You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@mahout.apache.org by sr...@apache.org on 2012/02/11 11:22:31 UTC
svn commit: r1243022 [27/38] - 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...
Added: mahout/site/new_website/MAHOUT/stochastic-singular-value-decomposition.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/stochastic-singular-value-decomposition.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/stochastic-singular-value-decomposition.html (added)
+++ mahout/site/new_website/MAHOUT/stochastic-singular-value-decomposition.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,194 @@
+
+<!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>Stochastic Singular Value Decomposition</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="">
+ <A href="mahout-wiki.html" title="Apache Mahout">Apache Mahout</A> > <A href="mahout-wiki.html" title="Mahout Wiki">Mahout Wiki</A> > <A href="algorithms.html" title="Algorithms">Algorithms</A> > <A href="" title="Stochastic Singular Value Decomposition">Stochastic Singular Value Decomposition</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">Stochastic Singular Value Decomposition</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=27832158">
+ <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=27832158">Edit Page</A>
+
+ <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>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=27832158">
+ <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=27832158">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=27832158">
+ <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=27832158">Add News</A>
+ </DIV>
+ </DIV>
+
+ <DIV class="pagecontent">
+ <DIV class="wiki-content">
+ <P>Stochastic SVD method in Mahout produces reduced rank Singular Value Decomposition output in its strict mathematical definition: A=USV'.</P>
+
+<H5><A name="StochasticSingularValueDecomposition-Thebenefitsoverothermethodsare%3A"></A>The benefits over other methods are: </H5>
+<UL>
+ <LI>reduced flops required compared to Krylov subspace methods</LI>
+ <LI>In map-reduce world, a fixed number of MR iterations required regardless of rank requested</LI>
+ <LI>Tweak precision/speed balance with options.</LI>
+ <LI>A is a Distributed Row Matrix where rows may be identified by any Writable (such as a document path). As such, it would work directly on the output of seq2sparse.</LI>
+</UL>
+
+
+<P>map-reduce characteristics: <BR>
+SSVD uses at most 3 MR <EM>sequential</EM> steps (map-only + map-reduce + 2 optional parallel map-reduce jobs) to produce reduced rank approximation of U, V and S matrices. Additionally, two more map-reduce steps are added for each power iteration step if requested.</P>
+
+<H5><A name="StochasticSingularValueDecomposition-Potentialdrawbacks%3A"></A>Potential drawbacks: </H5>
+<UL>
+ <LI>potentially less precise (but adding even one power iteration seems to fix that quite a bit).</LI>
+</UL>
+
+
+<H5><A name="StochasticSingularValueDecomposition-Documentation"></A>Documentation</H5>
+
+<P><A href="stochastic-singular-value-decomposition.data/SSVD-CLI.pdf">Overview and Usage</A><BR>
+Note: Please use 0.6 trunk or later!</P>
+
+<H5><A name="StochasticSingularValueDecomposition-Rsimulation"></A>R simulation</H5>
+<P><A href="stochastic-singular-value-decomposition.data/ssvd.R">SSVD implementation flow in R with power iterations and PCA options</A>. Note that this implementation is not most optimal for sequential flow solver, but it is for demonstration purposes only. </P>
+
+<P>However, try this R code to simulate a meaningful input:</P>
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeHeader panelHeader" style="border-bottom-width: 1px;"><B>tests.R</B></DIV><DIV class="codeContent panelContent">
+<PRE class="code-java">
+n<-1000
+m<-2000
+k<-10
+
+qi<-1
+
+#simulated input
+svalsim<-diag(k:1)
+
+usim<- qr.Q(qr(matrix(rnorm(m*k, mean=3), nrow=m,ncol=k)))
+vsim<- qr.Q(qr( matrix(rnorm(n*k,mean=5), nrow=n,ncol=k)))
+
+
+x<- usim %*% svalsim %*% t(vsim)
+
+</PRE>
+</DIV></DIV>
+
+<P>and try to compare ssvd.svd(x) and stock svd(x) performance for the same rank k, notice the difference in the running time. Also play with power iterations (qIter) and compare accuracies of standard svd and SSVD.</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/support-vector-machines.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/support-vector-machines.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/support-vector-machines.html (added)
+++ mahout/site/new_website/MAHOUT/support-vector-machines.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,143 @@
+
+<!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>Support Vector Machines</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="">
+ <A href="mahout-wiki.html" title="Apache Mahout">Apache Mahout</A> > <A href="mahout-wiki.html" title="Mahout Wiki">Mahout Wiki</A> > <A href="algorithms.html" title="Algorithms">Algorithms</A> > <A href="" title="Support Vector Machines">Support Vector Machines</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">Support Vector Machines</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=75683">
