll" data-target="#bd-toc-nav" data-offset="80"> |
| |
| <div class="container-fluid" id="banner"></div> |
| |
| |
| <nav class="navbar navbar-light navbar-expand-lg bg-light fixed-top bd-navbar" id="navbar-main"><div class="container-xl"> |
| |
| <div id="navbar-start"> |
| |
| |
| |
| <a class="navbar-brand" href="../../../index.html"> |
| <img src="../../../_static/spark-logo-reverse.png" class="logo" alt="logo"> |
| </a> |
| |
| |
| |
| </div> |
| |
| <button class="navbar-toggler" type="button" data-toggle="collapse" data-target="#navbar-collapsible" aria-controls="navbar-collapsible" aria-expanded="false" aria-label="Toggle navigation"> |
| <span class="navbar-toggler-icon"></span> |
| </button> |
| |
| |
| <div id="navbar-collapsible" class="col-lg-9 collapse navbar-collapse"> |
| <div id="navbar-center" class="mr-auto"> |
| |
| <div class="navbar-center-item"> |
| <ul id="navbar-main-elements" class="navbar-nav"> |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../index.html"> |
| Overview |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../getting_started/index.html"> |
| Getting Started |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../user_guide/index.html"> |
| User Guides |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../reference/index.html"> |
| API Reference |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../development/index.html"> |
| Development |
| </a> |
| </li> |
| |
| <li class="toctree-l1 nav-item"> |
| <a class="reference internal nav-link" href="../../../migration_guide/index.html"> |
| Migration Guides |
| </a> |
| </li> |
| |
| |
| </ul> |
| </div> |
| |
| </div> |
| |
| <div id="navbar-end"> |
| |
| <div class="navbar-end-item"> |
| <!-- |
| Licensed to the Apache Software Foundation (ASF) under one or more |
| contributor license agreements. See the NOTICE file distributed with |
| this work for additional information regarding copyright ownership. |
| The ASF licenses this file to You under the Apache License, Version 2.0 |
| (the "License"); you may not use this file except in compliance with |
| the License. You may obtain a copy of the License at |
| |
| http://www.apache.org/licenses/LICENSE-2.0 |
| |
| Unless required by applicable law or agreed to in writing, software |
| distributed under the License is distributed on an "AS IS" BASIS, |
| WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. |
| See the License for the specific language governing permissions and |
| limitations under the License. |
| --> |
| |
| <div id="version-button" class="dropdown"> |
| <button type="button" class="btn btn-secondary btn-sm navbar-btn dropdown-toggle" id="version_switcher_button" data-toggle="dropdown"> |
| master |
| <span class="caret"></span> |
| </button> |
| <div id="version_switcher" class="dropdown-menu list-group-flush py-0" aria-labelledby="version_switcher_button"> |
| <!-- dropdown will be populated by javascript on page load --> |
| </div> |
| </div> |
| |
| <script type="text/javascript"> |
| // Function to construct the target URL from the JSON components |
| function buildURL(entry) { |
| var template = "https://spark.apache.org/docs/{version}/api/python/index.html"; // supplied by jinja |
| template = template.replace("{version}", entry.version); |
| return template; |
| } |
| |
| // Function to check if corresponding page path exists in other version of docs |
| // and, if so, go there instead of the homepage of the other docs version |
| function checkPageExistsAndRedirect(event) { |
| const currentFilePath = "_modules/pyspark/pandas/mlflow.html", |
| otherDocsHomepage = event.target.getAttribute("href"); |
| let tryUrl = `${otherDocsHomepage}${currentFilePath}`; |
| $.ajax({ |
| type: 'HEAD', |
| url: tryUrl, |
| // if the page exists, go there |
| success: function() { |
| location.href = tryUrl; |
| } |
| }).fail(function() { |
| location.href = otherDocsHomepage; |
| }); |
| return false; |
| } |
| |
| // Function to populate the version switcher |
| (function () { |
| // get JSON config |
| $.getJSON("_static/versions.json", function(data, textStatus, jqXHR) { |
| // create the nodes first (before AJAX calls) to ensure the order is |
| // correct (for now, links will go to doc version homepage) |
| $.each(data, function(index, entry) { |
| // if no custom name specified (e.g., "latest"), use version string |
| if (!("name" in entry)) { |
| entry.name = entry.version; |
| } |
| // construct the appropriate URL, and add it to the dropdown |
