GitHub/ReAgent
1
0
Fork 0
mirror of https://github.com/facebookresearch/ReAgent.git synced 2026-06-16 12:44:41 +00:00
Code Issues Packages Projects Releases Wiki Activity
Files
gh-pages
ReAgent/api/reagent.preprocessing.html
T
Zhengxing Chen f2d2a25aff Update docs 11/20/2021
2021-11-20 20:47:01 -08:00

967 lines
135 KiB
HTML
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
<!DOCTYPE html>
<html class="writer-html5" lang="en" >
<head>
<meta charset="utf-8" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" />
<meta name="viewport" content="width=device-width, initial-scale=1.0" />
<title>reagent.preprocessing package &mdash; ReAgent 1.0 documentation</title>
<link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
<link rel="stylesheet" href="../_static/css/theme.css" type="text/css" />
<!--[if lt IE 9]>
<script src="../_static/js/html5shiv.min.js"></script>
<![endif]-->
<script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script>
<script src="../_static/jquery.js"></script>
<script src="../_static/underscore.js"></script>
<script src="../_static/doctools.js"></script>
<script src="../_static/js/theme.js"></script>
<link rel="index" title="Index" href="../genindex.html" />
<link rel="search" title="Search" href="../search.html" />
<link rel="next" title="reagent.training package" href="reagent.training.html" />
<link rel="prev" title="reagent.prediction.synthetic_reward package" href="reagent.prediction.synthetic_reward.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"> ReAgent
</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" />
<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">
<p class="caption" role="heading"><span class="caption-text">Getting Started</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../installation.html">Installation</a></li>
<li class="toctree-l1"><a class="reference internal" href="../usage.html">Usage</a></li>
<li class="toctree-l1"><a class="reference internal" href="../rasp_tutorial.html">RASP (Not Actively Maintained)</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Advanced Topics</span></p>
<ul>
<li class="toctree-l1"><a class="reference internal" href="../continuous_integration.html">Continuous Integration</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Package Reference</span></p>
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="reagent.core.html">Core</a></li>
<li class="toctree-l1"><a class="reference internal" href="reagent.data.html">Data</a></li>
<li class="toctree-l1"><a class="reference internal" href="reagent.gym.html">Gym</a></li>
<li class="toctree-l1"><a class="reference internal" href="reagent.evaluation.html">Evaluation</a></li>
<li class="toctree-l1"><a class="reference internal" href="reagent.lite.html">Lite</a></li>
<li class="toctree-l1"><a class="reference internal" href="reagent.mab.html">MAB</a></li>
<li class="toctree-l1"><a class="reference internal" href="reagent.model_managers.html">Model Managers</a></li>
<li class="toctree-l1"><a class="reference internal" href="reagent.model_utils.html">Model Utils</a></li>
<li class="toctree-l1"><a class="reference internal" href="reagent.net_builder.html">Net Builders</a></li>
<li class="toctree-l1"><a class="reference internal" href="reagent.optimizer.html">Optimizers</a></li>
<li class="toctree-l1"><a class="reference internal" href="reagent.models.html">Models</a></li>
<li class="toctree-l1"><a class="reference internal" href="reagent.prediction.html">Prediction</a></li>
<li class="toctree-l1 current"><a class="current reference internal" href="#">Preprocessing</a><ul>
<li class="toctree-l2"><a class="reference internal" href="#submodules">Submodules</a></li>
<li class="toctree-l2"><a class="reference internal" href="#module-reagent.preprocessing.batch_preprocessor">reagent.preprocessing.batch_preprocessor module</a></li>
<li class="toctree-l2"><a class="reference internal" href="#module-reagent.preprocessing.identify_types">reagent.preprocessing.identify_types module</a></li>
<li class="toctree-l2"><a class="reference internal" href="#module-reagent.preprocessing.normalization">reagent.preprocessing.normalization module</a></li>
<li class="toctree-l2"><a class="reference internal" href="#module-reagent.preprocessing.postprocessor">reagent.preprocessing.postprocessor module</a></li>
<li class="toctree-l2"><a class="reference internal" href="#module-reagent.preprocessing.preprocessor">reagent.preprocessing.preprocessor module</a></li>
<li class="toctree-l2"><a class="reference internal" href="#module-reagent.preprocessing.sparse_preprocessor">reagent.preprocessing.sparse_preprocessor module</a></li>
<li class="toctree-l2"><a class="reference internal" href="#module-reagent.preprocessing.sparse_to_dense">reagent.preprocessing.sparse_to_dense module</a></li>
<li class="toctree-l2"><a class="reference internal" href="#module-reagent.preprocessing.transforms">reagent.preprocessing.transforms module</a></li>
<li class="toctree-l2"><a class="reference internal" href="#module-reagent.preprocessing.types">reagent.preprocessing.types module</a></li>
<li class="toctree-l2"><a class="reference internal" href="#module-reagent.preprocessing">Module contents</a></li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="reagent.training.html">Training</a></li>
<li class="toctree-l1"><a class="reference internal" href="reagent.workflow.html">Workflow</a></li>
<li class="toctree-l1"><a class="reference internal" href="modules.html">All Modules</a></li>
</ul>
<p class="caption" role="heading"><span class="caption-text">Others</span></p>
<ul>
<li class="toctree-l1"><a class="reference external" href="https://github.com/facebookresearch/ReAgent">Github</a></li>
<li class="toctree-l1"><a class="reference internal" href="../license.html">License</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">ReAgent</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"></a> &raquo;</li>
<li>reagent.preprocessing package</li>
<li class="wy-breadcrumbs-aside">
<a href="../_sources/api/reagent.preprocessing.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="reagent-preprocessing-package">
<h1>reagent.preprocessing package<a class="headerlink" href="#reagent-preprocessing-package" title="Permalink to this headline"></a></h1>
<section id="submodules">
<h2>Submodules<a class="headerlink" href="#submodules" title="Permalink to this headline"></a></h2>
</section>
<section id="module-reagent.preprocessing.batch_preprocessor">
<span id="reagent-preprocessing-batch-preprocessor-module"></span><h2>reagent.preprocessing.batch_preprocessor module<a class="headerlink" href="#module-reagent.preprocessing.batch_preprocessor" title="Permalink to this headline"></a></h2>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.batch_preprocessor.BatchPreprocessor">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.batch_preprocessor.</span></span><span class="sig-name descname"><span class="pre">BatchPreprocessor</span></span><a class="headerlink" href="#reagent.preprocessing.batch_preprocessor.BatchPreprocessor" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.modules.module.Module</span></code></p>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.batch_preprocessor.BatchPreprocessor.training">
<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#reagent.preprocessing.batch_preprocessor.BatchPreprocessor.training" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.batch_preprocessor.DiscreteDqnBatchPreprocessor">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.batch_preprocessor.</span></span><span class="sig-name descname"><span class="pre">DiscreteDqnBatchPreprocessor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">num_actions</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">state_preprocessor</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#reagent.preprocessing.preprocessor.Preprocessor" title="reagent.preprocessing.preprocessor.Preprocessor"><span class="pre">reagent.preprocessing.preprocessor.Preprocessor</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_gpu</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</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">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.batch_preprocessor.DiscreteDqnBatchPreprocessor" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <a class="reference internal" href="#reagent.preprocessing.batch_preprocessor.BatchPreprocessor" title="reagent.preprocessing.batch_preprocessor.BatchPreprocessor"><code class="xref py py-class docutils literal notranslate"><span class="pre">reagent.preprocessing.batch_preprocessor.BatchPreprocessor</span></code></a></p>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.batch_preprocessor.DiscreteDqnBatchPreprocessor.forward">
