| |
| |
| <!DOCTYPE html> |
| <html class="writer-html5" lang="en" data-content_root="./"> |
| <head> |
| <meta charset="utf-8" /><meta name="viewport" content="width=device-width, initial-scale=1" /> |
| |
| <meta name="viewport" content="width=device-width, initial-scale=1.0" /> |
| <title>apache_beam.ml.transforms.tft module — Apache Beam 2.68.0 documentation</title> |
| <link rel="stylesheet" type="text/css" href="_static/pygments.css?v=b86133f3" /> |
| <link rel="stylesheet" type="text/css" href="_static/css/theme.css?v=e59714d7" /> |
| |
| |
| <script src="_static/jquery.js?v=5d32c60e"></script> |
| <script src="_static/_sphinx_javascript_frameworks_compat.js?v=2cd50e6c"></script> |
| <script src="_static/documentation_options.js?v=2388e03a"></script> |
| <script src="_static/doctools.js?v=9a2dae69"></script> |
| <script src="_static/sphinx_highlight.js?v=dc90522c"></script> |
| <script src="_static/js/theme.js"></script> |
| <link rel="index" title="Index" href="genindex.html" /> |
| <link rel="search" title="Search" href="search.html" /> |
| <link rel="next" title="apache_beam.ml.transforms.utils module" href="apache_beam.ml.transforms.utils.html" /> |
| <link rel="prev" title="apache_beam.ml.transforms.handlers module" href="apache_beam.ml.transforms.handlers.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 role="search"> |
| <form id="rtd-search-form" class="wy-form" action="search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" aria-label="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="Navigation menu"> |
| <ul class="current"> |
| <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 current"><a class="reference internal" href="apache_beam.ml.html">apache_beam.ml package</a><ul class="current"> |
| <li class="toctree-l2 current"><a class="reference internal" href="apache_beam.ml.html#subpackages">Subpackages</a><ul class="current"> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.ml.anomaly.html">apache_beam.ml.anomaly package</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.ml.gcp.html">apache_beam.ml.gcp package</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.ml.inference.html">apache_beam.ml.inference package</a></li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.ml.rag.html">apache_beam.ml.rag package</a></li> |
| <li class="toctree-l3 current"><a class="reference internal" href="apache_beam.ml.transforms.html">apache_beam.ml.transforms package</a><ul class="current"> |
| <li class="toctree-l4"><a class="reference internal" href="apache_beam.ml.transforms.html#subpackages">Subpackages</a></li> |
| <li class="toctree-l4 current"><a class="reference internal" href="apache_beam.ml.transforms.html#submodules">Submodules</a></li> |
| </ul> |
| </li> |
| <li class="toctree-l3"><a class="reference internal" href="apache_beam.ml.ts.html">apache_beam.ml.ts package</a></li> |
| </ul> |
| </li> |
| </ul> |
| </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="Mobile navigation menu" > |
| <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="Page navigation"> |
| <ul class="wy-breadcrumbs"> |
| <li><a href="index.html" class="icon icon-home" aria-label="Home"></a></li> |
| <li class="breadcrumb-item"><a href="apache_beam.ml.html">apache_beam.ml package</a></li> |
| <li class="breadcrumb-item"><a href="apache_beam.ml.transforms.html">apache_beam.ml.transforms package</a></li> |
| <li class="breadcrumb-item active">apache_beam.ml.transforms.tft module</li> |
| <li class="wy-breadcrumbs-aside"> |
| <a href="_sources/apache_beam.ml.transforms.tft.rst.txt" rel="nofollow"> View page source</a> |
| </li> |
| </ul> |
| <hr/> |
| </div> |
| <div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article"> |
| <div itemprop="articleBody"> |
| |
| <section id="module-apache_beam.ml.transforms.tft"> |
| <span id="apache-beam-ml-transforms-tft-module"></span><h1>apache_beam.ml.transforms.tft module<a class="headerlink" href="#module-apache_beam.ml.transforms.tft" title="Link to this heading"></a></h1> |
| <p>This module defines a set of data processing transforms that can be used |
| to perform common data transformations on a dataset. These transforms are |
| implemented using the TensorFlow Transform (TFT) library. The transforms |
| in this module are intended to be used in conjunction with the |
| MLTransform class, which provides a convenient interface for |
| applying a sequence of data processing transforms to a dataset.</p> |
| <p>See the documentation for MLTransform for more details.</p> |
| <p>Note: The data processing transforms defined in this module don’t |
| perform the transformation immediately. Instead, it returns a |
| configured operation object, which encapsulates the details of the |
| transformation. The actual computation takes place later in the Apache Beam |
| pipeline, after all transformations are set up and the pipeline is run.</p> |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.ComputeAndApplyVocabulary"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.transforms.tft.</span></span><span class="sig-name descname"><span class="pre">ComputeAndApplyVocabulary</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">columns</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_string_by_delimiter</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">default_value</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/typing.html#typing.Any" title="(in Python v3.13)"><span class="pre">Any</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">-1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">top_k</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">frequency_threshold</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_oov_buckets</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vocab_filename</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ComputeAndApplyVocabulary"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ComputeAndApplyVocabulary" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#apache_beam.ml.transforms.tft.TFTOperation" title="apache_beam.ml.transforms.tft.TFTOperation"><code class="xref py py-class docutils literal notranslate"><span class="pre">TFTOperation</span></code></a></p> |
