<!DOCTYPE html>
<!--[if IE 8]><html class="no-js lt-ie9" lang="en" > <![endif]-->
<!--[if gt IE 8]><!--> <html class="no-js" lang="en" > <!--<![endif]-->
<head>
<meta charset="utf-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Dataset — PaddlePaddle documentation</title>
<link rel="stylesheet" href="../../../_static/css/theme.css" type="text/css" />
<link rel="index" title="Index"
href="../../../genindex.html"/>
<link rel="search" title="Search" href="../../../search.html"/>
<link rel="top" title="PaddlePaddle documentation" href="../../../index.html"/>
<link rel="up" title="Data Reader Interface and DataSets" href="../data.html"/>
<link rel="next" title="Training and Inference" href="../run_logic.html"/>
<link rel="prev" title="Image Interface" href="image.html"/>
<link rel="stylesheet" href="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/css/perfect-scrollbar.min.css" type="text/css" />
<link rel="stylesheet" href="../../../_static/css/override.css" type="text/css" />
<script>
var _hmt = _hmt || [];
(function() {
var hm = document.createElement("script");
hm.src = "//hm.baidu.com/hm.js?b9a314ab40d04d805655aab1deee08ba";
var s = document.getElementsByTagName("script")[0];
s.parentNode.insertBefore(hm, s);
})();
</script>
<script src="../../../_static/js/modernizr.min.js"></script>
</head>
<body class="wy-body-for-nav" role="document">
<header class="site-header">
<div class="site-logo">
<a href="/"><img src="../../../_static/images/PP_w.png"></a>
</div>
<div class="site-nav-links">
<div class="site-menu">
<a class="fork-on-github" href="https://github.com/PaddlePaddle/Paddle" target="_blank"><i class="fa fa-github"></i>Fork me on Github</a>
<div class="language-switcher dropdown">
<a type="button" data-toggle="dropdown">
<span>English</span>
<i class="fa fa-angle-up"></i>
<i class="fa fa-angle-down"></i>
</a>
<ul class="dropdown-menu">
<li><a href="/doc_cn">中文</a></li>
<li><a href="/doc">English</a></li>
</ul>
</div>
<ul class="site-page-links">
<li><a href="/">Home</a></li>
</ul>
</div>
<div class="doc-module">
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_en.html">GET STARTED</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../howto/index_en.html">HOW TO</a></li>
<li class="toctree-l1 current"><a class="reference internal" href="../../index_en.html">API</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../mobile/index_en.html">MOBILE</a></li>
</ul>
<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>
</header>
<div class="main-content-wrap">
<nav class="doc-menu-vertical" role="navigation">
<ul class="current">
<li class="toctree-l1"><a class="reference internal" href="../../../getstarted/index_en.html">GET STARTED</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../getstarted/build_and_install/index_en.html">Install and Build</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/pip_install_en.html">Install Using pip</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/docker_install_en.html">Run in Docker Containers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/dev/build_en.html">Build using Docker</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../getstarted/build_and_install/build_from_source_en.html">Build from Sources</a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../howto/index_en.html">HOW TO</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/cmd_parameter/index_en.html">Set Command-line Parameters</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cmd_parameter/use_case_en.html">Use Case</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cmd_parameter/arguments_en.html">Argument Outline</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cmd_parameter/detail_introduction_en.html">Detail Description</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/usage/cluster/cluster_train_en.html">Distributed Training</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cluster/fabric_en.html">fabric</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cluster/openmpi_en.html">openmpi</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cluster/k8s_en.html">kubernetes</a></li>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/usage/cluster/k8s_aws_en.html">kubernetes on AWS</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/new_layer_en.html">Write New Layers</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/contribute_to_paddle_en.html">Contribute Code</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/dev/write_docs_en.html">Contribute Documentation</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/deep_model/rnn/index_en.html">RNN Models</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../../../howto/deep_model/rnn/rnn_config_en.html">RNN Configuration</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../../../howto/optimization/gpu_profiling_en.html">Tune GPU Performance</a></li>
</ul>
</li>
<li class="toctree-l1 current"><a class="reference internal" href="../../index_en.html">API</a><ul class="current">
