mahout-commits mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From sro...@apache.org
Subject svn commit: r1243022 [31/38] - in /mahout/site/new_website: ./ MAHOUT/ MAHOUT/2010/ MAHOUT/2010/09/ MAHOUT/2010/09/14/ MAHOUT/2011/ MAHOUT/2011/10/ MAHOUT/2011/10/21/ MAHOUT/books-tutorials-and-talks.data/ MAHOUT/books-tutorials-talks.data/ MAHOUT/book...
Date Sat, 11 Feb 2012 10:22:31 GMT
Added: mahout/site/new_website/MAHOUT/using-mahout-with-python-via-jpype.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/using-mahout-with-python-via-jpype.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/using-mahout-with-python-via-jpype.html (added)
+++ mahout/site/new_website/MAHOUT/using-mahout-with-python-via-jpype.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,348 @@
+
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<HTML>
+  <HEAD>
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/space.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/master.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/wiki-content.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/abs.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/menu.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/menu-ie.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/tables.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/panels.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/master-ie.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/renderer-macros.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/content-types.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/login.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/information-macros.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/layout-macros.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/default-theme.css">
+    <LINK type="text/css" rel="stylesheet" href="resources/space.css">
+    <STYLE type="text/css">
+      .footer {
+        background-image:      url('https://cwiki.apache.org/confluence/images/border/border_bottom.gif');
+        background-repeat:     repeat-x;
+        background-position:   left top;
+        padding-top:           4px;
+        color:                 #666;
+      }
+    </STYLE>
+    <SCRIPT type="text/javascript" language="javascript">
+      var hide = null;
+      var show = null;
+      var children = null;
+
+      function init() {
+        /* Search form initialization */
+        var form = document.forms['search'];
+        if (form != null) {
+          form.elements['domains'].value = location.hostname;
+          form.elements['sitesearch'].value = location.hostname;
+        }
+
+        /* Children initialization */
+        hide = document.getElementById('hide');
+        show = document.getElementById('show');
+        children = document.all != null ?
+                   document.all['children'] :
+                   document.getElementById('children');
+        if (children != null) {
+          children.style.display = 'none';
+          show.style.display = 'inline';
+          hide.style.display = 'none';
+        }
+      }
+
+      function showChildren() {
+        children.style.display = 'block';
+        show.style.display = 'none';
+        hide.style.display = 'inline';
+      }
+
+      function hideChildren() {
+        children.style.display = 'none';
+        show.style.display = 'inline';
+        hide.style.display = 'none';
+      }
+    </SCRIPT>
+    <TITLE>Using Mahout with Python via JPype</TITLE>
+  <META http-equiv="Content-Type" content="text/html;charset=UTF-8"></HEAD>
+  <BODY onload="init()">
+    <TABLE border="0" cellpadding="2" cellspacing="0" width="100%">
+      <TR class="topBar">
+        <TD align="left" valign="middle" class="topBarDiv" align="left" nowrap="">
+          &nbsp;<A href="mahout-wiki.html" title="Apache Mahout">Apache Mahout</A>&nbsp;&gt;&nbsp;<A href="mahout-wiki.html" title="Mahout Wiki">Mahout Wiki</A>&nbsp;&gt;&nbsp;<A href="quickstart.html" title="Quickstart">Quickstart</A>&nbsp;&gt;&nbsp;<A href="" title="Using Mahout with Python via JPype">Using Mahout with Python via JPype</A>
+        </TD>
+        <TD align="right" valign="middle" nowrap="">
+          <FORM name="search" action="http://www.google.com/search" method="get">
+            <INPUT type="hidden" name="ie" value="UTF-8">
+            <INPUT type="hidden" name="oe" value="UTF-8">
+            <INPUT type="hidden" name="domains" value="">
+            <INPUT type="hidden" name="sitesearch" value="">
+            <INPUT type="text" name="q" maxlength="255" value="">        
+            <INPUT type="submit" name="btnG" value="Google Search">
+          </FORM>
+        </TD>
+      </TR> 
+    </TABLE>
+
+    <DIV id="PageContent">
+      <DIV class="pageheader" style="padding: 6px 0px 0px 0px;">
+        <!-- We'll enable this once we figure out how to access (and save) the logo resource -->
+        <!--img src="/wiki/images/confluence_logo.gif" style="float: left; margin: 4px 4px 4px 10px;" border="0"-->
+        <DIV style="margin: 0px 10px 0px 10px" class="smalltext">Apache Mahout</DIV>
+        <DIV style="margin: 0px 10px 8px 10px" class="pagetitle">Using Mahout with Python via JPype</DIV>
+
+        <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+          <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=25203890">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/notep_16.gif" height="16" width="16" border="0" align="absmiddle" title="Edit Page"></A>
+            <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=25203890">Edit Page</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/listpages.action?key=MAHOUT">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/browse_space.gif" height="16" width="16" border="0" align="absmiddle" title="Browse Space"></A>
+            <A href="https://cwiki.apache.org/confluence/pages/listpages.action?key=MAHOUT">Browse Space</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=25203890">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/add_page_16.gif" height="16" width="16" border="0" align="absmiddle" title="Add Page"></A>
+          <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=25203890">Add Page</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=25203890">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/add_blogentry_16.gif" height="16" width="16" border="0" align="absmiddle" title="Add News"></A>
+          <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=25203890">Add News</A>
+        </DIV>
+      </DIV>
+
+      <DIV class="pagecontent">
+        <DIV class="wiki-content">
+          <H1><A name="UsingMahoutwithPythonviaJPype-overview"></A>overview</H1>
+<P>This tutorial provides some sample code illustrating how we can read and write sequence files containing Mahout vectors from Python using JPype. This tutorial is intended for people who want to use Python for analyzing and plotting Mahout data. Using Mahout from Python turns out to be quite easy.</P>
+
+<P>This tutorial concerns the use of cPython (cython) as opposed to Jython.<BR>
+JPython wasn't an option for me, because  (to the best of my knowledge) JPython doesn't work with Python extensions numpy, matplotlib, or h5py which I rely on heavily.</P>
+
+<P>The instructions below explain how to setup a python script to read and write the output of Mahout clustering.</P>
+
+<P>You will first need to download and install the JPype package for python.</P>
+
+<P>The first step to setting up JPype is determining the path to the dynamic library for the jvm ; on linux this will be a .so file on and on windows it will be a .dll.</P>
+
+<P>In your python script, create a global variable with the path to this dll</P>
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">jvmlib=<SPAN class="code-quote">&quot;/usr/java/jdk1.6.0_23/jre/lib/amd64/server/libjvm.so&quot;</SPAN>
+</PRE>
+</DIV></DIV>
+
+<P>Next we need to figure out how we need to set the classpath for mahout. The easiest way to do this is to edit the script in &quot;bin/mahout&quot; to print out the classpath. Add the line &quot;echo $CLASSPATH&quot; to the script somewhere after the comment &quot;run it&quot; (this is line 195 or so). Execute the script to print out the classpath.  Copy this output and paste it into a variable in your python script. The result for me looks like the following</P>
+
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">classpath=<SPAN class="code-quote">&quot;/usr/local/programs/svn_mahout/conf::/usr/java/jdk1.6.0_23/lib/tools.jar:/usr/local/programs/svn_mahout/mahout\-*.jar:/usr/local/programs/svn_mahout/core/target/mahout-core-0.5-SNAPSHOT-job.jar:/usr/local/programs/svn_mahout/examples/target/mahout-examples-0.5-SNAPSHOT-job.jar:/usr/local/programs/svn_mahout/lib/*.jar:/usr/local/programs/svn_mahout/examples/target/dependency/cglib-nodep-2.2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/commons-beanutils-1.7.0.jar:/usr/local/programs/svn_mahout/examples/target/dependency/commons-cli-1.2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/commons-cli-2.0-mahout.jar:/usr/local/programs/svn_mahout/examples/target/dependency/commons-codec-1.3.jar:/usr/local/programs/svn_mahout/examples/target/dependency/commons-collections-3.2.1.jar:/usr/local/programs/svn_mahout/examples/target/dependency/commons-dbcp-1.2.2.jar:/usr/local/programs/svn_mahout