| <p>This function computes the vocabulary for the given columns of incoming |
| data. The transformation converts the input values to indices of the |
| vocabulary.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>columns</strong> – List of column names to apply the transformation.</p></li> |
| <li><p><strong>split_string_by_delimiter</strong> – (Optional) A string that specifies the |
| delimiter to split strings.</p></li> |
| <li><p><strong>default_value</strong> – (Optional) The value to use for out-of-vocabulary values.</p></li> |
| <li><p><strong>top_k</strong> – (Optional) The number of most frequent tokens to keep.</p></li> |
| <li><p><strong>frequency_threshold</strong> – (Optional) Limit the generated vocabulary only to |
| elements whose absolute frequency is >= to the supplied threshold. |
| If set to None, the full vocabulary is generated.</p></li> |
| <li><p><strong>num_oov_buckets</strong> – Any lookup of an out-of-vocabulary token will return a |
| bucket ID based on its hash if <cite>num_oov_buckets</cite> is greater than zero. |
| Otherwise it is assigned the <cite>default_value</cite>.</p></li> |
| <li><p><strong>vocab_filename</strong> – The file name for the vocabulary file. The vocab file |
| will be suffixed with the column name. |
| NOTE in order to make your pipelines resilient to implementation |
| details please set <cite>vocab_filename</cite> when you are using |
| the vocab_filename on a downstream component.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.ComputeAndApplyVocabulary.apply_transform"> |
| <span class="sig-name descname"><span class="pre">apply_transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">tensorflow_transform.common_types.TensorType</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_column_name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.13)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">tensorflow_transform.common_types.TensorType</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ComputeAndApplyVocabulary.apply_transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ComputeAndApplyVocabulary.apply_transform" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.ScaleToZScore"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.transforms.tft.</span></span><span class="sig-name descname"><span class="pre">ScaleToZScore</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">columns</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">elementwise</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.13)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ScaleToZScore"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ScaleToZScore" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#apache_beam.ml.transforms.tft.TFTOperation" title="apache_beam.ml.transforms.tft.TFTOperation"><code class="xref py py-class docutils literal notranslate"><span class="pre">TFTOperation</span></code></a></p> |
| <p>This function performs a scaling transformation on the specified columns of |
| the incoming data. It processes the input data such that it’s normalized |
| to have a mean of 0 and a variance of 1. The transformation achieves this |
| by subtracting the mean from the input data and then dividing it by the |
| square root of the variance.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>columns</strong> – A list of column names to apply the transformation on.</p></li> |
| <li><p><strong>elementwise</strong> – If True, the transformation is applied elementwise. |
| Otherwise, the transformation is applied on the entire column.</p></li> |
| <li><p><strong>name</strong> – A name for the operation (optional).</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p>scale_to_z_score also outputs additional artifacts. The artifacts are |
| mean, which is the mean value in the column, and var, which is the |
| variance in the column. The artifacts are stored in the column |
| named with the suffix <original_col_name>_mean and <original_col_name>_var |
| respectively.</p> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.ScaleToZScore.apply_transform"> |
| <span class="sig-name descname"><span class="pre">apply_transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">tensorflow_transform.common_types.TensorType</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_column_name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.13)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">tensorflow_transform.common_types.TensorType</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ScaleToZScore.apply_transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ScaleToZScore.apply_transform" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.ScaleTo01"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.transforms.tft.</span></span><span class="sig-name descname"><span class="pre">ScaleTo01</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">columns</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">elementwise</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.13)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ScaleTo01"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ScaleTo01" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#apache_beam.ml.transforms.tft.TFTOperation" title="apache_beam.ml.transforms.tft.TFTOperation"><code class="xref py py-class docutils literal notranslate"><span class="pre">TFTOperation</span></code></a></p> |
| <p>This function applies a scaling transformation on the given columns |
| of incoming data. The transformation scales the input values to the |
| range [0, 1] by dividing each value by the maximum value in the |
| column.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>columns</strong> – A list of column names to apply the transformation on.</p></li> |
| <li><p><strong>elementwise</strong> – If True, the transformation is applied elementwise. |
| Otherwise, the transformation is applied on the entire column.</p></li> |
| <li><p><strong>name</strong> – A name for the operation (optional).</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p>ScaleTo01 also outputs additional artifacts. The artifacts are |