<li class="toctree-l2"><a class="reference internal" href="../model_configs.html">Model Configuration</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../config/activation.html">Activation</a></li>
<li class="toctree-l3"><a class="reference internal" href="../config/layer.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../config/evaluators.html">Evaluators</a></li>
<li class="toctree-l3"><a class="reference internal" href="../config/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../config/pooling.html">Pooling</a></li>
<li class="toctree-l3"><a class="reference internal" href="../config/networks.html">Networks</a></li>
<li class="toctree-l3"><a class="reference internal" href="../config/attr.html">Parameter Attribute</a></li>
</ul>
</li>
<li class="toctree-l2 current"><a class="reference internal" href="../data.html">Data Reader Interface and DataSets</a><ul class="current">
<li class="toctree-l3"><a class="reference internal" href="data_reader.html">Data Reader Interface</a></li>
<li class="toctree-l3"><a class="reference internal" href="image.html">Image Interface</a></li>
<li class="toctree-l3 current"><a class="current reference internal" href="#">Dataset</a></li>
</ul>
</li>
<li class="toctree-l2"><a class="reference internal" href="../run_logic.html">Training and Inference</a></li>
<li class="toctree-l2"><a class="reference internal" href="../fluid.html">Fluid</a><ul>
<li class="toctree-l3"><a class="reference internal" href="../fluid/layers.html">Layers</a></li>
<li class="toctree-l3"><a class="reference internal" href="../fluid/data_feeder.html">DataFeeder</a></li>
<li class="toctree-l3"><a class="reference internal" href="../fluid/executor.html">Executor</a></li>
<li class="toctree-l3"><a class="reference internal" href="../fluid/initializer.html">Initializer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../fluid/evaluator.html">Evaluator</a></li>
<li class="toctree-l3"><a class="reference internal" href="../fluid/nets.html">Nets</a></li>
<li class="toctree-l3"><a class="reference internal" href="../fluid/optimizer.html">Optimizer</a></li>
<li class="toctree-l3"><a class="reference internal" href="../fluid/param_attr.html">ParamAttr</a></li>
<li class="toctree-l3"><a class="reference internal" href="../fluid/profiler.html">Profiler</a></li>
<li class="toctree-l3"><a class="reference internal" href="../fluid/regularizer.html">Regularizer</a></li>
</ul>
</li>
</ul>
</li>
<li class="toctree-l1"><a class="reference internal" href="../../../mobile/index_en.html">MOBILE</a><ul>
<li class="toctree-l2"><a class="reference internal" href="../../../mobile/cross_compiling_for_android_en.html">Build PaddlePaddle for Android</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../mobile/cross_compiling_for_ios_en.html">PaddlePaddle Compiling Guide for iOS</a></li>
<li class="toctree-l2"><a class="reference internal" href="../../../mobile/cross_compiling_for_raspberry_en.html">Build PaddlePaddle for Raspberry Pi</a></li>
</ul>
</li>
</ul>
</nav>
<section class="doc-content-wrap">
<div role="navigation" aria-label="breadcrumbs navigation">
<ul class="wy-breadcrumbs">
<li><a href="../../index_en.html">API</a> > </li>
<li><a href="../data.html">Data Reader Interface and DataSets</a> > </li>
<li>Dataset</li>
</ul>
</div>
<div class="wy-nav-content" id="doc-content">
<div class="rst-content">
<div role="main" class="document" itemscope="itemscope" itemtype="http://schema.org/Article">
<div itemprop="articleBody">
<div class="section" id="dataset">
<h1>Dataset<a class="headerlink" href="#dataset" title="Permalink to this headline">¶</a></h1>
<p>Dataset package.</p>
<div class="section" id="mnist">
<h2>mnist<a class="headerlink" href="#mnist" title="Permalink to this headline">¶</a></h2>
<p>MNIST dataset.</p>
<p>This module will download dataset from <a class="reference external" href="http://yann.lecun.com/exdb/mnist/">http://yann.lecun.com/exdb/mnist/</a> and
parse training set and test set into paddle reader creators.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.mnist.</code><code class="descname">train</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>MNIST training set creator.</p>
<p>It returns a reader creator, each sample in the reader is image pixels in
[0, 1] and label in [0, 9].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">Training reader creator</td>
</tr>
<tr class="field-even field"><th class="field-name">Return type:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.mnist.</code><code class="descname">test</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>MNIST test set creator.</p>
<p>It returns a reader creator, each sample in the reader is image pixels in
[0, 1] and label in [0, 9].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">Test reader creator.</td>
</tr>