| entry.url = buildURL(entry); |
| const node = document.createElement("a"); |
| node.setAttribute("class", "list-group-item list-group-item-action py-1"); |
| node.setAttribute("href", `${entry.url}`); |
| node.textContent = `${entry.name}`; |
| node.onclick = checkPageExistsAndRedirect; |
| $("#version_switcher").append(node); |
| }); |
| }); |
| })(); |
| </script> |
| </div> |
| |
| </div> |
| </div> |
| </div> |
| </nav> |
| |
| |
| <div class="container-xl"> |
| <div class="row"> |
| |
| |
| <!-- Only show if we have sidebars configured, else just a small margin --> |
| <div class="col-12 col-md-3 bd-sidebar"> |
| <div class="sidebar-start-items"><form class="bd-search d-flex align-items-center" action="../../../search.html" method="get"> |
| <i class="icon fas fa-search"></i> |
| <input type="search" class="form-control" name="q" id="search-input" placeholder="Search the docs ..." aria-label="Search the docs ..." autocomplete="off" > |
| </form><nav class="bd-links" id="bd-docs-nav" aria-label="Main navigation"> |
| <div class="bd-toc-item active"> |
| |
| </div> |
| </nav> |
| </div> |
| <div class="sidebar-end-items"> |
| </div> |
| </div> |
| |
| |
| |
| |
| <div class="d-none d-xl-block col-xl-2 bd-toc"> |
| |
| </div> |
| |
| |
| |
| |
| |
| |
| <main class="col-12 col-md-9 col-xl-7 py-md-5 pl-md-5 pr-md-4 bd-content" role="main"> |
| |
| <div> |
| |
| <h1>Source code for pyspark.pandas.mlflow</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="c1">#</span> |
| |
| <span class="sd">"""</span> |
| <span class="sd">MLflow-related functions to load models and apply them to pandas-on-Spark dataframes.</span> |
| <span class="sd">"""</span> |
| <span class="kn">from</span> <span class="nn">typing</span> <span class="kn">import</span> <span class="n">List</span><span class="p">,</span> <span class="n">Union</span> |
| |
| <span class="kn">from</span> <span class="nn">pyspark.sql.types</span> <span class="kn">import</span> <span class="n">DataType</span> |
| <span class="kn">import</span> <span class="nn">pandas</span> <span class="k">as</span> <span class="nn">pd</span> |
| <span class="kn">import</span> <span class="nn">numpy</span> <span class="k">as</span> <span class="nn">np</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">pyspark.pandas._typing</span> <span class="kn">import</span> <span class="n">Label</span><span class="p">,</span> <span class="n">Dtype</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.utils</span> <span class="kn">import</span> <span class="n">lazy_property</span><span class="p">,</span> <span class="n">default_session</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.frame</span> <span class="kn">import</span> <span class="n">DataFrame</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.series</span> <span class="kn">import</span> <span class="n">Series</span><span class="p">,</span> <span class="n">first_series</span> |
| <span class="kn">from</span> <span class="nn">pyspark.pandas.typedef</span> <span class="kn">import</span> <span class="n">as_spark_type</span> |
| |
| <span class="n">__all__</span> <span class="o">=</span> <span class="p">[</span><span class="s2">"PythonModelWrapper"</span><span class="p">,</span> <span class="s2">"load_model"</span><span class="p">]</span> |
| |
| |
| <div class="viewcode-block" id="PythonModelWrapper"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.mlflow.PythonModelWrapper.html#pyspark.pandas.mlflow.PythonModelWrapper">[docs]</a><span class="k">class</span> <span class="nc">PythonModelWrapper</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> A wrapper around MLflow's Python object model.</span> |
| |
| <span class="sd"> This wrapper acts as a predictor on pandas-on-Spark</span> |
| |
| <span class="sd"> """</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">return_type_hint</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">type</span><span class="p">,</span> <span class="n">Dtype</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_uri</span> |
| <span class="bp">self</span><span class="o">.</span><span class="n">_return_type_hint</span> <span class="o">=</span> <span class="n">return_type_hint</span> |
| |
| <span class="nd">@lazy_property</span> |
| <span class="k">def</span> <span class="nf">_return_type</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">DataType</span><span class="p">:</span> |
| <span class="n">hint</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_return_type_hint</span> |