 /examples/target/dependency/commons-digester-1.7.jar:/usr/local/programs/svn_mahout/examples/target/dependency/commons-httpclient-3.1.jar:/usr/local/programs/svn_mahout/examples/target/dependency/commons-lang-2.4.jar:/usr/local/programs/svn_mahout/examples/target/dependency/commons-logging-1.1.1.jar:/usr/local/programs/svn_mahout/examples/target/dependency/commons-math-1.2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/commons-pool-1.4.jar:/usr/local/programs/svn_mahout/examples/target/dependency/easymock-2.5.2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/easymockclassextension-2.5.2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/google-collections-1.0-rc2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/gson-1.3.jar:/usr/local/programs/svn_mahout/examples/target/dependency/guava-r03.jar:/usr/local/programs/svn_mahout/examples/target/dependency/hadoop-core-0.20.2.jar:/usr/local/programs/svn_mahout/examples/target/de
 pendency/hbase-0.20.0.jar:/usr/local/programs/svn_mahout/examples/target/dependency/jets3t-0.7.1.jar:/usr/local/programs/svn_mahout/examples/target/dependency/junit-4.7.jar:/usr/local/programs/svn_mahout/examples/target/dependency/lucene-analyzers-3.0.2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/lucene-benchmark-3.0.2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/lucene-core-3.0.2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/lucene-demos-3.0.2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/lucene-highlighter-3.0.2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/lucene-memory-3.0.2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/lucene-wikipedia-3.0.2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/mahout-collections-1.0.jar:/usr/local/programs/svn_mahout/examples/target/dependency/mahout-core-0.5-SNAPSHOT.jar:/usr/local/programs/svn_mahout/examples/target/dependency/m
 ahout-core-0.5-SNAPSHOT-tests.jar:/usr/local/programs/svn_mahout/examples/target/dependency/mahout-math-0.5-SNAPSHOT.jar:/usr/local/programs/svn_mahout/examples/target/dependency/mahout-math-0.5-SNAPSHOT-tests.jar:/usr/local/programs/svn_mahout/examples/target/dependency/mahout-utils-0.5-SNAPSHOT.jar:/usr/local/programs/svn_mahout/examples/target/dependency/objenesis-1.2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/slf4j-api-1.6.0.jar:/usr/local/programs/svn_mahout/examples/target/dependency/slf4j-jcl-1.6.0.jar:/usr/local/programs/svn_mahout/examples/target/dependency/uncommons-maths-1.2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/watchmaker-framework-0.6.2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/watchmaker-swing-0.6.2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/xml-apis-1.0.b2.jar:/usr/local/programs/svn_mahout/examples/target/dependency/xpp3_min-1.1.4c.jar:/usr/local/programs/svn_mahout/examples/tar
 get/dependency/xstream-1.3.1.jar&quot;</SPAN>
+</PRE>
+</DIV></DIV>
+
+<P>Now we can create a function to start the jvm in python using jype</P>
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">from jpype <SPAN class="code-keyword">import</SPAN> *
+jvm=None
+def start_jpype():
+global jvm
+<SPAN class="code-keyword">if</SPAN> (jvm is None):
+cpopt=<SPAN class="code-quote">&quot;-Djava.class.path={cp}&quot;</SPAN>.format(cp=classpath)
+startJVM(jvmlib,<SPAN class="code-quote">&quot;-ea&quot;</SPAN>,cpopt)
+jvm=<SPAN class="code-quote">&quot;started&quot;</SPAN>
+</PRE>
+</DIV></DIV>
+
+
+<H1><A name="UsingMahoutwithPythonviaJPype-WritingNamedVectorstoSequenceFilesfromPython"></A>Writing Named Vectors to Sequence Files from Python</H1>
+<P>We can now use JPype to create sequence files which will contain vectors to be used by Mahout for kmeans. The example below is a function which creates vectors from two Gaussian distributions with unit variance.</P>
+
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+def create_inputs(ifile,*args,**param):
+ &quot;&quot;&quot;Create a sequence file containing some normally distributed
+        ifile - path to the sequence file to create
+ &quot;&quot;&quot;
+ 
+ #matrix of the cluster means
+ cmeans=np.array([[1,1],[-1,-1]],np.<SPAN class="code-object">int</SPAN>)
+ 
+ nperc=30  #number of points per cluster
+ 
+ vecs=[]
+ 
+ vnames=[]
+ <SPAN class="code-keyword">for</SPAN> cind in range(cmeans.shape[0]):
+  pts=np.random.randn(nperc,2)
+  pts=pts+cmeans[cind,:].reshape([1,cmeans.shape[1]])
+  vecs.append(pts)
+ 
+  #names <SPAN class="code-keyword">for</SPAN> the vectors
+  #names are just the points with an index
+  #we <SPAN class="code-keyword">do</SPAN> <SPAN class="code-keyword">this</SPAN> so we can validate by cross-refencing the name with the vector
+  vn=np.empty(nperc,dtype=(np.str,30))
+  <SPAN class="code-keyword">for</SPAN> row in range(nperc):
+   vn[row]=<SPAN class="code-quote">&quot;c&quot;</SPAN>+str(cind)+<SPAN class="code-quote">&quot;_&quot;</SPAN>+pts[row,0].astype((np.str,4))+<SPAN class="code-quote">&quot;_&quot;</SPAN>+pts[row,1].astype((np.str,4))
+  vnames.append(vn)
+  
+ vecs=np.vstack(vecs)
+ vnames=np.hstack(vnames)
+ 
+
+ #start the jvm
+ start_jpype()
+ 
+ #create the sequence file that we will write to
+ io=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.hadoop.io 
+ FileSystemCls=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.hadoop.fs.FileSystem
+ 
+ PathCls=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.hadoop.fs.Path
+ path=PathCls(ifile)
+
+ ConfCls=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.hadoop.conf.Configuration 
+ conf=ConfCls()
+ 
+ fs=FileSystemCls.get(conf)
+ 
+ #vector classes
+ VectorWritableCls=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.mahout.math.VectorWritable
+ DenseVectorCls=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.mahout.math.DenseVector
+ NamedVectorCls=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.mahout.math.NamedVector
+ writer=io.SequenceFile.createWriter(fs, conf, path, io.Text,VectorWritableCls)
+ 
+ 
+ vecwritable=VectorWritableCls()
+ <SPAN class="code-keyword">for</SPAN> row in range(vecs.shape[0]):
+  nvector=NamedVectorCls(DenseVectorCls(JArray(JDouble,1)(vecs[row,:])),vnames[row])
+  #need to wrap key and value because of overloading
+  wrapkey=JObject(io.Text(<SPAN class="code-quote">&quot;key &quot;</SPAN>+str(row)),io.Writable)
+  wrapval=JObject(vecwritable,io.Writable)
+  
+  vecwritable.set(nvector)
+  writer.append(wrapkey,wrapval)
+  
+ writer.close()
+</PRE>
+</DIV></DIV>
+
+<H1><A name="UsingMahoutwithPythonviaJPype-ReadingtheKMeansClusteredPointsfromPython"></A>Reading the KMeans Clustered Points from Python</H1>
+<P>Similarly we can use JPype to easily read the clustered points outputted by mahout.</P>
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+def read_clustered_pts(ifile,*args,**param):
+ &quot;&quot;&quot;Read the clustered points
+ ifile - path to the sequence file containing the clustered points
+ &quot;&quot;&quot; 
+
+ #start the jvm
+ start_jpype()
+ 
+ #create the sequence file that we will write to
+ io=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.hadoop.io 
+ FileSystemCls=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.hadoop.fs.FileSystem
+ 
+ PathCls=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.hadoop.fs.Path
+ path=PathCls(ifile)
+
+ ConfCls=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.hadoop.conf.Configuration 
+ conf=ConfCls()
+ 
+ fs=FileSystemCls.get(conf)
+ 
+ #vector classes
+ VectorWritableCls=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.mahout.math.VectorWritable
+ NamedVectorCls=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.mahout.math.NamedVector
+ 
+ 
+ ReaderCls=io.__getattribute__(<SPAN class="code-quote">&quot;SequenceFile$Reader&quot;</SPAN>) 
+ reader=ReaderCls(fs, path,conf)
+ 
+
+ key=reader.getKeyClass()()
+ 
+
+ valcls=reader.getValueClass()
+ vecwritable=valcls()
+ <SPAN class="code-keyword">while</SPAN> (reader.next(key,vecwritable)):  
+  weight=vecwritable.getWeight()
+  nvec=vecwritable.getVector()
+  
+  cname=nvec.__class__.__name__
+  <SPAN class="code-keyword">if</SPAN> (cname.rsplit('.',1)[1]==<SPAN class="code-quote">&quot;NamedVector&quot;</SPAN>):  
+   print <SPAN class="code-quote">&quot;cluster={key} Name={name} x={x} y={y}&quot;</SPAN>.format(key=key.toString(),name=nvec.getName(),x=nvec.get(0),y=nvec.get(1))
+  <SPAN class="code-keyword">else</SPAN>:
+   raise NotImplementedError(<SPAN class="code-quote">&quot;Vector isn't a NamedVector. Need to modify/test the code to handle <SPAN class="code-keyword">this</SPAN> <SPAN class="code-keyword">case</SPAN>.&quot;</SPAN>)
+</PRE>
+</DIV></DIV>
+
+<H1><A name="UsingMahoutwithPythonviaJPype-ReadingtheKMeansCentroids"></A>Reading the KMeans Centroids</H1>
+<P>Finally we can create a function to print out the actual cluster centers found by mahout,</P>
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+def getClusters(ifile,*args,**param):
+ &quot;&quot;&quot;Read the centroids from the clusters outputted by kmenas
+           ifile - Path to the sequence file containing the centroids
+ &quot;&quot;&quot; 
+
+ #start the jvm
+ start_jpype()
+ 
+ #create the sequence file that we will write to
+ io=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.hadoop.io 
+ FileSystemCls=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.hadoop.fs.FileSystem
+ 
+ PathCls=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.hadoop.fs.Path
+ path=PathCls(ifile)
+
+ ConfCls=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.hadoop.conf.Configuration 
+ conf=ConfCls()
+ 
+ fs=FileSystemCls.get(conf)
+ 
+ #vector classes
+ VectorWritableCls=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.mahout.math.VectorWritable
+ NamedVectorCls=JPackage(<SPAN class="code-quote">&quot;org&quot;</SPAN>).apache.mahout.math.NamedVector
+ ReaderCls=io.__getattribute__(<SPAN class="code-quote">&quot;SequenceFile$Reader&quot;</SPAN>)
+ reader=ReaderCls(fs, path,conf)
+ 
+
+ key=io.Text()
+ 
+
+ valcls=reader.getValueClass()
+
+ vecwritable=valcls()
+ 