+ <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=75683">Edit Page</A>
+
+ <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>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=75683">
+ <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=75683">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=75683">
+ <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=75683">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="SupportVectorMachines-SupportVectorMachines"></A>Support Vector Machines</H1>
+
+<P>As with Naive Bayes, Support Vector Machines (or SVMs in short) can be used to solve the task of assigning objects to classes. However, the way this task is solved is completely different to the setting in Naive Bayes.</P>
+
+<P>Each object is considered to be a point in <EM>n</EM> dimensional feature space, <EM>n</EM> being the number of features used to describe the objects numerically. In addition each object is assigned a binary label, let us assume the labels are "positive" and "negative". During learning, the algorithm tries to find a hyperplane in that space, that perfectly separates positive from negative objects.<BR>
+It is trivial to think of settings where this might very well be impossible. To remedy this situation, objects can be assigned so called slack terms, that punish mistakes made during learning appropriately. That way, the algorithm is forced to find the hyperplane that causes the least number of mistakes.</P>
+
+<P>Another way to overcome the problem of there being no linear hyperplane to separate positive from negative objects is to simply project each feature vector into an higher dimensional feature space and search for a linear separating hyperplane in that new space. Usually the main problem with learning in high dimensional feature spaces is the so called curse of dimensionality. That is, there are fewer learning examples available than free parameters to tune. In the case of SVMs this problem is less detrimental, as SVMs impose additional structural constraints on their solutions. Each separating hyperplane needs to have a maximal margin to all training examples. In addition, that way, the solution may be based on the information encoded in only very few examples.</P>
+
+<H2><A name="SupportVectorMachines-Strategyforparallelization"></A>Strategy for parallelization</H2>
+
+<H2><A name="SupportVectorMachines-Designofpackages"></A>Design of packages</H2>
+ </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/svd-singular-value-decomposition.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/svd-singular-value-decomposition.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/svd-singular-value-decomposition.html (added)
+++ mahout/site/new_website/MAHOUT/svd-singular-value-decomposition.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,174 @@
+
+<!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>SVD - Singular Value Decomposition</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="">
+ <A href="mahout-wiki.html" title="Apache Mahout">Apache Mahout</A> > <A href="mahout-wiki.html" title="Mahout Wiki">Mahout Wiki</A> > <A href="glossary.html" title="Glossary">Glossary</A> > <A href="" title="SVD - Singular Value Decomposition">SVD - Singular Value Decomposition</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">SVD - Singular Value Decomposition</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=10846337">
+ <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=10846337">Edit Page</A>
+
+ <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>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=10846337">
+ <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=10846337">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=10846337">
+ <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=10846337">Add News</A>
+ </DIV>
+ </DIV>
+
+ <DIV class="pagecontent">
+ <DIV class="wiki-content">
+ <P>Singular Value Decomposition is a form of product decomposition of a matrix in which a rectangular matrix A is decomposed into a product U s V' where U and V are orthonormal and s is a diagonal matrix. The values of A can be real or complex, but the real case dominates applications in machine learning. The most prominent properties of the SVD are:</P>
+
+<UL>
+ <LI>The decomposition of any real matrix has only real values</LI>
+ <LI>The SVD is unique except for column permutations of U, s and V</LI>
+ <LI>If you take only the largest n values of s and set the rest to zero, you have a least squares approximation of A with rank n. This allows SVD to be used very effectively in least squares regression and makes partial SVD useful.</LI>
+ <LI>The SVD can be computed accurately for singular or nearly singular matrices. For a matrix of rank n, only the first n singular values will be non-zero. This allows SVD to be used for solution of singular linear systems. The columns of U and V corresponding to zero singular values define the null space of A.</LI>
