added UCI corpus docs

piskvorky · Mar 8, 2012 · 28d887b · 28d887b
1 parent ebe07e7
commit 28d887b
Show file tree

Hide file tree

Showing 55 changed files with 401 additions and 75 deletions.
diff --git a/docs/_sources/apiref.txt b/docs/_sources/apiref.txt
@@ -18,6 +18,7 @@ Modules:
     corpora/svmlightcorpus
     corpora/wikicorpus
     corpora/textcorpus
+    corpora/ucicorpus
     corpora/indexedcorpus
     models/ldamodel
     models/lsimodel

diff --git a/docs/_sources/corpora/ucicorpus.txt b/docs/_sources/corpora/ucicorpus.txt
@@ -0,0 +1,8 @@
+:mod:`corpora.ucicorpus` -- Corpus in UCI bag-of-words format
+==============================================================================================================
+
+.. automodule:: gensim.corpora.ucicorpus
+    :synopsis: Corpus in University of California, Irvine (UCI) bag-of-words format
+    :members:
+    :inherited-members:
+
diff --git a/docs/_sources/index.txt b/docs/_sources/index.txt
@@ -44,7 +44,7 @@ Quick Reference Example
 
 
 .. admonition:: What's new?
-
+   * 8 Mar 2012: release 0.8.4: `Hierarchical Dirichlet Process <http://radimrehurek.com/gensim/models/hdpmodel.html>`_
    * 2 Dec 2011: bug-fix release 0.8.3 out; `CHANGELOG <https://github.com/piskvorky/gensim/blob/develop/CHANGELOG.txt>`_
    * 1 Dec 2011: released `simserver <http://pypi.python.org/pypi/simserver>`_, a Python document similarity server based on gensim
 

diff --git a/docs/about.html b/docs/about.html
@@ -16,7 +16,7 @@
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '',
-        VERSION:     '0.8.3',
+        VERSION:     '0.8.4',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true

diff --git a/docs/apiref.html b/docs/apiref.html
@@ -16,7 +16,7 @@
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '',
-        VERSION:     '0.8.3',
+        VERSION:     '0.8.4',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true
@@ -126,6 +126,7 @@ <h3>Quick search</h3>
 <li class="toctree-l1"><a class="reference internal" href="corpora/svmlightcorpus.html"><tt class="docutils literal"><span class="pre">corpora.svmlightcorpus</span></tt> &#8211; Corpus in SVMlight format</a></li>
 <li class="toctree-l1"><a class="reference internal" href="corpora/wikicorpus.html"><tt class="docutils literal"><span class="pre">corpora.wikicorpus</span></tt> &#8211; Corpus from a Wikipedia dump</a></li>
 <li class="toctree-l1"><a class="reference internal" href="corpora/textcorpus.html"><tt class="docutils literal"><span class="pre">corpora.textcorpus</span></tt> &#8211; Building corpora with dictionaries</a></li>
+<li class="toctree-l1"><a class="reference internal" href="corpora/ucicorpus.html"><tt class="docutils literal"><span class="pre">corpora.ucicorpus</span></tt> &#8211; Corpus in UCI bag-of-words format</a></li>
 <li class="toctree-l1"><a class="reference internal" href="corpora/indexedcorpus.html"><tt class="docutils literal"><span class="pre">corpora.indexedcorpus</span></tt> &#8211; Random access to corpus documents</a></li>
 <li class="toctree-l1"><a class="reference internal" href="models/ldamodel.html"><tt class="docutils literal"><span class="pre">models.ldamodel</span></tt> &#8211; Latent Dirichlet Allocation</a></li>
 <li class="toctree-l1"><a class="reference internal" href="models/lsimodel.html"><tt class="docutils literal"><span class="pre">models.lsimodel</span></tt> &#8211; Latent Semantic Indexing</a></li>

diff --git a/docs/changes_080.html b/docs/changes_080.html
@@ -16,7 +16,7 @@
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '',
-        VERSION:     '0.8.3',
+        VERSION:     '0.8.4',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true

diff --git a/docs/corpora/bleicorpus.html b/docs/corpora/bleicorpus.html
@@ -16,7 +16,7 @@
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../',
-        VERSION:     '0.8.3',
+        VERSION:     '0.8.4',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true

diff --git a/docs/corpora/corpora.html b/docs/corpora/corpora.html
@@ -16,7 +16,7 @@
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../',
-        VERSION:     '0.8.3',
+        VERSION:     '0.8.4',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true

