| |
| |
| <!DOCTYPE html> |
| <!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]--> |
| <!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]--> |
| <head> |
| <meta charset="utf-8"> |
| |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> |
| |
| <title>apache_beam.ml.transforms.tft module — Apache Beam 2.52.0 documentation</title> |
| |
| |
| |
| |
| |
| |
| |
| |
| <script type="text/javascript" src="_static/js/modernizr.min.js"></script> |
| |
| |
| <script type="text/javascript" id="documentation_options" data-url_root="./" src="_static/documentation_options.js"></script> |
| <script type="text/javascript" src="_static/jquery.js"></script> |
| <script type="text/javascript" src="_static/underscore.js"></script> |
| <script type="text/javascript" src="_static/doctools.js"></script> |
| <script type="text/javascript" src="_static/language_data.js"></script> |
| <script async="async" type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.5/latest.js?config=TeX-AMS-MML_HTMLorMML"></script> |
| |
| <script type="text/javascript" src="_static/js/theme.js"></script> |
| |
| |
| |
| |
| <link rel="stylesheet" href="_static/css/theme.css" type="text/css" /> |
| <link rel="stylesheet" href="_static/pygments.css" type="text/css" /> |
| <link rel="index" title="Index" href="genindex.html" /> |
| <link rel="search" title="Search" href="search.html" /> |
| <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 class="version"> |
| 2.52.0 |
| </div> |
| |
| |
| |
| |
| <div role="search"> |
| <form id="rtd-search-form" class="wy-form" action="search.html" method="get"> |
| <input type="text" name="q" placeholder="Search docs" /> |
| <input type="hidden" name="check_keywords" value="yes" /> |
| <input type="hidden" name="area" value="default" /> |
| </form> |
| </div> |
| |
| |
| </div> |
| |
| <div class="wy-menu wy-menu-vertical" data-spy="affix" role="navigation" aria-label="main navigation"> |
| |
| |
| |
| |
| |
| |
| <ul 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.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 current"><a class="reference internal" href="apache_beam.ml.transforms.html">apache_beam.ml.transforms package</a><ul class="current"> |
| <li class="toctree-l4 current"><a class="reference internal" href="apache_beam.ml.transforms.html#submodules">Submodules</a></li> |
| </ul> |
| </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="top navigation"> |
| |
| <i data-toggle="wy-nav-top" class="fa fa-bars"></i> |
| <a href="index.html">Apache Beam</a> |
| |
| </nav> |
| |
| |
| <div class="wy-nav-content"> |
| |
| <div class="rst-content"> |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| <div role="navigation" aria-label="breadcrumbs navigation"> |
| |
| <ul class="wy-breadcrumbs"> |
| |
| <li><a href="index.html">Docs</a> »</li> |
| |
| <li><a href="apache_beam.ml.html">apache_beam.ml package</a> »</li> |
| |
| <li><a href="apache_beam.ml.transforms.html">apache_beam.ml.transforms package</a> »</li> |
| |
| <li>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"> |
| |
| <div class="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="Permalink to this headline">¶</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="class"> |
| <dt id="apache_beam.ml.transforms.tft.TFTOperation"> |
| <em class="property">class </em><code class="descclassname">apache_beam.ml.transforms.tft.</code><code class="descname">TFTOperation</code><span class="sig-paren">(</span><em>columns: List[str]</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#TFTOperation"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.TFTOperation" title="Permalink 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">apache_beam.ml.transforms.base.BaseOperation</span></code></a></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> |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.ml.transforms.tft.ComputeAndApplyVocabulary"> |
| <em class="property">class </em><code class="descclassname">apache_beam.ml.transforms.tft.</code><code class="descname">ComputeAndApplyVocabulary</code><span class="sig-paren">(</span><em>columns: List[str], split_string_by_delimiter: Optional[str] = None, *, default_value: Any = -1, top_k: Optional[int] = None, frequency_threshold: Optional[int] = None, num_oov_buckets: int = 0, vocab_filename: Optional[str] = None, name: Optional[str] = None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ComputeAndApplyVocabulary"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ComputeAndApplyVocabulary" title="Permalink 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">apache_beam.ml.transforms.tft.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> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name" /> |
| <col class="field-body" /> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>columns</strong> – List of column names to apply the transformation.</li> |
| <li><strong>split_string_by_delimiter</strong> – (Optional) A string that specifies the |
| delimiter to split strings.</li> |
| <li><strong>default_value</strong> – (Optional) The value to use for out-of-vocabulary values.</li> |
| <li><strong>top_k</strong> – (Optional) The number of most frequent tokens to keep.</li> |
| <li><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.</li> |
| <li><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>.</li> |
| <li><strong>vocab_filename</strong> – The file name for the vocabulary file. If not provided, |
| the default name would be <cite>compute_and_apply_vocab’ |
| NOTE in order to make your pipelines resilient to implementation |
| details please set `vocab_filename</cite> when you are using |