| <span class="c1"># The logic is simple for now, because it corresponds to the default</span> |
| <span class="c1"># case: continuous predictions</span> |
| <span class="c1"># TODO: do something smarter, for example when there is a sklearn.Classifier (it should</span> |
| <span class="c1"># return an integer or a categorical)</span> |
| <span class="c1"># We can do the same for pytorch/tensorflow/keras models by looking at the output types.</span> |
| <span class="c1"># However, this is probably better done in mlflow than here.</span> |
| <span class="k">if</span> <span class="n">hint</span> <span class="o">==</span> <span class="s2">"infer"</span> <span class="ow">or</span> <span class="ow">not</span> <span class="n">hint</span><span class="p">:</span> |
| <span class="n">hint</span> <span class="o">=</span> <span class="n">np</span><span class="o">.</span><span class="n">float64</span> |
| <span class="k">return</span> <span class="n">as_spark_type</span><span class="p">(</span><span class="n">hint</span><span class="p">)</span> |
| |
| <span class="nd">@lazy_property</span> |
| <span class="k">def</span> <span class="nf">_model</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Any</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> The return object has to follow the API of mlflow.pyfunc.PythonModel.</span> |
| <span class="sd"> """</span> |
| <span class="kn">from</span> <span class="nn">mlflow</span> <span class="kn">import</span> <span class="n">pyfunc</span> |
| |
| <span class="k">return</span> <span class="n">pyfunc</span><span class="o">.</span><span class="n">load_model</span><span class="p">(</span><span class="n">model_uri</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_model_uri</span><span class="p">)</span> |
| |
| <span class="nd">@lazy_property</span> |
| <span class="k">def</span> <span class="nf">_model_udf</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="n">Any</span><span class="p">:</span> |
| <span class="kn">from</span> <span class="nn">mlflow</span> <span class="kn">import</span> <span class="n">pyfunc</span> |
| |
| <span class="n">spark</span> <span class="o">=</span> <span class="n">default_session</span><span class="p">()</span> |
| <span class="k">return</span> <span class="n">pyfunc</span><span class="o">.</span><span class="n">spark_udf</span><span class="p">(</span><span class="n">spark</span><span class="p">,</span> <span class="n">model_uri</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_model_uri</span><span class="p">,</span> <span class="n">result_type</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">_return_type</span><span class="p">)</span> |
| |
| <span class="k">def</span> <span class="fm">__str__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s2">"PythonModelWrapper(</span><span class="si">{}</span><span class="s2">)"</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="bp">self</span><span class="o">.</span><span class="n">_model</span><span class="p">))</span> |
| |
| <span class="k">def</span> <span class="fm">__repr__</span><span class="p">(</span><span class="bp">self</span><span class="p">)</span> <span class="o">-></span> <span class="nb">str</span><span class="p">:</span> |
| <span class="k">return</span> <span class="s2">"PythonModelWrapper(</span><span class="si">{}</span><span class="s2">)"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="nb">repr</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">def</span> <span class="nf">predict</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="n">DataFrame</span><span class="p">,</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">])</span> <span class="o">-></span> <span class="n">Union</span><span class="p">[</span><span class="n">Series</span><span class="p">,</span> <span class="n">pd</span><span class="o">.</span><span class="n">Series</span><span class="p">]:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Returns a prediction on the data.</span> |
| |
| <span class="sd"> If the data is a pandas-on-Spark DataFrame, the return is a pandas-on-Spark Series.</span> |
| |
| <span class="sd"> If the data is a pandas Dataframe, the return is the expected output of the underlying</span> |
| <span class="sd"> pyfunc object (typically a pandas Series or a numpy array).</span> |
| <span class="sd"> """</span> |
| <span class="k">if</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">pd</span><span class="o">.</span><span class="n">DataFrame</span><span class="p">):</span> |