+ <LI>The partial SVD of very large matrices can be computed very quickly using stochastic decompositions. See <A href="http://arxiv.org/abs/0909.4061v1" class="external-link" rel="nofollow">http://arxiv.org/abs/0909.4061v1</A> for details. Gradient descent can also be used to compute partial SVD's and is very useful where some values of the matrix being decomposed are not known.</LI>
+</UL>
+
+
+<P>In collaborative filtering and text retrieval, it is common to compute the partial decomposition of the user x item interaction matrix or the document x term matrix. This allows the projection of users and items (or documents and terms) into a common vector space representation that is often referred to as the latent semantic representation. This process is sometimes called Latent Semantic Analysis and has been very effective in the analysis of the Netflix dataset.</P>
+
+<P>Dimension Reduction in Mahout:</P>
+<UL>
+ <LI><A href="https://cwiki.apache.org/MAHOUT/dimensional-reduction.html" class="external-link" rel="nofollow">https://cwiki.apache.org/MAHOUT/dimensional-reduction.html</A></LI>
+</UL>
+
+
+<P> See Also:</P>
+<UL>
+ <LI><A href="http://www.kwon3d.com/theory/jkinem/svd.html" class="external-link" rel="nofollow">http://www.kwon3d.com/theory/jkinem/svd.html</A></LI>
+ <LI><A href="http://en.wikipedia.org/wiki/Singular_value_decomposition" class="external-link" rel="nofollow">http://en.wikipedia.org/wiki/Singular_value_decomposition</A></LI>
+ <LI><A href="http://en.wikipedia.org/wiki/Latent_semantic_analysis" class="external-link" rel="nofollow">http://en.wikipedia.org/wiki/Latent_semantic_analysis</A></LI>
+ <LI><A href="http://en.wikipedia.org/wiki/Netflix_Prize" class="external-link" rel="nofollow">http://en.wikipedia.org/wiki/Netflix_Prize</A></LI>
+ <LI><A href="http://www.amazon.com/Understanding-Complex-Datasets-Decompositions-Knowledge/dp/1584888326" class="external-link" rel="nofollow">http://www.amazon.com/Understanding-Complex-Datasets-Decompositions-Knowledge/dp/1584888326</A></LI>
+ <LI><A href="http://web.mit.edu/be.400/www/SVD/Singular_Value_Decomposition.htm" class="external-link" rel="nofollow">http://web.mit.edu/be.400/www/SVD/Singular_Value_Decomposition.htm</A></LI>
+ <LI><A href="http://www.quora.com/What-s-the-best-parallelized-sparse-SVD-code-publicly-available" class="external-link" rel="nofollow">http://www.quora.com/What-s-the-best-parallelized-sparse-SVD-code-publicly-available</A></LI>
+ <LI><A href="http://mail-archives.apache.org/mod_mbox/mahout-user/201102.mbox/%3CAANLkTinQ5K4XrM7naBWn8qoBXZGVobBot2RtjZSV4yOd@mail.gmail.com%3E" class="external-link" rel="nofollow">understanding Mahout Hadoop SVD thread</A></LI>
+</UL>
+
+ </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/synthetic-control-data.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/synthetic-control-data.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/synthetic-control-data.html (added)
+++ mahout/site/new_website/MAHOUT/synthetic-control-data.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,386 @@
+
+<!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>Synthetic Control Data</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="">
+ <A href="mahout-wiki.html" title="Apache Mahout">Apache Mahout</A> > <A href="mahout-wiki.html" title="Mahout Wiki">Mahout Wiki</A> > <A href="quickstart.html" title="Quickstart">Quickstart</A> > <A href="" title="Synthetic Control Data">Synthetic Control Data</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">Synthetic Control Data</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=103663">
+ <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=103663">Edit Page</A>
+
+ <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>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=103663">
+ <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=103663">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=103663">
+ <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=103663">Add News</A>
+ </DIV>
+ </DIV>
+
+ <DIV class="pagecontent">
+ <DIV class="wiki-content">
+ <H1><A name="SyntheticControlData-Introduction"></A>Introduction</H1>
+<P>The example will demonstrate clustering of control charts which exhibits a time series. <A href="http://en.wikipedia.org/wiki/Control_chart" class="external-link" rel="nofollow">Control charts </A> are tools used to determine whether or not a manufacturing or business process is in a state of statistical control. Such control charts are generated / simulated over equal time interval and available for use in UCI machine learning database. The data is described <A href="http://archive.ics.uci.edu/ml/databases/synthetic_control/synthetic_control.data.html" class="external-link" rel="nofollow">here </A>.</P>
+
+<H1><A name="SyntheticControlData-Problemdescription"></A>Problem description</H1>
+<P>A time series of control charts needs to be clustered into their close knit groups. The data set we use is synthetic and so resembles real world information in an anonymized format. It contains six different classes (Normal, Cyclic, Increasing trend, Decreasing trend, Upward shift, Downward shift). With these trends occurring on the input data set, the Mahout clustering algorithm will cluster the data into their corresponding class buckets. At the end of this example, you'll get to learn how to perform clustering using Mahout.</P>
