/doc/tagger.extras-module.html
HTML | 290 lines | 253 code | 14 blank | 23 comment | 0 complexity | 22069097a1db4fb09438a100c8d2947a MD5 | raw file
- <?xml version="1.0" encoding="ascii"?>
- <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
- "DTD/xhtml1-transitional.dtd">
- <html xmlns="http://www.w3.org/1999/xhtml" xml:lang="en" lang="en">
- <head>
- <title>tagger.extras</title>
- <link rel="stylesheet" href="epydoc.css" type="text/css" />
- <script type="text/javascript" src="epydoc.js"></script>
- </head>
- <body bgcolor="white" text="black" link="blue" vlink="#204080"
- alink="#204080">
- <!-- ==================== NAVIGATION BAR ==================== -->
- <table class="navbar" border="0" width="100%" cellpadding="0"
- bgcolor="#a0c0ff" cellspacing="0">
- <tr valign="middle">
- <!-- Tree link -->
- <th> <a
- href="module-tree.html">Trees</a> </th>
- <!-- Index link -->
- <th> <a
- href="identifier-index.html">Indices</a> </th>
- <!-- Help link -->
- <th> <a
- href="help.html">Help</a> </th>
- <!-- Project homepage -->
- <th class="navbar" align="right" width="100%">
- <table border="0" cellpadding="0" cellspacing="0">
- <tr><th class="navbar" align="center"
- ><a class="navbar" target="_top" href="http://github.com/apresta/tagger">tagger</a></th>
- </tr></table></th>
- </tr>
- </table>
- <table width="100%" cellpadding="0" cellspacing="0">
- <tr valign="top">
- <td width="100%">
- <span class="breadcrumbs">
- Package tagger ::
- Module extras
- </span>
- </td>
- <td>
- <table cellpadding="0" cellspacing="0">
- <!-- hide/show private -->
- <tr><td align="right"><span class="options">[<a href="javascript:void(0);" class="privatelink"
- onclick="toggle_private();">hide private</a>]</span></td></tr>
- <tr><td align="right"><span class="options"
- >[<a href="frames.html" target="_top">frames</a
- >] | <a href="tagger.extras-module.html"
- target="_top">no frames</a>]</span></td></tr>
- </table>
- </td>
- </tr>
- </table>
- <!-- ==================== MODULE DESCRIPTION ==================== -->
- <h1 class="epydoc">Module extras</h1><p class="nomargin-top"><span class="codelink"><a href="tagger.extras-pysrc.html">source code</a></span></p>
- <!-- ==================== CLASSES ==================== -->
- <a name="section-Classes"></a>
- <table class="summary" border="1" cellpadding="3"
- cellspacing="0" width="100%" bgcolor="white">
- <tr bgcolor="#70b0f0" class="table-header">
- <td colspan="2" class="table-header">
- <table border="0" cellpadding="0" cellspacing="0" width="100%">
- <tr valign="top">
- <td align="left"><span class="table-header">Classes</span></td>
- <td align="right" valign="top"
- ><span class="options">[<a href="#section-Classes"
- class="privatelink" onclick="toggle_private();"
- >hide private</a>]</span></td>
- </tr>
- </table>
- </td>
- </tr>
- <tr>
- <td width="15%" align="right" valign="top" class="summary">
- <span class="summary-type"> </span>
- </td><td class="summary">
- <a href="tagger.extras.UnicodeReader-class.html" class="summary-name">UnicodeReader</a><br />
- Reader subclass that converts Unicode strings to a close ASCII
- representation
- </td>
- </tr>
- <tr>
- <td width="15%" align="right" valign="top" class="summary">
- <span class="summary-type"> </span>
- </td><td class="summary">
- <a href="tagger.extras.HTMLReader-class.html" class="summary-name">HTMLReader</a><br />
- Reader subclass that can parse HTML code from the input
- </td>
- </tr>
- <tr>
- <td width="15%" align="right" valign="top" class="summary">
- <span class="summary-type"> </span>
- </td><td class="summary">
- <a href="tagger.extras.SimpleReader-class.html" class="summary-name">SimpleReader</a><br />
- Reader subclass that doesn't perform any advanced analysis of the
- text
- </td>
- </tr>
- <tr>
- <td width="15%" align="right" valign="top" class="summary">