<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="reagent.core.html#reagent.core.types.DiscreteDqnInput" title="reagent.core.types.DiscreteDqnInput"><span class="pre">reagent.core.types.DiscreteDqnInput</span></a></span></span><a class="headerlink" href="#reagent.preprocessing.batch_preprocessor.DiscreteDqnBatchPreprocessor.forward" title="Permalink to this definition"></a></dt>
<dd><p>Defines the computation performed at every call.</p>
<p>Should be overridden by all subclasses.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Although the recipe for forward pass needs to be defined within
this function, one should call the <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code> instance afterwards
instead of this since the former takes care of running the
registered hooks while the latter silently ignores them.</p>
</div>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.batch_preprocessor.DiscreteDqnBatchPreprocessor.training">
<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#reagent.preprocessing.batch_preprocessor.DiscreteDqnBatchPreprocessor.training" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.batch_preprocessor.ParametricDqnBatchPreprocessor">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.batch_preprocessor.</span></span><span class="sig-name descname"><span class="pre">ParametricDqnBatchPreprocessor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_preprocessor</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#reagent.preprocessing.preprocessor.Preprocessor" title="reagent.preprocessing.preprocessor.Preprocessor"><span class="pre">reagent.preprocessing.preprocessor.Preprocessor</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">action_preprocessor</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#reagent.preprocessing.preprocessor.Preprocessor" title="reagent.preprocessing.preprocessor.Preprocessor"><span class="pre">reagent.preprocessing.preprocessor.Preprocessor</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_gpu</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.batch_preprocessor.ParametricDqnBatchPreprocessor" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <a class="reference internal" href="#reagent.preprocessing.batch_preprocessor.BatchPreprocessor" title="reagent.preprocessing.batch_preprocessor.BatchPreprocessor"><code class="xref py py-class docutils literal notranslate"><span class="pre">reagent.preprocessing.batch_preprocessor.BatchPreprocessor</span></code></a></p>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.batch_preprocessor.ParametricDqnBatchPreprocessor.forward">
<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="reagent.core.html#reagent.core.types.ParametricDqnInput" title="reagent.core.types.ParametricDqnInput"><span class="pre">reagent.core.types.ParametricDqnInput</span></a></span></span><a class="headerlink" href="#reagent.preprocessing.batch_preprocessor.ParametricDqnBatchPreprocessor.forward" title="Permalink to this definition"></a></dt>
<dd><p>Defines the computation performed at every call.</p>
<p>Should be overridden by all subclasses.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Although the recipe for forward pass needs to be defined within
this function, one should call the <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code> instance afterwards
instead of this since the former takes care of running the
registered hooks while the latter silently ignores them.</p>
</div>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.batch_preprocessor.ParametricDqnBatchPreprocessor.training">
<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#reagent.preprocessing.batch_preprocessor.ParametricDqnBatchPreprocessor.training" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.batch_preprocessor.PolicyNetworkBatchPreprocessor">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.batch_preprocessor.</span></span><span class="sig-name descname"><span class="pre">PolicyNetworkBatchPreprocessor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">state_preprocessor</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#reagent.preprocessing.preprocessor.Preprocessor" title="reagent.preprocessing.preprocessor.Preprocessor"><span class="pre">reagent.preprocessing.preprocessor.Preprocessor</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">action_preprocessor</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="#reagent.preprocessing.preprocessor.Preprocessor" title="reagent.preprocessing.preprocessor.Preprocessor"><span class="pre">reagent.preprocessing.preprocessor.Preprocessor</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_gpu</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</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">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.batch_preprocessor.PolicyNetworkBatchPreprocessor" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <a class="reference internal" href="#reagent.preprocessing.batch_preprocessor.BatchPreprocessor" title="reagent.preprocessing.batch_preprocessor.BatchPreprocessor"><code class="xref py py-class docutils literal notranslate"><span class="pre">reagent.preprocessing.batch_preprocessor.BatchPreprocessor</span></code></a></p>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.batch_preprocessor.PolicyNetworkBatchPreprocessor.forward">
<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="reagent.core.html#reagent.core.types.PolicyNetworkInput" title="reagent.core.types.PolicyNetworkInput"><span class="pre">reagent.core.types.PolicyNetworkInput</span></a></span></span><a class="headerlink" href="#reagent.preprocessing.batch_preprocessor.PolicyNetworkBatchPreprocessor.forward" title="Permalink to this definition"></a></dt>
<dd><p>Defines the computation performed at every call.</p>
<p>Should be overridden by all subclasses.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Although the recipe for forward pass needs to be defined within
this function, one should call the <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code> instance afterwards
instead of this since the former takes care of running the
registered hooks while the latter silently ignores them.</p>
</div>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.batch_preprocessor.PolicyNetworkBatchPreprocessor.training">
<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#reagent.preprocessing.batch_preprocessor.PolicyNetworkBatchPreprocessor.training" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="reagent.preprocessing.batch_preprocessor.batch_to_device">
<span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.batch_preprocessor.</span></span><span class="sig-name descname"><span class="pre">batch_to_device</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">batch</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.device</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.batch_preprocessor.batch_to_device" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</section>
<section id="module-reagent.preprocessing.identify_types">
<span id="reagent-preprocessing-identify-types-module"></span><h2>reagent.preprocessing.identify_types module<a class="headerlink" href="#module-reagent.preprocessing.identify_types" title="Permalink to this headline"></a></h2>
<dl class="py function">
<dt class="sig sig-object py" id="reagent.preprocessing.identify_types.identify_type">
<span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.identify_types.</span></span><span class="sig-name descname"><span class="pre">identify_type</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">values</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">enum_threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.identify_types.identify_type" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</section>