diff --git a/docs/corpora/dictionary.html b/docs/corpora/dictionary.html
@@ -16,7 +16,7 @@
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../',
-        VERSION:     '0.8.3',
+        VERSION:     '0.8.4',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true

diff --git a/docs/corpora/indexedcorpus.html b/docs/corpora/indexedcorpus.html
@@ -16,7 +16,7 @@
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../',
-        VERSION:     '0.8.3',
+        VERSION:     '0.8.4',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true
@@ -29,7 +29,7 @@
     <link rel="top" title="gensim" href="../index.html" />
     <link rel="up" title="API Reference" href="../apiref.html" />
     <link rel="next" title="models.ldamodel – Latent Dirichlet Allocation" href="../models/ldamodel.html" />
-    <link rel="prev" title="corpora.textcorpus – Building corpora with dictionaries" href="textcorpus.html" />
+    <link rel="prev" title="corpora.ucicorpus – Corpus in University of California, Irvine (UCI) bag-of-words format" href="ucicorpus.html" />
 
 
 	<!-- twitter search widget
@@ -68,7 +68,7 @@ <h3>Navigation</h3>
           <a href="../models/ldamodel.html" title="models.ldamodel – Latent Dirichlet Allocation"
              accesskey="N">next</a> |</li>
         <li class="right" >
-          <a href="textcorpus.html" title="corpora.textcorpus – Building corpora with dictionaries"
+          <a href="ucicorpus.html" title="corpora.ucicorpus – Corpus in University of California, Irvine (UCI) bag-of-words format"
              accesskey="P">previous</a> |</li>
         <li><a href="../index.html">Gensim home</a>|&nbsp;</li>
         <li><a href="../tutorial.html">Tutorials</a>|&nbsp;</li>
@@ -84,8 +84,8 @@ <h3>Navigation</h3>
       <div class="sphinxsidebar">
         <div class="sphinxsidebarwrapper">
   <h4>Previous topic</h4>
-  <p class="topless"><a href="textcorpus.html"
-                        title="previous chapter"><tt class="docutils literal"><span class="pre">corpora.textcorpus</span></tt> &#8211; Building corpora with dictionaries</a></p>
+  <p class="topless"><a href="ucicorpus.html"
+                        title="previous chapter"><tt class="docutils literal"><span class="pre">corpora.ucicorpus</span></tt> &#8211; Corpus in University of California, Irvine (UCI) bag-of-words format</a></p>
   <h4>Next topic</h4>
   <p class="topless"><a href="../models/ldamodel.html"
                         title="next chapter"><tt class="docutils literal"><span class="pre">models.ldamodel</span></tt> &#8211; Latent Dirichlet Allocation</a></p>
@@ -222,7 +222,7 @@ <h3>Navigation</h3>
           <a href="../models/ldamodel.html" title="models.ldamodel – Latent Dirichlet Allocation"
              >next</a> |</li>
         <li class="right" >
-          <a href="textcorpus.html" title="corpora.textcorpus – Building corpora with dictionaries"
+          <a href="ucicorpus.html" title="corpora.ucicorpus – Corpus in University of California, Irvine (UCI) bag-of-words format"
              >previous</a> |</li>
         <li><a href="../index.html">Gensim home</a>|&nbsp;</li>
         <li><a href="../tutorial.html">Tutorials</a>|&nbsp;</li>

diff --git a/docs/corpora/lowcorpus.html b/docs/corpora/lowcorpus.html
@@ -16,7 +16,7 @@
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../',
-        VERSION:     '0.8.3',
+        VERSION:     '0.8.4',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true
@@ -118,7 +118,7 @@ <h3>Quick search</h3>
 <p>Corpus in GibbsLda++ format of List-Of-Words.</p>
 <dl class="class">
 <dt id="gensim.corpora.lowcorpus.LowCorpus">
-<em class="property">class </em><tt class="descclassname">gensim.corpora.lowcorpus.</tt><tt class="descname">LowCorpus</tt><big>(</big><em>fname</em>, <em>id2word=None</em>, <em>line2words=&lt;function split_on_space at 0x27a21f0&gt;</em><big>)</big><a class="headerlink" href="#gensim.corpora.lowcorpus.LowCorpus" title="Permalink to this definition">¶</a></dt>
+<em class="property">class </em><tt class="descclassname">gensim.corpora.lowcorpus.</tt><tt class="descname">LowCorpus</tt><big>(</big><em>fname</em>, <em>id2word=None</em>, <em>line2words=&lt;function split_on_space at 0x27a21b0&gt;</em><big>)</big><a class="headerlink" href="#gensim.corpora.lowcorpus.LowCorpus" title="Permalink to this definition">¶</a></dt>
 <dd><p>List_Of_Words corpus handles input in GibbsLda++ format.</p>
 <p>Quoting <a class="reference external" href="http://gibbslda.sourceforge.net/#3.2_Input_Data_Format">http://gibbslda.sourceforge.net/#3.2_Input_Data_Format</a>:</p>
 <div class="highlight-python"><pre>Both data for training/estimating the model and new data (i.e., previously