+ <SPAN class="code-keyword">while</SPAN> (reader.next(key,vecwritable)):  
+  center=vecwritable.getCenter()
+  
+  print <SPAN class="code-quote">&quot;id={cid} center={center}&quot;</SPAN>.format(cid=vecwritable.getId(),center=center.values)
+  pass
+</PRE>
+</DIV></DIV>
+        </DIV>
+
+        
+      </DIV>
+    </DIV>
+    <DIV class="footer">
+      Generated by
+      <A href="http://www.atlassian.com/confluence/">Atlassian Confluence</A> (Version: 3.4.6 Build: 2036 Dec 21, 2010)
+      <A href="http://could.it/autoexport/">Auto Export Plugin</A> (Version: 1.0.0-dkulp)
+    </DIV>
+<SCRIPT type="text/javascript">
+
+  var _gaq = _gaq || [];
+  _gaq.push(['_setAccount', 'UA-17359171-1']);
+  _gaq.push(['_setDomainName', 'none']);
+  _gaq.push(['_setAllowLinker', true]);
+  _gaq.push(['_trackPageview']);
+
+  (function() {
+    var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
+    ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
+    var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
+  })();
+
+</SCRIPT>
+  </BODY>
+</HTML>
\ No newline at end of file

Added: mahout/site/new_website/MAHOUT/version-control.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/version-control.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/version-control.html (added)
+++ mahout/site/new_website/MAHOUT/version-control.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,150 @@
+
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<HTML>
+  <HEAD>
+    <LINK type="text/css" rel="stylesheet" href="resources/space.css">
+    <STYLE type="text/css">
+      .footer {
+        background-image:      url('https://cwiki.apache.org/confluence/images/border/border_bottom.gif');
+        background-repeat:     repeat-x;
+        background-position:   left top;
+        padding-top:           4px;
+        color:                 #666;
+      }
+    </STYLE>
+    <SCRIPT type="text/javascript" language="javascript">
+      var hide = null;
+      var show = null;
+      var children = null;
+
+      function init() {
+        /* Search form initialization */
+        var form = document.forms['search'];
+        if (form != null) {
+          form.elements['domains'].value = location.hostname;
+          form.elements['sitesearch'].value = location.hostname;
+        }
+
+        /* Children initialization */
+        hide = document.getElementById('hide');
+        show = document.getElementById('show');
+        children = document.all != null ?
+                   document.all['children'] :
+                   document.getElementById('children');
+        if (children != null) {
+          children.style.display = 'none';
+          show.style.display = 'inline';
+          hide.style.display = 'none';
+        }
+      }
+
+      function showChildren() {
+        children.style.display = 'block';
+        show.style.display = 'none';
+        hide.style.display = 'inline';
+      }
+
+      function hideChildren() {
+        children.style.display = 'none';
+        show.style.display = 'inline';
+        hide.style.display = 'none';
+      }
+    </SCRIPT>
+    <TITLE>Version Control</TITLE>
+  <META http-equiv="Content-Type" content="text/html;charset=UTF-8"></HEAD>
+  <BODY onload="init()">
+    <TABLE border="0" cellpadding="2" cellspacing="0" width="100%">
+      <TR class="topBar">
+        <TD align="left" valign="middle" class="topBarDiv" align="left" nowrap="">
+          &nbsp;<A href="mahout-wiki.html" title="Apache Mahout">Apache Mahout</A>&nbsp;&gt;&nbsp;<A href="mahout-wiki.html" title="Mahout Wiki">Mahout Wiki</A>&nbsp;&gt;&nbsp;<A href="" title="Version Control">Version Control</A>
+        </TD>
+        <TD align="right" valign="middle" nowrap="">
+          <FORM name="search" action="http://www.google.com/search" method="get">
+            <INPUT type="hidden" name="ie" value="UTF-8">
+            <INPUT type="hidden" name="oe" value="UTF-8">
+            <INPUT type="hidden" name="domains" value="">
+            <INPUT type="hidden" name="sitesearch" value="">
+            <INPUT type="text" name="q" maxlength="255" value="">        
+            <INPUT type="submit" name="btnG" value="Google Search">
+          </FORM>
+        </TD>
+      </TR> 
+    </TABLE>
+
+    <DIV id="PageContent">
+      <DIV class="pageheader" style="padding: 6px 0px 0px 0px;">
+        <!-- We'll enable this once we figure out how to access (and save) the logo resource -->
+        <!--img src="/wiki/images/confluence_logo.gif" style="float: left; margin: 4px 4px 4px 10px;" border="0"-->
+        <DIV style="margin: 0px 10px 0px 10px" class="smalltext">Apache Mahout</DIV>
+        <DIV style="margin: 0px 10px 8px 10px" class="pagetitle">Version Control</DIV>
+
+        <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+          <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=22872452">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/notep_16.gif" height="16" width="16" border="0" align="absmiddle" title="Edit Page"></A>
+            <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=22872452">Edit Page</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/listpages.action?key=MAHOUT">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/browse_space.gif" height="16" width="16" border="0" align="absmiddle" title="Browse Space"></A>
+            <A href="https://cwiki.apache.org/confluence/pages/listpages.action?key=MAHOUT">Browse Space</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=22872452">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/add_page_16.gif" height="16" width="16" border="0" align="absmiddle" title="Add Page"></A>
+          <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=22872452">Add Page</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=22872452">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/add_blogentry_16.gif" height="16" width="16" border="0" align="absmiddle" title="Add News"></A>
+          <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=22872452">Add News</A>
+        </DIV>
+      </DIV>
+      <DIV class="pagesubheading" style="margin: 0px 10px 0px 10px;">
+        #editReport()
+      </DIV>
+
+      <DIV class="pagecontent">
+        <DIV class="wiki-content">
+          <P>The Mahout source code resides in the <A href="http://subversion.tigris.org/" class="external-link" rel="nofollow">Apache Subversion (SVN)</A> repository. The command-line SVN client can be obtained <A href="http://subversion.tigris.org/project_packages.html" class="external-link" rel="nofollow">here</A>. The TortoiseSVN GUI client for Windows can be obtained <A href="http://tortoisesvn.tigris.org/" class="external-link" rel="nofollow">here</A>. There are also SVN plugins available for both <A href="http://subclipse.tigris.org/" class="external-link" rel="nofollow">Eclipse</A> and <A href="http://svnup.tigris.org/" class="external-link" rel="nofollow">IntelliJ IDEA</A>. </P>
+
+<P>There is also a <A href="http://git-scm.com/" class="external-link" rel="nofollow">git</A> repository for Mahout available <A href="http://git.apache.org/" class="external-link" rel="nofollow">at Apache</A>.</P>
+
+<H2><A name="VersionControl-WebAccess%28readonly%29"></A>Web Access (read-only)</H2>
+
+<P>The source code can be browsed via the Web at <A href="http://svn.apache.org/viewvc/mahout/" class="external-link" rel="nofollow">http://svn.apache.org/viewvc/mahout/</A>. No SVN client software is required. </P>
+
+<H2><A name="VersionControl-AnonymousAccess%28readonly%29"></A>Anonymous Access (read-only)</H2>
+
+<P>The SVN URL for anonymous users is <A href="http://svn.apache.org/repos/asf/mahout/trunk" class="external-link" rel="nofollow">http://svn.apache.org/repos/asf/mahout/trunk</A>. Instructions for anonymous SVN access are here. </P>
+
+<H2><A name="VersionControl-CommitterAccess%28readwrite%29"></A>Committer Access (read-write)</H2>
+
+<P>The SVN URL for committers is <A href="https://svn.apache.org/repos/asf/mahout/trunk" class="external-link" rel="nofollow">https://svn.apache.org/repos/asf/mahout/trunk</A>. Instructions for committer SVN access are <A href="https://cwiki.apache.org/confluence/pages/viewpage.action?spaceKey=MAHOUT&title=IssueTracker" class="external-link" rel="nofollow">here</A>. </P>
+
+<H2><A name="VersionControl-Issues"></A>Issues</H2>
+
+<P>All bugs, improvements, patches, etc. should be logged in <A href="http://issues.apache.org/jira/browse/MAHOUT" class="external-link" rel="nofollow">JIRA</A>.</P>
+        </DIV>
+
+        
+      </DIV>
+    </DIV>
+    <DIV class="footer">
+      Generated by
+      <A href="http://www.atlassian.com/confluence/">Atlassian Confluence</A> (Version: 3.2 Build: 1810 Mar 16, 2010)
+      <A href="http://could.it/autoexport/">Auto Export Plugin</A> (Version: 1.0.0-dkulp)
+    </DIV>
+<SCRIPT type="text/javascript">
+
+  var _gaq = _gaq || [];
+  _gaq.push(['_setAccount', 'UA-17359171-1']);
+  _gaq.push(['_setDomainName', 'none']);
+  _gaq.push(['_setAllowLinker', true]);
+  _gaq.push(['_trackPageview']);
+
+  (function() {
+    var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
+    ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
+    var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
+  })();
+
+</SCRIPT>
+  </BODY>
+</HTML>
\ No newline at end of file

Added: mahout/site/new_website/MAHOUT/versioncontrol.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/versioncontrol.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/versioncontrol.html (added)
+++ mahout/site/new_website/MAHOUT/versioncontrol.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,137 @@
+
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<HTML>
+  <HEAD>
+    <LINK type="text/css" rel="stylesheet" href="resources/space.css">