| max, which is the maximum value in the column, and min, which is the |
| minimum value in the column. The artifacts are stored in the column |
| named with the suffix <original_col_name>_min and <original_col_name>_max |
| respectively.</p> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.ScaleTo01.apply_transform"> |
| <span class="sig-name descname"><span class="pre">apply_transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">tensorflow_transform.common_types.TensorType</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_column_name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.13)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">tensorflow_transform.common_types.TensorType</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ScaleTo01.apply_transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ScaleTo01.apply_transform" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.ScaleToGaussian"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.transforms.tft.</span></span><span class="sig-name descname"><span class="pre">ScaleToGaussian</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">columns</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">elementwise</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.13)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ScaleToGaussian"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ScaleToGaussian" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#apache_beam.ml.transforms.tft.TFTOperation" title="apache_beam.ml.transforms.tft.TFTOperation"><code class="xref py py-class docutils literal notranslate"><span class="pre">TFTOperation</span></code></a></p> |
| <p>This operation scales the given input column values to an approximately |
| normal distribution with mean 0 and variance of 1. The Gaussian |
| transformation is only applied if the column has long tails; |
| otherwise, the transformation is the same as normalizing to z scores.</p> |
| <p>For more information, see: |
| <a class="reference external" href="https://www.tensorflow.org/tfx/transform/api_docs/python/tft/scale_to_gaussian">https://www.tensorflow.org/tfx/transform/api_docs/python/tft/scale_to_gaussian</a></p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>columns</strong> – A list of column names to apply the transformation on.</p></li> |
| <li><p><strong>elementwise</strong> – If True, the transformation is applied elementwise. |
| Otherwise, the transformation is applied on the entire column.</p></li> |
| <li><p><strong>name</strong> – A name for the operation (optional).</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.ScaleToGaussian.apply_transform"> |
| <span class="sig-name descname"><span class="pre">apply_transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">tensorflow_transform.common_types.TensorType</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_column_name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.13)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">tensorflow_transform.common_types.TensorType</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ScaleToGaussian.apply_transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ScaleToGaussian.apply_transform" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.ApplyBuckets"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.transforms.tft.</span></span><span class="sig-name descname"><span class="pre">ApplyBuckets</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">columns</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bucket_boundaries</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Iterable" title="(in Python v3.13)"><span class="pre">Iterable</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.13)"><span class="pre">float</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ApplyBuckets"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ApplyBuckets" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#apache_beam.ml.transforms.tft.TFTOperation" title="apache_beam.ml.transforms.tft.TFTOperation"><code class="xref py py-class docutils literal notranslate"><span class="pre">TFTOperation</span></code></a></p> |
| <p>This functions is used to map the element to a positive index i for |
| which <cite>bucket_boundaries[i-1] <= element < bucket_boundaries[i]</cite>, |
| if it exists. If <cite>input < bucket_boundaries[0]</cite>, then element is |
| mapped to 0. If <cite>element >= bucket_boundaries[-1]</cite>, then element is |
| mapped to len(bucket_boundaries). NaNs are mapped to |
| len(bucket_boundaries).</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>columns</strong> – A list of column names to apply the transformation on.</p></li> |
| <li><p><strong>bucket_boundaries</strong> – An iterable of ints or floats representing the bucket |
| boundaries. Must be sorted in ascending order.</p></li> |
| <li><p><strong>name</strong> – (Optional) A string that specifies the name of the operation.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.ApplyBuckets.apply_transform"> |
| <span class="sig-name descname"><span class="pre">apply_transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">tensorflow_transform.common_types.TensorType</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_column_name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.13)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">tensorflow_transform.common_types.TensorType</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ApplyBuckets.apply_transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ApplyBuckets.apply_transform" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.ApplyBucketsWithInterpolation"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.transforms.tft.</span></span><span class="sig-name descname"><span class="pre">ApplyBucketsWithInterpolation</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">columns</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">bucket_boundaries</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/collections.abc.html#collections.abc.Iterable" title="(in Python v3.13)"><span class="pre">Iterable</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.13)"><span class="pre">float</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ApplyBucketsWithInterpolation"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ApplyBucketsWithInterpolation" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#apache_beam.ml.transforms.tft.TFTOperation" title="apache_beam.ml.transforms.tft.TFTOperation"><code class="xref py py-class docutils literal notranslate"><span class="pre">TFTOperation</span></code></a></p> |