diff --git a/docs/corpora/mmcorpus.html b/docs/corpora/mmcorpus.html
@@ -16,7 +16,7 @@
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../',
-        VERSION:     '0.8.3',
+        VERSION:     '0.8.4',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true

diff --git a/docs/corpora/svmlightcorpus.html b/docs/corpora/svmlightcorpus.html
@@ -16,7 +16,7 @@
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../',
-        VERSION:     '0.8.3',
+        VERSION:     '0.8.4',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true

diff --git a/docs/corpora/textcorpus.html b/docs/corpora/textcorpus.html
@@ -16,7 +16,7 @@
     <script type="text/javascript">
       var DOCUMENTATION_OPTIONS = {
         URL_ROOT:    '../',
-        VERSION:     '0.8.3',
+        VERSION:     '0.8.4',
         COLLAPSE_INDEX: false,
         FILE_SUFFIX: '.html',
         HAS_SOURCE:  true
@@ -28,7 +28,7 @@
     <link rel="author" title="About these documents" href="../about.html" />
     <link rel="top" title="gensim" href="../index.html" />
     <link rel="up" title="API Reference" href="../apiref.html" />
-    <link rel="next" title="corpora.indexedcorpus – Random access to corpus documents" href="indexedcorpus.html" />
+    <link rel="next" title="corpora.ucicorpus – Corpus in University of California, Irvine (UCI) bag-of-words format" href="ucicorpus.html" />
     <link rel="prev" title="corpora.wikicorpus – Corpus from a Wikipedia dump" href="wikicorpus.html" />
 
 
@@ -65,7 +65,7 @@ <h3>Navigation</h3>
           <a href="../py-modindex.html" title="Python Module Index"
              >modules</a> |</li>
         <li class="right" >
-          <a href="indexedcorpus.html" title="corpora.indexedcorpus – Random access to corpus documents"
+          <a href="ucicorpus.html" title="corpora.ucicorpus – Corpus in University of California, Irvine (UCI) bag-of-words format"
              accesskey="N">next</a> |</li>
         <li class="right" >
           <a href="wikicorpus.html" title="corpora.wikicorpus – Corpus from a Wikipedia dump"
@@ -87,8 +87,8 @@ <h4>Previous topic</h4>
   <p class="topless"><a href="wikicorpus.html"
                         title="previous chapter"><tt class="docutils literal docutils literal"><span class="pre">corpora.wikicorpus</span></tt> &#8211; Corpus from a Wikipedia dump</a></p>
   <h4>Next topic</h4>
-  <p class="topless"><a href="indexedcorpus.html"
-                        title="next chapter"><tt class="docutils literal docutils literal"><span class="pre">corpora.indexedcorpus</span></tt> &#8211; Random access to corpus documents</a></p>
+  <p class="topless"><a href="ucicorpus.html"
+                        title="next chapter"><tt class="docutils literal docutils literal"><span class="pre">corpora.ucicorpus</span></tt> &#8211; Corpus in University of California, Irvine (UCI) bag-of-words format</a></p>
 <div id="searchbox" style="display: none">
   <h3>Quick search</h3>
     <form class="search" action="../search.html" method="get">
@@ -213,7 +213,7 @@ <h3>Navigation</h3>
           <a href="../py-modindex.html" title="Python Module Index"
              >modules</a> |</li>
         <li class="right" >
-          <a href="indexedcorpus.html" title="corpora.indexedcorpus – Random access to corpus documents"
+          <a href="ucicorpus.html" title="corpora.ucicorpus – Corpus in University of California, Irvine (UCI) bag-of-words format"
              >next</a> |</li>
         <li class="right" >
           <a href="wikicorpus.html" title="corpora.wikicorpus – Corpus from a Wikipedia dump"