| the vocab_filename on a downstream component.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="apache_beam.ml.transforms.tft.ComputeAndApplyVocabulary.apply_transform"> |
| <code class="descname">apply_transform</code><span class="sig-paren">(</span><em>data: <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbed400></em>, <em>output_column_name: str</em><span class="sig-paren">)</span> → Dict[str, <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbed400>]<a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ComputeAndApplyVocabulary.apply_transform"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ComputeAndApplyVocabulary.apply_transform" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.ml.transforms.tft.ScaleToZScore"> |
| <em class="property">class </em><code class="descclassname">apache_beam.ml.transforms.tft.</code><code class="descname">ScaleToZScore</code><span class="sig-paren">(</span><em>columns: List[str], *, elementwise: bool = False, name: Optional[str] = None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ScaleToZScore"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ScaleToZScore" title="Permalink 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">apache_beam.ml.transforms.tft.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> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name" /> |
| <col class="field-body" /> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>columns</strong> – A list of column names to apply the transformation on.</li> |
| <li><strong>elementwise</strong> – If True, the transformation is applied elementwise. |
| Otherwise, the transformation is applied on the entire column.</li> |
| <li><strong>name</strong> – A name for the operation (optional).</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <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="method"> |
| <dt id="apache_beam.ml.transforms.tft.ScaleToZScore.apply_transform"> |
| <code class="descname">apply_transform</code><span class="sig-paren">(</span><em>data: <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbed400></em>, <em>output_column_name: str</em><span class="sig-paren">)</span> → Dict[str, <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbed400>]<a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ScaleToZScore.apply_transform"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ScaleToZScore.apply_transform" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.ml.transforms.tft.ScaleTo01"> |
| <em class="property">class </em><code class="descclassname">apache_beam.ml.transforms.tft.</code><code class="descname">ScaleTo01</code><span class="sig-paren">(</span><em>columns: List[str], elementwise: bool = False, name: Optional[str] = None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ScaleTo01"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ScaleTo01" title="Permalink 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">apache_beam.ml.transforms.tft.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> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name" /> |
| <col class="field-body" /> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>columns</strong> – A list of column names to apply the transformation on.</li> |
| <li><strong>elementwise</strong> – If True, the transformation is applied elementwise. |
| Otherwise, the transformation is applied on the entire column.</li> |
| <li><strong>name</strong> – A name for the operation (optional).</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <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="method"> |
| <dt id="apache_beam.ml.transforms.tft.ScaleTo01.apply_transform"> |
| <code class="descname">apply_transform</code><span class="sig-paren">(</span><em>data: <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbed400></em>, <em>output_column_name: str</em><span class="sig-paren">)</span> → Dict[str, <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbed400>]<a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ScaleTo01.apply_transform"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ScaleTo01.apply_transform" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.ml.transforms.tft.ApplyBuckets"> |
| <em class="property">class </em><code class="descclassname">apache_beam.ml.transforms.tft.</code><code class="descname">ApplyBuckets</code><span class="sig-paren">(</span><em>columns: List[str], bucket_boundaries: Iterable[Union[int, float]], name: Optional[str] = None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ApplyBuckets"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ApplyBuckets" title="Permalink 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">apache_beam.ml.transforms.tft.TFTOperation</span></code></a></p> |
| <p>This functions is used to map the element to a positive index i for |
| which bucket_boundaries[i-1] <= element < bucket_boundaries[i], |
| if it exists. If input < bucket_boundaries[0], then element is |
| mapped to 0. If element >= bucket_boundaries[-1], then element is |
| mapped to len(bucket_boundaries). NaNs are mapped to |
| len(bucket_boundaries).</p> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name" /> |
| <col class="field-body" /> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>columns</strong> – A list of column names to apply the transformation on.</li> |
| <li><strong>bucket_boundaries</strong> – A rank 2 Tensor or list representing the bucket |
| boundaries sorted in ascending order.</li> |
| <li><strong>name</strong> – (Optional) A string that specifies the name of the operation.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="apache_beam.ml.transforms.tft.ApplyBuckets.apply_transform"> |