+    <STYLE type="text/css">
+      .footer {
+        background-image:      url('https://cwiki.apache.org/confluence/images/border/border_bottom.gif');
+        background-repeat:     repeat-x;
+        background-position:   left top;
+        padding-top:           4px;
+        color:                 #666;
+      }
+    </STYLE>
+    <SCRIPT type="text/javascript" language="javascript">
+      var hide = null;
+      var show = null;
+      var children = null;
+
+      function init() {
+        /* Search form initialization */
+        var form = document.forms['search'];
+        if (form != null) {
+          form.elements['domains'].value = location.hostname;
+          form.elements['sitesearch'].value = location.hostname;
+        }
+
+        /* Children initialization */
+        hide = document.getElementById('hide');
+        show = document.getElementById('show');
+        children = document.all != null ?
+                   document.all['children'] :
+                   document.getElementById('children');
+        if (children != null) {
+          children.style.display = 'none';
+          show.style.display = 'inline';
+          hide.style.display = 'none';
+        }
+      }
+
+      function showChildren() {
+        children.style.display = 'block';
+        show.style.display = 'none';
+        hide.style.display = 'inline';
+      }
+
+      function hideChildren() {
+        children.style.display = 'none';
+        show.style.display = 'inline';
+        hide.style.display = 'none';
+      }
+    </SCRIPT>
+    <TITLE>VersionControl</TITLE>
+  <META http-equiv="Content-Type" content="text/html;charset=UTF-8"></HEAD>
+  <BODY onload="init()">
+    <TABLE border="0" cellpadding="2" cellspacing="0" width="100%">
+      <TR class="topBar">
+        <TD align="left" valign="middle" class="topBarDiv" align="left" nowrap="">
+          &nbsp;<A href="index.html" title="Apache Lucene Mahout">Apache Lucene Mahout</A>&nbsp;&gt;&nbsp;<A href="index.html" title="index">index</A>&nbsp;&gt;&nbsp;<A href="" title="VersionControl">VersionControl</A>
+        </TD>
+        <TD align="right" valign="middle" nowrap="">
+          <FORM name="search" action="http://www.google.com/search" method="get">
+            <INPUT type="hidden" name="ie" value="UTF-8">
+            <INPUT type="hidden" name="oe" value="UTF-8">
+            <INPUT type="hidden" name="domains" value="">
+            <INPUT type="hidden" name="sitesearch" value="">
+            <INPUT type="text" name="q" maxlength="255" value="">        
+            <INPUT type="submit" name="btnG" value="Google Search">
+          </FORM>
+        </TD>
+      </TR> 
+    </TABLE>
+
+    <DIV id="PageContent">
+      <DIV class="pageheader" style="padding: 6px 0px 0px 0px;">
+        <!-- We'll enable this once we figure out how to access (and save) the logo resource -->
+        <!--img src="/wiki/images/confluence_logo.gif" style="float: left; margin: 4px 4px 4px 10px;" border="0"-->
+        <DIV style="margin: 0px 10px 0px 10px" class="smalltext">Apache Lucene Mahout</DIV>
+        <DIV style="margin: 0px 10px 8px 10px" class="pagetitle">VersionControl</DIV>
+
+        <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+          <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=22872452">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/notep_16.gif" height="16" width="16" border="0" align="absmiddle" title="Edit Page"></A>
+            <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=22872452">Edit Page</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/listpages.action?key=MAHOUT">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/browse_space.gif" height="16" width="16" border="0" align="absmiddle" title="Browse Space"></A>
+            <A href="https://cwiki.apache.org/confluence/pages/listpages.action?key=MAHOUT">Browse Space</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=22872452">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/add_page_16.gif" height="16" width="16" border="0" align="absmiddle" title="Add Page"></A>
+          <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=22872452">Add Page</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=22872452">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/add_blogentry_16.gif" height="16" width="16" border="0" align="absmiddle" title="Add News"></A>
+          <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=22872452">Add News</A>
+        </DIV>
+      </DIV>
+      <DIV class="pagesubheading" style="margin: 0px 10px 0px 10px;">
+        #editReport()
+      </DIV>
+
+      <DIV class="pagecontent">
+        <DIV class="wiki-content">
+          <H1><A name="VersionControl-VersionControlatMahout"></A>Version Control at Mahout</H1>
+
+<P>The Mahout source code resides in the <A href="http://subversion.tigris.org/" class="external-link" rel="nofollow">Apache Subversion (SVN)</A> repository. The command-line SVN client can be obtained <A href="http://subversion.tigris.org/project_packages.html" class="external-link" rel="nofollow">here</A>. The TortoiseSVN GUI client for Windows can be obtained <A href="http://tortoisesvn.tigris.org/" class="external-link" rel="nofollow">here</A>. There are also SVN plugins available for both <A href="http://subclipse.tigris.org/" class="external-link" rel="nofollow">Eclipse</A> and <A href="http://svnup.tigris.org/" class="external-link" rel="nofollow">IntelliJ IDEA</A>. </P>
+
+<P>There is also a <A href="http://git-scm.com/" class="external-link" rel="nofollow">git</A> repository for Mahout available <A href="http://git.apache.org/" class="external-link" rel="nofollow">at Apache</A>.</P>
+
+<H2><A name="VersionControl-WebAccess%28readonly%29"></A>Web Access (read-only)</H2>
+
+<P>The source code can be browsed via the Web at <A href="http://svn.apache.org/viewvc/mahout/" class="external-link" rel="nofollow">http://svn.apache.org/viewvc/mahout/</A>. No SVN client software is required. </P>
+
+<H2><A name="VersionControl-AnonymousAccess%28readonly%29"></A>Anonymous Access (read-only)</H2>
+
+<P>The SVN URL for anonymous users is <A href="http://svn.apache.org/repos/asf/mahout/trunk" class="external-link" rel="nofollow">http://svn.apache.org/repos/asf/mahout/trunk</A>. Instructions for anonymous SVN access are here. </P>
+
+<H2><A name="VersionControl-CommitterAccess%28readwrite%29"></A>Committer Access (read-write)</H2>
+
+<P>The SVN URL for committers is <A href="https://svn.apache.org/repos/asf/mahout/trunk" class="external-link" rel="nofollow">https://svn.apache.org/repos/asf/mahout/trunk</A>. Instructions for committer SVN access are <A href="issuetracker.html" class="external-link" rel="nofollow">here</A>. </P>
+
+<H2><A name="VersionControl-Issues"></A>Issues</H2>
+
+<P>All bugs, improvements, patches, etc. should be logged in <A href="http://issues.apache.org/jira/browse/MAHOUT" class="external-link" rel="nofollow">JIRA</A>.</P>
+        </DIV>
+
+        
+      </DIV>
+    </DIV>
+    <DIV class="footer">
+      Generated by
+      <A href="http://www.atlassian.com/confluence/">Atlassian Confluence</A> (Version: 3.2 Build: 1810 Mar 16, 2010)
+      <A href="http://could.it/autoexport/">Auto Export Plugin</A> (Version: 1.0.0-dkulp)
+    </DIV>
+  </BODY>
+</HTML>
\ No newline at end of file

Added: mahout/site/new_website/MAHOUT/viewing-result.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/viewing-result.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/viewing-result.html (added)
+++ mahout/site/new_website/MAHOUT/viewing-result.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,213 @@
+
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<HTML>
+  <HEAD>
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/space.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/master.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/wiki-content.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/abs.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/menu.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/menu-ie.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/tables.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/panels.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/master-ie.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/renderer-macros.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/content-types.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/login.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/information-macros.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/layout-macros.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/default-theme.css">
+    <LINK type="text/css" rel="stylesheet" href="resources/space.css">
+    <STYLE type="text/css">
+      .footer {
+        background-image:      url('https://cwiki.apache.org/confluence/images/border/border_bottom.gif');
+        background-repeat:     repeat-x;
+        background-position:   left top;
+        padding-top:           4px;
+        color:                 #666;
+      }
+    </STYLE>
+    <SCRIPT type="text/javascript" language="javascript">
+      var hide = null;
+      var show = null;
+      var children = null;
+
+      function init() {
+        /* Search form initialization */
+        var form = document.forms['search'];
+        if (form != null) {
+          form.elements['domains'].value = location.hostname;
+          form.elements['sitesearch'].value = location.hostname;
+        }
+
+        /* Children initialization */
+        hide = document.getElementById('hide');
+        show = document.getElementById('show');
+        children = document.all != null ?