- <span class="summary-type"> </span>
- </td><td class="summary">
- <a href="tagger.extras.FastStemmer-class.html" class="summary-name">FastStemmer</a><br />
- Stemmer subclass that uses a much faster, but less correct
- algorithm
- </td>
- </tr>
- <tr>
- <td width="15%" align="right" valign="top" class="summary">
- <span class="summary-type"> </span>
- </td><td class="summary">
- <a href="tagger.extras.NaiveRater-class.html" class="summary-name">NaiveRater</a><br />
- Rater subclass that jusk ranks single-word tags by their frequency
- and weight
- </td>
- </tr>
- </table>
- <!-- ==================== FUNCTIONS ==================== -->
- <a name="section-Functions"></a>
- <table class="summary" border="1" cellpadding="3"
- cellspacing="0" width="100%" bgcolor="white">
- <tr bgcolor="#70b0f0" class="table-header">
- <td colspan="2" class="table-header">
- <table border="0" cellpadding="0" cellspacing="0" width="100%">
- <tr valign="top">
- <td align="left"><span class="table-header">Functions</span></td>
- <td align="right" valign="top"
- ><span class="options">[<a href="#section-Functions"
- class="privatelink" onclick="toggle_private();"
- >hide private</a>]</span></td>
- </tr>
- </table>
- </td>
- </tr>
- <tr>
- <td width="15%" align="right" valign="top" class="summary">
- <span class="summary-type"> </span>
- </td><td class="summary">
- <table width="100%" cellpadding="0" cellspacing="0" border="0">
- <tr>
- <td><span class="summary-sig"><a href="tagger.extras-module.html#build_dict_from_nltk" class="summary-sig-name">build_dict_from_nltk</a>(<span class="summary-sig-arg">output_file</span>,
- <span class="summary-sig-arg">corpus</span>=<span class="summary-sig-default">None</span>,
- <span class="summary-sig-arg">stopwords</span>=<span class="summary-sig-default">None</span>,
- <span class="summary-sig-arg">stemmer</span>=<span class="summary-sig-default">Stemmer()</span>,
- <span class="summary-sig-arg">measure</span>=<span class="summary-sig-default"><code class="variable-quote">'</code><code class="variable-string">IDF</code><code class="variable-quote">'</code></span>,
- <span class="summary-sig-arg">verbose</span>=<span class="summary-sig-default">False</span>)</span></td>
- <td align="right" valign="top">
- <span class="codelink"><a href="tagger.extras-pysrc.html#build_dict_from_nltk">source code</a></span>
-
- </td>
- </tr>
- </table>
-
- </td>
- </tr>
- </table>
- <!-- ==================== VARIABLES ==================== -->
- <a name="section-Variables"></a>
- <table class="summary" border="1" cellpadding="3"
- cellspacing="0" width="100%" bgcolor="white">
- <tr bgcolor="#70b0f0" class="table-header">
- <td colspan="2" class="table-header">
- <table border="0" cellpadding="0" cellspacing="0" width="100%">
- <tr valign="top">
- <td align="left"><span class="table-header">Variables</span></td>
- <td align="right" valign="top"
- ><span class="options">[<a href="#section-Variables"
- class="privatelink" onclick="toggle_private();"
- >hide private</a>]</span></td>
- </tr>
- </table>
- </td>
- </tr>
- <tr>
- <td width="15%" align="right" valign="top" class="summary">
- <span class="summary-type"> </span>
- </td><td class="summary">
- <a name="__package__"></a><span class="summary-name">__package__</span> = <code title="'tagger'"><code class="variable-quote">'</code><code class="variable-string">tagger</code><code class="variable-quote">'</code></code>
- </td>
- </tr>
- </table>
- <!-- ==================== FUNCTION DETAILS ==================== -->
- <a name="section-FunctionDetails"></a>
- <table class="details" border="1" cellpadding="3"
- cellspacing="0" width="100%" bgcolor="white">
- <tr bgcolor="#70b0f0" class="table-header">
- <td colspan="2" class="table-header">
- <table border="0" cellpadding="0" cellspacing="0" width="100%">