<tr class="field-even field"><th class="field-name">Return type:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.mnist.</code><code class="descname">convert</code><span class="sig-paren">(</span><em>path</em><span class="sig-paren">)</span></dt>
<dd><p>Converts dataset to recordio format</p>
</dd></dl>
</div>
<div class="section" id="cifar">
<h2>cifar<a class="headerlink" href="#cifar" title="Permalink to this headline">¶</a></h2>
<p>CIFAR dataset.</p>
<p>This module will download dataset from
<a class="reference external" href="https://www.cs.toronto.edu/~kriz/cifar.html">https://www.cs.toronto.edu/~kriz/cifar.html</a> and parse train/test set into
paddle reader creators.</p>
<p>The CIFAR-10 dataset consists of 60000 32x32 colour images in 10 classes,
with 6000 images per class. There are 50000 training images and 10000 test
images.</p>
<p>The CIFAR-100 dataset is just like the CIFAR-10, except it has 100 classes
containing 600 images each. There are 500 training images and 100 testing
images per class.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.cifar.</code><code class="descname">train100</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>CIFAR-100 training set creator.</p>
<p>It returns a reader creator, each sample in the reader is image pixels in
[0, 1] and label in [0, 99].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">Training reader creator</td>
</tr>
<tr class="field-even field"><th class="field-name">Return type:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.cifar.</code><code class="descname">test100</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>CIFAR-100 test set creator.</p>
<p>It returns a reader creator, each sample in the reader is image pixels in
[0, 1] and label in [0, 9].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">Test reader creator.</td>
</tr>
<tr class="field-even field"><th class="field-name">Return type:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.cifar.</code><code class="descname">train10</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>CIFAR-10 training set creator.</p>
<p>It returns a reader creator, each sample in the reader is image pixels in
[0, 1] and label in [0, 9].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">Training reader creator</td>
</tr>
<tr class="field-even field"><th class="field-name">Return type:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.cifar.</code><code class="descname">test10</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>CIFAR-10 test set creator.</p>
<p>It returns a reader creator, each sample in the reader is image pixels in
[0, 1] and label in [0, 9].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">Test reader creator.</td>
</tr>
<tr class="field-even field"><th class="field-name">Return type:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.cifar.</code><code class="descname">convert</code><span class="sig-paren">(</span><em>path</em><span class="sig-paren">)</span></dt>
<dd><p>Converts dataset to recordio format</p>
</dd></dl>
</div>
<div class="section" id="conll05">
<h2>conll05<a class="headerlink" href="#conll05" title="Permalink to this headline">¶</a></h2>
<p>Conll05 dataset.
Paddle semantic role labeling Book and demo use this dataset as an example.
Because Conll05 is not free in public, the default downloaded URL is test set
of Conll05 (which is public). Users can change URL and MD5 to their Conll
dataset. And a pre-trained word vector model based on Wikipedia corpus is used
to initialize SRL model.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.conll05.</code><code class="descname">get_dict</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get the word, verb and label dictionary of Wikipedia corpus.</p>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.conll05.</code><code class="descname">get_embedding</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get the trained word vector based on Wikipedia corpus.</p>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.conll05.</code><code class="descname">test</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Conll05 test set creator.</p>
<p>Because the training dataset is not free, the test dataset is used for
training. It returns a reader creator, each sample in the reader is nine
features, including sentence sequence, predicate, predicate context,
predicate context flag and tagged sequence.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">Training reader creator</td>
</tr>
<tr class="field-even field"><th class="field-name">Return type:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>
</div>
<div class="section" id="imdb">
<h2>imdb<a class="headerlink" href="#imdb" title="Permalink to this headline">¶</a></h2>
<p>IMDB dataset.</p>
<p>This module downloads IMDB dataset from
<a class="reference external" href="http://ai.stanford.edu/%7Eamaas/data/sentiment/">http://ai.stanford.edu/%7Eamaas/data/sentiment/</a>. This dataset contains a set
of 25,000 highly polar movie reviews for training, and 25,000 for testing.