+                   document.all['children'] :
+                   document.getElementById('children');
+        if (children != null) {
+          children.style.display = 'none';
+          show.style.display = 'inline';
+          hide.style.display = 'none';
+        }
+      }
+
+      function showChildren() {
+        children.style.display = 'block';
+        show.style.display = 'none';
+        hide.style.display = 'inline';
+      }
+
+      function hideChildren() {
+        children.style.display = 'none';
+        show.style.display = 'inline';
+        hide.style.display = 'none';
+      }
+    </SCRIPT>
+    <TITLE>Viewing Result</TITLE>
+  <META http-equiv="Content-Type" content="text/html;charset=UTF-8"></HEAD>
+  <BODY onload="init()">
+    <TABLE border="0" cellpadding="2" cellspacing="0" width="100%">
+      <TR class="topBar">
+        <TD align="left" valign="middle" class="topBarDiv" align="left" nowrap="">
+          &nbsp;<A href="mahout-wiki.html" title="Apache Mahout">Apache Mahout</A>&nbsp;&gt;&nbsp;<A href="mahout-wiki.html" title="Mahout Wiki">Mahout Wiki</A>&nbsp;&gt;&nbsp;<A href="" title="Viewing Result">Viewing Result</A>
+        </TD>
+        <TD align="right" valign="middle" nowrap="">
+          <FORM name="search" action="http://www.google.com/search" method="get">
+            <INPUT type="hidden" name="ie" value="UTF-8">
+            <INPUT type="hidden" name="oe" value="UTF-8">
+            <INPUT type="hidden" name="domains" value="">
+            <INPUT type="hidden" name="sitesearch" value="">
+            <INPUT type="text" name="q" maxlength="255" value="">        
+            <INPUT type="submit" name="btnG" value="Google Search">
+          </FORM>
+        </TD>
+      </TR> 
+    </TABLE>
+
+    <DIV id="PageContent">
+      <DIV class="pageheader" style="padding: 6px 0px 0px 0px;">
+        <!-- We'll enable this once we figure out how to access (and save) the logo resource -->
+        <!--img src="/wiki/images/confluence_logo.gif" style="float: left; margin: 4px 4px 4px 10px;" border="0"-->
+        <DIV style="margin: 0px 10px 0px 10px" class="smalltext">Apache Mahout</DIV>
+        <DIV style="margin: 0px 10px 8px 10px" class="pagetitle">Viewing Result</DIV>
+
+        <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+          <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=26119011">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/notep_16.gif" height="16" width="16" border="0" align="absmiddle" title="Edit Page"></A>
+            <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=26119011">Edit Page</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/listpages.action?key=MAHOUT">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/browse_space.gif" height="16" width="16" border="0" align="absmiddle" title="Browse Space"></A>
+            <A href="https://cwiki.apache.org/confluence/pages/listpages.action?key=MAHOUT">Browse Space</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=26119011">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/add_page_16.gif" height="16" width="16" border="0" align="absmiddle" title="Add Page"></A>
+          <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=26119011">Add Page</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=26119011">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/add_blogentry_16.gif" height="16" width="16" border="0" align="absmiddle" title="Add News"></A>
+          <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=26119011">Add News</A>
+        </DIV>
+      </DIV>
+
+      <DIV class="pagecontent">
+        <DIV class="wiki-content">
+          <DIV>
+<UL>
+    <LI><A href="#ViewingResult-AlgorithmViewingpages">Algorithm Viewing pages</A></LI>
+</UL></DIV>
+
+<P>There are various technologies available to view the output of Mahout algorithms.</P>
+<UL>
+	<LI>Clusters</LI>
+</UL>
+
+
+<H1><A name="ViewingResult-AlgorithmViewingpages"></A>Algorithm Viewing pages</H1>
+    
+    
+
+<DIV class="plugin_pagetree">
+
+        
+                <DIV>
+            <SPAN class="plugin_pagetree_status hidden">Collapse all</SPAN>
+            <DIV class="plugin_pagetree_expandcollapse">
+                <A class="plugin_pagetree_expandall" href="">Expand all</A>&nbsp;&nbsp;
+                <A class="plugin_pagetree_collapseall" href="">Collapse all</A>
+            </DIV>
+        </DIV>
+    
+    <UL class="plugin_pagetree_children_list plugin_pagetree_children_list_noleftspace">
+        <DIV class="plugin_pagetree_children">
+        </DIV>
+    </UL>
+
+    <FIELDSET class="hidden">
+        <INPUT type="hidden" name="treeId" value="">
+        <INPUT type="hidden" name="treeRequestId" value="/confluence/plugins/pagetree/naturalchildren.action?decorator=none&excerpt=true&sort=position&reverse=false&disableLinks=false">
+        <INPUT type="hidden" name="treePageId" value="23335706">
+
+        <INPUT type="hidden" name="noRoot" value="false">
+        <INPUT type="hidden" name="rootPageId" value="26119011">
+
+        <INPUT type="hidden" name="rootPage" value="">
+        <INPUT type="hidden" name="startDepth" value="0">
+        <INPUT type="hidden" name="spaceKey" value="MAHOUT">
+
+        <INPUT type="hidden" name="i18n-pagetree.loading" value="Loading...">
+        <INPUT type="hidden" name="i18n-pagetree.error.permission" value="Unable to load page tree. It seems that you do not have permission to view the root page.">
+        <INPUT type="hidden" name="i18n-pagetree.eeror.general" value="There was a problem retrieving the page tree. Please check the server log file for more information.">
+        <INPUT type="hidden" name="loginUrl" value="/confluence/login.action?os_destination=%2Fpages%2Fdoeditpage.action%3FpageId%3D23335706">
+
+                <FIELDSET class="hidden">
+                                                <INPUT type="hidden" name="ancestorId" value="26119011">
+                                    </FIELDSET>
+    </FIELDSET>
+</DIV>
+
+
+        </DIV>
+
+                  <DIV class="tabletitle">
+            Children
+            <SPAN class="smalltext" id="show" style="display: inline;">
+              <A href="javascript:showChildren()">Show Children</A></SPAN>
+            <SPAN class="smalltext" id="hide" style="display: none;">
+              <A href="javascript:hideChildren()">Hide Children</A></SPAN>
+          </DIV>
+          <DIV class="greybox" id="children" style="display: none;">
+                                      <A href="visualizing-sample-clusters.html" title="Visualizing Sample Clusters">Visualizing Sample Clusters</A>
+              <SPAN class="smalltext">(Apache Mahout)</SPAN>
+              <BR>
+                          <A href="visualize-classification-results.html" title="Visualize Classification Results">Visualize Classification Results</A>
+              <SPAN class="smalltext">(Apache Mahout)</SPAN>
+              <BR>
+                      </DIV>
+        
+      </DIV>
+    </DIV>
+    <DIV class="footer">
+      Generated by
+      <A href="http://www.atlassian.com/confluence/">Atlassian Confluence</A> (Version: 3.4.9 Build: 2042 Feb 14, 2011)
+      <A href="http://could.it/autoexport/">Auto Export Plugin</A> (Version: 1.0.0-dkulp)
+    </DIV>
+<SCRIPT type="text/javascript">
+
+  var _gaq = _gaq || [];
+  _gaq.push(['_setAccount', 'UA-17359171-1']);
+  _gaq.push(['_setDomainName', 'none']);
+  _gaq.push(['_setAllowLinker', true]);
+  _gaq.push(['_trackPageview']);
+
+  (function() {
+    var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
+    ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
+    var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
+  })();
+
+</SCRIPT>
+  </BODY>
+</HTML>
\ No newline at end of file

Added: mahout/site/new_website/MAHOUT/viewing-results.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/viewing-results.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/viewing-results.html (added)
+++ mahout/site/new_website/MAHOUT/viewing-results.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,166 @@
+
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<HTML>
+  <HEAD>
+    <LINK type="text/css" rel="stylesheet" href="resources/space.css">
+    <STYLE type="text/css">
+      .footer {
+        background-image:      url('https://cwiki.apache.org/confluence/images/border/border_bottom.gif');
+        background-repeat:     repeat-x;
+        background-position:   left top;
+        padding-top:           4px;
+        color:                 #666;
+      }
+    </STYLE>
+    <SCRIPT type="text/javascript" language="javascript">
+      var hide = null;
+      var show = null;
+      var children = null;
+
+      function init() {
+        /* Search form initialization */
+        var form = document.forms['search'];
