Google Git
Sign in
apache / mxnet-site / 7c979c3950c5081994a0e7d0c43c288c6fefb049 / . / _modules / mxnet / contrib / text / embedding.html
blob: 097f6b72fe1698b1db3575c75032d4281a4400f1 [file] [log] [blame]
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="utf-8"/>
<meta content="IE=edge" http-equiv="X-UA-Compatible"/>
<meta content="width=device-width, initial-scale=1" name="viewport"/>
<title>mxnet.contrib.text.embedding — mxnet documentation</title>
<link crossorigin="anonymous" href="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/css/bootstrap.min.css" integrity="sha384-1q8mTJOASx8j1Au+a5WDVnPi2lkFfwwEAa8hDDdjZlpLegxhjVME1fgjWPGmkzs7" rel="stylesheet"/>
<link href="https://maxcdn.bootstrapcdn.com/font-awesome/4.5.0/css/font-awesome.min.css" rel="stylesheet"/>
<link href="../../../../_static/basic.css" rel="stylesheet" type="text/css">
<link href="../../../../_static/pygments.css" rel="stylesheet" type="text/css">
<link href="../../../../_static/mxnet.css" rel="stylesheet" type="text/css"/>
<script type="text/javascript">
var DOCUMENTATION_OPTIONS = {
URL_ROOT: '../../../../',
VERSION: '',
COLLAPSE_INDEX: false,
FILE_SUFFIX: '.html',
HAS_SOURCE: true,
SOURCELINK_SUFFIX: ''
};
</script>
<script src="https://code.jquery.com/jquery-1.11.1.min.js" type="text/javascript"></script>
<script src="../../../../_static/underscore.js" type="text/javascript"></script>
<script src="../../../../_static/searchtools_custom.js" type="text/javascript"></script>
<script src="../../../../_static/doctools.js" type="text/javascript"></script>
<script src="../../../../_static/selectlang.js" type="text/javascript"></script>
<script src="https://cdnjs.cloudflare.com/ajax/libs/mathjax/2.7.1/MathJax.js?config=TeX-AMS-MML_HTMLorMML" type="text/javascript"></script>
<script type="text/javascript"> jQuery(function() { Search.loadIndex("/searchindex.js"); Search.init();}); </script>
<script>
(function(i,s,o,g,r,a,m){i['GoogleAnalyticsObject']=r;i[r]=i[r]||function(){
(i[r].q=i[r].q||[]).push(arguments)},i[r].l=1*new
Date();a=s.createElement(o),
m=s.getElementsByTagName(o)[0];a.async=1;a.src=g;m.parentNode.insertBefore(a,m)
})(window,document,'script','https://www.google-analytics.com/analytics.js','ga');
ga('create', 'UA-96378503-1', 'auto');
ga('send', 'pageview');
</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://cdn.mathjax.org/mathjax/latest/MathJax.js?config=TeX-AMS-MML_HTMLorMML"></script> -->
<!-- -->
<link href="../../../index.html" rel="up" title="Module code">
<link href="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-icon.png" rel="icon" type="image/png"/>
</link></link></link></head>
<body background="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet-background-compressed.jpeg" role="document">
<div class="content-block"><div class="navbar navbar-fixed-top">
<div class="container" id="navContainer">
<div class="innder" id="header-inner">
<h1 id="logo-wrap">
<a href="../../../../" id="logo"><img src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/mxnet_logo.png"/></a>
</h1>
<nav class="nav-bar" id="main-nav">
<a class="main-nav-link" href="../../../../install/index.html">Install</a>
<span id="dropdown-menu-position-anchor">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Gluon <span class="caret"></span></a>
<ul class="dropdown-menu navbar-menu" id="package-dropdown-menu">
<li><a class="main-nav-link" href="../../../../gluon/index.html">About</a></li>
<li><a class="main-nav-link" href="http://gluon.mxnet.io">Tutorials</a></li>
</ul>
</span>
<span id="dropdown-menu-position-anchor">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">API <span class="caret"></span></a>
<ul class="dropdown-menu navbar-menu" id="package-dropdown-menu">
<li><a class="main-nav-link" href="../../../../api/python/index.html">Python</a></li>
<li><a class="main-nav-link" href="../../../../api/scala/index.html">Scala</a></li>
<li><a class="main-nav-link" href="../../../../api/r/index.html">R</a></li>
<li><a class="main-nav-link" href="../../../../api/julia/index.html">Julia</a></li>
<li><a class="main-nav-link" href="../../../../api/c++/index.html">C++</a></li>
<li><a class="main-nav-link" href="../../../../api/perl/index.html">Perl</a></li>
</ul>
</span>
<span id="dropdown-menu-position-anchor-docs">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Docs <span class="caret"></span></a>
<ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-docs">
<li><a class="main-nav-link" href="../../../../tutorials/index.html">Tutorials</a>
<li><a class="main-nav-link" href="../../../../faq/index.html">FAQ</a></li>
<li><a class="main-nav-link" href="../../../../architecture/index.html">Architecture</a></li>
<li><a class="main-nav-link" href="https://github.com/apache/incubator-mxnet/tree/1.1.0/example">Examples</a></li>
<li><a class="main-nav-link" href="../../../../api/python/gluon/model_zoo.html">Gluon Model Zoo</a></li>
</li></ul>
</span>
<a class="main-nav-link" href="https://github.com/dmlc/mxnet">Github</a>
<span id="dropdown-menu-position-anchor-community">
<a aria-expanded="true" aria-haspopup="true" class="main-nav-link dropdown-toggle" data-toggle="dropdown" href="#" role="button">Community <span class="caret"></span></a>
<ul class="dropdown-menu navbar-menu" id="package-dropdown-menu-community">
<li><a class="main-nav-link" href="../../../../community/index.html">Community</a></li>
<li><a class="main-nav-link" href="../../../../community/contribute.html">Contribute</a></li>
<li><a class="main-nav-link" href="../../../../community/powered_by.html">Powered By</a></li>
<li><a class="main-nav-link" href="http://discuss.mxnet.io">Discuss</a></li>
</ul>
</span>
<span id="dropdown-menu-position-anchor-version" style="position: relative"><a href="#" class="main-nav-link dropdown-toggle" data-toggle="dropdown" role="button" aria-haspopup="true" aria-expanded="true">Versions(1.1.0)<span class="caret"></span></a><ul id="package-dropdown-menu" class="dropdown-menu"><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/>1.1.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/1.0.0/index.html>1.0.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/0.12.1/index.html>0.12.1</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/0.12.0/index.html>0.12.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/0.11.0/index.html>0.11.0</a></li><li><a class="main-nav-link" href=https://mxnet.incubator.apache.org/versions/master/index.html>master</a></li></ul></span></nav>
<script> function getRootPath(){ return "../../../../" } </script>
<div class="burgerIcon dropdown">
<a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button">☰</a>
<ul class="dropdown-menu" id="burgerMenu">
<li><a href="../../../../install/index.html">Install</a></li>
<li><a class="main-nav-link" href="../../../../tutorials/index.html">Tutorials</a></li>
<li class="dropdown-submenu">
<a href="#" tabindex="-1">Community</a>
<ul class="dropdown-menu">
<li><a href="../../../../community/index.html" tabindex="-1">Community</a></li>
<li><a href="../../../../community/contribute.html" tabindex="-1">Contribute</a></li>
<li><a href="../../../../community/powered_by.html" tabindex="-1">Powered By</a></li>
</ul>
</li>
<li class="dropdown-submenu">
<a href="#" tabindex="-1">API</a>
<ul class="dropdown-menu">
<li><a href="../../../../api/python/index.html" tabindex="-1">Python</a>
</li>
<li><a href="../../../../api/scala/index.html" tabindex="-1">Scala</a>
</li>
<li><a href="../../../../api/r/index.html" tabindex="-1">R</a>
</li>
<li><a href="../../../../api/julia/index.html" tabindex="-1">Julia</a>
</li>
<li><a href="../../../../api/c++/index.html" tabindex="-1">C++</a>
</li>
<li><a href="../../../../api/perl/index.html" tabindex="-1">Perl</a>
</li>
</ul>
</li>
<li class="dropdown-submenu">
<a href="#" tabindex="-1">Docs</a>
<ul class="dropdown-menu">
<li><a href="../../../../tutorials/index.html" tabindex="-1">Tutorials</a></li>
<li><a href="../../../../faq/index.html" tabindex="-1">FAQ</a></li>
<li><a href="../../../../architecture/index.html" tabindex="-1">Architecture</a></li>
<li><a href="https://github.com/apache/incubator-mxnet/tree/1.1.0/example" tabindex="-1">Examples</a></li>
<li><a href="../../../../api/python/gluon/model_zoo.html" tabindex="-1">Gluon Model Zoo</a></li>
</ul>
</li>
<li><a href="../../../../architecture/index.html">Architecture</a></li>
<li><a class="main-nav-link" href="https://github.com/dmlc/mxnet">Github</a></li>
<li id="dropdown-menu-position-anchor-version-mobile" class="dropdown-submenu" style="position: relative"><a href="#" tabindex="-1">Versions(1.1.0)</a><ul class="dropdown-menu"><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/>1.1.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/1.0.0/index.html>1.0.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/0.12.1/index.html>0.12.1</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/0.12.0/index.html>0.12.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/0.11.0/index.html>0.11.0</a></li><li><a tabindex="-1" href=https://mxnet.incubator.apache.org/versions/master/index.html>master</a></li></ul></li></ul>
</div>
<div class="plusIcon dropdown">
<a class="dropdown-toggle" data-toggle="dropdown" href="#" role="button"><span aria-hidden="true" class="glyphicon glyphicon-plus"></span></a>
<ul class="dropdown-menu dropdown-menu-right" id="plusMenu"></ul>
</div>
<div id="search-input-wrap">
<form action="../../../../search.html" autocomplete="off" class="" method="get" role="search">
<div class="form-group inner-addon left-addon">
<i class="glyphicon glyphicon-search"></i>
<input class="form-control" name="q" placeholder="Search" type="text"/>
</div>
<input name="check_keywords" type="hidden" value="yes">
<input name="area" type="hidden" value="default"/>
</input></form>
<div id="search-preview"></div>
</div>
<div id="searchIcon">
<span aria-hidden="true" class="glyphicon glyphicon-search"></span>
</div>
<!-- <div id="lang-select-wrap"> -->
<!-- <label id="lang-select-label"> -->
<!-- <\!-- <i class="fa fa-globe"></i> -\-> -->
<!-- <span></span> -->
<!-- </label> -->
<!-- <select id="lang-select"> -->
<!-- <option value="en">Eng</option> -->
<!-- <option value="zh">中文</option> -->
<!-- </select> -->
<!-- </div> -->
<!-- <a id="mobile-nav-toggle">
<span class="mobile-nav-toggle-bar"></span>
<span class="mobile-nav-toggle-bar"></span>
<span class="mobile-nav-toggle-bar"></span>
</a> -->
</div>
</div>
</div>
<script type="text/javascript">
$('body').css('background', 'white');
</script>
<div class="container">
<div class="row">
<div aria-label="main navigation" class="sphinxsidebar leftsidebar" role="navigation">
<div class="sphinxsidebarwrapper">
<ul>