+
+<H1><A name="SyntheticControlData-PrePrep"></A>Pre-Prep</H1>
+<P>Make sure you have the following covered before you work out the example.</P>
+<OL>
+ <LI>Input data set. Download it <A href="http://archive.ics.uci.edu/ml/databases/synthetic_control/synthetic_control.data" class="external-link" rel="nofollow">here </A>.
+ <OL>
+ <LI>Sample input data:<BR>
+Input consists of 600 rows and 60 columns. The rows from 1 - 100 contains Normal data. Rows from 101 - 200 contains cyclic data and so on.. More info <A href="http://archive.ics.uci.edu/ml/databases/synthetic_control/synthetic_control.data.html" class="external-link" rel="nofollow">here </A>. Sample of how the data looks is like below.
+<DIV class="table-wrap">
+<TABLE class="confluenceTable"><TBODY>
+<TR>
+<TH class="confluenceTh"> _time </TH>
+<TH class="confluenceTh"> _time+x </TH>
+<TH class="confluenceTh"> _time+2x </TH>
+<TH class="confluenceTh"> .. </TH>
+<TH class="confluenceTh"> _time+60x </TH>
+</TR>
+<TR>
+<TD class="confluenceTd"> 28.7812 </TD>
+<TD class="confluenceTd"> 34.4632 </TD>
+<TD class="confluenceTd"> 31.3381 </TD>
+<TD class="confluenceTd"> .. </TD>
+<TD class="confluenceTd"> 31.2834 </TD>
+</TR>
+<TR>
+<TD class="confluenceTd"> 24.8923 </TD>
+<TD class="confluenceTd"> 25.741 </TD>
+<TD class="confluenceTd"> 27.5532 </TD>
+<TD class="confluenceTd"> .. </TD>
+<TD class="confluenceTd"> 32.8217 </TD>
+</TR>
+</TBODY></TABLE>
+</DIV>
+
+<P>..<BR>
+..</P>
+<DIV class="table-wrap">
+<TABLE class="confluenceTable"><TBODY>
+<TR>
+<TD class="confluenceTd"> 35.5351 </TD>
+<TD class="confluenceTd"> 41.7067 </TD>
+<TD class="confluenceTd"> 39.1705 </TD>
+<TD class="confluenceTd"> 48.3964 </TD>
+<TD class="confluenceTd"> .. </TD>
+<TD class="confluenceTd"> 38.6103 </TD>
+</TR>
+<TR>
+<TD class="confluenceTd"> 24.2104 </TD>
+<TD class="confluenceTd"> 41.7679 </TD>
+<TD class="confluenceTd"> 45.2228 </TD>
+<TD class="confluenceTd"> 43.7762 </TD>
+<TD class="confluenceTd"> .. </TD>
+<TD class="confluenceTd"> 48.8175 </TD>
+</TR>
+</TBODY></TABLE>
+</DIV>
+
+<P>..<BR>
+..</P></LI>
+ </OL>
+ </LI>
+ <LI>Setup Hadoop
+ <OL>
+ <LI>Assuming that you have installed Hadooop, start the daemons using $HADOOP_HOME/bin/start-all.sh. If you have issues starting Hadoop, please reference the <A href="http://hadoop.apache.org/common/docs/current/quickstart.html" class="external-link" rel="nofollow">Hadoop quick start guide </A></LI>
+ <LI>Copy the input to HDFS using $HADOOP_HOME/bin/hadoop fs -put <PATH TO DATA> testdata (HDFS input directory name should be testdata)</LI>
+ </OL>
+ </LI>
+</OL>
+
+
+<OL>
+ <LI>Mahout Example job<BR>
+Mahout's mahout-examples-$MAHOUT_VERSION.job does the actual clustering task and so it needs to be created. This can be done as
+ <OL>
+ <LI>cd $MAHOUT_HOME</LI>
+ <LI>mvn install. You will see BUILD SUCCESSFUL once all the corresponding tasks are through. The job will be generated in $MAHOUT_HOME/examples/target/ and it's name will contain the $MAHOUT_VERSION number. For example, when using Mahout 0.3 release, the job will be mahout-examples-0.3.job<BR>
+This completes the pre-requisites to perform clustering process using Mahout.</LI>
+ </OL>
+ </LI>
+</OL>
+
+
+<H1><A name="SyntheticControlData-PerformClustering"></A>Perform Clustering</H1>
+<P>With all the pre-work done, clustering the control data gets real simple.</P>
+<OL>
+ <LI>Depending on which clustering technique to use, you can invoke the corresponding job as below
+ <OL>
+ <LI>For <A href="canopy-clustering.html" title="Canopy Clustering">canopy </A>:<BR>
+$HADOOP_HOME/bin/hadoop jar $MAHOUT_HOME/examples/target/mahout-examples-$MAHOUT_VERSION.job org.apache.mahout.clustering.syntheticcontrol.canopy.Job</LI>
+ <LI>For <A href="k-means-clustering.html" title="K-Means Clustering">kmeans </A>:<BR>
+$HADOOP_HOME/bin/hadoop jar $MAHOUT_HOME/examples/target/mahout-examples-$MAHOUT_VERSION.job org.apache.mahout.clustering.syntheticcontrol.kmeans.Job</LI>
+ <LI>For <A href="fuzzy-k-means.html" title="Fuzzy K-Means">fuzzykmeans </A>:<BR>
+$HADOOP_HOME/bin/hadoop jar $MAHOUT_HOME/examples/target/mahout-examples-$MAHOUT_VERSION.job org.apache.mahout.clustering.syntheticcontrol.fuzzykmeans.Job</LI>
+ <LI>For <A href="dirichlet-process-clustering.html" title="Dirichlet Process Clustering">dirichlet </A>:<BR>
+$HADOOP_HOME/bin/hadoop jar $MAHOUT_HOME/examples/target/mahout-examples-$MAHOUT_VERSION.job org.apache.mahout.clustering.syntheticcontrol.dirichlet.Job</LI>
+ <LI>For <A href="mean-shift-clustering.html" title="Mean Shift Clustering">meanshift </A>: $HADOOP_HOME/bin/hadoop jar $MAHOUT_HOME/examples/target/mahout-examples-$MAHOUT_VERSION.job org.apache.mahout.clustering.syntheticcontrol.meanshift.Job</LI>
+ </OL>
+ </LI>
+ <LI>Get the data out of HDFS<STYLE type="text/css">
+.FootnoteMarker, .FootnoteNum a {