| <p>Interpolates values within the provided buckets and then normalizes to |
| [0, 1].</p> |
| <p>Input values are bucketized based on the provided boundaries such that the |
| input is mapped to a positive index i for which <cite>bucket_boundaries[i-1] <= |
| element < bucket_boundaries[i]</cite>, if it exists. The values are then |
| normalized to the range [0,1] within the bucket, with NaN values being |
| mapped to 0.5.</p> |
| <p>For more information, see: |
| <a class="reference external" href="https://www.tensorflow.org/tfx/transform/api_docs/python/tft/apply_buckets_with_interpolation">https://www.tensorflow.org/tfx/transform/api_docs/python/tft/apply_buckets_with_interpolation</a></p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>columns</strong> – A list of column names to apply the transformation on.</p></li> |
| <li><p><strong>bucket_boundaries</strong> – An iterable of ints or floats representing the bucket |
| boundaries sorted in ascending order.</p></li> |
| <li><p><strong>name</strong> – (Optional) A string that specifies the name of the operation.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.ApplyBucketsWithInterpolation.apply_transform"> |
| <span class="sig-name descname"><span class="pre">apply_transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">tensorflow_transform.common_types.TensorType</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_column_name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.13)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">tensorflow_transform.common_types.TensorType</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ApplyBucketsWithInterpolation.apply_transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ApplyBucketsWithInterpolation.apply_transform" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.Bucketize"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.transforms.tft.</span></span><span class="sig-name descname"><span class="pre">Bucketize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">columns</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_buckets</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">epsilon</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.13)"><span class="pre">float</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">elementwise</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.13)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#Bucketize"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.Bucketize" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#apache_beam.ml.transforms.tft.TFTOperation" title="apache_beam.ml.transforms.tft.TFTOperation"><code class="xref py py-class docutils literal notranslate"><span class="pre">TFTOperation</span></code></a></p> |
| <p>This function applies a bucketizing transformation on the given columns |
| of incoming data. The transformation splits the input data range into |
| a set of consecutive bins/buckets, and converts the input values to |
| bucket IDs (integers) where each ID corresponds to a particular bin.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>columns</strong> – List of column names to apply the transformation.</p></li> |
| <li><p><strong>num_buckets</strong> – Number of buckets to be created.</p></li> |
| <li><p><strong>epsilon</strong> – (Optional) A float number that specifies the error tolerance |
| when computing quantiles, so that we guarantee that any value x will |
| have a quantile q such that x is in the interval |
| [q - epsilon, q + epsilon] (or the symmetric interval for even |
| num_buckets). Must be greater than 0.0.</p></li> |
| <li><p><strong>elementwise</strong> – (Optional) A boolean that specifies whether the quantiles |
| should be computed on an element-wise basis. If False, the quantiles |
| are computed globally.</p></li> |
| <li><p><strong>name</strong> – (Optional) A string that specifies the name of the operation.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.Bucketize.apply_transform"> |
| <span class="sig-name descname"><span class="pre">apply_transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">tensorflow_transform.common_types.TensorType</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_column_name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.13)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">tensorflow_transform.common_types.TensorType</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#Bucketize.apply_transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.Bucketize.apply_transform" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.TFIDF"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.transforms.tft.</span></span><span class="sig-name descname"><span class="pre">TFIDF</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">columns</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">vocab_size</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">smooth</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.13)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">True</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#TFIDF"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.TFIDF" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#apache_beam.ml.transforms.tft.TFTOperation" title="apache_beam.ml.transforms.tft.TFTOperation"><code class="xref py py-class docutils literal notranslate"><span class="pre">TFTOperation</span></code></a></p> |
| <p>This function applies a tf-idf transformation on the given columns |
| of incoming data.</p> |
| <p>TFIDF outputs two artifacts for each column: the vocabulary index and |