<section id="module-reagent.preprocessing.normalization">
<span id="reagent-preprocessing-normalization-module"></span><h2>reagent.preprocessing.normalization module<a class="headerlink" href="#module-reagent.preprocessing.normalization" title="Permalink to this headline"></a></h2>
<dl class="py function">
<dt class="sig sig-object py" id="reagent.preprocessing.normalization.construct_action_scale_tensor">
<span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.normalization.</span></span><span class="sig-name descname"><span class="pre">construct_action_scale_tensor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">action_norm_params</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">action_scale_overrides</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.normalization.construct_action_scale_tensor" title="Permalink to this definition"></a></dt>
<dd><p>Construct tensors that will rescale each action value on each dimension i
from [min_serving_value[i], max_serving_value[i]] to [-1, 1] for training.</p>
</dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="reagent.preprocessing.normalization.deserialize">
<span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.normalization.</span></span><span class="sig-name descname"><span class="pre">deserialize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters_json</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="reagent.core.html#reagent.core.parameters.NormalizationParameters" title="reagent.core.parameters.NormalizationParameters"><span class="pre">reagent.core.parameters.NormalizationParameters</span></a><span class="p"><span class="pre">]</span></span></span></span><a class="headerlink" href="#reagent.preprocessing.normalization.deserialize" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="reagent.preprocessing.normalization.get_feature_config">
<span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.normalization.</span></span><span class="sig-name descname"><span class="pre">get_feature_config</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">float_features</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">Tuple</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">str</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><a class="reference internal" href="reagent.core.html#reagent.core.types.ModelFeatureConfig" title="reagent.core.types.ModelFeatureConfig"><span class="pre">reagent.core.types.ModelFeatureConfig</span></a></span></span><a class="headerlink" href="#reagent.preprocessing.normalization.get_feature_config" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="reagent.preprocessing.normalization.get_feature_norm_metadata">
<span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.normalization.</span></span><span class="sig-name descname"><span class="pre">get_feature_norm_metadata</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">feature_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">feature_value_list</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">norm_params</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.normalization.get_feature_norm_metadata" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="reagent.preprocessing.normalization.get_feature_start_indices">
<span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.normalization.</span></span><span class="sig-name descname"><span class="pre">get_feature_start_indices</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sorted_features</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalization_parameters</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="reagent.core.html#reagent.core.parameters.NormalizationParameters" title="reagent.core.parameters.NormalizationParameters"><span class="pre">reagent.core.parameters.NormalizationParameters</span></a><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.normalization.get_feature_start_indices" title="Permalink to this definition"></a></dt>
<dd><p>Returns the starting index for each feature in the output feature vector</p>
</dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="reagent.preprocessing.normalization.get_num_output_features">
<span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.normalization.</span></span><span class="sig-name descname"><span class="pre">get_num_output_features</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalization_parameters</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="reagent.core.html#reagent.core.parameters.NormalizationParameters" title="reagent.core.parameters.NormalizationParameters"><span class="pre">reagent.core.parameters.NormalizationParameters</span></a><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">int</span></span></span><a class="headerlink" href="#reagent.preprocessing.normalization.get_num_output_features" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="reagent.preprocessing.normalization.identify_parameter">
<span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.normalization.</span></span><span class="sig-name descname"><span class="pre">identify_parameter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">feature_name</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">values</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">max_unique_enum_values</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">10</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quantile_size</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">20</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">quantile_k2_threshold</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">1000.0</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_box_cox</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">skip_quantiles</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">False</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">feature_type</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.normalization.identify_parameter" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="reagent.preprocessing.normalization.no_op_feature">
<span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.normalization.</span></span><span class="sig-name descname"><span class="pre">no_op_feature</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.normalization.no_op_feature" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="reagent.preprocessing.normalization.serialize">
<span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.normalization.</span></span><span class="sig-name descname"><span class="pre">serialize</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">parameters</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.normalization.serialize" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="reagent.preprocessing.normalization.serialize_one">
<span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.normalization.</span></span><span class="sig-name descname"><span class="pre">serialize_one</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">feature_parameters</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.normalization.serialize_one" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="reagent.preprocessing.normalization.sort_features_by_normalization">
<span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.normalization.</span></span><span class="sig-name descname"><span class="pre">sort_features_by_normalization</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalization_parameters</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="reagent.core.html#reagent.core.parameters.NormalizationParameters" title="reagent.core.parameters.NormalizationParameters"><span class="pre">reagent.core.parameters.NormalizationParameters</span></a><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Tuple</span><span class="p"><span class="pre">[</span></span><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></span><a class="headerlink" href="#reagent.preprocessing.normalization.sort_features_by_normalization" title="Permalink to this definition"></a></dt>
<dd><p>Helper function to return a sorted list from a normalization map.