| <span class="k">return</span> <span class="bp">self</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">data</span><span class="p">)</span> |
| <span class="k">elif</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">data</span><span class="p">,</span> <span class="n">DataFrame</span><span class="p">):</span> |
| <span class="n">return_col</span> <span class="o">=</span> <span class="bp">self</span><span class="o">.</span><span class="n">_model_udf</span><span class="p">(</span><span class="o">*</span><span class="n">data</span><span class="o">.</span><span class="n">_internal</span><span class="o">.</span><span class="n">data_spark_columns</span><span class="p">)</span> |
| <span class="c1"># TODO: the columns should be named according to the mlflow spec</span> |
| <span class="c1"># However, this is only possible with spark >= 3.0</span> |
| <span class="c1"># s = F.struct(*data.columns)</span> |
| <span class="c1"># return_col = self._model_udf(s)</span> |
| <span class="n">column_labels</span><span class="p">:</span> <span class="n">List</span><span class="p">[</span><span class="n">Label</span><span class="p">]</span> <span class="o">=</span> <span class="p">[</span> |
| <span class="p">(</span><span class="n">col</span><span class="p">,)</span> <span class="k">for</span> <span class="n">col</span> <span class="ow">in</span> <span class="n">data</span><span class="o">.</span><span class="n">_internal</span><span class="o">.</span><span class="n">spark_frame</span><span class="o">.</span><span class="n">select</span><span class="p">(</span><span class="n">return_col</span><span class="p">)</span><span class="o">.</span><span class="n">columns</span> |
| <span class="p">]</span> |
| <span class="n">internal</span> <span class="o">=</span> <span class="n">data</span><span class="o">.</span><span class="n">_internal</span><span class="o">.</span><span class="n">copy</span><span class="p">(</span> |
| <span class="n">column_labels</span><span class="o">=</span><span class="n">column_labels</span><span class="p">,</span> <span class="n">data_spark_columns</span><span class="o">=</span><span class="p">[</span><span class="n">return_col</span><span class="p">],</span> <span class="n">data_fields</span><span class="o">=</span><span class="kc">None</span> |
| <span class="p">)</span> |
| <span class="k">return</span> <span class="n">first_series</span><span class="p">(</span><span class="n">DataFrame</span><span class="p">(</span><span class="n">internal</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="s2">"unknown data type: </span><span class="si">{}</span><span class="s2">"</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="nb">type</span><span class="p">(</span><span class="n">data</span><span class="p">)</span><span class="o">.</span><span class="vm">__name__</span><span class="p">))</span></div> |
| |
| |
| <div class="viewcode-block" id="load_model"><a class="viewcode-back" href="../../../reference/pyspark.pandas/api/pyspark.pandas.mlflow.load_model.html#pyspark.pandas.mlflow.load_model">[docs]</a><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="nb">str</span><span class="p">,</span> <span class="n">predict_type</span><span class="p">:</span> <span class="n">Union</span><span class="p">[</span><span class="nb">str</span><span class="p">,</span> <span class="nb">type</span><span class="p">,</span> <span class="n">Dtype</span><span class="p">]</span> <span class="o">=</span> <span class="s2">"infer"</span> |
| <span class="p">)</span> <span class="o">-></span> <span class="n">PythonModelWrapper</span><span class="p">:</span> |
| <span class="w"> </span><span class="sd">"""</span> |
| <span class="sd"> Loads an MLflow model into a wrapper that can be used both for pandas and pandas-on-Spark</span> |
| <span class="sd"> DataFrame.</span> |
| |
| <span class="sd"> Parameters</span> |
| <span class="sd"> ----------</span> |
| <span class="sd"> model_uri : str</span> |
| <span class="sd"> URI pointing to the model. See MLflow documentation for more details.</span> |
| <span class="sd"> predict_type : a python basic type, a numpy basic type, a Spark type or 'infer'.</span> |
| <span class="sd"> This is the return type that is expected when calling the predict function of the model.</span> |
| <span class="sd"> If 'infer' is specified, the wrapper will attempt to automatically determine the return type</span> |