<li class="toctree-l1"><a class="reference internal" href="../../../../api/python/index.html">Python Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../api/r/index.html">R Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../api/julia/index.html">Julia Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../api/c++/index.html">C++ Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../api/scala/index.html">Scala Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../api/perl/index.html">Perl Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../faq/index.html">HowTo Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../architecture/index.html">System Documents</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../tutorials/index.html">Tutorials</a></li>
<li class="toctree-l1"><a class="reference internal" href="../../../../community/index.html">Community</a></li>
</ul>
</div>
</div>
<div class="content">
<div class="page-tracker"></div>
<h1>Source code for mxnet.contrib.text.embedding</h1><div class="highlight"><pre>
<span></span><span class="c1"># Licensed to the Apache Software Foundation (ASF) under one</span>
<span class="c1"># or more contributor license agreements. See the NOTICE file</span>
<span class="c1"># distributed with this work for additional information</span>
<span class="c1"># regarding copyright ownership. The ASF licenses this file</span>
<span class="c1"># to you under the Apache License, Version 2.0 (the</span>
<span class="c1"># "License"); you may not use this file except in compliance</span>
<span class="c1"># with the License. You may obtain a copy of the License at</span>
<span class="c1">#</span>
<span class="c1"># http://www.apache.org/licenses/LICENSE-2.0</span>
<span class="c1">#</span>
<span class="c1"># Unless required by applicable law or agreed to in writing,</span>
<span class="c1"># software distributed under the License is distributed on an</span>
<span class="c1"># "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY</span>
<span class="c1"># KIND, either express or implied. See the License for the</span>
<span class="c1"># specific language governing permissions and limitations</span>
<span class="c1"># under the License.</span>
<span class="c1"># coding: utf-8</span>
<span class="c1"># pylint: disable=consider-iterating-dictionary</span>
<span class="c1"># pylint: disable=super-init-not-called</span>
<span class="sd">"""Text token embeddings."""</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">absolute_import</span>
<span class="kn">from</span> <span class="nn">__future__</span> <span class="kn">import</span> <span class="n">print_function</span>
<span class="kn">import</span> <span class="nn">io</span>
<span class="kn">import</span> <span class="nn">logging</span>
<span class="kn">import</span> <span class="nn">os</span>
<span class="kn">import</span> <span class="nn">tarfile</span>
<span class="kn">import</span> <span class="nn">warnings</span>
<span class="kn">import</span> <span class="nn">zipfile</span>
<span class="kn">from</span> <span class="nn">.</span> <span class="kn">import</span> <span class="n">_constants</span> <span class="k">as</span> <span class="n">C</span>
<span class="kn">from</span> <span class="nn">.</span> <span class="kn">import</span> <span class="n">vocab</span>
<span class="kn">from</span> <span class="nn">...</span> <span class="kn">import</span> <span class="n">ndarray</span> <span class="k">as</span> <span class="n">nd</span>
<span class="kn">from</span> <span class="nn">...</span> <span class="kn">import</span> <span class="n">registry</span>
<div class="viewcode-block" id="register"><a class="viewcode-back" href="../../../../api/python/contrib/text.html#mxnet.contrib.text.embedding.register">[docs]</a><span class="k">def</span> <span class="nf">register</span><span class="p">(</span><span class="n">embedding_cls</span><span class="p">):</span>
<span class="sd">"""Registers a new token embedding.</span>
<span class="sd"> Once an embedding is registered, we can create an instance of this embedding with</span>
<span class="sd"> :func:`~mxnet.contrib.text.embedding.create`.</span>
<span class="sd"> Examples</span>
<span class="sd"> --------</span>
<span class="sd"> >>> @mxnet.contrib.text.embedding.register</span>
<span class="sd"> ... class MyTextEmbed(mxnet.contrib.text.embedding._TokenEmbedding):</span>
<span class="sd"> ... def __init__(self, pretrained_file_name='my_pretrain_file'):</span>
<span class="sd"> ... pass</span>
<span class="sd"> >>> embed = mxnet.contrib.text.embedding.create('MyTokenEmbed')</span>
<span class="sd"> >>> print(type(embed))</span>
<span class="sd"> <class '__main__.MyTokenEmbed'></span>
<span class="sd"> """</span>
<span class="n">register_text_embedding</span> <span class="o">=</span> <span class="n">registry</span><span class="o">.</span><span class="n">get_register_func</span><span class="p">(</span><span class="n">_TokenEmbedding</span><span class="p">,</span> <span class="s1">'token embedding'</span><span class="p">)</span>
<span class="k">return</span> <span class="n">register_text_embedding</span><span class="p">(</span><span class="n">embedding_cls</span><span class="p">)</span></div>
<div class="viewcode-block" id="create"><a class="viewcode-back" href="../../../../api/python/contrib/text.html#mxnet.contrib.text.embedding.create">[docs]</a><span class="k">def</span> <span class="nf">create</span><span class="p">(</span><span class="n">embedding_name</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="sd">"""Creates an instance of token embedding.</span>
<span class="sd"> Creates a token embedding instance by loading embedding vectors from an externally hosted</span>
<span class="sd"> pre-trained token embedding file, such as those of GloVe and FastText. To get all the valid</span>
<span class="sd"> `embedding_name` and `pretrained_file_name`, use</span>
<span class="sd"> `mxnet.contrib.text.embedding.get_pretrained_file_names()`.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> embedding_name : str</span>
<span class="sd"> The token embedding name (case-insensitive).</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> An instance of `mxnet.contrib.text.glossary._TokenEmbedding`:</span>
<span class="sd"> A token embedding instance that loads embedding vectors from an externally hosted</span>
<span class="sd"> pre-trained token embedding file.</span>
<span class="sd"> """</span>
<span class="n">create_text_embedding</span> <span class="o">=</span> <span class="n">registry</span><span class="o">.</span><span class="n">get_create_func</span><span class="p">(</span><span class="n">_TokenEmbedding</span><span class="p">,</span> <span class="s1">'token embedding'</span><span class="p">)</span>
<span class="k">return</span> <span class="n">create_text_embedding</span><span class="p">(</span><span class="n">embedding_name</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">)</span></div>
<div class="viewcode-block" id="get_pretrained_file_names"><a class="viewcode-back" href="../../../../api/python/contrib/text.html#mxnet.contrib.text.embedding.get_pretrained_file_names">[docs]</a><span class="k">def</span> <span class="nf">get_pretrained_file_names</span><span class="p">(</span><span class="n">embedding_name</span><span class="o">=</span><span class="bp">None</span><span class="p">):</span>
<span class="sd">"""Get valid token embedding names and their pre-trained file names.</span>
<span class="sd"> To load token embedding vectors from an externally hosted pre-trained token embedding file,</span>
<span class="sd"> such as those of GloVe and FastText, one should use</span>
<span class="sd"> `mxnet.contrib.text.embedding.create(embedding_name, pretrained_file_name)`.</span>
<span class="sd"> This method returns all the valid names of `pretrained_file_name` for the specified</span>
<span class="sd"> `embedding_name`. If `embedding_name` is set to None, this method returns all the valid</span>
<span class="sd"> names of `embedding_name` with their associated `pretrained_file_name`.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> embedding_name : str or None, default None</span>
<span class="sd"> The pre-trained token embedding name.</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> dict or list:</span>
<span class="sd"> A list of all the valid pre-trained token embedding file names (`pretrained_file_name`)</span>
<span class="sd"> for the specified token embedding name (`embedding_name`). If the text embeding name is</span>
<span class="sd"> set to None, returns a dict mapping each valid token embedding name to a list of valid</span>
<span class="sd"> pre-trained files (`pretrained_file_name`). They can be plugged into</span>
<span class="sd"> `mxnet.contrib.text.embedding.create(embedding_name,</span>
<span class="sd"> pretrained_file_name)`.</span>
<span class="sd"> """</span>
<span class="n">text_embedding_reg</span> <span class="o">=</span> <span class="n">registry</span><span class="o">.</span><span class="n">get_registry</span><span class="p">(</span><span class="n">_TokenEmbedding</span><span class="p">)</span>
<span class="k">if</span> <span class="n">embedding_name</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">if</span> <span class="n">embedding_name</span> <span class="ow">not</span> <span class="ow">in</span> <span class="n">text_embedding_reg</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">KeyError</span><span class="p">(</span><span class="s1">'Cannot find `embedding_name` </span><span class="si">%s</span><span class="s1">. Use '</span>
<span class="s1">'`get_pretrained_file_names('</span>
<span class="s1">'embedding_name=None).keys()` to get all the valid embedding '</span>
<span class="s1">'names.'</span> <span class="o">%</span> <span class="n">embedding_name</span><span class="p">)</span>
<span class="k">return</span> <span class="nb">list</span><span class="p">(</span><span class="n">text_embedding_reg</span><span class="p">[</span><span class="n">embedding_name</span><span class="p">]</span><span class="o">.</span><span class="n">pretrained_file_name_sha1</span><span class="o">.</span><span class="n">keys</span><span class="p">())</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">return</span> <span class="p">{</span><span class="n">embedding_name</span><span class="p">:</span> <span class="nb">list</span><span class="p">(</span><span class="n">embedding_cls</span><span class="o">.</span><span class="n">pretrained_file_name_sha1</span><span class="o">.</span><span class="n">keys</span><span class="p">())</span>
<span class="k">for</span> <span class="n">embedding_name</span><span class="p">,</span> <span class="n">embedding_cls</span> <span class="ow">in</span> <span class="n">registry</span><span class="o">.</span><span class="n">get_registry</span><span class="p">(</span><span class="n">_TokenEmbedding</span><span class="p">)</span><span class="o">.</span><span class="n">items</span><span class="p">()}</span></div>
<span class="k">class</span> <span class="nc">_TokenEmbedding</span><span class="p">(</span><span class="n">vocab</span><span class="o">.</span><span class="n">Vocabulary</span><span class="p">):</span>
<span class="sd">"""Token embedding base class.</span>
<span class="sd"> To load token embeddings from an externally hosted pre-trained token embedding file, such as</span>