+ background: transparent url(/confluence/download/resources/com.adaptavist.confluence.footnoteMacros:footnote/gfx/footnote.png) no-repeat top right;
+ padding: 1px 2px 0px 1px;
+ border-left: 1px solid #8898B8;
+ border-bottom: 1px solid #6B7C9B;
+ margin: 1px;
+ text-decoration: none;
+}
+.FootnoteNum a {
+ margin-top: 2px;
+ margin-right: 0px;
+}
+.FootnoteNum {
+ font-size: x-small;
+ text-align: right;
+ padding-bottom: 4px;
+}
+.footnote-th1 {
+ text-align: right;
+}
+.Footnote {
+ padding-left: 7px;
+ margin-bottom: 4px;
+ border: 1px none #DDDDDD;
+ writingMode: tb-rl;
+}
+.accessibility {
+ display: none;
+ visibility: hidden;
+}
+@media aural,braille,embossed {
+ .FootnoteMarker, .FootnoteNum a {
+ border: 1px solid #000000;
+ background: #ffffff none;
+ }
+ .accessibility {
+ display: run-in;
+ visibility: visible;
+ }
+}
+</STYLE>
+<SCRIPT type="text/javascript" language="JavaScript">
+//<!--\n
+var effectInProgress = {};
+var despamEffect = function (id,effectType,duration) {
+ if ((effectInProgress[id]) || (typeof(Effect)=="undefined") || (typeof(Effect[effectType])=="undefined")) return;
+ new Effect[effectType](id);
+ effectInProgress[id]=true;
+ setTimeout('effectInProgress[\"'+id+'\"]=false;',duration*1000);
+};
+var oldFootnoteId = '';
+var footnoteHighlight = function(id,pulsateNum) {
+ if (oldFootnoteId!='') document.getElementById('Footnote'+oldFootnoteId).style['borderStyle'] = 'none';
+ oldFootnoteId = id;
+ document.getElementById('Footnote'+id).style['borderStyle'] = 'solid';
+ despamEffect('Footnote'+id,'Highlight',1)
+ if (pulsateNum) despamEffect('FootnoteNum'+id,'Pulsate',3)
+}
+var footnoteMarkerHighlight = function(id) {
+ if (oldFootnoteId!='') document.getElementById('Footnote'+oldFootnoteId).style['borderStyle'] = 'none';
+ oldFootnoteId = '';
+ despamEffect('FootnoteMarker'+id,'Pulsate',3)
+}
+//-->
+</SCRIPT>
+
+<SUP id="FootnoteMarker1">
+ <A name="FootnoteMarker1" href="#Footnote1" onclick="footnoteHighlight("1",true);" alt="Footnote: Click here to display the footnote" title="Footnote: Click here to display the footnote" class="FootnoteMarker">
+ 1
+ </A>
+</SUP>
+
+<SUP id="FootnoteMarker2">
+ <A name="FootnoteMarker2" href="#Footnote2" onclick="footnoteHighlight("2",true);" alt="Footnote: Click here to display the footnote" title="Footnote: Click here to display the footnote" class="FootnoteMarker">
+ 2
+ </A>
+</SUP>
+ and have a look
+<SUP id="FootnoteMarker3">
+ <A name="FootnoteMarker3" href="#Footnote3" onclick="footnoteHighlight("3",true);" alt="Footnote: Click here to display the footnote" title="Footnote: Click here to display the footnote" class="FootnoteMarker">
+ 3
+ </A>
+</SUP>
+ by following the below steps</LI>
+</OL>
+
+
+<H1><A name="SyntheticControlData-Read%2FAnalyzeOutput"></A>Read / Analyze Output</H1>
+
+<OL>
+ <LI>Use $HADOOP_HOME/bin/hadoop fs -lsr output_ to view all outputs.</LI>
+ <LI>Use $HADOOP_HOME/bin/hadoop fs -get output $MAHOUT_HOME/examples/output to copy them all to your local machine and the output data points are in vector format.</LI>
+ <LI>Computed clusters are contained in <EM>output/clusters-i</EM></LI>
+ <LI>All result clustered points are placed into <EM>output/clusteredPoints</EM></LI>
+ <LI>you can run the ClusterDumper on them.</LI>
+</OL>
+
+
+<P><TABLE class="Footnotes" style="width: 100%; border:none;" cellspacing="0" cellpadding="0" summary="This table contains one or more notes for references made elsewhere on the page.">
+ <CAPTION class="accessibility">Footnotes</CAPTION>
+ <THEAD class="accessibility">
+ <TR class="accessibility">
+ <TH class="accessibility" id="footnote-th1">Reference</TH>
+ <TH class="accessibility" id="footnote-th2">Notes</TH>
+ </TR>
+ </THEAD>
+ <TBODY>
+ <TR name="Footnote1">
+ <TD valign="top" class="FootnoteNum" headings="footnote-th1">
+ <A href="#FootnoteMarker1" onclick="footnoteMarkerHighlight("1");" onmouseover="footnoteHighlight("1",false);" alt="Footnote: Click to return to reference in text" title="Footnote: Click to return to reference in text" id="FootnoteNum1">
+ 1
+ </A>
+ </TD>
+ <TD id="Footnote1" valign="top" width="100%" class="Footnote" headings="footnote-th2">
+ See <A href="http://hadoop.apache.org/core/docs/current/hdfs_shell.html" class="external-link" rel="nofollow">HDFS Shell </A>
+ </TD>
+ </TR>
+ <TR name="Footnote2">
+ <TD valign="top" class="FootnoteNum" headings="footnote-th1">
+ <A href="#FootnoteMarker2" onclick="footnoteMarkerHighlight("2");" onmouseover="footnoteHighlight("2",false);" alt="Footnote: Click to return to reference in text" title="Footnote: Click to return to reference in text" id="FootnoteNum2">
+ 2
+ </A>
+ </TD>
+ <TD id="Footnote2" valign="top" width="100%" class="Footnote" headings="footnote-th2">
+ The output directory is cleared when a new run starts so the results must be retrieved before a new run
+ </TD>
+ </TR>
+ <TR name="Footnote3">
+ <TD valign="top" class="FootnoteNum" headings="footnote-th1">
+ <A href="#FootnoteMarker3" onclick="footnoteMarkerHighlight("3");" onmouseover="footnoteHighlight("3",false);" alt="Footnote: Click to return to reference in text" title="Footnote: Click to return to reference in text" id="FootnoteNum3">