| <code class="descname">apply_transform</code><span class="sig-paren">(</span><em>data: <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbed400></em>, <em>output_column_name: str</em><span class="sig-paren">)</span> → Dict[str, <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbed400>]<a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ApplyBuckets.apply_transform"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ApplyBuckets.apply_transform" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.ml.transforms.tft.Bucketize"> |
| <em class="property">class </em><code class="descclassname">apache_beam.ml.transforms.tft.</code><code class="descname">Bucketize</code><span class="sig-paren">(</span><em>columns: List[str], num_buckets: int, *, epsilon: Optional[float] = None, elementwise: bool = False, name: Optional[str] = None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#Bucketize"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.Bucketize" title="Permalink 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">apache_beam.ml.transforms.tft.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> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name" /> |
| <col class="field-body" /> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>columns</strong> – List of column names to apply the transformation.</li> |
| <li><strong>num_buckets</strong> – Number of buckets to be created.</li> |
| <li><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.</li> |
| <li><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.</li> |
| <li><strong>name</strong> – (Optional) A string that specifies the name of the operation.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="apache_beam.ml.transforms.tft.Bucketize.apply_transform"> |
| <code class="descname">apply_transform</code><span class="sig-paren">(</span><em>data: <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbed400></em>, <em>output_column_name: str</em><span class="sig-paren">)</span> → Dict[str, <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbed400>]<a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#Bucketize.apply_transform"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.Bucketize.apply_transform" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.ml.transforms.tft.TFIDF"> |
| <em class="property">class </em><code class="descclassname">apache_beam.ml.transforms.tft.</code><code class="descname">TFIDF</code><span class="sig-paren">(</span><em>columns: List[str], vocab_size: Optional[int] = None, smooth: bool = True, name: Optional[str] = None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#TFIDF"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.TFIDF" title="Permalink 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">apache_beam.ml.transforms.tft.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 vocabu index and |
| the tfidf weight. The vocabu 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> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name" /> |
| <col class="field-body" /> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>columns</strong> – List of column names to apply the transformation.</li> |
| <li><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> |
| </li> |
| <li><strong>smooth</strong> – (Optional) A boolean that specifies whether to apply |
| smoothing to the tf-idf score. Defaults to True.</li> |
| <li><strong>name</strong> – (Optional) A string that specifies the name of the operation.</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="apache_beam.ml.transforms.tft.TFIDF.apply_transform"> |
| <code class="descname">apply_transform</code><span class="sig-paren">(</span><em>data: <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbed400></em>, <em>output_column_name: str</em><span class="sig-paren">)</span> → <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbed400><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#TFIDF.apply_transform"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.TFIDF.apply_transform" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.ml.transforms.tft.ScaleByMinMax"> |
| <em class="property">class </em><code class="descclassname">apache_beam.ml.transforms.tft.</code><code class="descname">ScaleByMinMax</code><span class="sig-paren">(</span><em>columns: List[str], min_value: float = 0.0, max_value: float = 1.0, name: Optional[str] = None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ScaleByMinMax"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ScaleByMinMax" title="Permalink 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">apache_beam.ml.transforms.tft.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> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name" /> |
| <col class="field-body" /> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>columns</strong> – A list of column names to apply the transformation on.</li> |
| <li><strong>min_value</strong> – The minimum value of the output range.</li> |
| <li><strong>max_value</strong> – The maximum value of the output range.</li> |
| <li><strong>name</strong> – A name for the operation (optional).</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="apache_beam.ml.transforms.tft.ScaleByMinMax.apply_transform"> |
| <code class="descname">apply_transform</code><span class="sig-paren">(</span><em>data: <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbed400></em>, <em>output_column_name: str</em><span class="sig-paren">)</span> → <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbed400><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#ScaleByMinMax.apply_transform"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.ScaleByMinMax.apply_transform" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.ml.transforms.tft.NGrams"> |