<span class="sd"> those of GloVe and FastText, use</span>
<span class="sd"> :func:`~mxnet.contrib.text.embedding.create(embedding_name, pretrained_file_name)`.</span>
<span class="sd"> To get all the available `embedding_name` and `pretrained_file_name`, use</span>
<span class="sd"> :func:`~mxnet.contrib.text.embedding.get_pretrained_file_names()`.</span>
<span class="sd"> Alternatively, to load embedding vectors from a custom pre-trained token embedding file, use</span>
<span class="sd"> :class:`~mxnet.contrib.text.embedding.CustomEmbedding`.</span>
<span class="sd"> Moreover, to load composite embedding vectors, such as to concatenate embedding vectors, use</span>
<span class="sd"> :class:`~mxnet.contrib.text.embedding.CompositeEmbedding`.</span>
<span class="sd"> For every unknown token, if its representation `self.unknown_token` is encountered in the</span>
<span class="sd"> pre-trained token embedding file, index 0 of `self.idx_to_vec` maps to the pre-trained token</span>
<span class="sd"> embedding vector loaded from the file; otherwise, index 0 of `self.idx_to_vec` maps to the</span>
<span class="sd"> token embedding vector initialized by `init_unknown_vec`.</span>
<span class="sd"> If a token is encountered multiple times in the pre-trained token embedding file, only the</span>
<span class="sd"> first-encountered token embedding vector will be loaded and the rest will be skipped.</span>
<span class="sd"> The indexed tokens in a text token embedding may come from a vocabulary or from the loaded</span>
<span class="sd"> embedding vectors. In the former case, only the indexed tokens in a vocabulary are associated</span>
<span class="sd"> with the loaded embedding vectors, such as loaded from a pre-trained token embedding file. In</span>
<span class="sd"> the later case, all the tokens from the loaded embedding vectors, such as loaded from a</span>
<span class="sd"> pre-trained token embedding file, are taken as the indexed tokens of the embedding.</span>
<span class="sd"> Properties</span>
<span class="sd"> ----------</span>
<span class="sd"> token_to_idx : dict mapping str to int</span>
<span class="sd"> A dict mapping each token to its index integer.</span>
<span class="sd"> idx_to_token : list of strs</span>
<span class="sd"> A list of indexed tokens where the list indices and the token indices are aligned.</span>
<span class="sd"> unknown_token : hashable object</span>
<span class="sd"> The representation for any unknown token. In other words, any unknown token will be indexed</span>
<span class="sd"> as the same representation.</span>
<span class="sd"> reserved_tokens : list of strs or None</span>
<span class="sd"> A list of reserved tokens that will always be indexed.</span>
<span class="sd"> vec_len : int</span>
<span class="sd"> The length of the embedding vector for each token.</span>
<span class="sd"> idx_to_vec : mxnet.ndarray.NDArray</span>
<span class="sd"> For all the indexed tokens in this embedding, this NDArray maps each token's index to an</span>
<span class="sd"> embedding vector. The largest valid index maps to the initialized embedding vector for every</span>
<span class="sd"> reserved token, such as an unknown_token token and a padding token.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">_TokenEmbedding</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="nd">@classmethod</span>
<span class="k">def</span> <span class="nf">_get_download_file_name</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">pretrained_file_name</span><span class="p">):</span>
<span class="k">return</span> <span class="n">pretrained_file_name</span>
<span class="nd">@classmethod</span>
<span class="k">def</span> <span class="nf">_get_pretrained_file_url</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">pretrained_file_name</span><span class="p">):</span>
<span class="n">repo_url</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">environ</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="s1">'MXNET_GLUON_REPO'</span><span class="p">,</span> <span class="n">C</span><span class="o">.</span><span class="n">APACHE_REPO_URL</span><span class="p">)</span>
<span class="n">embedding_cls</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="vm">__name__</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span>
<span class="n">url_format</span> <span class="o">=</span> <span class="s1">'{repo_url}gluon/embeddings/{cls}/{file_name}'</span>
<span class="k">return</span> <span class="n">url_format</span><span class="o">.</span><span class="n">format</span><span class="p">(</span><span class="n">repo_url</span><span class="o">=</span><span class="n">repo_url</span><span class="p">,</span> <span class="bp">cls</span><span class="o">=</span><span class="n">embedding_cls</span><span class="p">,</span>
<span class="n">file_name</span><span class="o">=</span><span class="bp">cls</span><span class="o">.</span><span class="n">_get_download_file_name</span><span class="p">(</span><span class="n">pretrained_file_name</span><span class="p">))</span>
<span class="nd">@classmethod</span>
<span class="k">def</span> <span class="nf">_get_pretrained_file</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">embedding_root</span><span class="p">,</span> <span class="n">pretrained_file_name</span><span class="p">):</span>
<span class="kn">from</span> <span class="nn">...gluon.utils</span> <span class="kn">import</span> <span class="n">check_sha1</span><span class="p">,</span> <span class="n">download</span>
<span class="n">embedding_cls</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="vm">__name__</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span>
<span class="n">embedding_root</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">expanduser</span><span class="p">(</span><span class="n">embedding_root</span><span class="p">)</span>
<span class="n">url</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="n">_get_pretrained_file_url</span><span class="p">(</span><span class="n">pretrained_file_name</span><span class="p">)</span>
<span class="n">embedding_dir</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">embedding_root</span><span class="p">,</span> <span class="n">embedding_cls</span><span class="p">)</span>
<span class="n">pretrained_file_path</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">embedding_dir</span><span class="p">,</span> <span class="n">pretrained_file_name</span><span class="p">)</span>
<span class="n">downloaded_file</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">basename</span><span class="p">(</span><span class="n">url</span><span class="p">)</span>
<span class="n">downloaded_file_path</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">embedding_dir</span><span class="p">,</span> <span class="n">downloaded_file</span><span class="p">)</span>
<span class="n">expected_file_hash</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="n">pretrained_file_name_sha1</span><span class="p">[</span><span class="n">pretrained_file_name</span><span class="p">]</span>
<span class="k">if</span> <span class="nb">hasattr</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="s1">'pretrained_archive_name_sha1'</span><span class="p">):</span>
<span class="n">expected_downloaded_hash</span> <span class="o">=</span> \
<span class="bp">cls</span><span class="o">.</span><span class="n">pretrained_archive_name_sha1</span><span class="p">[</span><span class="n">downloaded_file</span><span class="p">]</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">expected_downloaded_hash</span> <span class="o">=</span> <span class="n">expected_file_hash</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">exists</span><span class="p">(</span><span class="n">pretrained_file_path</span><span class="p">)</span> \
<span class="ow">or</span> <span class="ow">not</span> <span class="n">check_sha1</span><span class="p">(</span><span class="n">pretrained_file_path</span><span class="p">,</span> <span class="n">expected_file_hash</span><span class="p">):</span>
<span class="n">download</span><span class="p">(</span><span class="n">url</span><span class="p">,</span> <span class="n">downloaded_file_path</span><span class="p">,</span> <span class="n">sha1_hash</span><span class="o">=</span><span class="n">expected_downloaded_hash</span><span class="p">)</span>
<span class="n">ext</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">splitext</span><span class="p">(</span><span class="n">downloaded_file</span><span class="p">)[</span><span class="mi">1</span><span class="p">]</span>
<span class="k">if</span> <span class="n">ext</span> <span class="o">==</span> <span class="s1">'.zip'</span><span class="p">:</span>
<span class="k">with</span> <span class="n">zipfile</span><span class="o">.</span><span class="n">ZipFile</span><span class="p">(</span><span class="n">downloaded_file_path</span><span class="p">,</span> <span class="s1">'r'</span><span class="p">)</span> <span class="k">as</span> <span class="n">zf</span><span class="p">:</span>
<span class="n">zf</span><span class="o">.</span><span class="n">extractall</span><span class="p">(</span><span class="n">embedding_dir</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">ext</span> <span class="o">==</span> <span class="s1">'.gz'</span><span class="p">:</span>
<span class="k">with</span> <span class="n">tarfile</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">downloaded_file_path</span><span class="p">,</span> <span class="s1">'r:gz'</span><span class="p">)</span> <span class="k">as</span> <span class="n">tar</span><span class="p">:</span>
<span class="n">tar</span><span class="o">.</span><span class="n">extractall</span><span class="p">(</span><span class="n">path</span><span class="o">=</span><span class="n">embedding_dir</span><span class="p">)</span>
<span class="k">return</span> <span class="n">pretrained_file_path</span>
<span class="k">def</span> <span class="nf">_load_embedding</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pretrained_file_path</span><span class="p">,</span> <span class="n">elem_delim</span><span class="p">,</span> <span class="n">init_unknown_vec</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s1">'utf8'</span><span class="p">):</span>
<span class="sd">"""Load embedding vectors from the pre-trained token embedding file.</span>
<span class="sd"> For every unknown token, if its representation `self.unknown_token` is encountered in the</span>
<span class="sd"> pre-trained token embedding file, index 0 of `self.idx_to_vec` maps to the pre-trained token</span>
<span class="sd"> embedding vector loaded from the file; otherwise, index 0 of `self.idx_to_vec` maps to the</span>
<span class="sd"> text embedding vector initialized by `init_unknown_vec`.</span>
<span class="sd"> If a token is encountered multiple times in the pre-trained text embedding file, only the</span>
<span class="sd"> first-encountered token embedding vector will be loaded and the rest will be skipped.</span>
<span class="sd"> """</span>