Also returns the starting index for each feature type</p>
</dd></dl>
</section>
<section id="module-reagent.preprocessing.postprocessor">
<span id="reagent-preprocessing-postprocessor-module"></span><h2>reagent.preprocessing.postprocessor module<a class="headerlink" href="#module-reagent.preprocessing.postprocessor" title="Permalink to this headline"></a></h2>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.postprocessor.Postprocessor">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.postprocessor.</span></span><span class="sig-name descname"><span class="pre">Postprocessor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalization_parameters</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="reagent.core.html#reagent.core.parameters.NormalizationParameters" title="reagent.core.parameters.NormalizationParameters"><span class="pre">reagent.core.parameters.NormalizationParameters</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_gpu</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.postprocessor.Postprocessor" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.modules.module.Module</span></code></p>
<p>Inverting action</p>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.postprocessor.Postprocessor.forward">
<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.Tensor</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">torch.Tensor</span></span></span><a class="headerlink" href="#reagent.preprocessing.postprocessor.Postprocessor.forward" title="Permalink to this definition"></a></dt>
<dd><p>Defines the computation performed at every call.</p>
<p>Should be overridden by all subclasses.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Although the recipe for forward pass needs to be defined within
this function, one should call the <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code> instance afterwards
instead of this since the former takes care of running the
registered hooks while the latter silently ignores them.</p>
</div>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.postprocessor.Postprocessor.input_prototype">
<span class="sig-name descname"><span class="pre">input_prototype</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Tuple</span><span class="p"><span class="pre">[</span></span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">]</span></span></span></span><a class="headerlink" href="#reagent.preprocessing.postprocessor.Postprocessor.input_prototype" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.postprocessor.Postprocessor.training">
<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#reagent.preprocessing.postprocessor.Postprocessor.training" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
</section>
<section id="module-reagent.preprocessing.preprocessor">
<span id="reagent-preprocessing-preprocessor-module"></span><h2>reagent.preprocessing.preprocessor module<a class="headerlink" href="#module-reagent.preprocessing.preprocessor" title="Permalink to this headline"></a></h2>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.preprocessor.Preprocessor">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.preprocessor.</span></span><span class="sig-name descname"><span class="pre">Preprocessor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">normalization_parameters</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="reagent.core.html#reagent.core.parameters.NormalizationParameters" title="reagent.core.parameters.NormalizationParameters"><span class="pre">reagent.core.parameters.NormalizationParameters</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">use_gpu</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">bool</span><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">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">torch.device</span><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">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.preprocessor.Preprocessor" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.modules.module.Module</span></code></p>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.preprocessor.Preprocessor.forward">
<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.Tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">input_presence_byte</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.Tensor</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">torch.Tensor</span></span></span><a class="headerlink" href="#reagent.preprocessing.preprocessor.Preprocessor.forward" title="Permalink to this definition"></a></dt>
<dd><p>Preprocess the input matrix
:param input tensor</p>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.preprocessor.Preprocessor.input_prototype">
<span class="sig-name descname"><span class="pre">input_prototype</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Tuple</span><span class="p"><span class="pre">[</span></span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">]</span></span></span></span><a class="headerlink" href="#reagent.preprocessing.preprocessor.Preprocessor.input_prototype" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.preprocessor.Preprocessor.training">
<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#reagent.preprocessing.preprocessor.Preprocessor.training" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
</section>
<section id="module-reagent.preprocessing.sparse_preprocessor">
<span id="reagent-preprocessing-sparse-preprocessor-module"></span><h2>reagent.preprocessing.sparse_preprocessor module<a class="headerlink" href="#module-reagent.preprocessing.sparse_preprocessor" title="Permalink to this headline"></a></h2>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.ExplicitMapIDList">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.sparse_preprocessor.</span></span><span class="sig-name descname"><span class="pre">ExplicitMapIDList</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">id2index</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">int</span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.ExplicitMapIDList" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <a class="reference internal" href="#reagent.preprocessing.sparse_preprocessor.MapIDList" title="reagent.preprocessing.sparse_preprocessor.MapIDList"><code class="xref py py-class docutils literal notranslate"><span class="pre">reagent.preprocessing.sparse_preprocessor.MapIDList</span></code></a></p>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.ExplicitMapIDList.forward">
<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">raw_values</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.Tensor</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">torch.Tensor</span></span></span><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.ExplicitMapIDList.forward" title="Permalink to this definition"></a></dt>
<dd><p>Defines the computation performed at every call.</p>
<p>Should be overridden by all subclasses.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Although the recipe for forward pass needs to be defined within
this function, one should call the <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code> instance afterwards
instead of this since the former takes care of running the
registered hooks while the latter silently ignores them.</p>
</div>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.ExplicitMapIDList.training">
<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.ExplicitMapIDList.training" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.ExplicitMapIDScoreList">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.sparse_preprocessor.</span></span><span class="sig-name descname"><span class="pre">ExplicitMapIDScoreList</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">id2index</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">int</span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.ExplicitMapIDScoreList" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <a class="reference internal" href="#reagent.preprocessing.sparse_preprocessor.MapIDScoreList" title="reagent.preprocessing.sparse_preprocessor.MapIDScoreList"><code class="xref py py-class docutils literal notranslate"><span class="pre">reagent.preprocessing.sparse_preprocessor.MapIDScoreList</span></code></a></p>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.ExplicitMapIDScoreList.forward">
<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">raw_keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.Tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">raw_values</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.Tensor</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Tuple</span><span class="p"><span class="pre">[</span></span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">]</span></span></span></span><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.ExplicitMapIDScoreList.forward" title="Permalink to this definition"></a></dt>
<dd><p>Defines the computation performed at every call.</p>
<p>Should be overridden by all subclasses.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Although the recipe for forward pass needs to be defined within
this function, one should call the <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code> instance afterwards
instead of this since the former takes care of running the
registered hooks while the latter silently ignores them.</p>
</div>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.ExplicitMapIDScoreList.training">
<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.ExplicitMapIDScoreList.training" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.MapIDList">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.sparse_preprocessor.</span></span><span class="sig-name descname"><span class="pre">MapIDList</span></span><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.MapIDList" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.modules.module.Module</span></code></p>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.MapIDList.forward">
<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">raw_values</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.Tensor</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">torch.Tensor</span></span></span><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.MapIDList.forward" title="Permalink to this definition"></a></dt>
<dd><p>Defines the computation performed at every call.</p>
<p>Should be overridden by all subclasses.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Although the recipe for forward pass needs to be defined within
this function, one should call the <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code> instance afterwards