| <em class="property">class </em><code class="descclassname">apache_beam.ml.transforms.tft.</code><code class="descname">NGrams</code><span class="sig-paren">(</span><em>columns: List[str], split_string_by_delimiter: Optional[str] = None, *, ngram_range: Tuple[int, int] = (1, 1), ngrams_separator: Optional[str] = None, name: Optional[str] = None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#NGrams"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.NGrams" title="Permalink 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">apache_beam.ml.transforms.tft.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> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name" /> |
| <col class="field-body" /> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>columns</strong> – A list of column names to apply the transformation on.</li> |
| <li><strong>split_string_by_delimiter</strong> – (Optional) A string that specifies the |
| delimiter to split the input strings before computing ngrams.</li> |
| <li><strong>ngram_range</strong> – A tuple of integers(inclusive) specifying the range of |
| n-gram sizes.</li> |
| <li><strong>ngrams_separator</strong> – A string that will be inserted between each ngram.</li> |
| <li><strong>name</strong> – A name for the operation (optional).</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <dl class="method"> |
| <dt id="apache_beam.ml.transforms.tft.NGrams.apply_transform"> |
| <code class="descname">apply_transform</code><span class="sig-paren">(</span><em>data: <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbed400></em>, <em>output_column_name: str</em><span class="sig-paren">)</span> → Dict[str, <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbed400>]<a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#NGrams.apply_transform"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.NGrams.apply_transform" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| <dl class="class"> |
| <dt id="apache_beam.ml.transforms.tft.BagOfWords"> |
| <em class="property">class </em><code class="descclassname">apache_beam.ml.transforms.tft.</code><code class="descname">BagOfWords</code><span class="sig-paren">(</span><em>columns: List[str], split_string_by_delimiter: Optional[str] = None, *, ngram_range: Tuple[int, int] = (1, 1), ngrams_separator: Optional[str] = None, compute_word_count: bool = False, key_vocab_filename: str = 'key_vocab_mapping', name: Optional[str] = None</em><span class="sig-paren">)</span><a class="reference internal" href="_modules/apache_beam/ml/transforms/tft.html#BagOfWords"><span class="viewcode-link">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.BagOfWords" title="Permalink 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">apache_beam.ml.transforms.tft.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> |
| <table class="docutils field-list" frame="void" rules="none"> |
| <col class="field-name" /> |
| <col class="field-body" /> |
| <tbody valign="top"> |
| <tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first last simple"> |
| <li><strong>columns</strong> – A list of column names to apply the transformation on.</li> |
| <li><strong>split_string_by_delimiter</strong> – (Optional) A string that specifies the |
| delimiter to split the input strings before computing ngrams.</li> |
| <li><strong>ngram_range</strong> – A tuple of integers(inclusive) specifying the range of |
| n-gram sizes.</li> |
| <li><strong>seperator</strong> – A string that will be inserted between each ngram.</li> |
| <li><strong>compute_word_count</strong> – A boolean that specifies whether to compute |
| the unique word count over the entire dataset. Defaults to False.</li> |
| <li><strong>key_vocab_filename</strong> – The file name for the key vocabulary file when |
| compute_word_count is True.</li> |
| <li><strong>name</strong> – A name for the operation (optional).</li> |
| </ul> |
| </td> |
| </tr> |
| </tbody> |
| </table> |
| <p>Note that original order of the input may not be preserved.</p> |
| <dl class="method"> |
| <dt id="apache_beam.ml.transforms.tft.BagOfWords.apply_transform"> |
| <code class="descname">apply_transform</code><span class="sig-paren">(</span><em>data: <sphinx.ext.autodoc.importer._MockObject object at 0x7f50cfbfe280></em>, <em>output_col_name: str</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">[source]</span></a><a class="headerlink" href="#apache_beam.ml.transforms.tft.BagOfWords.apply_transform" title="Permalink to this definition">¶</a></dt> |
| <dd></dd></dl> |
| |
| </dd></dl> |
| |
| </div> |
| |
| |
| </div> |
| |
| </div> |
| <footer> |
| |
| <div class="rst-footer-buttons" role="navigation" aria-label="footer navigation"> |
| |
| <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"></span></a> |
| |
| |
| <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"></span> Previous</a> |
| |
| </div> |
| |
| |
| <hr/> |
| |
| <div role="contentinfo"> |
| <p> |
| © Copyright |
| |
| </p> |
| </div> |
| Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/rtfd/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>. |
| |
| </footer> |
| |
| </div> |
| </div> |
| |
| </section> |
| |
| </div> |
| |
| |
| |
| <script type="text/javascript"> |
| jQuery(function () { |
| SphinxRtdTheme.Navigation.enable(true); |
| }); |
| </script> |
| |
| |
| |
| |
| |
| |
| </body> |
| </html> |