| <span class="sd"> based on the model type.</span> |
| |
| <span class="sd"> Returns</span> |
| <span class="sd"> -------</span> |
| <span class="sd"> PythonModelWrapper</span> |
| <span class="sd"> A wrapper around MLflow PythonModel objects. This wrapper is expected to adhere to the</span> |
| <span class="sd"> interface of mlflow.pyfunc.PythonModel.</span> |
| |
| <span class="sd"> Examples</span> |
| <span class="sd"> --------</span> |
| <span class="sd"> Here is a full example that creates a model with scikit-learn and saves the model with</span> |
| <span class="sd"> MLflow. The model is then loaded as a predictor that can be applied on a pandas-on-Spark</span> |
| <span class="sd"> Dataframe.</span> |
| |
| <span class="sd"> We first initialize our MLflow environment:</span> |
| |
| <span class="sd"> >>> from mlflow.tracking import MlflowClient, set_tracking_uri</span> |
| <span class="sd"> >>> import mlflow.sklearn</span> |
| <span class="sd"> >>> from tempfile import mkdtemp</span> |
| <span class="sd"> >>> d = mkdtemp("pandas_on_spark_mlflow")</span> |
| <span class="sd"> >>> set_tracking_uri("file:%s"%d)</span> |
| <span class="sd"> >>> client = MlflowClient()</span> |
| <span class="sd"> >>> exp_id = mlflow.create_experiment("my_experiment")</span> |
| <span class="sd"> >>> exp = mlflow.set_experiment("my_experiment")</span> |
| |
| <span class="sd"> We aim at learning this numerical function using a simple linear regressor.</span> |
| |
| <span class="sd"> >>> from sklearn.linear_model import LinearRegression</span> |
| <span class="sd"> >>> train = pd.DataFrame({"x1": np.arange(8), "x2": np.arange(8)**2,</span> |
| <span class="sd"> ... "y": np.log(2 + np.arange(8))})</span> |
| <span class="sd"> >>> train_x = train[["x1", "x2"]]</span> |
| <span class="sd"> >>> train_y = train[["y"]]</span> |
| <span class="sd"> >>> with mlflow.start_run():</span> |
| <span class="sd"> ... lr = LinearRegression()</span> |
| <span class="sd"> ... lr.fit(train_x, train_y)</span> |
| <span class="sd"> ... mlflow.sklearn.log_model(lr, "model")</span> |
| <span class="sd"> LinearRegression...</span> |
| |
| <span class="sd"> Now that our model is logged using MLflow, we load it back and apply it on a pandas-on-Spark</span> |
| <span class="sd"> dataframe:</span> |
| |
| <span class="sd"> >>> from pyspark.pandas.mlflow import load_model</span> |
| <span class="sd"> >>> run_info = client.search_runs(exp_id)[-1].info</span> |
| <span class="sd"> >>> model = load_model("runs:/{run_id}/model".format(run_id=run_info.run_id))</span> |
| <span class="sd"> >>> prediction_df = ps.DataFrame({"x1": [2.0], "x2": [4.0]})</span> |
| <span class="sd"> >>> prediction_df["prediction"] = model.predict(prediction_df)</span> |
| <span class="sd"> >>> prediction_df</span> |
| <span class="sd"> x1 x2 prediction</span> |
| <span class="sd"> 0 2.0 4.0 1.355551</span> |
| |
| <span class="sd"> The model also works on pandas DataFrames as expected:</span> |
| |
| <span class="sd"> >>> model.predict(prediction_df[["x1", "x2"]].to_pandas())</span> |
| <span class="sd"> array([[1.35555142]])</span> |
| |
| <span class="sd"> Notes</span> |
| <span class="sd"> -----</span> |
| <span class="sd"> Currently, the model prediction can only be merged back with the existing dataframe.</span> |
| <span class="sd"> Other columns must be manually joined.</span> |
| <span class="sd"> For example, this code will not work:</span> |
| |
| <span class="sd"> >>> df = ps.DataFrame({"x1": [2.0], "x2": [3.0], "z": [-1]})</span> |
| <span class="sd"> >>> features = df[["x1", "x2"]]</span> |
| <span class="sd"> >>> y = model.predict(features)</span> |
| <span class="sd"> >>> # Works:</span> |
| <span class="sd"> >>> features["y"] = y # doctest: +SKIP</span> |
| <span class="sd"> >>> # Will fail with a message about dataframes not aligned.</span> |
| <span class="sd"> >>> df["y"] = y # doctest: +SKIP</span> |
| |
| <span class="sd"> A current workaround is to use the .merge() function, using the feature values</span> |
| <span class="sd"> as merging keys.</span> |
| |
| <span class="sd"> >>> features['y'] = y</span> |
| <span class="sd"> >>> everything = df.merge(features, on=['x1', 'x2'])</span> |
| <span class="sd"> >>> everything</span> |
| <span class="sd"> x1 x2 z y</span> |
| <span class="sd"> 0 2.0 3.0 -1 1.376932</span> |
| <span class="sd"> """</span> |
| <span class="k">return</span> <span class="n">PythonModelWrapper</span><span class="p">(</span><span class="n">model_uri</span><span class="p">,</span> <span class="n">predict_type</span><span class="p">)</span></div> |