<span class="n">pretrained_file_path</span> <span class="o">=</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">expanduser</span><span class="p">(</span><span class="n">pretrained_file_path</span><span class="p">)</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">isfile</span><span class="p">(</span><span class="n">pretrained_file_path</span><span class="p">):</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'`pretrained_file_path` must be a valid path to '</span>
<span class="s1">'the pre-trained token embedding file.'</span><span class="p">)</span>
<span class="n">logging</span><span class="o">.</span><span class="n">info</span><span class="p">(</span><span class="s1">'Loading pre-trained token embedding vectors from </span><span class="si">%s</span><span class="s1">'</span><span class="p">,</span> <span class="n">pretrained_file_path</span><span class="p">)</span>
<span class="n">vec_len</span> <span class="o">=</span> <span class="bp">None</span>
<span class="n">all_elems</span> <span class="o">=</span> <span class="p">[]</span>
<span class="n">tokens</span> <span class="o">=</span> <span class="nb">set</span><span class="p">()</span>
<span class="n">loaded_unknown_vec</span> <span class="o">=</span> <span class="bp">None</span>
<span class="n">line_num</span> <span class="o">=</span> <span class="mi">0</span>
<span class="k">with</span> <span class="n">io</span><span class="o">.</span><span class="n">open</span><span class="p">(</span><span class="n">pretrained_file_path</span><span class="p">,</span> <span class="s1">'r'</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="n">encoding</span><span class="p">)</span> <span class="k">as</span> <span class="n">f</span><span class="p">:</span>
<span class="k">for</span> <span class="n">line</span> <span class="ow">in</span> <span class="n">f</span><span class="p">:</span>
<span class="n">line_num</span> <span class="o">+=</span> <span class="mi">1</span>
<span class="n">elems</span> <span class="o">=</span> <span class="n">line</span><span class="o">.</span><span class="n">rstrip</span><span class="p">()</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="n">elem_delim</span><span class="p">)</span>
<span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">elems</span><span class="p">)</span> <span class="o">></span> <span class="mi">1</span><span class="p">,</span> <span class="s1">'At line </span><span class="si">%d</span><span class="s1"> of the pre-trained text embedding file: the '</span> \
<span class="s1">'data format of the pre-trained token embedding file </span><span class="si">%s</span><span class="s1"> '</span> \
<span class="s1">'is unexpected.'</span> <span class="o">%</span> <span class="p">(</span><span class="n">line_num</span><span class="p">,</span> <span class="n">pretrained_file_path</span><span class="p">)</span>
<span class="n">token</span><span class="p">,</span> <span class="n">elems</span> <span class="o">=</span> <span class="n">elems</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span> <span class="p">[</span><span class="nb">float</span><span class="p">(</span><span class="n">i</span><span class="p">)</span> <span class="k">for</span> <span class="n">i</span> <span class="ow">in</span> <span class="n">elems</span><span class="p">[</span><span class="mi">1</span><span class="p">:]]</span>
<span class="k">if</span> <span class="n">token</span> <span class="o">==</span> <span class="bp">self</span><span class="o">.</span><span class="n">unknown_token</span> <span class="ow">and</span> <span class="n">loaded_unknown_vec</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">loaded_unknown_vec</span> <span class="o">=</span> <span class="n">elems</span>
<span class="n">tokens</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">unknown_token</span><span class="p">)</span>
<span class="k">elif</span> <span class="n">token</span> <span class="ow">in</span> <span class="n">tokens</span><span class="p">:</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s1">'At line </span><span class="si">%d</span><span class="s1"> of the pre-trained token embedding file: the '</span>
<span class="s1">'embedding vector for token </span><span class="si">%s</span><span class="s1"> has been loaded and a duplicate '</span>
<span class="s1">'embedding for the same token is seen and skipped.'</span> <span class="o">%</span>
<span class="p">(</span><span class="n">line_num</span><span class="p">,</span> <span class="n">token</span><span class="p">))</span>
<span class="k">elif</span> <span class="nb">len</span><span class="p">(</span><span class="n">elems</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
<span class="n">warnings</span><span class="o">.</span><span class="n">warn</span><span class="p">(</span><span class="s1">'At line </span><span class="si">%d</span><span class="s1"> of the pre-trained text embedding file: token </span><span class="si">%s</span><span class="s1"> '</span>
<span class="s1">'with 1-dimensional vector </span><span class="si">%s</span><span class="s1"> is likely a header and is '</span>
<span class="s1">'skipped.'</span> <span class="o">%</span> <span class="p">(</span><span class="n">line_num</span><span class="p">,</span> <span class="n">token</span><span class="p">,</span> <span class="n">elems</span><span class="p">))</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">if</span> <span class="n">vec_len</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="n">vec_len</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="n">elems</span><span class="p">)</span>
<span class="c1"># Reserve a vector slot for the unknown token at the very beggining because</span>
<span class="c1"># the unknown index is 0.</span>
<span class="n">all_elems</span><span class="o">.</span><span class="n">extend</span><span class="p">([</span><span class="mi">0</span><span class="p">]</span> <span class="o">*</span> <span class="n">vec_len</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">assert</span> <span class="nb">len</span><span class="p">(</span><span class="n">elems</span><span class="p">)</span> <span class="o">==</span> <span class="n">vec_len</span><span class="p">,</span> \
<span class="s1">'At line </span><span class="si">%d</span><span class="s1"> of the pre-trained token embedding file: the dimension '</span> \
<span class="s1">'of token </span><span class="si">%s</span><span class="s1"> is </span><span class="si">%d</span><span class="s1"> but the dimension of previous tokens is </span><span class="si">%d</span><span class="s1">. '</span> \
<span class="s1">'Dimensions of all the tokens must be the same.'</span> \
<span class="o">%</span> <span class="p">(</span><span class="n">line_num</span><span class="p">,</span> <span class="n">token</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="n">elems</span><span class="p">),</span> <span class="n">vec_len</span><span class="p">)</span>
<span class="n">all_elems</span><span class="o">.</span><span class="n">extend</span><span class="p">(</span><span class="n">elems</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_idx_to_token</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="n">token</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_token_to_idx</span><span class="p">[</span><span class="n">token</span><span class="p">]</span> <span class="o">=</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">_idx_to_token</span><span class="p">)</span> <span class="o">-</span> <span class="mi">1</span>
<span class="n">tokens</span><span class="o">.</span><span class="n">add</span><span class="p">(</span><span class="n">token</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_vec_len</span> <span class="o">=</span> <span class="n">vec_len</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_idx_to_vec</span> <span class="o">=</span> <span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">all_elems</span><span class="p">)</span><span class="o">.</span><span class="n">reshape</span><span class="p">((</span><span class="o">-</span><span class="mi">1</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">vec_len</span><span class="p">))</span>
<span class="k">if</span> <span class="n">loaded_unknown_vec</span> <span class="ow">is</span> <span class="bp">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_idx_to_vec</span><span class="p">[</span><span class="n">C</span><span class="o">.</span><span class="n">UNKNOWN_IDX</span><span class="p">]</span> <span class="o">=</span> <span class="n">init_unknown_vec</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="bp">self</span><span class="o">.</span><span class="n">vec_len</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_idx_to_vec</span><span class="p">[</span><span class="n">C</span><span class="o">.</span><span class="n">UNKNOWN_IDX</span><span class="p">]</span> <span class="o">=</span> <span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">loaded_unknown_vec</span><span class="p">)</span>
<span class="k">def</span> <span class="nf">_index_tokens_from_vocabulary</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vocabulary</span><span class="p">):</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_token_to_idx</span> <span class="o">=</span> <span class="n">vocabulary</span><span class="o">.</span><span class="n">token_to_idx</span><span class="o">.</span><span class="n">copy</span><span class="p">()</span> \
<span class="k">if</span> <span class="n">vocabulary</span><span class="o">.</span><span class="n">token_to_idx</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span> <span class="k">else</span> <span class="bp">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_idx_to_token</span> <span class="o">=</span> <span class="n">vocabulary</span><span class="o">.</span><span class="n">idx_to_token</span><span class="p">[:]</span> \
<span class="k">if</span> <span class="n">vocabulary</span><span class="o">.</span><span class="n">idx_to_token</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span> <span class="k">else</span> <span class="bp">None</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_unknown_token</span> <span class="o">=</span> <span class="n">vocabulary</span><span class="o">.</span><span class="n">unknown_token</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_reserved_tokens</span> <span class="o">=</span> <span class="n">vocabulary</span><span class="o">.</span><span class="n">reserved_tokens</span><span class="p">[:]</span> \
<span class="k">if</span> <span class="n">vocabulary</span><span class="o">.</span><span class="n">reserved_tokens</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span> <span class="k">else</span> <span class="bp">None</span>
<span class="k">def</span> <span class="nf">_set_idx_to_vec_by_embeddings</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">token_embeddings</span><span class="p">,</span> <span class="n">vocab_len</span><span class="p">,</span> <span class="n">vocab_idx_to_token</span><span class="p">):</span>
