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 [7/38] - 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/books...
Added: mahout/site/new_website/MAHOUT/creating-vectors-from-wekas-arff-format.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/creating-vectors-from-wekas-arff-format.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/creating-vectors-from-wekas-arff-format.html (added)
+++ mahout/site/new_website/MAHOUT/creating-vectors-from-wekas-arff-format.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,183 @@
+
+<!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>Creating Vectors from Weka's ARFF Format</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="creating-vectors.html" title="Creating Vectors">Creating Vectors</A> > <A href="" title="Creating Vectors from Weka's ARFF Format">Creating Vectors from Weka's ARFF Format</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">Creating Vectors from Weka's ARFF Format</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=2329939">
+ <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=2329939">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=2329939">
+ <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=2329939">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=2329939">
+ <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=2329939">Add News</A>
+ </DIV>
+ </DIV>
+
+ <DIV class="pagecontent">
+ <DIV class="wiki-content">
+ <H1><A name="CreatingVectorsfromWeka%27sARFFFormat-Introduction"></A>Introduction</H1>
+
+<P>Mahout now has capabilities for converting Weka's <A href="http://www.cs.waikato.ac.nz/~ml/weka/arff.html" class="external-link" rel="nofollow">ARFF</A> (2.1) format to Mahout's Vector format.</P>
+
+<H1><A name="CreatingVectorsfromWeka%27sARFFFormat-RunningtheConverter"></A>Running the Converter</H1>
+
+<P>ARFF files are easily converted using the org.apache.mahout.utils.arff.Driver program. The input arguments can be found by running it with the --help argument which produces results similar to:</P>
+<DIV class="preformatted panel" style="border-width: 1px;"><DIV class="preformattedContent panelContent">
+<PRE>Usage:
+ [--input <input> --output <output> --max <max> --help --dictOut <dictOut>
+--outputWriter <outputWriter> --delimiter <delimiter>]
+Options
+ --input (-d) input The file or directory containing the ARFF
+ files. If it is a directory, all .arff
+ files will be converted. (Mandatory parameter)
+ --output (-o) output The output directory. Files will have
+ the same name as the input, but with the
+ extension .mvc (Mandatory parameter)
+ --max (-m) max The maximum number of vectors to output.
+ If not specified, then it will loop over
+ all docs (Optional parameter)
+ --help (-h) Print out help (Optional parameter)
+ --dictOut (-t) dictOut The file to output the label bindings
+ (Mandatory parameter)
+ --outputWriter (-e) outputWriter The VectorWriter to use, either seq
+ (SequenceFileVectorWriter - default) or
+ file (Writes to a File using JSON format)
+ (Optional parameter)
+ --delimiter (-l) delimiter The delimiter for outputing the
+ dictionary (Optional parameter)
+
+</PRE>
+</DIV></DIV>
+
+<P>You can use the parameters in its long format like --input or using the equivalent short name -d. From here, running the Driver is as simple as pointing it at the ARFF file:</P>
+<DIV class="preformatted panel" style="border-width: 1px;"><DIV class="preformattedContent panelContent">
+<PRE>$MAHOUT_HOME/bin/mahout arff.vector -d ./content/reuters-modapte/ \
+ -t ./content/reuters-modapte/output/dict.txt -o ./content/reuters-modapte/output/convert
+</PRE>
+</DIV></DIV>
+ </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/creating-vectors.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/creating-vectors.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/creating-vectors.html (added)
+++ mahout/site/new_website/MAHOUT/creating-vectors.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,165 @@
+
+<!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>Creating Vectors</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="Creating Vectors">Creating Vectors</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">Creating Vectors</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=2329241">
+ <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=2329241">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=2329241">