+ 3
+ </A>
+ </TD>
+ <TD id="Footnote3" valign="top" width="100%" class="Footnote" headings="footnote-th2">
+ Dirichlet also prints data to console
+ </TD>
+ </TR>
+ </TBODY>
+</TABLE></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/syntheticcontroldata.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/syntheticcontroldata.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/syntheticcontroldata.html (added)
+++ mahout/site/new_website/MAHOUT/syntheticcontroldata.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,314 @@
+
+<!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('http://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>SyntheticControlData</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="">
+ <A href="index.html" title="Apache Lucene Mahout">Apache Lucene Mahout</A> > <A href="index.html" title="index">index</A> > <A href="quickstart.html" title="QuickStart">QuickStart</A> > <A href="" title="SyntheticControlData">SyntheticControlData</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">SyntheticControlData</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="http://cwiki.apache.org/confluence/pages/editpage.action?pageId=103663">
+ <IMG src="http://cwiki.apache.org/confluence/images/icons/notep_16.gif" height="16" width="16" border="0" align="absmiddle" title="Edit Page"></A>
+ <A href="http://cwiki.apache.org/confluence/pages/editpage.action?pageId=103663">Edit Page</A>
+
+ <A href="http://cwiki.apache.org/confluence/pages/listpages.action?key=MAHOUT">
+ <IMG src="http://cwiki.apache.org/confluence/images/icons/browse_space.gif" height="16" width="16" border="0" align="absmiddle" title="Browse Space"></A>
+ <A href="http://cwiki.apache.org/confluence/pages/listpages.action?key=MAHOUT">Browse Space</A>
+
+ <A href="http://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=103663">
+ <IMG src="http://cwiki.apache.org/confluence/images/icons/add_page_16.gif" height="16" width="16" border="0" align="absmiddle" title="Add Page"></A>
+ <A href="http://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=103663">Add Page</A>
+
+ <A href="http://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=103663">
+ <IMG src="http://cwiki.apache.org/confluence/images/icons/add_blogentry_16.gif" height="16" width="16" border="0" align="absmiddle" title="Add News"></A>
+ <A href="http://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=103663">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="SyntheticControlData-Introduction"></A>Introduction</H1>
+
+<P>This quick start page shows how to run the clustering Synthetic Control Data example. The data is described <A href="http://archive.ics.uci.edu/ml/databases/synthetic_control/synthetic_control.data.html" class="external-link" rel="nofollow">here </A>.</P>
+
+
+<H1><A name="SyntheticControlData-Steps"></A>Steps</H1>
+
+<UL>
+ <LI>Download the data at <A href="http://archive.ics.uci.edu/ml/datasets/Synthetic%20Control%20Chart%20Time%20Series" class="external-link" rel="nofollow">http://archive.ics.uci.edu/ml/datasets/Synthetic+Control+Chart+Time+Series</A>.</LI>
+ <LI>In $MAHOUT_HOME/, build the Job file
+ <UL>
+ <LI>The same job is used for all examples so this only needs to be done once</LI>
+ <LI>mvn install</LI>
+ <LI>The job will be generated in $MAHOUT_HOME/examples/target/ and it's name will contain the $MAHOUT_VERSION number. For example, when using Mahout 0.3 release, the job will be mahout-examples-0.3.job</LI>
+ </UL>
+ </LI>
+ <LI>(Optional)<STYLE type="text/css">
+.FootnoteMarker, .FootnoteNum a {
+ background: transparent url(/confluence/download/resources/com.adaptavist.confluence.footnoteMacros:footnote/gfx/footnote.png) no-repeat top right;
+ padding: 1px 2px 0px 1px;
+ border-left: 1px solid #8898B8;
+ border-bottom: 1px solid #6B7C9B;
+ margin: 1px;
+ text-decoration: none;
+}
+.FootnoteNum a {
+ margin-top: 2px;
+ margin-right: 0px;
+}
+.FootnoteNum {
+ font-size: x-small;
+ text-align: right;
+ padding-bottom: 4px;
+}
+.footnote-th1 {
+ text-align: right;
+}
+.Footnote {
+ padding-left: 7px;
+ margin-bottom: 4px;
+ border: 1px none #DDDDDD;
+ writingMode: tb-rl;
+}
+.accessibility {
+ display: none;
+ visibility: hidden;
+}
+@media aural,braille,embossed {
+ .FootnoteMarker, .FootnoteNum a {
+ border: 1px solid #000000;
+ background: #ffffff none;
+ }
+ .accessibility {
+ display: run-in;
+ visibility: visible;
+ }
+}
+</STYLE>
+<SCRIPT type="text/javascript" language="JavaScript">
+//<!--\n
+var effectInProgress = {};
+var despamEffect = function (id,effectType,duration) {
+ if ((effectInProgress[id]) || (typeof(Effect)=="undefined") || (typeof(Effect[effectType])=="undefined")) return;
+ new Effect[effectType](id);
+ effectInProgress[id]=true;
+ setTimeout('effectInProgress[\"'+id+'\"]=false;',duration*1000);
+};
+var oldFootnoteId = '';
+var footnoteHighlight = function(id,pulsateNum) {
+ if (oldFootnoteId!='') document.getElementById('Footnote'+oldFootnoteId).style['borderStyle'] = 'none';
+ oldFootnoteId = id;
+ document.getElementById('Footnote'+id).style['borderStyle'] = 'solid';