- <tr valign="top">
- <td align="left"><span class="table-header">Function Details</span></td>
- <td align="right" valign="top"
- ><span class="options">[<a href="#section-FunctionDetails"
- class="privatelink" onclick="toggle_private();"
- >hide private</a>]</span></td>
- </tr>
- </table>
- </td>
- </tr>
- </table>
- <a name="build_dict_from_nltk"></a>
- <div>
- <table class="details" border="1" cellpadding="3"
- cellspacing="0" width="100%" bgcolor="white">
- <tr><td>
- <table width="100%" cellpadding="0" cellspacing="0" border="0">
- <tr valign="top"><td>
- <h3 class="epydoc"><span class="sig"><span class="sig-name">build_dict_from_nltk</span>(<span class="sig-arg">output_file</span>,
- <span class="sig-arg">corpus</span>=<span class="sig-default">None</span>,
- <span class="sig-arg">stopwords</span>=<span class="sig-default">None</span>,
- <span class="sig-arg">stemmer</span>=<span class="sig-default">Stemmer()</span>,
- <span class="sig-arg">measure</span>=<span class="sig-default"><code class="variable-quote">'</code><code class="variable-string">IDF</code><code class="variable-quote">'</code></span>,
- <span class="sig-arg">verbose</span>=<span class="sig-default">False</span>)</span>
- </h3>
- </td><td align="right" valign="top"
- ><span class="codelink"><a href="tagger.extras-pysrc.html#build_dict_from_nltk">source code</a></span>
- </td>
- </tr></table>
-
-
- <dl class="fields">
- <dt>Parameters:</dt>
- <dd><ul class="nomargin-top">
- <li><strong class="pname"><code>output_file</code></strong> - the name of the file where the dictionary should be saved</li>
- <li><strong class="pname"><code>corpus</code></strong> - the NLTK corpus to use (defaults to nltk.corpus.reuters)</li>
- <li><strong class="pname"><code>stopwords</code></strong> - a list of (not stemmed) stopwords (defaults to
- nltk.corpus.reuters.words('stopwords'))</li>
- <li><strong class="pname"><code>stemmer</code></strong> - the <a href="tagger.tagger.Stemmer-class.html"
- class="link">Stemmer</a> object to be used</li>
- <li><strong class="pname"><code>measure</code></strong> - the measure used to compute the weights ('IDF' i.e. 'inverse
- document frequency' or 'ICF' i.e. 'inverse collection frequency';
- defaults to 'IDF')</li>
- <li><strong class="pname"><code>verbose</code></strong> - whether information on the progress should be printed on screen</li>
- </ul></dd>
- </dl>
- </td></tr></table>
- </div>
- <br />
- <!-- ==================== NAVIGATION BAR ==================== -->
- <table class="navbar" border="0" width="100%" cellpadding="0"
- bgcolor="#a0c0ff" cellspacing="0">
- <tr valign="middle">
- <!-- Tree link -->
- <th> <a
- href="module-tree.html">Trees</a> </th>
- <!-- Index link -->
- <th> <a
- href="identifier-index.html">Indices</a> </th>
- <!-- Help link -->
- <th> <a
- href="help.html">Help</a> </th>
- <!-- Project homepage -->
- <th class="navbar" align="right" width="100%">
- <table border="0" cellpadding="0" cellspacing="0">
- <tr><th class="navbar" align="center"
- ><a class="navbar" target="_top" href="http://github.com/apresta/tagger">tagger</a></th>
- </tr></table></th>
- </tr>
- </table>
- <table border="0" cellpadding="0" cellspacing="0" width="100%%">
- <tr>
- <td align="left" class="footer">
- Generated by Epydoc 3.0.1 on Wed Jun 8 01:57:42 2011
- </td>
- <td align="right" class="footer">
- <a target="mainFrame" href="http://epydoc.sourceforge.net"
- >http://epydoc.sourceforge.net</a>
- </td>
- </tr>
- </table>
- <script type="text/javascript">
- <!--
- // Private objects are initially displayed (because if
- // javascript is turned off then we want them to be
- // visible); but by default, we want to hide them. So hide
- // them unless we have a cookie that says to show them.
- checkCookie();
- // -->
- </script>
- </body>
- </html>