Besides, this module also provides API for building dictionary.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.imdb.</code><code class="descname">build_dict</code><span class="sig-paren">(</span><em>pattern</em>, <em>cutoff</em><span class="sig-paren">)</span></dt>
<dd><p>Build a word dictionary from the corpus. Keys of the dictionary are words,
and values are zero-based IDs of these words.</p>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.imdb.</code><code class="descname">train</code><span class="sig-paren">(</span><em>word_idx</em><span class="sig-paren">)</span></dt>
<dd><p>IMDB training set creator.</p>
<p>It returns a reader creator, each sample in the reader is an zero-based ID
sequence and label in [0, 1].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>word_idx</strong> (<em>dict</em>) – word dictionary</td>
</tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">Training reader creator</td>
</tr>
<tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.imdb.</code><code class="descname">test</code><span class="sig-paren">(</span><em>word_idx</em><span class="sig-paren">)</span></dt>
<dd><p>IMDB test set creator.</p>
<p>It returns a reader creator, each sample in the reader is an zero-based ID
sequence and label in [0, 1].</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><strong>word_idx</strong> (<em>dict</em>) – word dictionary</td>
</tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body">Test reader creator</td>
</tr>
<tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.imdb.</code><code class="descname">convert</code><span class="sig-paren">(</span><em>path</em><span class="sig-paren">)</span></dt>
<dd><p>Converts dataset to recordio format</p>
</dd></dl>
</div>
<div class="section" id="imikolov">
<h2>imikolov<a class="headerlink" href="#imikolov" title="Permalink to this headline">¶</a></h2>
<p>imikolov’s simple dataset.</p>
<p>This module will download dataset from
<a class="reference external" href="http://www.fit.vutbr.cz/~imikolov/rnnlm/">http://www.fit.vutbr.cz/~imikolov/rnnlm/</a> and parse training set and test set
into paddle reader creators.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.imikolov.</code><code class="descname">build_dict</code><span class="sig-paren">(</span><em>min_word_freq=50</em><span class="sig-paren">)</span></dt>
<dd><p>Build a word dictionary from the corpus, Keys of the dictionary are words,
and values are zero-based IDs of these words.</p>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.imikolov.</code><code class="descname">train</code><span class="sig-paren">(</span><em>word_idx</em>, <em>n</em>, <em>data_type=1</em><span class="sig-paren">)</span></dt>
<dd><p>imikolov training set creator.</p>
<p>It returns a reader creator, each sample in the reader is a word ID
tuple.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
<li><strong>word_idx</strong> (<em>dict</em>) – word dictionary</li>
<li><strong>n</strong> (<em>int</em>) – sliding window size if type is ngram, otherwise max length of sequence</li>
<li><strong>data_type</strong> (<em>member variable of DataType</em><em> (</em><em>NGRAM</em><em> or </em><em>SEQ</em><em>)</em>) – data type (ngram or sequence)</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first">Training reader creator</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body"><p class="first last">callable</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.imikolov.</code><code class="descname">test</code><span class="sig-paren">(</span><em>word_idx</em>, <em>n</em>, <em>data_type=1</em><span class="sig-paren">)</span></dt>
<dd><p>imikolov test set creator.</p>
<p>It returns a reader creator, each sample in the reader is a word ID
tuple.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Parameters:</th><td class="field-body"><ul class="first simple">
<li><strong>word_idx</strong> (<em>dict</em>) – word dictionary</li>
<li><strong>n</strong> (<em>int</em>) – sliding window size if type is ngram, otherwise max length of sequence</li>
<li><strong>data_type</strong> (<em>member variable of DataType</em><em> (</em><em>NGRAM</em><em> or </em><em>SEQ</em><em>)</em>) – data type (ngram or sequence)</li>
</ul>
</td>
</tr>
<tr class="field-even field"><th class="field-name">Returns:</th><td class="field-body"><p class="first">Test reader creator</p>
</td>
</tr>
<tr class="field-odd field"><th class="field-name">Return type:</th><td class="field-body"><p class="first last">callable</p>
</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.imikolov.</code><code class="descname">convert</code><span class="sig-paren">(</span><em>path</em><span class="sig-paren">)</span></dt>
<dd><p>Converts dataset to recordio format</p>
</dd></dl>
</div>
<div class="section" id="movielens">
<h2>movielens<a class="headerlink" href="#movielens" title="Permalink to this headline">¶</a></h2>
<p>Movielens 1-M dataset.</p>
<p>Movielens 1-M dataset contains 1 million ratings from 6000 users on 4000
movies, which was collected by GroupLens Research. This module will download