| the tfidf weight. The vocabulary index is a mapping from the original |
| vocabulary to the new vocabulary. The tfidf weight is a mapping |
| from the original vocabulary to the tfidf score.</p> |
| <p>Input passed to the TFIDF is not modified and used to calculate the |
| required artifacts.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>columns</strong> – List of column names to apply the transformation.</p></li> |
| <li><p><strong>vocab_size</strong> – <p>(Optional) An integer that specifies the size of the |
| vocabulary. Defaults to None.</p> |
| <p>If vocab_size is None, then the size of the vocabulary is |
| determined by <cite>tft.get_num_buckets_for_transformed_feature</cite>.</p> |
| </p></li> |
| <li><p><strong>smooth</strong> – (Optional) A boolean that specifies whether to apply |
| smoothing to the tf-idf score. Defaults to True.</p></li> |
| <li><p><strong>name</strong> – (Optional) A string that specifies the name of the operation.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.TFIDF.apply_transform"> |
| <span class="sig-name descname"><span class="pre">apply_transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">tensorflow_transform.common_types.TensorType</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_column_name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">tensorflow_transform.common_types.TensorType</span></span></span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#TFIDF.apply_transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.TFIDF.apply_transform" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.TFTOperation"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.transforms.tft.</span></span><span class="sig-name descname"><span class="pre">TFTOperation</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">columns</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#TFTOperation"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.TFTOperation" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference internal" href="apache_beam.ml.transforms.base.html#apache_beam.ml.transforms.base.BaseOperation" title="apache_beam.ml.transforms.base.BaseOperation"><code class="xref py py-class docutils literal notranslate"><span class="pre">BaseOperation</span></code></a>[<code class="xref py py-class docutils literal notranslate"><span class="pre">TensorType</span></code>, <code class="xref py py-class docutils literal notranslate"><span class="pre">TensorType</span></code>]</p> |
| <p>Base Operation class for TFT data processing transformations. |
| Processing logic for the transformation is defined in the |
| apply_transform() method. If you have a custom transformation that is not |
| supported by the existing transforms, you can extend this class |
| and implement the apply_transform() method. |
| :param columns: List of column names to apply the transformation.</p> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.TFTOperation.get_ptransform_for_processing"> |
| <span class="sig-name descname"><span class="pre">get_ptransform_for_processing</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">**</span></span><span class="n"><span class="pre">kwargs</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference internal" href="apache_beam.transforms.ptransform.html#apache_beam.transforms.ptransform.PTransform" title="apache_beam.transforms.ptransform.PTransform"><span class="pre">PTransform</span></a></span></span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#TFTOperation.get_ptransform_for_processing"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.TFTOperation.get_ptransform_for_processing" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.ScaleByMinMax"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.transforms.tft.</span></span><span class="sig-name descname"><span class="pre">ScaleByMinMax</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">columns</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">min_value</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.13)"><span class="pre">float</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">0.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_value</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#float" title="(in Python v3.13)"><span class="pre">float</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">1.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ScaleByMinMax"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ScaleByMinMax" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#apache_beam.ml.transforms.tft.TFTOperation" title="apache_beam.ml.transforms.tft.TFTOperation"><code class="xref py py-class docutils literal notranslate"><span class="pre">TFTOperation</span></code></a></p> |
| <p>This function applies a scaling transformation on the given columns |
| of incoming data. The transformation scales the input values to the |
| range [min_value, max_value].</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>columns</strong> – A list of column names to apply the transformation on.</p></li> |
| <li><p><strong>min_value</strong> – The minimum value of the output range.</p></li> |
| <li><p><strong>max_value</strong> – The maximum value of the output range.</p></li> |
| <li><p><strong>name</strong> – A name for the operation (optional).</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.ScaleByMinMax.apply_transform"> |