+ <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=2329241">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=2329241">
+ <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=2329241">Add News</A>
+ </DIV>
+ </DIV>
+
+ <DIV class="pagecontent">
+ <DIV class="wiki-content">
+ <H1><A name="CreatingVectors-UtilitiesforCreatingVectors"></A>Utilities for Creating Vectors</H1>
+
+<OL>
+ <LI><A href="creating-vectors-from-text.html" title="Creating Vectors from Text">Text</A></LI>
+ <LI><A href="creating-vectors-from-wekas-arff-format.html" title="Creating Vectors from Weka's ARFF Format">ARFF</A></LI>
+</OL>
+
+ </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="creating-vectors-from-text.html" title="Creating Vectors from Text">Creating Vectors from Text</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="creating-vectors-from-wekas-arff-format.html" title="Creating Vectors from Weka's ARFF Format">Creating Vectors from Weka's ARFF Format</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/data-formats.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/data-formats.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/data-formats.html (added)
+++ mahout/site/new_website/MAHOUT/data-formats.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,247 @@
+
+<!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>Data Formats</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="Data Formats">Data Formats</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">Data Formats</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=27831075">
+ <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=27831075">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=27831075">
+ <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=27831075">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=27831075">
+ <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=27831075">Add News</A>
+ </DIV>
+ </DIV>
+
+ <DIV class="pagecontent">
+ <DIV class="wiki-content">
+ <P>Mahout uses a few file formats quite a bit in its various job implementations.</P>
+<DIV>
+<UL>
+ <LI><A href="#DataFormats-Fileformats">File formats</A></LI>
+<UL>
+ <LI><A href="#DataFormats-Rawformatsforimport">Raw formats for import</A></LI>
+ <LI><A href="#DataFormats-Rawformatsforexport">Raw formats for export</A></LI>
+</UL>
+ <LI><A href="#DataFormats-WhoStoresWhatinaSequenceFile%253F">Who Stores What in a SequenceFile?</A></LI>
+<UL>
+ <LI><A href="#DataFormats-%2522Simple%2522TextVectors">"Simple" Text Vectors</A></LI>
+ <LI><A href="#DataFormats-EncodedTextVectors">Encoded Text Vectors</A></LI>
+ <LI><A href="#DataFormats-Directories">Directories</A></LI>
+ <LI><A href="#DataFormats-Matrices">Matrices</A></LI>
+ <LI><A href="#DataFormats-Clusters">Clusters</A></LI>
+ <LI><A href="#DataFormats-FPGrowthClusters">FPGrowth Clusters</A></LI>
+</UL>
+ <LI><A href="#DataFormats-Lifecycle">Life cycle</A></LI>
+</UL></DIV>
+<H2><A name="DataFormats-Fileformats"></A>File formats</H2>
+<H3><A name="DataFormats-Rawformatsforimport"></A>Raw formats for import</H3>
+<UL>
+ <LI>Text files
+ <UL>
+ <LI>can be parsed into SequenceFiles of:
+ <UL>
+ <LI>(line number, text of line)</LI>
+ <LI>(file name, full contents of file)</LI>
+ <LI>(line number, parts of line extracted with regex patterns)</LI>
+ </UL>
+ </LI>
+ <LI>can also be parsed into Lucene indexes:
+ <UL>
+ <LI><EM>precise index design ???</EM></LI>
+ </UL>
+ </LI>
+ </UL>
+ </LI>
+ <LI>ARFF files
+ <UL>
+ <LI>Weka project text data format</LI>
+ <LI>Parsed into SequenceFile of <Int,Vector></LI>
+ </UL>
+ </LI>
+ <LI>Mailbox files
+ <UL>
+ <LI>can be parsed into SequenceFiles of:
+ <UL>
+ <LI>(mail message id, text body of mail message)</LI>
+ <LI>no html or attachment support</LI>
+ </UL>
+ </LI>
+ </UL>
+ </LI>
+ <LI>CSV files
+ <UL>
+ <LI>generally without column or row headers</LI>
+ <LI>no "multiple values per column" options</LI>
+ </UL>
+ </LI>
+ <LI>Hadoop SequenceFile
+ <UL>
+ <LI>canonical, no variations. Currently no use of metadata.</LI>
+ </UL>
+ </LI>
+ <LI>Lucene indexes
+ <UL>
+ <LI>translated into SequenceFiles
+ <UL>
+ <LI><EM>precise index design ???</EM></LI>
+ </UL>
+ </LI>
+ </UL>
+ </LI>
+</UL>
+
+
+<H3><A name="DataFormats-Rawformatsforexport"></A>Raw formats for export</H3>
+<UL>
+ <LI>SequenceFiles</LI>
+ <LI>Text lines, mostly of the toString() variety</LI>
+ <LI>MatrixWritable for ConfusionMatrix</LI>
+ <LI>CSV for MatrixWritable</LI>
+ <LI>A special CSV format for Clusters</LI>