Movielens 1-M dataset from
<a class="reference external" href="http://files.grouplens.org/datasets/movielens/ml-1m.zip">http://files.grouplens.org/datasets/movielens/ml-1m.zip</a> and parse training
set and test set into paddle reader creators.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">get_movie_title_dict</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get movie title dictionary.</p>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">max_movie_id</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get the maximum value of movie id.</p>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">max_user_id</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get the maximum value of user id.</p>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">max_job_id</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get the maximum value of job id.</p>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">movie_categories</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get movie categoriges dictionary.</p>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">user_info</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get user info dictionary.</p>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">movie_info</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Get movie info dictionary.</p>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">convert</code><span class="sig-paren">(</span><em>path</em><span class="sig-paren">)</span></dt>
<dd><p>Converts dataset to recordio format</p>
</dd></dl>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">MovieInfo</code><span class="sig-paren">(</span><em>index</em>, <em>categories</em>, <em>title</em><span class="sig-paren">)</span></dt>
<dd><p>Movie id, title and categories information are stored in MovieInfo.</p>
</dd></dl>
<dl class="class">
<dt>
<em class="property">class </em><code class="descclassname">paddle.v2.dataset.movielens.</code><code class="descname">UserInfo</code><span class="sig-paren">(</span><em>index</em>, <em>gender</em>, <em>age</em>, <em>job_id</em><span class="sig-paren">)</span></dt>
<dd><p>User id, gender, age, and job information are stored in UserInfo.</p>
</dd></dl>
</div>
<div class="section" id="sentiment">
<h2>sentiment<a class="headerlink" href="#sentiment" title="Permalink to this headline">¶</a></h2>
<p>The script fetch and preprocess movie_reviews data set that provided by NLTK</p>
<p>TODO(yuyang18): Complete dataset.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.sentiment.</code><code class="descname">get_word_dict</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Sorted the words by the frequency of words which occur in sample
:return:</p>
<blockquote>
<div>words_freq_sorted</div></blockquote>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.sentiment.</code><code class="descname">train</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Default training set reader creator</p>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.sentiment.</code><code class="descname">test</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>Default test set reader creator</p>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.sentiment.</code><code class="descname">convert</code><span class="sig-paren">(</span><em>path</em><span class="sig-paren">)</span></dt>
<dd><p>Converts dataset to recordio format</p>
</dd></dl>
</div>
<div class="section" id="uci-housing">
<h2>uci_housing<a class="headerlink" href="#uci-housing" title="Permalink to this headline">¶</a></h2>
<p>UCI Housing dataset.</p>
<p>This module will download dataset from
<a class="reference external" href="https://archive.ics.uci.edu/ml/machine-learning-databases/housing/">https://archive.ics.uci.edu/ml/machine-learning-databases/housing/</a> and
parse training set and test set into paddle reader creators.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.uci_housing.</code><code class="descname">train</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>UCI_HOUSING training set creator.</p>
<p>It returns a reader creator, each sample in the reader is features after
normalization and price number.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">Training reader creator</td>
</tr>
<tr class="field-even field"><th class="field-name">Return type:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.uci_housing.</code><code class="descname">test</code><span class="sig-paren">(</span><span class="sig-paren">)</span></dt>
<dd><p>UCI_HOUSING test set creator.</p>
<p>It returns a reader creator, each sample in the reader is features after
normalization and price number.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">Test reader creator</td>
</tr>
<tr class="field-even field"><th class="field-name">Return type:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>
</div>
<div class="section" id="wmt14">
<h2>wmt14<a class="headerlink" href="#wmt14" title="Permalink to this headline">¶</a></h2>
<p>WMT14 dataset.