+ despamEffect('Footnote'+id,'Highlight',1)
+ if (pulsateNum) despamEffect('FootnoteNum'+id,'Pulsate',3)
+}
+var footnoteMarkerHighlight = function(id) {
+ if (oldFootnoteId!='') document.getElementById('Footnote'+oldFootnoteId).style['borderStyle'] = 'none';
+ oldFootnoteId = '';
+ despamEffect('FootnoteMarker'+id,'Pulsate',3)
+}
+//-->
+</SCRIPT>
+
+<SUP id="FootnoteMarker1">
+ <A name="FootnoteMarker1" href="#Footnote1" onclick="footnoteHighlight("1",true);" alt="Footnote: Click here to display the footnote" title="Footnote: Click here to display the footnote" class="FootnoteMarker">
+ 1
+ </A>
+</SUP>
+ Start up Hadoop: $HADOOP_HOME/bin/start-all.sh</LI>
+ <LI>Put the data: $HADOOP_HOME/bin/hadoop fs -put <PATH TO DATA> testdata</LI>
+ <LI>Run the Job: $HADOOP_HOME/bin/hadoop jar $MAHOUT_HOME/examples/target/mahout-examples-$MAHOUT_VERSION.job org.apache.mahout.clustering.syntheticcontrol.kmeans.Job
+<SUP id="FootnoteMarker2">
+ <A name="FootnoteMarker2" href="#Footnote2" onclick="footnoteHighlight("2",true);" alt="Footnote: Click here to display the footnote" title="Footnote: Click here to display the footnote" class="FootnoteMarker">
+ 2
+ </A>
+</SUP>
+
+ <UL>
+ <LI>For <A href="k-means.html" title="k-Means">kmeans </A>: $HADOOP_HOME/bin/hadoop jar $MAHOUT_HOME/examples/target/mahout-examples-$MAHOUT_VERSION.job org.apache.mahout.clustering.syntheticcontrol.kmeans.Job</LI>
+ <LI>For <A href="canopy-clustering.html" title="Canopy Clustering">canopy </A>: $HADOOP_HOME/bin/hadoop jar $MAHOUT_HOME/examples/target/mahout-examples-$MAHOUT_VERSION.job org.apache.mahout.clustering.syntheticcontrol.canopy.Job</LI>
+ <LI>For <A href="dirichlet-process-clustering.html" title="Dirichlet Process Clustering">dirichlet </A>: $HADOOP_HOME/bin/hadoop jar $MAHOUT_HOME/examples/target/mahout-examples-$MAHOUT_VERSION.job org.apache.mahout.clustering.syntheticcontrol.dirichlet.Job</LI>
+ <LI>For <A href="mean-shift.html" title="Mean Shift">meanshift </A>: $HADOOP_HOME/bin/hadoop jar $MAHOUT_HOME/examples/target/mahout-examples-$MAHOUT_VERSION.job org.apache.mahout.clustering.syntheticcontrol.meanshift.Job</LI>
+ </UL>
+ </LI>
+ <LI>Get the data out of HDFS
+<SUP id="FootnoteMarker3">
+ <A name="FootnoteMarker3" href="#Footnote3" onclick="footnoteHighlight("3",true);" alt="Footnote: Click here to display the footnote" title="Footnote: Click here to display the footnote" class="FootnoteMarker">
+ 3
+ </A>
+</SUP>
+
+<SUP id="FootnoteMarker4">
+ <A name="FootnoteMarker4" href="#Footnote4" onclick="footnoteHighlight("4",true);" alt="Footnote: Click here to display the footnote" title="Footnote: Click here to display the footnote" class="FootnoteMarker">
+ 4
+ </A>
+</SUP>
+ and have a look
+<SUP id="FootnoteMarker5">
+ <A name="FootnoteMarker5" href="#Footnote5" onclick="footnoteHighlight("5",true);" alt="Footnote: Click here to display the footnote" title="Footnote: Click here to display the footnote" class="FootnoteMarker">
+ 5
+ </A>
+</SUP>
+
+ <UL>
+ <LI>All example jobs use <EM>testdata</EM> as input and output to directory <EM>output</EM></LI>
+ <LI>Use <EM>bin/hadoop fs -lsr output</EM> to view all outputs. Copy them all to your local machine and you can run the ClusterDumper on them.
+ <UL>
+ <LI>Sequence files containing the original points in Vector form are in <EM>output/data</EM></LI>
+ <LI>Computed clusters are contained in <EM>output/clusters-i</EM></LI>
+ <LI>All result clustered points are placed into <EM>output/clusteredPoints</EM></LI>
+ </UL>
+ </LI>
+ </UL>
+ </LI>
+</UL>
+
+
+<P><TABLE class="Footnotes" style="width: 100%; border:none;" cellspacing="0" cellpadding="0" summary="This table contains one or more notes for references made elsewhere on the page.">
+ <CAPTION class="accessibility">Footnotes</CAPTION>
+ <THEAD class="accessibility">
+ <TR class="accessibility">
+ <TH class="accessibility" id="footnote-th1">Reference</TH>
+ <TH class="accessibility" id="footnote-th2">Notes</TH>
+ </TR>
+ </THEAD>
+ <TBODY>
+ <TR name="Footnote1">
+ <TD valign="top" class="FootnoteNum" headings="footnote-th1">
+ <A href="#FootnoteMarker1" onclick="footnoteMarkerHighlight("1");" onmouseover="footnoteHighlight("1",false);" alt="Footnote: Click to return to reference in text" title="Footnote: Click to return to reference in text" id="FootnoteNum1">
+ 1
+ </A>
+ </TD>
+ <TD id="Footnote1" valign="top" width="100%" class="Footnote" headings="footnote-th2">
+ This step should be skipped when using standalone Hadoop
+ </TD>
+ </TR>
+ <TR name="Footnote2">
+ <TD valign="top" class="FootnoteNum" headings="footnote-th1">
+ <A href="#FootnoteMarker2" onclick="footnoteMarkerHighlight("2");" onmouseover="footnoteHighlight("2",false);" alt="Footnote: Click to return to reference in text" title="Footnote: Click to return to reference in text" id="FootnoteNum2">
+ 2
+ </A>
+ </TD>
+ <TD id="Footnote2" valign="top" width="100%" class="Footnote" headings="footnote-th2">
+ Substitute in whichever Clustring Job you want here: KMeans, Canopy, etc. See subdirectories of $MAHOUT_HOME/examples/src/main/java/org/apache/mahout/clustering/syntheticcontrol/.