+        if (form != null) {
+          form.elements['domains'].value = location.hostname;
+          form.elements['sitesearch'].value = location.hostname;
+        }
+
+        /* Children initialization */
+        hide = document.getElementById('hide');
+        show = document.getElementById('show');
+        children = document.all != null ?
+                   document.all['children'] :
+                   document.getElementById('children');
+        if (children != null) {
+          children.style.display = 'none';
+          show.style.display = 'inline';
+          hide.style.display = 'none';
+        }
+      }
+
+      function showChildren() {
+        children.style.display = 'block';
+        show.style.display = 'none';
+        hide.style.display = 'inline';
+      }
+
+      function hideChildren() {
+        children.style.display = 'none';
+        show.style.display = 'inline';
+        hide.style.display = 'none';
+      }
+    </SCRIPT>
+    <TITLE>Viewing Results</TITLE>
+  <META http-equiv="Content-Type" content="text/html;charset=UTF-8"></HEAD>
+  <BODY onload="init()">
+    <TABLE border="0" cellpadding="2" cellspacing="0" width="100%">
+      <TR class="topBar">
+        <TD align="left" valign="middle" class="topBarDiv" align="left" nowrap="">
+          &nbsp;<A href="mahout-wiki.html" title="Apache Mahout">Apache Mahout</A>&nbsp;&gt;&nbsp;<A href="mahout-wiki.html" title="Mahout Wiki">Mahout Wiki</A>&nbsp;&gt;&nbsp;<A href="quickstart.html" title="Quickstart">Quickstart</A>&nbsp;&gt;&nbsp;<A href="" title="Viewing Results">Viewing Results</A>
+        </TD>
+        <TD align="right" valign="middle" nowrap="">
+          <FORM name="search" action="http://www.google.com/search" method="get">
+            <INPUT type="hidden" name="ie" value="UTF-8">
+            <INPUT type="hidden" name="oe" value="UTF-8">
+            <INPUT type="hidden" name="domains" value="">
+            <INPUT type="hidden" name="sitesearch" value="">
+            <INPUT type="text" name="q" maxlength="255" value="">        
+            <INPUT type="submit" name="btnG" value="Google Search">
+          </FORM>
+        </TD>
+      </TR> 
+    </TABLE>
+
+    <DIV id="PageContent">
+      <DIV class="pageheader" style="padding: 6px 0px 0px 0px;">
+        <!-- We'll enable this once we figure out how to access (and save) the logo resource -->
+        <!--img src="/wiki/images/confluence_logo.gif" style="float: left; margin: 4px 4px 4px 10px;" border="0"-->
+        <DIV style="margin: 0px 10px 0px 10px" class="smalltext">Apache Mahout</DIV>
+        <DIV style="margin: 0px 10px 8px 10px" class="pagetitle">Viewing Results</DIV>
+
+        <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+          <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=9798244">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/notep_16.gif" height="16" width="16" border="0" align="absmiddle" title="Edit Page"></A>
+            <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=9798244">Edit Page</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/listpages.action?key=MAHOUT">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/browse_space.gif" height="16" width="16" border="0" align="absmiddle" title="Browse Space"></A>
+            <A href="https://cwiki.apache.org/confluence/pages/listpages.action?key=MAHOUT">Browse Space</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=9798244">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/add_page_16.gif" height="16" width="16" border="0" align="absmiddle" title="Add Page"></A>
+          <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=9798244">Add Page</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=9798244">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/add_blogentry_16.gif" height="16" width="16" border="0" align="absmiddle" title="Add News"></A>
+          <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=9798244">Add News</A>
+        </DIV>
+      </DIV>
+      <DIV class="pagesubheading" style="margin: 0px 10px 0px 10px;">
+        #editReport()
+      </DIV>
+
+      <DIV class="pagecontent">
+        <DIV class="wiki-content">
+          <H1><A name="ViewingResults-Intro"></A>Intro</H1>
+
+<P>Many of the Mahout libraries run as batch jobs, dumping results into Hadoop sequence files or other data structures.  This page is intended to demonstrate the various ways one might inspect the outcome of various jobs.  The page is organized by algorithms.</P>
+
+<H1><A name="ViewingResults-GeneralUtilities"></A>General Utilities</H1>
+
+<H2><A name="ViewingResults-SequenceFileDumper"></A>Sequence File Dumper</H2>
+
+
+<H1><A name="ViewingResults-Clustering"></A>Clustering</H1>
+
+<H2><A name="ViewingResults-ClusterDumper"></A>Cluster Dumper</H2>
+
+<P>Run the following to print out all options:</P>
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+java  -cp <SPAN class="code-quote">&quot;*&quot;</SPAN> org.apache.mahout.utils.clustering.ClusterDumper --help
+</PRE>
+</DIV></DIV>
+
+
+<H3><A name="ViewingResults-Example"></A>Example</H3>
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+java  -cp <SPAN class="code-quote">&quot;*&quot;</SPAN> org.apache.mahout.utils.clustering.ClusterDumper --seqFileDir ./solr-clust-n2/out/clusters-2
+      --dictionary ./solr-clust-n2/dictionary.txt
+      --substring 100 --pointsDir ./solr-clust-n2/out/points/
+
+</PRE>
+</DIV></DIV>
+
+
+<H2><A name="ViewingResults-ClusterLabels%28MAHOUT163%29"></A>Cluster Labels (MAHOUT-163)</H2>
+
+<H1><A name="ViewingResults-Classification"></A>Classification</H1>
+        </DIV>
+
+        
+      </DIV>
+    </DIV>
+    <DIV class="footer">
+      Generated by
+      <A href="http://www.atlassian.com/confluence/">Atlassian Confluence</A> (Version: 3.2 Build: 1810 Mar 16, 2010)
+      <A href="http://could.it/autoexport/">Auto Export Plugin</A> (Version: 1.0.0-dkulp)
+    </DIV>
+<SCRIPT type="text/javascript">
+
+  var _gaq = _gaq || [];
+  _gaq.push(['_setAccount', 'UA-17359171-1']);
+  _gaq.push(['_setDomainName', 'none']);
+  _gaq.push(['_setAllowLinker', true]);
+  _gaq.push(['_trackPageview']);
+
+  (function() {
+    var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
+    ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
+    var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
+  })();
+
+</SCRIPT>
+  </BODY>
+</HTML>
\ No newline at end of file

Added: mahout/site/new_website/MAHOUT/visualize-classification-results.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/visualize-classification-results.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/visualize-classification-results.html (added)
+++ mahout/site/new_website/MAHOUT/visualize-classification-results.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,144 @@
+
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<HTML>
+  <HEAD>
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/space.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/master.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/wiki-content.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/abs.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/menu.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/menu-ie.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/tables.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/panels.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/master-ie.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/renderer-macros.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/content-types.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/login.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/information-macros.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/layout-macros.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/default-theme.css">
+    <LINK type="text/css" rel="stylesheet" href="resources/space.css">
+    <STYLE type="text/css">
+      .footer {
+        background-image:      url('https://cwiki.apache.org/confluence/images/border/border_bottom.gif');
+        background-repeat:     repeat-x;
+        background-position:   left top;
+        padding-top:           4px;
+        color:                 #666;
+      }
+    </STYLE>
+    <SCRIPT type="text/javascript" language="javascript">
+      var hide = null;
+      var show = null;
+      var children = null;
+
+      function init() {
+        /* Search form initialization */
+        var form = document.forms['search'];
+        if (form != null) {
+          form.elements['domains'].value = location.hostname;
+          form.elements['sitesearch'].value = location.hostname;
+        }
+
+        /* Children initialization */
+        hide = document.getElementById('hide');
+        show = document.getElementById('show');
+        children = document.all != null ?