<span class="sd">"""Sets the mapping between token indices and token embedding vectors.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> token_embeddings : instance or list `mxnet.contrib.text.embedding._TokenEmbedding`</span>
<span class="sd"> One or multiple pre-trained token embeddings to load. If it is a list of multiple</span>
<span class="sd"> embeddings, these embedding vectors will be concatenated for each token.</span>
<span class="sd"> vocab_len : int</span>
<span class="sd"> Length of vocabulary whose tokens are indexed in the token embedding.</span>
<span class="sd"> vocab_idx_to_token: list of str</span>
<span class="sd"> A list of indexed tokens in the vocabulary. These tokens are indexed in the token</span>
<span class="sd"> embedding.</span>
<span class="sd"> """</span>
<span class="n">new_vec_len</span> <span class="o">=</span> <span class="nb">sum</span><span class="p">(</span><span class="n">embed</span><span class="o">.</span><span class="n">vec_len</span> <span class="k">for</span> <span class="n">embed</span> <span class="ow">in</span> <span class="n">token_embeddings</span><span class="p">)</span>
<span class="n">new_idx_to_vec</span> <span class="o">=</span> <span class="n">nd</span><span class="o">.</span><span class="n">zeros</span><span class="p">(</span><span class="n">shape</span><span class="o">=</span><span class="p">(</span><span class="n">vocab_len</span><span class="p">,</span> <span class="n">new_vec_len</span><span class="p">))</span>
<span class="n">col_start</span> <span class="o">=</span> <span class="mi">0</span>
<span class="c1"># Concatenate all the embedding vectors in token_embeddings.</span>
<span class="k">for</span> <span class="n">embed</span> <span class="ow">in</span> <span class="n">token_embeddings</span><span class="p">:</span>
<span class="n">col_end</span> <span class="o">=</span> <span class="n">col_start</span> <span class="o">+</span> <span class="n">embed</span><span class="o">.</span><span class="n">vec_len</span>
<span class="c1"># Cancatenate vectors of the unknown token.</span>
<span class="n">new_idx_to_vec</span><span class="p">[</span><span class="mi">0</span><span class="p">,</span> <span class="n">col_start</span><span class="p">:</span><span class="n">col_end</span><span class="p">]</span> <span class="o">=</span> <span class="n">embed</span><span class="o">.</span><span class="n">idx_to_vec</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span>
<span class="n">new_idx_to_vec</span><span class="p">[</span><span class="mi">1</span><span class="p">:,</span> <span class="n">col_start</span><span class="p">:</span><span class="n">col_end</span><span class="p">]</span> <span class="o">=</span> <span class="n">embed</span><span class="o">.</span><span class="n">get_vecs_by_tokens</span><span class="p">(</span><span class="n">vocab_idx_to_token</span><span class="p">[</span><span class="mi">1</span><span class="p">:])</span>
<span class="n">col_start</span> <span class="o">=</span> <span class="n">col_end</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_vec_len</span> <span class="o">=</span> <span class="n">new_vec_len</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_idx_to_vec</span> <span class="o">=</span> <span class="n">new_idx_to_vec</span>
<span class="k">def</span> <span class="nf">_build_embedding_for_vocabulary</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vocabulary</span><span class="p">):</span>
<span class="k">if</span> <span class="n">vocabulary</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
<span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">vocabulary</span><span class="p">,</span> <span class="n">vocab</span><span class="o">.</span><span class="n">Vocabulary</span><span class="p">),</span> \
<span class="s1">'The argument `vocabulary` must be an instance of '</span> \
<span class="s1">'mxnet.contrib.text.vocab.Vocabulary.'</span>
<span class="c1"># Set _idx_to_vec so that indices of tokens from vocabulary are associated with the</span>
<span class="c1"># loaded token embedding vectors.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_set_idx_to_vec_by_embeddings</span><span class="p">([</span><span class="bp">self</span><span class="p">],</span> <span class="nb">len</span><span class="p">(</span><span class="n">vocabulary</span><span class="p">),</span> <span class="n">vocabulary</span><span class="o">.</span><span class="n">idx_to_token</span><span class="p">)</span>
<span class="c1"># Index tokens from vocabulary.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_index_tokens_from_vocabulary</span><span class="p">(</span><span class="n">vocabulary</span><span class="p">)</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">vec_len</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_vec_len</span>
<span class="nd">@property</span>
<span class="k">def</span> <span class="nf">idx_to_vec</span><span class="p">(</span><span class="bp">self</span><span class="p">):</span>
<span class="k">return</span> <span class="bp">self</span><span class="o">.</span><span class="n">_idx_to_vec</span>
<span class="k">def</span> <span class="nf">get_vecs_by_tokens</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tokens</span><span class="p">,</span> <span class="n">lower_case_backup</span><span class="o">=</span><span class="bp">False</span><span class="p">):</span>
<span class="sd">"""Look up embedding vectors of tokens.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> tokens : str or list of strs</span>
<span class="sd"> A token or a list of tokens.</span>
<span class="sd"> lower_case_backup : bool, default False</span>
<span class="sd"> If False, each token in the original case will be looked up; if True, each token in the</span>
<span class="sd"> original case will be looked up first, if not found in the keys of the property</span>
<span class="sd"> `token_to_idx`, the token in the lower case will be looked up.</span>
<span class="sd"> Returns</span>
<span class="sd"> -------</span>
<span class="sd"> mxnet.ndarray.NDArray:</span>
<span class="sd"> The embedding vector(s) of the token(s). According to numpy conventions, if `tokens` is</span>
<span class="sd"> a string, returns a 1-D NDArray of shape `self.vec_len`; if `tokens` is a list of</span>
<span class="sd"> strings, returns a 2-D NDArray of shape=(len(tokens), self.vec_len).</span>
<span class="sd"> """</span>
<span class="n">to_reduce</span> <span class="o">=</span> <span class="bp">False</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">tokens</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span>
<span class="n">tokens</span> <span class="o">=</span> <span class="p">[</span><span class="n">tokens</span><span class="p">]</span>
<span class="n">to_reduce</span> <span class="o">=</span> <span class="bp">True</span>
<span class="k">if</span> <span class="ow">not</span> <span class="n">lower_case_backup</span><span class="p">:</span>
<span class="n">indices</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">token_to_idx</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">token</span><span class="p">,</span> <span class="n">C</span><span class="o">.</span><span class="n">UNKNOWN_IDX</span><span class="p">)</span> <span class="k">for</span> <span class="n">token</span> <span class="ow">in</span> <span class="n">tokens</span><span class="p">]</span>
<span class="k">else</span><span class="p">:</span>
<span class="n">indices</span> <span class="o">=</span> <span class="p">[</span><span class="bp">self</span><span class="o">.</span><span class="n">token_to_idx</span><span class="p">[</span><span class="n">token</span><span class="p">]</span> <span class="k">if</span> <span class="n">token</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">token_to_idx</span>
<span class="k">else</span> <span class="bp">self</span><span class="o">.</span><span class="n">token_to_idx</span><span class="o">.</span><span class="n">get</span><span class="p">(</span><span class="n">token</span><span class="o">.</span><span class="n">lower</span><span class="p">(),</span> <span class="n">C</span><span class="o">.</span><span class="n">UNKNOWN_IDX</span><span class="p">)</span>
<span class="k">for</span> <span class="n">token</span> <span class="ow">in</span> <span class="n">tokens</span><span class="p">]</span>
<span class="n">vecs</span> <span class="o">=</span> <span class="n">nd</span><span class="o">.</span><span class="n">Embedding</span><span class="p">(</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">indices</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">idx_to_vec</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">idx_to_vec</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">0</span><span class="p">],</span>
<span class="bp">self</span><span class="o">.</span><span class="n">idx_to_vec</span><span class="o">.</span><span class="n">shape</span><span class="p">[</span><span class="mi">1</span><span class="p">])</span>
<span class="k">return</span> <span class="n">vecs</span><span class="p">[</span><span class="mi">0</span><span class="p">]</span> <span class="k">if</span> <span class="n">to_reduce</span> <span class="k">else</span> <span class="n">vecs</span>
<span class="k">def</span> <span class="nf">update_token_vectors</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tokens</span><span class="p">,</span> <span class="n">new_vectors</span><span class="p">):</span>
<span class="sd">"""Updates embedding vectors for tokens.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> tokens : str or a list of strs</span>
<span class="sd"> A token or a list of tokens whose embedding vector are to be updated.</span>
<span class="sd"> new_vectors : mxnet.ndarray.NDArray</span>
<span class="sd"> An NDArray to be assigned to the embedding vectors of `tokens`. Its length must be equal</span>
<span class="sd"> to the number of `tokens` and its width must be equal to the dimension of embeddings of</span>
<span class="sd"> the glossary. If `tokens` is a singleton, it must be 1-D or 2-D. If `tokens` is a list</span>
<span class="sd"> of multiple strings, it must be 2-D.</span>
<span class="sd"> """</span>
<span class="k">assert</span> <span class="bp">self</span><span class="o">.</span><span class="n">idx_to_vec</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">,</span> <span class="s1">'The property `idx_to_vec` has not been properly set.'</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">tokens</span><span class="p">,</span> <span class="nb">list</span><span class="p">)</span> <span class="ow">or</span> <span class="nb">len</span><span class="p">(</span><span class="n">tokens</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
<span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">new_vectors</span><span class="p">,</span> <span class="n">nd</span><span class="o">.</span><span class="n">NDArray</span><span class="p">)</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">new_vectors</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="ow">in</span> <span class="p">[</span><span class="mi">1</span><span class="p">,</span> <span class="mi">2</span><span class="p">],</span> \