instead of this since the former takes care of running the
registered hooks while the latter silently ignores them.</p>
</div>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.MapIDList.training">
<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.MapIDList.training" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.MapIDScoreList">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.sparse_preprocessor.</span></span><span class="sig-name descname"><span class="pre">MapIDScoreList</span></span><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.MapIDScoreList" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.modules.module.Module</span></code></p>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.MapIDScoreList.forward">
<em class="property"><span class="pre">abstract</span><span class="w"> </span></em><span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">raw_keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.Tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">raw_values</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.Tensor</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Tuple</span><span class="p"><span class="pre">[</span></span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">]</span></span></span></span><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.MapIDScoreList.forward" title="Permalink to this definition"></a></dt>
<dd><p>Defines the computation performed at every call.</p>
<p>Should be overridden by all subclasses.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Although the recipe for forward pass needs to be defined within
this function, one should call the <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code> instance afterwards
instead of this since the former takes care of running the
registered hooks while the latter silently ignores them.</p>
</div>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.MapIDScoreList.training">
<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.MapIDScoreList.training" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.ModuloMapIDList">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.sparse_preprocessor.</span></span><span class="sig-name descname"><span class="pre">ModuloMapIDList</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modulo</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.ModuloMapIDList" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <a class="reference internal" href="#reagent.preprocessing.sparse_preprocessor.MapIDList" title="reagent.preprocessing.sparse_preprocessor.MapIDList"><code class="xref py py-class docutils literal notranslate"><span class="pre">reagent.preprocessing.sparse_preprocessor.MapIDList</span></code></a></p>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.ModuloMapIDList.forward">
<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">raw_values</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.Tensor</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">torch.Tensor</span></span></span><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.ModuloMapIDList.forward" title="Permalink to this definition"></a></dt>
<dd><p>Defines the computation performed at every call.</p>
<p>Should be overridden by all subclasses.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Although the recipe for forward pass needs to be defined within
this function, one should call the <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code> instance afterwards
instead of this since the former takes care of running the
registered hooks while the latter silently ignores them.</p>
</div>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.ModuloMapIDList.training">
<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.ModuloMapIDList.training" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.ModuloMapIDScoreList">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.sparse_preprocessor.</span></span><span class="sig-name descname"><span class="pre">ModuloMapIDScoreList</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">modulo</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.ModuloMapIDScoreList" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <a class="reference internal" href="#reagent.preprocessing.sparse_preprocessor.MapIDScoreList" title="reagent.preprocessing.sparse_preprocessor.MapIDScoreList"><code class="xref py py-class docutils literal notranslate"><span class="pre">reagent.preprocessing.sparse_preprocessor.MapIDScoreList</span></code></a></p>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.ModuloMapIDScoreList.forward">
<span class="sig-name descname"><span class="pre">forward</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">raw_keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.Tensor</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">raw_values</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.Tensor</span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Tuple</span><span class="p"><span class="pre">[</span></span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">]</span></span></span></span><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.ModuloMapIDScoreList.forward" title="Permalink to this definition"></a></dt>
<dd><p>Defines the computation performed at every call.</p>
<p>Should be overridden by all subclasses.</p>
<div class="admonition note">
<p class="admonition-title">Note</p>
<p>Although the recipe for forward pass needs to be defined within
this function, one should call the <code class="xref py py-class docutils literal notranslate"><span class="pre">Module</span></code> instance afterwards
instead of this since the former takes care of running the
registered hooks while the latter silently ignores them.</p>
</div>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.ModuloMapIDScoreList.training">
<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.ModuloMapIDScoreList.training" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.SparsePreprocessor">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.sparse_preprocessor.</span></span><span class="sig-name descname"><span class="pre">SparsePreprocessor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">id2name</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">name2id</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">int</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">id_list_mappers</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#reagent.preprocessing.sparse_preprocessor.MapIDList" title="reagent.preprocessing.sparse_preprocessor.MapIDList"><span class="pre">reagent.preprocessing.sparse_preprocessor.MapIDList</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">id_score_list_mappers</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><a class="reference internal" href="#reagent.preprocessing.sparse_preprocessor.MapIDScoreList" title="reagent.preprocessing.sparse_preprocessor.MapIDScoreList"><span class="pre">reagent.preprocessing.sparse_preprocessor.MapIDScoreList</span></a><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.device</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.SparsePreprocessor" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">torch.nn.modules.module.Module</span></code></p>
<p>Performs preprocessing for sparse features (i.e. id_list, id_score_list)</p>
<p>Functionality includes:
(1) changes keys from feature_id to feature_name, for better debuggability
(2) maps sparse ids to embedding table indices based on id_mapping
(3) filters out ids which aren’t in the id2name</p>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.SparsePreprocessor.preprocess_id_list">
<span class="sig-name descname"><span class="pre">preprocess_id_list</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">id_list</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Tuple</span><span class="p"><span class="pre">[</span></span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Tuple</span><span class="p"><span class="pre">[</span></span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></span><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.SparsePreprocessor.preprocess_id_list" title="Permalink to this definition"></a></dt>
<dd><p>Input: rlt.ServingIdListFeature
Output: rlt.IdListFeature</p>
</dd></dl>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.SparsePreprocessor.preprocess_id_score_list">
<span class="sig-name descname"><span class="pre">preprocess_id_score_list</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">id_score_list</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Tuple</span><span class="p"><span class="pre">[</span></span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">Tuple</span><span class="p"><span class="pre">[</span></span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></span><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.SparsePreprocessor.preprocess_id_score_list" title="Permalink to this definition"></a></dt>
<dd><p>Input: rlt.ServingIdScoreListFeature
Output: rlt.IdScoreListFeature</p>
</dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.SparsePreprocessor.training">
<span class="sig-name descname"><span class="pre">training</span></span><em class="property"><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="pre">bool</span></em><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.SparsePreprocessor.training" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
<dl class="py function">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_preprocessor.make_sparse_preprocessor">
<span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.sparse_preprocessor.</span></span><span class="sig-name descname"><span class="pre">make_sparse_preprocessor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">feature_config</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="reagent.core.html#reagent.core.types.ModelFeatureConfig" title="reagent.core.types.ModelFeatureConfig"><span class="pre">reagent.core.types.ModelFeatureConfig</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.device</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.sparse_preprocessor.make_sparse_preprocessor" title="Permalink to this definition"></a></dt>
<dd><p>Helper to initialize, for scripting SparsePreprocessor</p>
</dd></dl>
</section>
<section id="module-reagent.preprocessing.sparse_to_dense">