+ </TD>
+ </TR>
+ <TR name="Footnote3">
+ <TD valign="top" class="FootnoteNum" headings="footnote-th1">
+ <A href="#FootnoteMarker3" onclick="footnoteMarkerHighlight("3");" onmouseover="footnoteHighlight("3",false);" alt="Footnote: Click to return to reference in text" title="Footnote: Click to return to reference in text" id="FootnoteNum3">
+ 3
+ </A>
+ </TD>
+ <TD id="Footnote3" valign="top" width="100%" class="Footnote" headings="footnote-th2">
+ See <A href="http://hadoop.apache.org/core/docs/current/hdfs_shell.html" class="external-link" rel="nofollow">HDFS Shell </A>
+ </TD>
+ </TR>
+ <TR name="Footnote4">
+ <TD valign="top" class="FootnoteNum" headings="footnote-th1">
+ <A href="#FootnoteMarker4" onclick="footnoteMarkerHighlight("4");" onmouseover="footnoteHighlight("4",false);" alt="Footnote: Click to return to reference in text" title="Footnote: Click to return to reference in text" id="FootnoteNum4">
+ 4
+ </A>
+ </TD>
+ <TD id="Footnote4" valign="top" width="100%" class="Footnote" headings="footnote-th2">
+ The output directory is cleared when a new run starts so the results must be retrieved before a new run
+ </TD>
+ </TR>
+ <TR name="Footnote5">
+ <TD valign="top" class="FootnoteNum" headings="footnote-th1">
+ <A href="#FootnoteMarker5" onclick="footnoteMarkerHighlight("5");" onmouseover="footnoteHighlight("5",false);" alt="Footnote: Click to return to reference in text" title="Footnote: Click to return to reference in text" id="FootnoteNum5">
+ 5
+ </A>
+ </TD>
+ <TD id="Footnote5" valign="top" width="100%" class="Footnote" headings="footnote-th2">
+ Dirichlet also prints data to console
+ </TD>
+ </TR>
+ </TBODY>
+</TABLE></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/system-requirements.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/system-requirements.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/system-requirements.html (added)
+++ mahout/site/new_website/MAHOUT/system-requirements.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,164 @@
+
+<!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>System Requirements</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="">
+ <A href="mahout-wiki.html" title="Apache Mahout">Apache Mahout</A> > <A href="mahout-wiki.html" title="Mahout Wiki">Mahout Wiki</A> > <A href="" title="System Requirements">System Requirements</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">System Requirements</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=22872408">
+ <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=22872408">Edit Page</A>
+
+ <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>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=22872408">
+ <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=22872408">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=22872408">
+ <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=22872408">Add News</A>
+ </DIV>
+ </DIV>
+
+ <DIV class="pagecontent">
+ <DIV class="wiki-content">
+ <UL>
+ <LI>Java 1.6.x or greater.</LI>
+ <LI>Maven 2.x to build the source code.</LI>
+</UL>
+
+
+<P>CPU, Disk and Memory requirements are based on the many choices made in implementing your application with Mahout (document size, number of documents, and number of hits retrieved to name a few.)</P>
+
+<P>Several of the Mahout algorithms are implemented to work on Hadoop clusters. If not advertised differently, those implementations work with Hadoop 0.20.0 or greater.</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="thirdparty-dependencies.html" title="Thirdparty Dependencies">Thirdparty Dependencies</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/systemrequirements.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/systemrequirements.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/systemrequirements.html (added)
+++ mahout/site/new_website/MAHOUT/systemrequirements.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,127 @@
+
+<!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>SystemRequirements</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="">
+ <A href="index.html" title="Apache Lucene Mahout">Apache Lucene Mahout</A> > <A href="index.html" title="index">index</A> > <A href="" title="SystemRequirements">SystemRequirements</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">SystemRequirements</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=22872408">
+ <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=22872408">Edit Page</A>
+
+ <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>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&fromPageId=22872408">
+ <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=22872408">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=22872408">
+ <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=22872408">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="SystemRequirements-SystemRequirements"></A>System Requirements</H1>
+
+<UL>
+ <LI>Java 1.6.x or greater.</LI>
+ <LI>Maven 2.x to build the source code.</LI>
+</UL>
+
+
+<P>CPU, Disk and Memory requirements are based on the many choices made in implementing your application with Mahout (document size, number of documents, and number of hits retrieved to name a few.)</P>
+
+<P>Several of the Mahout algorithms are implemented to work on Hadoop clusters. If not advertised differently, those implementations work with Hadoop 0.20.0 or greater.</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