The original WMT14 dataset is too large and a small set of data for set is
provided. This module will download dataset from
<a class="reference external" href="http://paddlepaddle.cdn.bcebos.com/demo/wmt_shrinked_data/wmt14.tgz">http://paddlepaddle.cdn.bcebos.com/demo/wmt_shrinked_data/wmt14.tgz</a> and
parse training set and test set into paddle reader creators.</p>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.wmt14.</code><code class="descname">train</code><span class="sig-paren">(</span><em>dict_size</em><span class="sig-paren">)</span></dt>
<dd><p>WMT14 training set creator.</p>
<p>It returns a reader creator, each sample in the reader is source language
word ID sequence, target language word ID sequence and next word ID
sequence.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">Training reader creator</td>
</tr>
<tr class="field-even field"><th class="field-name">Return type:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.wmt14.</code><code class="descname">test</code><span class="sig-paren">(</span><em>dict_size</em><span class="sig-paren">)</span></dt>
<dd><p>WMT14 test set creator.</p>
<p>It returns a reader creator, each sample in the reader is source language
word ID sequence, target language word ID sequence and next word ID
sequence.</p>
<table class="docutils field-list" frame="void" rules="none">
<col class="field-name" />
<col class="field-body" />
<tbody valign="top">
<tr class="field-odd field"><th class="field-name">Returns:</th><td class="field-body">Test reader creator</td>
</tr>
<tr class="field-even field"><th class="field-name">Return type:</th><td class="field-body">callable</td>
</tr>
</tbody>
</table>
</dd></dl>
<dl class="function">
<dt>
<code class="descclassname">paddle.v2.dataset.wmt14.</code><code class="descname">convert</code><span class="sig-paren">(</span><em>path</em><span class="sig-paren">)</span></dt>
<dd><p>Converts dataset to recordio format</p>
</dd></dl>
</div>
</div>
</div>
</div>
<footer>
<div class="rst-footer-buttons" role="navigation" aria-label="footer navigation">
<a href="../run_logic.html" class="btn btn-neutral float-right" title="Training and Inference" accesskey="n">Next <span class="fa fa-arrow-circle-right"></span></a>
<a href="image.html" class="btn btn-neutral" title="Image Interface" accesskey="p"><span class="fa fa-arrow-circle-left"></span> Previous</a>
</div>
<hr/>
<div role="contentinfo">
<p>
© Copyright 2016, PaddlePaddle developers.
</p>
</div>
Built with <a href="http://sphinx-doc.org/">Sphinx</a> using a <a href="https://github.com/snide/sphinx_rtd_theme">theme</a> provided by <a href="https://readthedocs.org">Read the Docs</a>.
</footer>
</div>
</div>
</section>
</div>
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT:'../../../',
VERSION:'',
COLLAPSE_INDEX:false,
FILE_SUFFIX:'.html',
HAS_SOURCE: true,
SOURCELINK_SUFFIX: ".txt",
};
</script>
<script type="text/javascript" src="../../../_static/jquery.js"></script>
<script type="text/javascript" src="../../../_static/underscore.js"></script>
<script type="text/javascript" src="../../../_static/doctools.js"></script>
<script type="text/javascript" src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.0/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script>
<script type="text/javascript" src="../../../_static/js/theme.js"></script>
<script src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.7/js/bootstrap.min.js" integrity="sha384-Tc5IQib027qvyjSMfHjOMaLkfuWVxZxUPnCJA7l2mCWNIpG9mGCD8wGNIcPD7Txa" crossorigin="anonymous"></script>
<script src="https://cdn.jsdelivr.net/perfect-scrollbar/0.6.14/js/perfect-scrollbar.jquery.min.js"></script>
<script src="../../../_static/js/paddle_doc_init.js"></script>
</body>
</html>