<span class="s1">'`new_vectors` must be a 1-D or 2-D NDArray if `tokens` is a singleton.'</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">tokens</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span>
<span class="n">tokens</span> <span class="o">=</span> <span class="p">[</span><span class="n">tokens</span><span class="p">]</span>
<span class="k">if</span> <span class="nb">len</span><span class="p">(</span><span class="n">new_vectors</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">==</span> <span class="mi">1</span><span class="p">:</span>
<span class="n">new_vectors</span> <span class="o">=</span> <span class="n">new_vectors</span><span class="o">.</span><span class="n">expand_dims</span><span class="p">(</span><span class="mi">0</span><span class="p">)</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">new_vectors</span><span class="p">,</span> <span class="n">nd</span><span class="o">.</span><span class="n">NDArray</span><span class="p">)</span> <span class="ow">and</span> <span class="nb">len</span><span class="p">(</span><span class="n">new_vectors</span><span class="o">.</span><span class="n">shape</span><span class="p">)</span> <span class="o">==</span> <span class="mi">2</span><span class="p">,</span> \
<span class="s1">'`new_vectors` must be a 2-D NDArray if `tokens` is a list of multiple strings.'</span>
<span class="k">assert</span> <span class="n">new_vectors</span><span class="o">.</span><span class="n">shape</span> <span class="o">==</span> <span class="p">(</span><span class="nb">len</span><span class="p">(</span><span class="n">tokens</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">vec_len</span><span class="p">),</span> \
<span class="s1">'The length of new_vectors must be equal to the number of tokens and the width of'</span> \
<span class="s1">'new_vectors must be equal to the dimension of embeddings of the glossary.'</span>
<span class="n">indices</span> <span class="o">=</span> <span class="p">[]</span>
<span class="k">for</span> <span class="n">token</span> <span class="ow">in</span> <span class="n">tokens</span><span class="p">:</span>
<span class="k">if</span> <span class="n">token</span> <span class="ow">in</span> <span class="bp">self</span><span class="o">.</span><span class="n">token_to_idx</span><span class="p">:</span>
<span class="n">indices</span><span class="o">.</span><span class="n">append</span><span class="p">(</span><span class="bp">self</span><span class="o">.</span><span class="n">token_to_idx</span><span class="p">[</span><span class="n">token</span><span class="p">])</span>
<span class="k">else</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">ValueError</span><span class="p">(</span><span class="s1">'Token </span><span class="si">%s</span><span class="s1"> is unknown. To update the embedding vector for an '</span>
<span class="s1">'unknown token, please specify it explicitly as the '</span>
<span class="s1">'`unknown_token` </span><span class="si">%s</span><span class="s1"> in `tokens`. This is to avoid unintended '</span>
<span class="s1">'updates.'</span> <span class="o">%</span> <span class="p">(</span><span class="n">token</span><span class="p">,</span> <span class="bp">self</span><span class="o">.</span><span class="n">idx_to_token</span><span class="p">[</span><span class="n">C</span><span class="o">.</span><span class="n">UNKNOWN_IDX</span><span class="p">]))</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_idx_to_vec</span><span class="p">[</span><span class="n">nd</span><span class="o">.</span><span class="n">array</span><span class="p">(</span><span class="n">indices</span><span class="p">)]</span> <span class="o">=</span> <span class="n">new_vectors</span>
<span class="nd">@classmethod</span>
<span class="k">def</span> <span class="nf">_check_pretrained_file_names</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">pretrained_file_name</span><span class="p">):</span>
<span class="sd">"""Checks if a pre-trained token embedding file name is valid.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> pretrained_file_name : str</span>
<span class="sd"> The pre-trained token embedding file.</span>
<span class="sd"> """</span>
<span class="n">embedding_name</span> <span class="o">=</span> <span class="bp">cls</span><span class="o">.</span><span class="vm">__name__</span><span class="o">.</span><span class="n">lower</span><span class="p">()</span>
<span class="k">if</span> <span class="n">pretrained_file_name</span> <span class="ow">not</span> <span class="ow">in</span> <span class="bp">cls</span><span class="o">.</span><span class="n">pretrained_file_name_sha1</span><span class="p">:</span>
<span class="k">raise</span> <span class="ne">KeyError</span><span class="p">(</span><span class="s1">'Cannot find pretrained file </span><span class="si">%s</span><span class="s1"> for token embedding </span><span class="si">%s</span><span class="s1">. Valid '</span>
<span class="s1">'pretrained files for embedding </span><span class="si">%s</span><span class="s1">: </span><span class="si">%s</span><span class="s1">'</span> <span class="o">%</span>
<span class="p">(</span><span class="n">pretrained_file_name</span><span class="p">,</span> <span class="n">embedding_name</span><span class="p">,</span> <span class="n">embedding_name</span><span class="p">,</span>
<span class="s1">', '</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="bp">cls</span><span class="o">.</span><span class="n">pretrained_file_name_sha1</span><span class="o">.</span><span class="n">keys</span><span class="p">())))</span>
<span class="nd">@register</span>
<div class="viewcode-block" id="GloVe"><a class="viewcode-back" href="../../../../api/python/contrib/text.html#mxnet.contrib.text.embedding.GloVe">[docs]</a><span class="k">class</span> <span class="nc">GloVe</span><span class="p">(</span><span class="n">_TokenEmbedding</span><span class="p">):</span>
<span class="sd">"""The GloVe word embedding.</span>
<span class="sd"> GloVe is an unsupervised learning algorithm for obtaining vector representations for words.</span>
<span class="sd"> Training is performed on aggregated global word-word co-occurrence statistics from a corpus, and</span>
<span class="sd"> the resulting representations showcase interesting linear substructures of the word vector</span>
<span class="sd"> space. (Source from https://nlp.stanford.edu/projects/glove/)</span>
<span class="sd"> Reference:</span>
<span class="sd"> GloVe: Global Vectors for Word Representation.</span>
<span class="sd"> Jeffrey Pennington, Richard Socher, and Christopher D. Manning.</span>
<span class="sd"> https://nlp.stanford.edu/pubs/glove.pdf</span>
<span class="sd"> Website:</span>
<span class="sd"> https://nlp.stanford.edu/projects/glove/</span>
<span class="sd"> To get the updated URLs to the externally hosted pre-trained token embedding</span>
<span class="sd"> files, visit https://nlp.stanford.edu/projects/glove/</span>
<span class="sd"> License for pre-trained embeddings:</span>
<span class="sd"> https://opendatacommons.org/licenses/pddl/</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> pretrained_file_name : str, default 'glove.840B.300d.txt'</span>
<span class="sd"> The name of the pre-trained token embedding file.</span>
<span class="sd"> embedding_root : str, default os.path.join('~', '.mxnet', 'embeddings')</span>
<span class="sd"> The root directory for storing embedding-related files.</span>
<span class="sd"> init_unknown_vec : callback</span>
<span class="sd"> The callback used to initialize the embedding vector for the unknown token.</span>
<span class="sd"> vocabulary : :class:`~mxnet.contrib.text.vocab.Vocabulary`, default None</span>
<span class="sd"> It contains the tokens to index. Each indexed token will be associated with the loaded</span>
<span class="sd"> embedding vectors, such as loaded from a pre-trained token embedding file. If None, all the</span>
<span class="sd"> tokens from the loaded embedding vectors, such as loaded from a pre-trained token embedding</span>
<span class="sd"> file, will be indexed.</span>
<span class="sd"> Properties</span>
<span class="sd"> ----------</span>
<span class="sd"> token_to_idx : dict mapping str to int</span>
<span class="sd"> A dict mapping each token to its index integer.</span>
<span class="sd"> idx_to_token : list of strs</span>
<span class="sd"> A list of indexed tokens where the list indices and the token indices are aligned.</span>
<span class="sd"> unknown_token : hashable object</span>
<span class="sd"> The representation for any unknown token. In other words, any unknown token will be indexed</span>
<span class="sd"> as the same representation.</span>
<span class="sd"> reserved_tokens : list of strs or None</span>
<span class="sd"> A list of reserved tokens that will always be indexed.</span>
<span class="sd"> vec_len : int</span>
<span class="sd"> The length of the embedding vector for each token.</span>
<span class="sd"> idx_to_vec : mxnet.ndarray.NDArray</span>
<span class="sd"> For all the indexed tokens in this embedding, this NDArray maps each token's index to an</span>
<span class="sd"> embedding vector. The largest valid index maps to the initialized embedding vector for every</span>
<span class="sd"> reserved token, such as an unknown_token token and a padding token.</span>
<span class="sd"> """</span>
<span class="c1"># Map a pre-trained token embedding archive file and its SHA-1 hash.</span>
<span class="n">pretrained_archive_name_sha1</span> <span class="o">=</span> <span class="n">C</span><span class="o">.</span><span class="n">GLOVE_PRETRAINED_FILE_SHA1</span>
<span class="c1"># Map a pre-trained token embedding file and its SHA-1 hash.</span>
<span class="n">pretrained_file_name_sha1</span> <span class="o">=</span> <span class="n">C</span><span class="o">.</span><span class="n">GLOVE_PRETRAINED_ARCHIVE_SHA1</span>
<span class="nd">@classmethod</span>
<span class="k">def</span> <span class="nf">_get_download_file_name</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">pretrained_file_name</span><span class="p">):</span>
<span class="c1"># Map a pre-trained embedding file to its archive to download.</span>
<span class="n">src_archive</span> <span class="o">=</span> <span class="p">{</span><span class="n">archive</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'.'</span><span class="p">)[</span><span class="mi">1</span><span class="p">]:</span> <span class="n">archive</span> <span class="k">for</span> <span class="n">archive</span> <span class="ow">in</span>
<span class="n">GloVe</span><span class="o">.</span><span class="n">pretrained_archive_name_sha1</span><span class="o">.</span><span class="n">keys</span><span class="p">()}</span>