<span id="reagent-preprocessing-sparse-to-dense-module"></span><h2>reagent.preprocessing.sparse_to_dense module<a class="headerlink" href="#module-reagent.preprocessing.sparse_to_dense" title="Permalink to this headline"></a></h2>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_to_dense.PythonSparseToDenseProcessor">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.sparse_to_dense.</span></span><span class="sig-name descname"><span class="pre">PythonSparseToDenseProcessor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sorted_features</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">set_missing_value_to_zero</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</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">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.sparse_to_dense.PythonSparseToDenseProcessor" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <a class="reference internal" href="#reagent.preprocessing.sparse_to_dense.SparseToDenseProcessor" title="reagent.preprocessing.sparse_to_dense.SparseToDenseProcessor"><code class="xref py py-class docutils literal notranslate"><span class="pre">reagent.preprocessing.sparse_to_dense.SparseToDenseProcessor</span></code></a></p>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_to_dense.PythonSparseToDenseProcessor.process">
<span class="sig-name descname"><span class="pre">process</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sparse_data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">float</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Tuple</span><span class="p"><span class="pre">[</span></span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">]</span></span></span></span><a class="headerlink" href="#reagent.preprocessing.sparse_to_dense.PythonSparseToDenseProcessor.process" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_to_dense.SparseToDenseProcessor">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.sparse_to_dense.</span></span><span class="sig-name descname"><span class="pre">SparseToDenseProcessor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sorted_features</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">set_missing_value_to_zero</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</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">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.sparse_to_dense.SparseToDenseProcessor" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_to_dense.StringKeySparseToDenseProcessor">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.sparse_to_dense.</span></span><span class="sig-name descname"><span class="pre">StringKeySparseToDenseProcessor</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sorted_features</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">set_missing_value_to_zero</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</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">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.sparse_to_dense.StringKeySparseToDenseProcessor" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <a class="reference internal" href="#reagent.preprocessing.sparse_to_dense.SparseToDenseProcessor" title="reagent.preprocessing.sparse_to_dense.SparseToDenseProcessor"><code class="xref py py-class docutils literal notranslate"><span class="pre">reagent.preprocessing.sparse_to_dense.SparseToDenseProcessor</span></code></a></p>
<p>We just have this in case the input data is keyed by string</p>
<dl class="py method">
<dt class="sig sig-object py" id="reagent.preprocessing.sparse_to_dense.StringKeySparseToDenseProcessor.process">
<span class="sig-name descname"><span class="pre">process</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">sparse_data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">Dict</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">float</span><span class="p"><span class="pre">]</span></span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span> <span class="sig-return"><span class="sig-return-icon">&#x2192;</span> <span class="sig-return-typehint"><span class="pre">Tuple</span><span class="p"><span class="pre">[</span></span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">,</span></span><span class="w"> </span><span class="pre">torch.Tensor</span><span class="p"><span class="pre">]</span></span></span></span><a class="headerlink" href="#reagent.preprocessing.sparse_to_dense.StringKeySparseToDenseProcessor.process" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
</section>
<section id="module-reagent.preprocessing.transforms">
<span id="reagent-preprocessing-transforms-module"></span><h2>reagent.preprocessing.transforms module<a class="headerlink" href="#module-reagent.preprocessing.transforms" title="Permalink to this headline"></a></h2>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.AppendConstant">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">AppendConstant</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</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">-</span> <span class="pre">1</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">const</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">float</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">1.0</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.AppendConstant" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>Append a column of constant value at the beginning of the specified dimension
Can be used to add a column of “1” to the Linear Regression input data to capture intercept/bias</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.Cat">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">Cat</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">input_keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_key</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">broadcast</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</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">True</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.Cat" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>This transform concatenates the tensors along a specified dim</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.ColumnVector">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">ColumnVector</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.ColumnVector" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>Ensure that the keys are column vectors</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.Compose">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">Compose</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">transforms</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.Compose" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>Applies an iterable collection of transform functions</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.DenseNormalization">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">DenseNormalization</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalization_data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="reagent.core.html#reagent.core.parameters.NormalizationData" title="reagent.core.parameters.NormalizationData"><span class="pre">reagent.core.parameters.NormalizationData</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">torch.device</span><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">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.DenseNormalization" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>Normalize the <cite>keys</cite> using <cite>normalization_data</cite>.
The keys are expected to be <cite>Tuple[torch.Tensor, torch.Tensor]</cite>,
where the first element is the value and the second element is the
presence mask.
This transform replaces the keys in the input data.</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.Filter">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">Filter</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="o"><span class="pre">*</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">keep_keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span><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">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">remove_keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span><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">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.Filter" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>Remove some keys from the dict.
Can specify keep_keys (they will be kept) or remove_keys (they will be removed)</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.FixedLengthSequenceDenseNormalization">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">FixedLengthSequenceDenseNormalization</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sequence_id</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">normalization_data</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="reagent.core.html#reagent.core.parameters.NormalizationData" title="reagent.core.parameters.NormalizationData"><span class="pre">reagent.core.parameters.NormalizationData</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">expected_length</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><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">None</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">torch.device</span><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">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.FixedLengthSequenceDenseNormalization" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>Combines the FixedLengthSequences, DenseNormalization, and SlateView transforms</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.FixedLengthSequences">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">FixedLengthSequences</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">sequence_id</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">expected_length</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><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">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">to_keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Optional</span><span class="p"><span class="pre">[</span></span><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span><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">None</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.FixedLengthSequences" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<dl>
<dt>Does two things:</dt><dd><ol class="arabic simple">
<li><p>makes sure each sequence in the list of keys has the expected fixed length</p></li>
</ol>
<p>2. if to_keys is provided, copies the relevant sequence_id to the new key,
otherwise overwrites the old key</p>
</dd>
</dl>
<p>Expects each data[key] to be <cite>Dict[Int, Tuple[Tensor, T]]</cite>. Where:
- key is the feature id
- sequence_id is the key of the dict data[key]
- The first element of the tuple is the offset for each example, which is expected to be in fixed interval.