+ <LI><A href="http://graphml.graphdrawing.org/" class="external-link" rel="nofollow">GraphML XML</A> for Clusters</LI>
+</UL>
+
+
+<H2><A name="DataFormats-WhoStoresWhatinaSequenceFile%3F"></A>Who Stores What in a SequenceFile? </H2>
+<H3><A name="DataFormats-%22Simple%22TextVectors"></A>"Simple" Text Vectors</H3>
+<P>Simple text vectors represent documents. The dimensions are the set of terms in the entire document set. Each document vector stores a number in the position of each term it contains. This number may be derived from the count of the term inside the document.</P>
+<H3><A name="DataFormats-EncodedTextVectors"></A>Encoded Text Vectors</H3>
+<P>Each vector represents a document. However, term dimensions are "collapsed" stochastically, meaning each term in the full term set is mapped randomly to several smaller indexes. </P>
+<H3><A name="DataFormats-Directories"></A>Directories</H3>
+<P><Integer,Text> pairs which match matrix rows to input text keys like movie names, document file names etc. These are made by RowIdJob.</P>
+<H3><A name="DataFormats-Matrices"></A>Matrices</H3>
+<P>Matrices are almost universally stored as LongWritable/VectorWritable pairs, where VectorWritable can be sparse or dense.</P>
+<H3><A name="DataFormats-Clusters"></A>Clusters</H3>
+<P>Clusters are stored in complex data structures.</P>
+<H3><A name="DataFormats-FPGrowthClusters"></A>FPGrowth Clusters</H3>
+<P>These are stored in a custom data structure.</P>
+
+<H2><A name="DataFormats-Lifecycle"></A>Life cycle</H2>
+<P>All Mahout jobs generally assume that files generated have no lifespan. All Writable formats may change, and some may disappear. There are no file compatibility requirements.</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/data-processing.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/data-processing.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/data-processing.html (added)
+++ mahout/site/new_website/MAHOUT/data-processing.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,190 @@
+
+<!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>Data Processing</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="Data Processing">Data Processing</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">Data Processing</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=27831059">
+ <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=27831059">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=27831059">
+ <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=27831059">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=27831059">
+ <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=27831059">Add News</A>
+ </DIV>
+ </DIV>
+
+ <DIV class="pagecontent">
+ <DIV class="wiki-content">
+ <P>Mahout has several programs which do useful operations on formats used in Mahout. These are Mahout jobs, mostly map/reduce capable.</P>
+<H3><A name="DataProcessing-Mathoperations"></A>Math operations</H3>
+<UL>
+ <LI>bin/mahout transpose
+ <UL>
+ <LI>transpose a matrix</LI>
+ </UL>
+ </LI>
+ <LI>bin/mahout matrixmult
+ <UL>
+ <LI>multiply two or more matrices</LI>
+ </UL>
+ </LI>
+ <LI>bin/mahout svd
+ <UL>
+ <LI>Lanzcos algorithm for SVD</LI>
+ </UL>
+ </LI>
+ <LI>bin/mahout ssvd
+ <UL>
+ <LI>Stochastic SVD</LI>
+ </UL>
+ </LI>
+ <LI>bin/mahout cleansvd
+ <UL>
+ <LI>Something useful</LI>
+ </UL>
+ </LI>
+</UL>
+
+
+<P><B>Note:</B> many of these have options to only create some outputs, or limit the accuracy of outputs in the name of efficiency & tractability</P>
+<H3><A name="DataProcessing-Otheroperations"></A>Other operations</H3>
+<UL>
+ <LI>bin/mahout split
+ <UL>
+ <LI>Split an input set into training and test parts</LI>
+ <LI>Can take text inputs or SequenceFiles</LI>
+ </UL>
+ </LI>
+ <LI>bin/mahout splitDataset
+ <UL>
+ <LI>Split a recommender rating dataset into training and test parts</LI>
+ </UL>
+ </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/database-integrations.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/database-integrations.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/database-integrations.html (added)
+++ mahout/site/new_website/MAHOUT/database-integrations.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>Database Integrations</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="Database Integrations">Database Integrations</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">Database Integrations</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=27830938">