<span class="n">archive</span> <span class="o">=</span> <span class="n">src_archive</span><span class="p">[</span><span class="n">pretrained_file_name</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'.'</span><span class="p">)[</span><span class="mi">1</span><span class="p">]]</span>
<span class="k">return</span> <span class="n">archive</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pretrained_file_name</span><span class="o">=</span><span class="s1">'glove.840B.300d.txt'</span><span class="p">,</span>
<span class="n">embedding_root</span><span class="o">=</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="s1">'~'</span><span class="p">,</span> <span class="s1">'.mxnet'</span><span class="p">,</span> <span class="s1">'embeddings'</span><span class="p">),</span>
<span class="n">init_unknown_vec</span><span class="o">=</span><span class="n">nd</span><span class="o">.</span><span class="n">zeros</span><span class="p">,</span> <span class="n">vocabulary</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="n">GloVe</span><span class="o">.</span><span class="n">_check_pretrained_file_names</span><span class="p">(</span><span class="n">pretrained_file_name</span><span class="p">)</span>
<span class="nb">super</span><span class="p">(</span><span class="n">GloVe</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="n">pretrained_file_path</span> <span class="o">=</span> <span class="n">GloVe</span><span class="o">.</span><span class="n">_get_pretrained_file</span><span class="p">(</span><span class="n">embedding_root</span><span class="p">,</span> <span class="n">pretrained_file_name</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_load_embedding</span><span class="p">(</span><span class="n">pretrained_file_path</span><span class="p">,</span> <span class="s1">' '</span><span class="p">,</span> <span class="n">init_unknown_vec</span><span class="p">)</span>
<span class="k">if</span> <span class="n">vocabulary</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_build_embedding_for_vocabulary</span><span class="p">(</span><span class="n">vocabulary</span><span class="p">)</span></div>
<span class="nd">@register</span>
<div class="viewcode-block" id="FastText"><a class="viewcode-back" href="../../../../api/python/contrib/text.html#mxnet.contrib.text.embedding.FastText">[docs]</a><span class="k">class</span> <span class="nc">FastText</span><span class="p">(</span><span class="n">_TokenEmbedding</span><span class="p">):</span>
<span class="sd">"""The fastText word embedding.</span>
<span class="sd"> FastText is an open-source, free, lightweight library that allows users to learn text</span>
<span class="sd"> representations and text classifiers. It works on standard, generic hardware. Models can later</span>
<span class="sd"> be reduced in size to even fit on mobile devices. (Source from https://fasttext.cc/)</span>
<span class="sd"> References:</span>
<span class="sd"> Enriching Word Vectors with Subword Information.</span>
<span class="sd"> Piotr Bojanowski, Edouard Grave, Armand Joulin, and Tomas Mikolov.</span>
<span class="sd"> https://arxiv.org/abs/1607.04606</span>
<span class="sd"> Bag of Tricks for Efficient Text Classification.</span>
<span class="sd"> Armand Joulin, Edouard Grave, Piotr Bojanowski, and Tomas Mikolov.</span>
<span class="sd"> https://arxiv.org/abs/1607.01759</span>
<span class="sd"> FastText.zip: Compressing text classification models.</span>
<span class="sd"> Armand Joulin, Edouard Grave, Piotr Bojanowski, Matthijs Douze, Herve Jegou,</span>
<span class="sd"> and Tomas Mikolov.</span>
<span class="sd"> https://arxiv.org/abs/1612.03651</span>
<span class="sd"> For 'wiki.multi' embeddings:</span>
<span class="sd"> Word Translation Without Parallel Data</span>
<span class="sd"> Alexis Conneau, Guillaume Lample, Marc'Aurelio Ranzato, Ludovic Denoyer,</span>
<span class="sd"> and Herve Jegou.</span>
<span class="sd"> https://arxiv.org/abs/1710.04087</span>
<span class="sd"> Website:</span>
<span class="sd"> https://fasttext.cc/</span>
<span class="sd"> To get the updated URLs to the externally hosted pre-trained token embedding files, visit</span>
<span class="sd"> https://github.com/facebookresearch/fastText/blob/master/pretrained-vectors.md</span>
<span class="sd"> License for pre-trained embeddings:</span>
<span class="sd"> https://creativecommons.org/licenses/by-sa/3.0/</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> pretrained_file_name : str, default 'wiki.en.vec'</span>
<span class="sd"> The name of the pre-trained token embedding file.</span>
<span class="sd"> embedding_root : str, default os.path.join('~', '.mxnet', 'embeddings')</span>
<span class="sd"> The root directory for storing embedding-related files.</span>
<span class="sd"> init_unknown_vec : callback</span>
<span class="sd"> The callback used to initialize the embedding vector for the unknown token.</span>
<span class="sd"> vocabulary : :class:`~mxnet.contrib.text.vocab.Vocabulary`, default None</span>
<span class="sd"> It contains the tokens to index. Each indexed token will be associated with the loaded</span>
<span class="sd"> embedding vectors, such as loaded from a pre-trained token embedding file. If None, all the</span>
<span class="sd"> tokens from the loaded embedding vectors, such as loaded from a pre-trained token embedding</span>
<span class="sd"> file, will be indexed.</span>
<span class="sd"> Properties</span>
<span class="sd"> ----------</span>
<span class="sd"> token_to_idx : dict mapping str to int</span>
<span class="sd"> A dict mapping each token to its index integer.</span>
<span class="sd"> idx_to_token : list of strs</span>
<span class="sd"> A list of indexed tokens where the list indices and the token indices are aligned.</span>
<span class="sd"> unknown_token : hashable object</span>
<span class="sd"> The representation for any unknown token. In other words, any unknown token will be indexed</span>
<span class="sd"> as the same representation.</span>
<span class="sd"> reserved_tokens : list of strs or None</span>
<span class="sd"> A list of reserved tokens that will always be indexed.</span>
<span class="sd"> vec_len : int</span>
<span class="sd"> The length of the embedding vector for each token.</span>
<span class="sd"> idx_to_vec : mxnet.ndarray.NDArray</span>
<span class="sd"> For all the indexed tokens in this embedding, this NDArray maps each token's index to an</span>
<span class="sd"> embedding vector. The largest valid index maps to the initialized embedding vector for every</span>
<span class="sd"> reserved token, such as an unknown_token token and a padding token.</span>
<span class="sd"> """</span>
<span class="c1"># Map a pre-trained token embedding archive file and its SHA-1 hash.</span>
<span class="n">pretrained_archive_name_sha1</span> <span class="o">=</span> <span class="n">C</span><span class="o">.</span><span class="n">FAST_TEXT_ARCHIVE_SHA1</span>
<span class="c1"># Map a pre-trained token embedding file and its SHA-1 hash.</span>
<span class="n">pretrained_file_name_sha1</span> <span class="o">=</span> <span class="n">C</span><span class="o">.</span><span class="n">FAST_TEXT_FILE_SHA1</span>
<span class="nd">@classmethod</span>
<span class="k">def</span> <span class="nf">_get_download_file_name</span><span class="p">(</span><span class="bp">cls</span><span class="p">,</span> <span class="n">pretrained_file_name</span><span class="p">):</span>
<span class="c1"># Map a pre-trained embedding file to its archive to download.</span>
<span class="k">return</span> <span class="s1">'.'</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="n">pretrained_file_name</span><span class="o">.</span><span class="n">split</span><span class="p">(</span><span class="s1">'.'</span><span class="p">)[:</span><span class="o">-</span><span class="mi">1</span><span class="p">])</span><span class="o">+</span><span class="s1">'.zip'</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pretrained_file_name</span><span class="o">=</span><span class="s1">'wiki.simple.vec'</span><span class="p">,</span>
<span class="n">embedding_root</span><span class="o">=</span><span class="n">os</span><span class="o">.</span><span class="n">path</span><span class="o">.</span><span class="n">join</span><span class="p">(</span><span class="s1">'~'</span><span class="p">,</span> <span class="s1">'.mxnet'</span><span class="p">,</span> <span class="s1">'embeddings'</span><span class="p">),</span>
<span class="n">init_unknown_vec</span><span class="o">=</span><span class="n">nd</span><span class="o">.</span><span class="n">zeros</span><span class="p">,</span> <span class="n">vocabulary</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="n">FastText</span><span class="o">.</span><span class="n">_check_pretrained_file_names</span><span class="p">(</span><span class="n">pretrained_file_name</span><span class="p">)</span>
<span class="nb">super</span><span class="p">(</span><span class="n">FastText</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="n">pretrained_file_path</span> <span class="o">=</span> <span class="n">FastText</span><span class="o">.</span><span class="n">_get_pretrained_file</span><span class="p">(</span><span class="n">embedding_root</span><span class="p">,</span> <span class="n">pretrained_file_name</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_load_embedding</span><span class="p">(</span><span class="n">pretrained_file_path</span><span class="p">,</span> <span class="s1">' '</span><span class="p">,</span> <span class="n">init_unknown_vec</span><span class="p">)</span>
<span class="k">if</span> <span class="n">vocabulary</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_build_embedding_for_vocabulary</span><span class="p">(</span><span class="n">vocabulary</span><span class="p">)</span></div>
<div class="viewcode-block" id="CustomEmbedding"><a class="viewcode-back" href="../../../../api/python/contrib/text.html#mxnet.contrib.text.embedding.CustomEmbedding">[docs]</a><span class="k">class</span> <span class="nc">CustomEmbedding</span><span class="p">(</span><span class="n">_TokenEmbedding</span><span class="p">):</span>
<span class="sd">"""User-defined token embedding.</span>
<span class="sd"> This is to load embedding vectors from a user-defined pre-trained text embedding file.</span>
<span class="sd"> Denote by '[ed]' the argument `elem_delim`. Denote by [v_ij] the j-th element of the token</span>
<span class="sd"> embedding vector for [token_i], the expected format of a custom pre-trained token embedding file</span>
<span class="sd"> is:</span>
<span class="sd"> '[token_1][ed][v_11][ed][v_12][ed]...[ed][v_1k]\\\\n[token_2][ed][v_21][ed][v_22][ed]...[ed]</span>
<span class="sd"> [v_2k]\\\\n...'</span>
<span class="sd"> where k is the length of the embedding vector `vec_len`.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> pretrained_file_path : str</span>
<span class="sd"> The path to the custom pre-trained token embedding file.</span>
<span class="sd"> elem_delim : str, default ' '</span>
<span class="sd"> The delimiter for splitting a token and every embedding vector element value on the same</span>