| <span class="sig-name descname"><span class="pre">apply_transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">tensorflow_transform.common_types.TensorType</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_column_name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><span class="pre">tensorflow_transform.common_types.TensorType</span></span></span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ScaleByMinMax.apply_transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ScaleByMinMax.apply_transform" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.NGrams"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.transforms.tft.</span></span><span class="sig-name descname"><span class="pre">NGrams</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">columns</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_string_by_delimiter</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ngram_range</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.13)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">(1,</span> <span class="pre">1)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ngrams_separator</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#NGrams"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.NGrams" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#apache_beam.ml.transforms.tft.TFTOperation" title="apache_beam.ml.transforms.tft.TFTOperation"><code class="xref py py-class docutils literal notranslate"><span class="pre">TFTOperation</span></code></a></p> |
| <p>An n-gram is a contiguous sequence of n items from a given sample of text |
| or speech. This operation applies an n-gram transformation to |
| specified columns of incoming data, splitting the input data into a |
| set of consecutive n-grams.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>columns</strong> – A list of column names to apply the transformation on.</p></li> |
| <li><p><strong>split_string_by_delimiter</strong> – (Optional) A string that specifies the |
| delimiter to split the input strings before computing ngrams.</p></li> |
| <li><p><strong>ngram_range</strong> – A tuple of integers(inclusive) specifying the range of |
| n-gram sizes.</p></li> |
| <li><p><strong>ngrams_separator</strong> – A string that will be inserted between each ngram.</p></li> |
| <li><p><strong>name</strong> – A name for the operation (optional).</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.NGrams.apply_transform"> |
| <span class="sig-name descname"><span class="pre">apply_transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">tensorflow_transform.common_types.TensorType</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_column_name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.13)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">tensorflow_transform.common_types.TensorType</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#NGrams.apply_transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.NGrams.apply_transform" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.BagOfWords"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.transforms.tft.</span></span><span class="sig-name descname"><span class="pre">BagOfWords</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">columns</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">split_string_by_delimiter</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ngram_range</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.13)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">(1,</span> <span class="pre">1)</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">ngrams_separator</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">compute_word_count</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#bool" title="(in Python v3.13)"><span class="pre">bool</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key_vocab_filename</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#BagOfWords"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.BagOfWords" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#apache_beam.ml.transforms.tft.TFTOperation" title="apache_beam.ml.transforms.tft.TFTOperation"><code class="xref py py-class docutils literal notranslate"><span class="pre">TFTOperation</span></code></a></p> |
| <p>Bag of words contains the unique words present in the input text. |
| This operation applies a bag of words transformation to specified |
| columns of incoming data. Also, the transformation accepts a Tuple of |
| integers specifying the range of n-gram sizes. The transformation |
| splits the input data into a set of consecutive n-grams if ngram_range |
| is specified. The n-grams are then converted to a bag of words. |
| Also, you can specify a seperator string that will be inserted between |
| each ngram.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>columns</strong> – A list of column names to apply the transformation on.</p></li> |
| <li><p><strong>split_string_by_delimiter</strong> – (Optional) A string that specifies the |
| delimiter to split the input strings before computing ngrams.</p></li> |
| <li><p><strong>ngram_range</strong> – A tuple of integers(inclusive) specifying the range of |
| n-gram sizes.</p></li> |
| <li><p><strong>seperator</strong> – A string that will be inserted between each ngram.</p></li> |
| <li><p><strong>compute_word_count</strong> – A boolean that specifies whether to compute |
| the unique word count over the entire dataset. Defaults to False.</p></li> |
| <li><p><strong>key_vocab_filename</strong> – The file name for the key vocabulary file when |
| compute_word_count is True. If empty, a file name |
| will be chosen based on the current scope. If provided, the vocab |
| file will be suffixed with the column name.</p></li> |
| <li><p><strong>name</strong> – A name for the operation (optional).</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <p>Note that original order of the input may not be preserved.</p> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.BagOfWords.apply_transform"> |
| <span class="sig-name descname"><span class="pre">apply_transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">tensorflow.SparseTensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_col_name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#BagOfWords.apply_transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.BagOfWords.apply_transform" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.HashStrings"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.transforms.tft.</span></span><span class="sig-name descname"><span class="pre">HashStrings</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">columns</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">hash_buckets</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">key</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#tuple" title="(in Python v3.13)"><span class="pre">tuple</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/functions.html#int" title="(in Python v3.13)"><span class="pre">int</span></a><span class="p"><span class="pre">]</span></span><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#HashStrings"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.HashStrings" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#apache_beam.ml.transforms.tft.TFTOperation" title="apache_beam.ml.transforms.tft.TFTOperation"><code class="xref py py-class docutils literal notranslate"><span class="pre">TFTOperation</span></code></a></p> |