+ <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=27830938">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=27830938">
+ <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=27830938">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=27830938">
+ <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=27830938">Add News</A>
+ </DIV>
+ </DIV>
+
+ <DIV class="pagecontent">
+ <DIV class="wiki-content">
+ <P>The Recommender suite has a few database integrations for reading preference data: JDBC, MongoDB and Cassandra. There are also integrations for SlopeOne delta data, including subclasses for various databases. Otherwise there are no explicit JDBC or NoSQL integrations in Mahout. File format drivers for Hadoop should work with Mahout.</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/developer-resources.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/developer-resources.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/developer-resources.html (added)
+++ mahout/site/new_website/MAHOUT/developer-resources.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,198 @@
+
+<!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>Developer Resources</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="Developer Resources">Developer Resources</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">Developer Resources</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=22872443">
+ <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=22872443">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=22872443">
+ <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=22872443">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=22872443">
+ <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=22872443">Add News</A>
+ </DIV>
+ </DIV>
+
+ <DIV class="pagecontent">
+ <DIV class="wiki-content">
+ <H2><A name="DeveloperResources-MakingaContribution"></A>Making a Contribution</H2>
+
+<P>Mahout is always looking for contributions, especially in the areas of documentation. See this Wiki for details on contributing: <A href="https://cwiki.apache.org/MAHOUT/how-to-contribute.html" class="external-link" rel="nofollow">How to contribute</A></P>
+
+<P>We provide a list of items in JIRA that are aimed at new contributors and should be fairly easy to start on, these are labeled with <A href="https://issues.apache.org/jira/secure/IssueNavigator.jspa?reset=true&jqlQuery=labels%20%3D%20MAHOUT_INTRO_CONTRIBUTE" class="external-link" rel="nofollow">MAHOUT_INTRO_CONTRIBUTE</A>.</P>
+
+<H2><A name="DeveloperResources-SourceCode"></A>Source Code</H2>
+
+<P>The source files are now stored using Subversion (see <A href="http://subversion.tigris.org/" class="external-link" rel="nofollow">http://subversion.tigris.org/</A> and <A href="http://svnbook.red-bean.com/" class="external-link" rel="nofollow">http://svnbook.red-bean.com/</A>).</P>
+
+<P>svn checkout <A href="http://svn.apache.org/repos/asf/mahout/trunk" class="external-link" rel="nofollow">http://svn.apache.org/repos/asf/mahout/trunk</A> mahout/trunk</P>
+
+<H2><A name="DeveloperResources-Documentation"></A>Documentation</H2>
+
+<P>Javadoc documentation is available online in our code reports:</P>
+
+<UL>
+ <LI><A href="https://builds.apache.org/hudson/job/Mahout-Quality/javadoc/" class="external-link" rel="nofollow">Latest Javadoc</A></LI>
+ <LI><A href="data-formats.html" class="external-link" rel="nofollow">Data Formats</A></LI>
+ <LI><A href="file-format-integrations.html" class="external-link" rel="nofollow">File Format Integrations</A></LI>
+ <LI><A href="database-integrations.html" class="external-link" rel="nofollow">Database Integrations</A></LI>
+</UL>
+
+
+<H2><A name="DeveloperResources-Issues"></A>Issues</H2>
+
+<P>All bugs, improvements, patches, etc. should be logged in <A href="https://issues.apache.org/jira/browse/MAHOUT" class="external-link" rel="nofollow">JIRA</A>.</P>
+
+<H2><A name="DeveloperResources-ContinuousIntegration"></A>Continuous Integration</H2>
+