- The second element is the data at each step in the sequence</p>
<p>This is mainly for FB internal use,
see fbcode/caffe2/caffe2/fb/proto/io_metadata.thrift
for the data format extracted from SequenceFeatureMetadata</p>
<p>NOTE: this is not product between two lists (keys and to_keys);
it’s setting keys[sequence_id] to to_keys in a parallel way</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.GetEye">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">GetEye</span></span><span class="sig-paren">(</span><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"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.GetEye" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>Place a diagonal tensor into the data dictionary</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.Lambda">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">Lambda</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">fn</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">Callable</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.Lambda" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>Applies an arbitrary callable transform</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.MapIDListFeatures">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">MapIDListFeatures</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">id_list_keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">id_score_list_keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">feature_config</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><a class="reference internal" href="reagent.core.html#reagent.core.types.ModelFeatureConfig" title="reagent.core.types.ModelFeatureConfig"><span class="pre">reagent.core.types.ModelFeatureConfig</span></a></span></em>, <em class="sig-param"><span class="n"><span class="pre">device</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">torch.device</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.MapIDListFeatures" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>Applies a SparsePreprocessor (see sparse_preprocessor.SparsePreprocessor)</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.MaskByPresence">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">MaskByPresence</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.MaskByPresence" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>Expect data to be (value, presence) and return value * presence.
This zeros out values that aren’t present.</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.OneHotActions">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">OneHotActions</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_actions</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.OneHotActions" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>Keys should be in the set {0,1,2,…,num_actions}, where
a value equal to num_actions denotes that it’s not valid.</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.OuterProduct">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">OuterProduct</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">key1</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">key2</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">output_key</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">drop_inputs</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">bool</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">False</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.OuterProduct" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>This transform creates a tensor with an outer product of elements of 2 tensors.
The outer product is stored under the new key.
The 2 input tensors might be dropped, depending on input arguments</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.Rename">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">Rename</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">old_names</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">new_names</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.Rename" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>Change key names</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.SelectValuePresenceColumns">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">SelectValuePresenceColumns</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">source</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dest</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">str</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">indices</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">int</span><span class="p"><span class="pre">]</span></span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.SelectValuePresenceColumns" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>Select columns from value-presence source key</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.SlateView">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">SlateView</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">slate_size</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.SlateView" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>Assuming that the keys are flatten fixed-length sequences with length of
<cite>slate_size</cite>, unflatten it by inserting <cite>slate_size</cite> to the 1st dim.
I.e., turns the input from the shape of <cite>[B * slate_size, D]</cite> to
<cite>[B, slate_size, D]</cite>.</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.StackDenseFixedSizeArray">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">StackDenseFixedSizeArray</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">size</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dtype</span></span><span class="o"><span class="pre">=</span></span><span class="default_value"><span class="pre">torch.float32</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.StackDenseFixedSizeArray" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>If data is a tensor, ensures it has the correct shape. If data is a list of
(value, presence) discards the presence tensors and concatenates the values
to output a tensor of shape (batch_size, feature_dim).</p>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.UnsqueezeRepeat">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">UnsqueezeRepeat</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">keys</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">List</span><span class="p"><span class="pre">[</span></span><span class="pre">str</span><span class="p"><span class="pre">]</span></span></span></em>, <em class="sig-param"><span class="n"><span class="pre">dim</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">num_repeat</span></span><span class="p"><span class="pre">:</span></span><span class="w"> </span><span class="n"><span class="pre">int</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></em><span class="sig-paren">)</span><a class="headerlink" href="#reagent.preprocessing.transforms.UnsqueezeRepeat" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<dl class="simple">
<dt>This transform adds an extra dimension to the tensor and repeats</dt><dd><p>the tensor along that dimension</p>
</dd>
</dl>
</dd></dl>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.transforms.ValuePresence">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.transforms.</span></span><span class="sig-name descname"><span class="pre">ValuePresence</span></span><a class="headerlink" href="#reagent.preprocessing.transforms.ValuePresence" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<p>For every key <cite>x</cite>, looks for <cite>x_presence</cite>; if <cite>x_presence</cite> exists,
replace <cite>x</cite> with tuple of <cite>x</cite> and <cite>x_presence</cite>, delete <cite>x_presence</cite> key</p>
</dd></dl>
</section>
<section id="module-reagent.preprocessing.types">
<span id="reagent-preprocessing-types-module"></span><h2>reagent.preprocessing.types module<a class="headerlink" href="#module-reagent.preprocessing.types" title="Permalink to this headline"></a></h2>
<dl class="py class">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn">
<em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">reagent.preprocessing.types.</span></span><span class="sig-name descname"><span class="pre">InputColumn</span></span><a class="headerlink" href="#reagent.preprocessing.types.InputColumn" title="Permalink to this definition"></a></dt>
<dd><p>Bases: <code class="xref py py-class docutils literal notranslate"><span class="pre">object</span></code></p>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.ACTION">
<span class="sig-name descname"><span class="pre">ACTION</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'action'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.ACTION" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.ACTION_PROBABILITY">
<span class="sig-name descname"><span class="pre">ACTION_PROBABILITY</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'action_probability'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.ACTION_PROBABILITY" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.CANDIDATE_FEATURES">
<span class="sig-name descname"><span class="pre">CANDIDATE_FEATURES</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'candidate_features'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.CANDIDATE_FEATURES" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.EXTRAS">
<span class="sig-name descname"><span class="pre">EXTRAS</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'extras'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.EXTRAS" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.ITEM_MASK">
<span class="sig-name descname"><span class="pre">ITEM_MASK</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'item_mask'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.ITEM_MASK" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.ITEM_PROBABILITY">