+                   document.all['children'] :
+                   document.getElementById('children');
+        if (children != null) {
+          children.style.display = 'none';
+          show.style.display = 'inline';
+          hide.style.display = 'none';
+        }
+      }
+
+      function showChildren() {
+        children.style.display = 'block';
+        show.style.display = 'none';
+        hide.style.display = 'inline';
+      }
+
+      function hideChildren() {
+        children.style.display = 'none';
+        show.style.display = 'inline';
+        hide.style.display = 'none';
+      }
+    </SCRIPT>
+    <TITLE>Visualize Classification Results</TITLE>
+  <META http-equiv="Content-Type" content="text/html;charset=UTF-8"></HEAD>
+  <BODY onload="init()">
+    <TABLE border="0" cellpadding="2" cellspacing="0" width="100%">
+      <TR class="topBar">
+        <TD align="left" valign="middle" class="topBarDiv" align="left" nowrap="">
+          &nbsp;<A href="mahout-wiki.html" title="Apache Mahout">Apache Mahout</A>&nbsp;&gt;&nbsp;<A href="mahout-wiki.html" title="Mahout Wiki">Mahout Wiki</A>&nbsp;&gt;&nbsp;<A href="viewing-result.html" title="Viewing Result">Viewing Result</A>&nbsp;&gt;&nbsp;<A href="" title="Visualize Classification Results">Visualize Classification Results</A>
+        </TD>
+        <TD align="right" valign="middle" nowrap="">
+          <FORM name="search" action="http://www.google.com/search" method="get">
+            <INPUT type="hidden" name="ie" value="UTF-8">
+            <INPUT type="hidden" name="oe" value="UTF-8">
+            <INPUT type="hidden" name="domains" value="">
+            <INPUT type="hidden" name="sitesearch" value="">
+            <INPUT type="text" name="q" maxlength="255" value="">        
+            <INPUT type="submit" name="btnG" value="Google Search">
+          </FORM>
+        </TD>
+      </TR> 
+    </TABLE>
+
+    <DIV id="PageContent">
+      <DIV class="pageheader" style="padding: 6px 0px 0px 0px;">
+        <!-- We'll enable this once we figure out how to access (and save) the logo resource -->
+        <!--img src="/wiki/images/confluence_logo.gif" style="float: left; margin: 4px 4px 4px 10px;" border="0"-->
+        <DIV style="margin: 0px 10px 0px 10px" class="smalltext">Apache Mahout</DIV>
+        <DIV style="margin: 0px 10px 8px 10px" class="pagetitle">Visualize Classification Results</DIV>
+
+        <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+          <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=27824812">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/notep_16.gif" height="16" width="16" border="0" align="absmiddle" title="Edit Page"></A>
+            <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=27824812">Edit Page</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/listpages.action?key=MAHOUT">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/browse_space.gif" height="16" width="16" border="0" align="absmiddle" title="Browse Space"></A>
+            <A href="https://cwiki.apache.org/confluence/pages/listpages.action?key=MAHOUT">Browse Space</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=27824812">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/add_page_16.gif" height="16" width="16" border="0" align="absmiddle" title="Add Page"></A>
+          <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=27824812">Add Page</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=27824812">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/add_blogentry_16.gif" height="16" width="16" border="0" align="absmiddle" title="Add News"></A>
+          <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=27824812">Add News</A>
+        </DIV>
+      </DIV>
+
+      <DIV class="pagecontent">
+        <DIV class="wiki-content">
+          <P>Lorem whatsit.</P>
+        </DIV>
+
+        
+      </DIV>
+    </DIV>
+    <DIV class="footer">
+      Generated by
+      <A href="http://www.atlassian.com/confluence/">Atlassian Confluence</A> (Version: 3.4.9 Build: 2042 Feb 14, 2011)
+      <A href="http://could.it/autoexport/">Auto Export Plugin</A> (Version: 1.0.0-dkulp)
+    </DIV>
+<SCRIPT type="text/javascript">
+
+  var _gaq = _gaq || [];
+  _gaq.push(['_setAccount', 'UA-17359171-1']);
+  _gaq.push(['_setDomainName', 'none']);
+  _gaq.push(['_setAllowLinker', true]);
+  _gaq.push(['_trackPageview']);
+
+  (function() {
+    var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
+    ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
+    var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
+  })();
+
+</SCRIPT>
+  </BODY>
+</HTML>
\ No newline at end of file

Added: mahout/site/new_website/MAHOUT/visualizing-sample-clusters.data/animation.gif
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/visualizing-sample-clusters.data/animation.gif?rev=1243022&view=auto
==============================================================================
Binary file - no diff available.

Propchange: mahout/site/new_website/MAHOUT/visualizing-sample-clusters.data/animation.gif
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: mahout/site/new_website/MAHOUT/visualizing-sample-clusters.data/animation.gif.jpeg
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/visualizing-sample-clusters.data/animation.gif.jpeg?rev=1243022&view=auto
==============================================================================
Binary file - no diff available.

Propchange: mahout/site/new_website/MAHOUT/visualizing-sample-clusters.data/animation.gif.jpeg
------------------------------------------------------------------------------
    svn:mime-type = application/octet-stream

Added: mahout/site/new_website/MAHOUT/visualizing-sample-clusters.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/visualizing-sample-clusters.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/visualizing-sample-clusters.html (added)
+++ mahout/site/new_website/MAHOUT/visualizing-sample-clusters.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,214 @@
+
+<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd">
+<HTML>
+  <HEAD>
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/space.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/master.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/wiki-content.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/abs.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/menu.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/menu-ie.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/tables.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/panels.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/master-ie.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/renderer-macros.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/content-types.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/login.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/information-macros.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/layout-macros.css">
+<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$stylebase/default-theme.css">
+    <LINK type="text/css" rel="stylesheet" href="resources/space.css">
+    <STYLE type="text/css">
+      .footer {
+        background-image:      url('https://cwiki.apache.org/confluence/images/border/border_bottom.gif');
+        background-repeat:     repeat-x;
+        background-position:   left top;
+        padding-top:           4px;
+        color:                 #666;
+      }
+    </STYLE>
+    <SCRIPT type="text/javascript" language="javascript">
+      var hide = null;
+      var show = null;
+      var children = null;
+
+      function init() {
+        /* Search form initialization */
+        var form = document.forms['search'];
+        if (form != null) {
+          form.elements['domains'].value = location.hostname;
+          form.elements['sitesearch'].value = location.hostname;
+        }
+
+        /* Children initialization */
+        hide = document.getElementById('hide');
+        show = document.getElementById('show');
+        children = document.all != null ?