| <p>Hashes strings into the provided number of buckets.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>columns</strong> – A list of the column names to apply the transformation on.</p></li> |
| <li><p><strong>hash_buckets</strong> – the number of buckets to hash the strings into.</p></li> |
| <li><p><strong>key</strong> – optional. An array of two Python <cite>uint64</cite>. If passed, output will be |
| a deterministic function of <cite>strings</cite> and <cite>key</cite>. Note that hashing will |
| be slower if this value is specified.</p></li> |
| <li><p><strong>name</strong> – optional. A name for this operation.</p></li> |
| </ul> |
| </dd> |
| <dt class="field-even">Raises<span class="colon">:</span></dt> |
| <dd class="field-even"><p><strong>ValueError if hash_buckets is not a positive and non-zero integer.</strong> – </p> |
| </dd> |
| </dl> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.HashStrings.apply_transform"> |
| <span class="sig-name descname"><span class="pre">apply_transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">tensorflow_transform.common_types.TensorType</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_col_name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.13)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">tensorflow_transform.common_types.TensorType</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#HashStrings.apply_transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.HashStrings.apply_transform" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="py class"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.DeduplicateTensorPerRow"> |
| <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">apache_beam.ml.transforms.tft.</span></span><span class="sig-name descname"><span class="pre">DeduplicateTensorPerRow</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">columns</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#list" title="(in Python v3.13)"><span class="pre">list</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="w"> </span><span class="p"><span class="pre">|</span></span><span class="w"> </span><a class="reference external" href="https://docs.python.org/3/library/constants.html#None" title="(in Python v3.13)"><span class="pre">None</span></a></span><span class="w"> </span><span class="o"><span class="pre">=</span></span><span class="w"> </span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#DeduplicateTensorPerRow"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.DeduplicateTensorPerRow" title="Link to this definition"></a></dt> |
| <dd><p>Bases: <a class="reference internal" href="#apache_beam.ml.transforms.tft.TFTOperation" title="apache_beam.ml.transforms.tft.TFTOperation"><code class="xref py py-class docutils literal notranslate"><span class="pre">TFTOperation</span></code></a></p> |
| <p>Deduplicates each row (0th dimension) of the provided tensor.</p> |
| <dl class="field-list simple"> |
| <dt class="field-odd">Parameters<span class="colon">:</span></dt> |
| <dd class="field-odd"><ul class="simple"> |
| <li><p><strong>columns</strong> – A list of the columns to apply the transformation on.</p></li> |
| <li><p><strong>name</strong> – optional. A name for this operation.</p></li> |
| </ul> |
| </dd> |
| </dl> |
| <dl class="py method"> |
| <dt class="sig sig-object py" id="apache_beam.ml.transforms.tft.DeduplicateTensorPerRow.apply_transform"> |
| <span class="sig-name descname"><span class="pre">apply_transform</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">tensorflow_transform.common_types.TensorType</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_col_name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">→</span> <span class="sig-return-typehint"><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#dict" title="(in Python v3.13)"><span class="pre">dict</span></a><span class="p"><span class="pre">[</span></span><a class="reference external" href="https://docs.python.org/3/library/stdtypes.html#str" title="(in Python v3.13)"><span class="pre">str</span></a><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">tensorflow_transform.common_types.TensorType</span><span class="p"><span class="pre">]</span></span></span></span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#DeduplicateTensorPerRow.apply_transform"><span class="viewcode-link"><span class="pre">[source]</span></span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.DeduplicateTensorPerRow.apply_transform" title="Link to this definition"></a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| </section> |
| |
| |
| </div> |
| </div> |
| <footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer"> |
| <a href="apache_beam.ml.transforms.handlers.html" class="btn btn-neutral float-left" title="apache_beam.ml.transforms.handlers module" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a> |
| <a href="apache_beam.ml.transforms.utils.html" class="btn btn-neutral float-right" title="apache_beam.ml.transforms.utils module" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a> |
| </div> |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p>© Copyright %Y, Apache Beam.</p> |
| </div> |
| |
| Built with <a href="https://www.sphinx-doc.org/">Sphinx</a> using a |
| <a href="https://github.com/readthedocs/sphinx_rtd_theme">theme</a> |
| provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| |
| </footer> |
| </div> |
| </div> |
| </section> |
| </div> |
| <script> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| </body> |
| </html> |