<span class="sig-name descname"><span class="pre">ITEM_PROBABILITY</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'item_probability'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.ITEM_PROBABILITY" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.MDP_ID">
<span class="sig-name descname"><span class="pre">MDP_ID</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'mdp_id'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.MDP_ID" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.METRICS">
<span class="sig-name descname"><span class="pre">METRICS</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'metrics'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.METRICS" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.NEXT_ACTION">
<span class="sig-name descname"><span class="pre">NEXT_ACTION</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'next_action'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.NEXT_ACTION" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.NEXT_CANDIDATE_FEATURES">
<span class="sig-name descname"><span class="pre">NEXT_CANDIDATE_FEATURES</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'next_candidate_features'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.NEXT_CANDIDATE_FEATURES" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.NEXT_ITEM_MASK">
<span class="sig-name descname"><span class="pre">NEXT_ITEM_MASK</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'next_item_mask'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.NEXT_ITEM_MASK" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.NEXT_ITEM_PROBABILITY">
<span class="sig-name descname"><span class="pre">NEXT_ITEM_PROBABILITY</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'next_item_probability'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.NEXT_ITEM_PROBABILITY" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.NEXT_STATE_FEATURES">
<span class="sig-name descname"><span class="pre">NEXT_STATE_FEATURES</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'next_state_features'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.NEXT_STATE_FEATURES" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.NEXT_STATE_ID_LIST_FEATURES">
<span class="sig-name descname"><span class="pre">NEXT_STATE_ID_LIST_FEATURES</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'next_state_id_list_features'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.NEXT_STATE_ID_LIST_FEATURES" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.NEXT_STATE_ID_SCORE_LIST_FEATURES">
<span class="sig-name descname"><span class="pre">NEXT_STATE_ID_SCORE_LIST_FEATURES</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'next_state_id_score_list_features'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.NEXT_STATE_ID_SCORE_LIST_FEATURES" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.NEXT_STATE_SEQUENCE_FEATURES">
<span class="sig-name descname"><span class="pre">NEXT_STATE_SEQUENCE_FEATURES</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'next_state_sequence_features'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.NEXT_STATE_SEQUENCE_FEATURES" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.NOT_TERMINAL">
<span class="sig-name descname"><span class="pre">NOT_TERMINAL</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'not_terminal'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.NOT_TERMINAL" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.POSITION_REWARD">
<span class="sig-name descname"><span class="pre">POSITION_REWARD</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'position_reward'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.POSITION_REWARD" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.POSSIBLE_ACTIONS">
<span class="sig-name descname"><span class="pre">POSSIBLE_ACTIONS</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'possible_actions'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.POSSIBLE_ACTIONS" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.POSSIBLE_ACTIONS_MASK">
<span class="sig-name descname"><span class="pre">POSSIBLE_ACTIONS_MASK</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'possible_actions_mask'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.POSSIBLE_ACTIONS_MASK" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.POSSIBLE_NEXT_ACTIONS">
<span class="sig-name descname"><span class="pre">POSSIBLE_NEXT_ACTIONS</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'possible_next_actions'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.POSSIBLE_NEXT_ACTIONS" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.POSSIBLE_NEXT_ACTIONS_MASK">
<span class="sig-name descname"><span class="pre">POSSIBLE_NEXT_ACTIONS_MASK</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'possible_next_actions_mask'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.POSSIBLE_NEXT_ACTIONS_MASK" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.REWARD">
<span class="sig-name descname"><span class="pre">REWARD</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'reward'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.REWARD" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.REWARD_MASK">
<span class="sig-name descname"><span class="pre">REWARD_MASK</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'reward_mask'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.REWARD_MASK" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.SCORES">
<span class="sig-name descname"><span class="pre">SCORES</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'scores'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.SCORES" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.SEQUENCE_NUMBER">
<span class="sig-name descname"><span class="pre">SEQUENCE_NUMBER</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'sequence_number'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.SEQUENCE_NUMBER" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.SLATE_REWARD">
<span class="sig-name descname"><span class="pre">SLATE_REWARD</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'slate_reward'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.SLATE_REWARD" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.STATE_FEATURES">
<span class="sig-name descname"><span class="pre">STATE_FEATURES</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'state_features'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.STATE_FEATURES" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.STATE_ID_LIST_FEATURES">
<span class="sig-name descname"><span class="pre">STATE_ID_LIST_FEATURES</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'state_id_list_features'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.STATE_ID_LIST_FEATURES" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.STATE_ID_SCORE_LIST_FEATURES">
<span class="sig-name descname"><span class="pre">STATE_ID_SCORE_LIST_FEATURES</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'state_id_score_list_features'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.STATE_ID_SCORE_LIST_FEATURES" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.STATE_SEQUENCE_FEATURES">
<span class="sig-name descname"><span class="pre">STATE_SEQUENCE_FEATURES</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'state_sequence_features'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.STATE_SEQUENCE_FEATURES" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.STEP">
<span class="sig-name descname"><span class="pre">STEP</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'step'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.STEP" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.TIME_DIFF">
<span class="sig-name descname"><span class="pre">TIME_DIFF</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'time_diff'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.TIME_DIFF" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.TIME_SINCE_FIRST">
<span class="sig-name descname"><span class="pre">TIME_SINCE_FIRST</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'time_since_first'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.TIME_SINCE_FIRST" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.VALID_STEP">
<span class="sig-name descname"><span class="pre">VALID_STEP</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'valid_step'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.VALID_STEP" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
<dl class="py attribute">
<dt class="sig sig-object py" id="reagent.preprocessing.types.InputColumn.WEIGHT">
<span class="sig-name descname"><span class="pre">WEIGHT</span></span><em class="property"><span class="w"> </span><span class="p"><span class="pre">=</span></span><span class="w"> </span><span class="pre">'weight'</span></em><a class="headerlink" href="#reagent.preprocessing.types.InputColumn.WEIGHT" title="Permalink to this definition"></a></dt>
<dd></dd></dl>
</dd></dl>
</section>
<section id="module-reagent.preprocessing">
<span id="module-contents"></span><h2>Module contents<a class="headerlink" href="#module-reagent.preprocessing" title="Permalink to this headline"></a></h2>
</section>
</section>
</div>
</div>
<footer><div class="rst-footer-buttons" role="navigation" aria-label="Footer">
<a href="reagent.prediction.synthetic_reward.html" class="btn btn-neutral float-left" title="reagent.prediction.synthetic_reward package" accesskey="p" rel="prev"><span class="fa fa-arrow-circle-left" aria-hidden="true"></span> Previous</a>
<a href="reagent.training.html" class="btn btn-neutral float-right" title="reagent.training package" accesskey="n" rel="next">Next <span class="fa fa-arrow-circle-right" aria-hidden="true"></span></a>
</div>
<hr/>
<div role="contentinfo">
<p>&#169; Copyright 2022, Meta Platforms, Inc.</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>
Reference in New Issue View Git Blame Copy Permalink