| |
| |
| <span class="k">def</span> <span class="nf">_test</span><span class="p">()</span> <span class="o">-></span> <span class="kc">None</span><span class="p">:</span> |
| <span class="kn">import</span> <span class="nn">os</span> |
| <span class="kn">import</span> <span class="nn">doctest</span> |
| <span class="kn">import</span> <span class="nn">sys</span> |
| <span class="kn">from</span> <span class="nn">pyspark.sql</span> <span class="kn">import</span> <span class="n">SparkSession</span> |
| <span class="kn">import</span> <span class="nn">pyspark.pandas.mlflow</span> |
| |
| <span class="n">os</span><span class="o">.</span><span class="n">chdir</span><span class="p">(</span><span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="p">[</span><span class="s2">"SPARK_HOME"</span><span class="p">])</span> |
| |
| <span class="n">globs</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">pandas</span><span class="o">.</span><span class="n">mlflow</span><span class="o">.</span><span class="vm">__dict__</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span> |
| <span class="n">globs</span><span class="p">[</span><span class="s2">"ps"</span><span class="p">]</span> <span class="o">=</span> <span class="n">pyspark</span><span class="o">.</span><span class="n">pandas</span> |
| <span class="n">spark</span> <span class="o">=</span> <span class="p">(</span> |
| <span class="n">SparkSession</span><span class="o">.</span><span class="n">builder</span><span class="o">.</span><span class="n">master</span><span class="p">(</span><span class="s2">"local[4]"</span><span class="p">)</span><span class="o">.</span><span class="n">appName</span><span class="p">(</span><span class="s2">"pyspark.pandas.mlflow tests"</span><span class="p">)</span><span class="o">.</span><span class="n">getOrCreate</span><span class="p">()</span> |
| <span class="p">)</span> |
| <span class="p">(</span><span class="n">failure_count</span><span class="p">,</span> <span class="n">test_count</span><span class="p">)</span> <span class="o">=</span> <span class="n">doctest</span><span class="o">.</span><span class="n">testmod</span><span class="p">(</span> |
| <span class="n">pyspark</span><span class="o">.</span><span class="n">pandas</span><span class="o">.</span><span class="n">mlflow</span><span class="p">,</span> |
| <span class="n">globs</span><span class="o">=</span><span class="n">globs</span><span class="p">,</span> |
| <span class="n">optionflags</span><span class="o">=</span><span class="n">doctest</span><span class="o">.</span><span class="n">ELLIPSIS</span> <span class="o">|</span> <span class="n">doctest</span><span class="o">.</span><span class="n">NORMALIZE_WHITESPACE</span><span class="p">,</span> |
| <span class="p">)</span> |
| <span class="n">spark</span><span class="o">.</span><span class="n">stop</span><span class="p">()</span> |
| <span class="k">if</span> <span class="n">failure_count</span><span class="p">:</span> |
| <span class="n">sys</span><span class="o">.</span><span class="n">exit</span><span class="p">(</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span> |
| |
| |
| <span class="k">if</span> <span class="vm">__name__</span> <span class="o">==</span> <span class="s2">"__main__"</span><span class="p">:</span> |
| <span class="k">try</span><span class="p">:</span> |
| <span class="kn">import</span> <span class="nn">mlflow</span> <span class="c1"># noqa: F401</span> |
| <span class="kn">import</span> <span class="nn">sklearn</span> <span class="c1"># noqa: F401</span> |
| |
| <span class="n">_test</span><span class="p">()</span> |
| <span class="k">except</span> <span class="ne">ImportError</span><span class="p">:</span> |
| <span class="k">pass</span> |
| </pre></div> |
| |
| </div> |
| |
| |
| <!-- Previous / next buttons --> |
| <div class='prev-next-area'> |
| </div> |
| |
| </main> |
| |
| |
| </div> |
| </div> |
| |
| <script src="../../../_static/scripts/pydata-sphinx-theme.js?digest=1999514e3f237ded88cf"></script> |
| <footer class="footer mt-5 mt-md-0"> |
| <div class="container"> |
| |
| <div class="footer-item"> |
| <p class="copyright"> |
| © Copyright .<br> |
| </p> |
| </div> |
| |
| <div class="footer-item"> |
| <p class="sphinx-version"> |
| Created using <a href="http://sphinx-doc.org/">Sphinx</a> 3.0.4.<br> |
| </p> |
| </div> |
| |
| </div> |
| </footer> |
| </body> |
| </html> |