+                   document.all['children'] :
+                   document.getElementById('children');
+        if (children != null) {
+          children.style.display = 'none';
+          show.style.display = 'inline';
+          hide.style.display = 'none';
+        }
+      }
+
+      function showChildren() {
+        children.style.display = 'block';
+        show.style.display = 'none';
+        hide.style.display = 'inline';
+      }
+
+      function hideChildren() {
+        children.style.display = 'none';
+        show.style.display = 'inline';
+        hide.style.display = 'none';
+      }
+    </SCRIPT>
+    <TITLE>Visualizing Sample Clusters</TITLE>
+  <META http-equiv="Content-Type" content="text/html;charset=UTF-8"></HEAD>
+  <BODY onload="init()">
+    <TABLE border="0" cellpadding="2" cellspacing="0" width="100%">
+      <TR class="topBar">
+        <TD align="left" valign="middle" class="topBarDiv" align="left" nowrap="">
+          &nbsp;<A href="mahout-wiki.html" title="Apache Mahout">Apache Mahout</A>&nbsp;&gt;&nbsp;<A href="mahout-wiki.html" title="Mahout Wiki">Mahout Wiki</A>&nbsp;&gt;&nbsp;<A href="viewing-result.html" title="Viewing Result">Viewing Result</A>&nbsp;&gt;&nbsp;<A href="" title="Visualizing Sample Clusters">Visualizing Sample Clusters</A>
+        </TD>
+        <TD align="right" valign="middle" nowrap="">
+          <FORM name="search" action="http://www.google.com/search" method="get">
+            <INPUT type="hidden" name="ie" value="UTF-8">
+            <INPUT type="hidden" name="oe" value="UTF-8">
+            <INPUT type="hidden" name="domains" value="">
+            <INPUT type="hidden" name="sitesearch" value="">
+            <INPUT type="text" name="q" maxlength="255" value="">        
+            <INPUT type="submit" name="btnG" value="Google Search">
+          </FORM>
+        </TD>
+      </TR> 
+    </TABLE>
+
+    <DIV id="PageContent">
+      <DIV class="pageheader" style="padding: 6px 0px 0px 0px;">
+        <!-- We'll enable this once we figure out how to access (and save) the logo resource -->
+        <!--img src="/wiki/images/confluence_logo.gif" style="float: left; margin: 4px 4px 4px 10px;" border="0"-->
+        <DIV style="margin: 0px 10px 0px 10px" class="smalltext">Apache Mahout</DIV>
+        <DIV style="margin: 0px 10px 8px 10px" class="pagetitle">Visualizing Sample Clusters</DIV>
+
+        <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+          <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=23335706">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/notep_16.gif" height="16" width="16" border="0" align="absmiddle" title="Edit Page"></A>
+            <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=23335706">Edit Page</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/listpages.action?key=MAHOUT">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/browse_space.gif" height="16" width="16" border="0" align="absmiddle" title="Browse Space"></A>
+            <A href="https://cwiki.apache.org/confluence/pages/listpages.action?key=MAHOUT">Browse Space</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=23335706">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/add_page_16.gif" height="16" width="16" border="0" align="absmiddle" title="Add Page"></A>
+          <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=23335706">Add Page</A>
+          &nbsp;
+          <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=23335706">
+            <IMG src="https://cwiki.apache.org/confluence/images/icons/add_blogentry_16.gif" height="16" width="16" border="0" align="absmiddle" title="Add News"></A>
+          <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=23335706">Add News</A>
+        </DIV>
+      </DIV>
+
+      <DIV class="pagecontent">
+        <DIV class="wiki-content">
+          <H1><A name="VisualizingSampleClusters-Introduction"></A>Introduction</H1>
+
+<P>Mahout provides examples to visualize sample clusters that gets created by various clustering algorithms like</P>
+<UL>
+	<LI>Canopy Clustering</LI>
+	<LI>Dirichlet Process</LI>
+	<LI>KMeans</LI>
+	<LI>Fuzzy KMeans</LI>
+	<LI>MeanShift Canopy</LI>
+	<LI>Spectral KMeans</LI>
+	<LI>MinHash</LI>
+</UL>
+
+
+<H5><A name="VisualizingSampleClusters-Note"></A>Note</H5>
+<P>These are Swing programs. You have to be in a window system on the same machine you run these, or logged in via a &quot;remote desktop&quot; or VNC program.</P>
+
+<H1><A name="VisualizingSampleClusters-PrePrep"></A>Pre - Prep</H1>
+
+<P>For visualizing the clusters, you would just have to execute the Java classes under org.apache.mahout.clustering.display package in mahout-examples module. If you are using eclipse, setup mahout-examples as a project as specified in <A href="buildingmahout.html#BuildingMahout-mahoutmaveneclipse">Working with Maven in Eclipse</A>.</P>
+
+<H1><A name="VisualizingSampleClusters-Visualizingclusters"></A>Visualizing clusters</H1>
+
+<P>The following classes in org.apache.mahout.clustering.display can be run without parameters to generate a sample data set and run the reference clustering implementations over them:</P>
+<OL>
+	<LI>DisplayClustering - generates 1000 samples from three, symmetric distributions. This is the same data set that is used by the following clustering programs. It displays the points on a screen and superimposes the model parameters that were used to generate the points. You can edit the generateSamples() method to change the sample points used by these programs.</LI>
+	<LI>DisplayClustering - displays initial areas of generated points</LI>
+	<LI>DisplayDirichlet - uses Dirichlet Process clustering</LI>
+	<LI>DisplayCanopy - uses Canopy clustering</LI>
+	<LI>DisplayKMeans - uses k-Means clustering</LI>
+	<LI>DisplayFuzzyKMeans - uses Fuzzy k-Means clustering</LI>
+	<LI>DisplayMeanShift - uses MeanShift clustering</LI>
+	<LI>DisplaySpectralKMeans - uses Spectral KMeans via map-reduce algorithm</LI>
+</OL>
+
+
+<P>If you are using Eclipse and have set it up as specified in Pre-Prep, just right-click on each of the classes mentioned above and choose &quot;Run As - Java Application&quot;. To run these directly from the command line:</P>
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+cd $MAHOUT_HOME/examples
+mvn -q exec:java -Dexec.mainClass=org.apache.mahout.clustering.display.DisplayClustering
+# substitute other names above <SPAN class="code-keyword">for</SPAN> DisplayClustering
+# Note: the DisplaySpectralKMeans program does a Hadoop job that takes 3 minutes on a laptop. Set <SPAN class="code-keyword">this</SPAN> MVN_OPTS=300m to give the program enough memory. You may find that some of the other programs also need more memory.
+</PRE>
+</DIV></DIV>
+
+<P>Note:</P>
+<UL>
+	<LI>Some of these programs display the sample points and then superimpose all of the clusters from each iteration. The last iteration's clusters are in bold red and the previous several are colored (orange, yellow, green, blue, magenta) in order after which all earlier clusters are in light grey. This helps to visualize how the clusters converge upon a solution over multiple iterations.</LI>
+</UL>
+
+
+<UL>
+	<LI>By changing the parameter values (k, ALPHA_0, numIterations) and the display SIGNIFICANCE you can obtain different results.</LI>
+</UL>
+
+
+<H1><A name="VisualizingSampleClusters-ScreenCaptureAnimation"></A>Screen Capture Animation</H1>
+<P>See <A href="sample-clusters-animation.html" title="Sample Clusters Animation">Sample Clusters Animation</A> for a screen caps of all the above programs, and an animated gif.</P>
+        </DIV>
+
+                  <DIV class="tabletitle">
+            Children
+            <SPAN class="smalltext" id="show" style="display: inline;">
+              <A href="javascript:showChildren()">Show Children</A></SPAN>
+            <SPAN class="smalltext" id="hide" style="display: none;">
+              <A href="javascript:hideChildren()">Hide Children</A></SPAN>
+          </DIV>
+          <DIV class="greybox" id="children" style="display: none;">
+                                      <A href="sample-clusters-animation.html" title="Sample Clusters Animation">Sample Clusters Animation</A>
+              <SPAN class="smalltext">(Apache Mahout)</SPAN>
+              <BR>
+                      </DIV>
+        
+      </DIV>
+    </DIV>
+    <DIV class="footer">
+      Generated by
+      <A href="http://www.atlassian.com/confluence/">Atlassian Confluence</A> (Version: 3.4.9 Build: 2042 Feb 14, 2011)
+      <A href="http://could.it/autoexport/">Auto Export Plugin</A> (Version: 1.0.0-dkulp)
+    </DIV>
+<SCRIPT type="text/javascript">
+
+  var _gaq = _gaq || [];
+  _gaq.push(['_setAccount', 'UA-17359171-1']);
+  _gaq.push(['_setDomainName', 'none']);
+  _gaq.push(['_setAllowLinker', true]);
+  _gaq.push(['_trackPageview']);
+
+  (function() {
+    var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true;
+    ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js';
+    var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s);
+  })();
+
+</SCRIPT>
+  </BODY>
+</HTML>
\ No newline at end of file



Mime
View raw message