<span class="sd"> line of the custom pre-trained token embedding file.</span>
<span class="sd"> encoding : str, default 'utf8'</span>
<span class="sd"> The encoding scheme for reading the custom pre-trained token embedding file.</span>
<span class="sd"> init_unknown_vec : callback</span>
<span class="sd"> The callback used to initialize the embedding vector for the unknown token.</span>
<span class="sd"> vocabulary : :class:`~mxnet.contrib.text.vocab.Vocabulary`, default None</span>
<span class="sd"> It contains the tokens to index. Each indexed token will be associated with the loaded</span>
<span class="sd"> embedding vectors, such as loaded from a pre-trained token embedding file. If None, all the</span>
<span class="sd"> tokens from the loaded embedding vectors, such as loaded from a pre-trained token embedding</span>
<span class="sd"> file, will be indexed.</span>
<span class="sd"> Properties</span>
<span class="sd"> ----------</span>
<span class="sd"> token_to_idx : dict mapping str to int</span>
<span class="sd"> A dict mapping each token to its index integer.</span>
<span class="sd"> idx_to_token : list of strs</span>
<span class="sd"> A list of indexed tokens where the list indices and the token indices are aligned.</span>
<span class="sd"> unknown_token : hashable object</span>
<span class="sd"> The representation for any unknown token. In other words, any unknown token will be indexed</span>
<span class="sd"> as the same representation.</span>
<span class="sd"> reserved_tokens : list of strs or None</span>
<span class="sd"> A list of reserved tokens that will always be indexed.</span>
<span class="sd"> vec_len : int</span>
<span class="sd"> The length of the embedding vector for each token.</span>
<span class="sd"> idx_to_vec : mxnet.ndarray.NDArray</span>
<span class="sd"> For all the indexed tokens in this embedding, this NDArray maps each token's index to an</span>
<span class="sd"> embedding vector. The largest valid index maps to the initialized embedding vector for every</span>
<span class="sd"> reserved token, such as an unknown_token token and a padding token.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">pretrained_file_path</span><span class="p">,</span> <span class="n">elem_delim</span><span class="o">=</span><span class="s1">' '</span><span class="p">,</span> <span class="n">encoding</span><span class="o">=</span><span class="s1">'utf8'</span><span class="p">,</span>
<span class="n">init_unknown_vec</span><span class="o">=</span><span class="n">nd</span><span class="o">.</span><span class="n">zeros</span><span class="p">,</span> <span class="n">vocabulary</span><span class="o">=</span><span class="bp">None</span><span class="p">,</span> <span class="o">**</span><span class="n">kwargs</span><span class="p">):</span>
<span class="nb">super</span><span class="p">(</span><span class="n">CustomEmbedding</span><span class="p">,</span> <span class="bp">self</span><span class="p">)</span><span class="o">.</span><span class="fm">__init__</span><span class="p">(</span><span class="o">**</span><span class="n">kwargs</span><span class="p">)</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_load_embedding</span><span class="p">(</span><span class="n">pretrained_file_path</span><span class="p">,</span> <span class="n">elem_delim</span><span class="p">,</span> <span class="n">init_unknown_vec</span><span class="p">,</span> <span class="n">encoding</span><span class="p">)</span>
<span class="k">if</span> <span class="n">vocabulary</span> <span class="ow">is</span> <span class="ow">not</span> <span class="bp">None</span><span class="p">:</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_build_embedding_for_vocabulary</span><span class="p">(</span><span class="n">vocabulary</span><span class="p">)</span></div>
<div class="viewcode-block" id="CompositeEmbedding"><a class="viewcode-back" href="../../../../api/python/contrib/text.html#mxnet.contrib.text.embedding.CompositeEmbedding">[docs]</a><span class="k">class</span> <span class="nc">CompositeEmbedding</span><span class="p">(</span><span class="n">_TokenEmbedding</span><span class="p">):</span>
<span class="sd">"""Composite token embeddings.</span>
<span class="sd"> For each indexed token in a vocabulary, multiple embedding vectors, such as concatenated</span>
<span class="sd"> multiple embedding vectors, will be associated with it. Such embedding vectors can be loaded</span>
<span class="sd"> from externally hosted or custom pre-trained token embedding files, such as via token embedding</span>
<span class="sd"> instances.</span>
<span class="sd"> Parameters</span>
<span class="sd"> ----------</span>
<span class="sd"> vocabulary : :class:`~mxnet.contrib.text.vocab.Vocabulary`</span>
<span class="sd"> For each indexed token in a vocabulary, multiple embedding vectors, such as concatenated</span>
<span class="sd"> multiple embedding vectors, will be associated with it.</span>
<span class="sd"> token_embeddings : instance or list of `mxnet.contrib.text.embedding._TokenEmbedding`</span>
<span class="sd"> One or multiple pre-trained token embeddings to load. If it is a list of multiple</span>
<span class="sd"> embeddings, these embedding vectors will be concatenated for each token.</span>
<span class="sd"> Properties</span>
<span class="sd"> ----------</span>
<span class="sd"> token_to_idx : dict mapping str to int</span>
<span class="sd"> A dict mapping each token to its index integer.</span>
<span class="sd"> idx_to_token : list of strs</span>
<span class="sd"> A list of indexed tokens where the list indices and the token indices are aligned.</span>
<span class="sd"> unknown_token : hashable object</span>
<span class="sd"> The representation for any unknown token. In other words, any unknown token will be indexed</span>
<span class="sd"> as the same representation.</span>
<span class="sd"> reserved_tokens : list of strs or None</span>
<span class="sd"> A list of reserved tokens that will always be indexed.</span>
<span class="sd"> vec_len : int</span>
<span class="sd"> The length of the embedding vector for each token.</span>
<span class="sd"> idx_to_vec : mxnet.ndarray.NDArray</span>
<span class="sd"> For all the indexed tokens in this embedding, this NDArray maps each token's index to an</span>
<span class="sd"> embedding vector. The largest valid index maps to the initialized embedding vector for every</span>
<span class="sd"> reserved token, such as an unknown_token token and a padding token.</span>
<span class="sd"> """</span>
<span class="k">def</span> <span class="fm">__init__</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">vocabulary</span><span class="p">,</span> <span class="n">token_embeddings</span><span class="p">):</span>
<span class="c1"># Sanity checks.</span>
<span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">vocabulary</span><span class="p">,</span> <span class="n">vocab</span><span class="o">.</span><span class="n">Vocabulary</span><span class="p">),</span> \
<span class="s1">'The argument `vocabulary` must be an instance of '</span> \
<span class="s1">'mxnet.contrib.text.indexer.Vocabulary.'</span>
<span class="k">if</span> <span class="ow">not</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">token_embeddings</span><span class="p">,</span> <span class="nb">list</span><span class="p">):</span>
<span class="n">token_embeddings</span> <span class="o">=</span> <span class="p">[</span><span class="n">token_embeddings</span><span class="p">]</span>
<span class="k">for</span> <span class="n">embed</span> <span class="ow">in</span> <span class="n">token_embeddings</span><span class="p">:</span>
<span class="k">assert</span> <span class="nb">isinstance</span><span class="p">(</span><span class="n">embed</span><span class="p">,</span> <span class="n">_TokenEmbedding</span><span class="p">),</span> \
<span class="s1">'The argument `token_embeddings` must be an instance or a list of instances '</span> \
<span class="s1">'of `mxnet.contrib.text.embedding.TextEmbedding` whose embedding vectors will be'</span> \
<span class="s1">'loaded or concatenated-then-loaded to map to the indexed tokens.'</span>
<span class="c1"># Index tokens.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_index_tokens_from_vocabulary</span><span class="p">(</span><span class="n">vocabulary</span><span class="p">)</span>
<span class="c1"># Set _idx_to_vec so that indices of tokens from keys of `counter` are associated with token</span>
<span class="c1"># embedding vectors from `token_embeddings`.</span>
<span class="bp">self</span><span class="o">.</span><span class="n">_set_idx_to_vec_by_embeddings</span><span class="p">(</span><span class="n">token_embeddings</span><span class="p">,</span> <span class="nb">len</span><span class="p">(</span><span class="bp">self</span><span class="p">),</span> <span class="bp">self</span><span class="o">.</span><span class="n">idx_to_token</span><span class="p">)</span></div>
</pre></div>
</div>
</div>
<div aria-label="main navigation" class="sphinxsidebar rightsidebar" role="navigation">
<div class="sphinxsidebarwrapper">
</div>
</div>
</div><div class="footer">
<div class="section-disclaimer">
<div class="container">
<div>
<img height="60" src="https://raw.githubusercontent.com/dmlc/web-data/master/mxnet/image/apache_incubator_logo.png"/>
<p>
Apache MXNet is an effort undergoing incubation at The Apache Software Foundation (ASF), <strong>sponsored by the <i>Apache Incubator</i></strong>. Incubation is required of all newly accepted projects until a further review indicates that the infrastructure, communications, and decision making process have stabilized in a manner consistent with other successful ASF projects. While incubation status is not necessarily a reflection of the completeness or stability of the code, it does indicate that the project has yet to be fully endorsed by the ASF.
</p>
<p>
"Copyright © 2017-2018, The Apache Software Foundation
Apache MXNet, MXNet, Apache, the Apache feather, and the Apache MXNet project logo are either registered trademarks or trademarks of the Apache Software Foundation."
</p>
</div>
</div>
</div>
</div> <!-- pagename != index -->
</div>
<script crossorigin="anonymous" integrity="sha384-0mSbJDEHialfmuBBQP6A4Qrprq5OVfW37PRR3j5ELqxss1yVqOtnepnHVP9aJ7xS" src="https://maxcdn.bootstrapcdn.com/bootstrap/3.3.6/js/bootstrap.min.js"></script>
<script src="../../../../_static/js/sidebar.js" type="text/javascript"></script>
<script src="../../../../_static/js/search.js" type="text/javascript"></script>
<script src="../../../../_static/js/navbar.js" type="text/javascript"></script>
<script src="../../../../_static/js/clipboard.min.js" type="text/javascript"></script>
<script src="../../../../_static/js/copycode.js" type="text/javascript"></script>
<script src="../../../../_static/js/page.js" type="text/javascript"></script>
<script type="text/javascript">
$('body').ready(function () {
$('body').css('visibility', 'visible');
});
</script>
</body>
</html>