+<P>Mahout is continuously built on an hourly basis on the Apache <A href="https://builds.apache.org/job/Mahout-Quality/" class="external-link" rel="nofollow">Jenkins</A> build system.</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="faq.html" title="FAQ">FAQ</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="how-to-contribute.html" title="How To Contribute">How To Contribute</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="how-to-update-the-website.html" title="How To Update The Website">How To Update The Website</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="how-to-become-a-committer.html" title="How To Become A Committer">How To Become A Committer</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="how-to-release.html" title="How To Release">How To Release</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/developerresources.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/developerresources.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/developerresources.html (added)
+++ mahout/site/new_website/MAHOUT/developerresources.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,172 @@
+
+<!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>DeveloperResources</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="DeveloperResources">DeveloperResources</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">DeveloperResources</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=22872443">
+ <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=22872443">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=22872443">
+ <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=22872443">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=22872443">
+ <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=22872443">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="DeveloperResources-ApacheMahoutDeveloperResources"></A>Apache Mahout - Developer Resources</H1>
+
+<H2><A name="DeveloperResources-MakingaContribution"></A>Making a Contribution</H2>
+
+<P>Mahout is always looking for contributions, especially in the areas of documentation. See this Wiki for details on contributing. </P>
+
+<H2><A name="DeveloperResources-SourceCode"></A>Source Code</H2>
+
+<P>The source files are now stored using Subversion (see <A href="http://subversion.tigris.org/" class="external-link" rel="nofollow">http://subversion.tigris.org/</A> and <A href="http://svnbook.red-bean.com/" class="external-link" rel="nofollow">http://svnbook.red-bean.com/</A>). </P>
+
+<P>svn checkout <A href="http://svn.apache.org/repos/asf/lucene/mahout/trunk" class="external-link" rel="nofollow">http://svn.apache.org/repos/asf/lucene/mahout/trunk</A> lucene/mahout/trunk </P>
+
+<H2><A name="DeveloperResources-Documentation"></A>Documentation</H2>
+
+<P>Javadoc documentation is available online in our code reports:</P>
+
+<UL>
+ <LI><A href="http://hudson.zones.apache.org/hudson/userContent/lucene-mahout/core-reports/index.html" class="external-link" rel="nofollow">Core</A></LI>
+ <LI><A href="http://hudson.zones.apache.org/hudson/userContent/lucene-mahout/utils-reports/index.html" class="external-link" rel="nofollow">Utils</A></LI>
+ <LI><A href="http://hudson.zones.apache.org/hudson/userContent/lucene-mahout/matrix-reports/index.html" class="external-link" rel="nofollow">Matrix</A></LI>
+ <LI><A href="http://hudson.zones.apache.org/hudson/userContent/lucene-mahout/examples-reports/index.html" class="external-link" rel="nofollow">Examples</A></LI>
+ <LI><A href="http://hudson.zones.apache.org/hudson/userContent/lucene-mahout/taste-web-reports/index.html" class="external-link" rel="nofollow">Taste</A></LI>
+</UL>
+
+
+<H2><A name="DeveloperResources-Issues"></A>Issues</H2>
+
+<P>All bugs, improvements, patches, etc. should be logged in <A href="https://issues.apache.org/jira/browse/MAHOUT" class="external-link" rel="nofollow">JIRA</A>. </P>
+
+<H2><A name="DeveloperResources-ContinuousIntegration"></A>Continuous Integration</H2>
+
+<P>Mahout is built on a nightly basis on <A href="http://hudson.zones.apache.org/hudson/job/Mahout%20Trunk/" class="external-link" rel="nofollow">Hudson</A>.</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="faq.html" title="FAQ">FAQ</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="how-to-contribute.html" title="How To Contribute">How To Contribute</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="how-to-update-the-website.html" title="How To Update The Website">How To Update The Website</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="how-to-become-a-committer.html" title="How To Become A Committer">How To Become A Committer</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="how-to-release.html" title="How To Release">How To Release</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: 3.2 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