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 [18/38] - 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/mahout-wiki.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/mahout-wiki.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/mahout-wiki.html (added)
+++ mahout/site/new_website/MAHOUT/mahout-wiki.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,434 @@
+
+<!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>Mahout Wiki</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="" title="Apache Mahout">Apache Mahout</A> > <A href="" title="Mahout Wiki">Mahout Wiki</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">Mahout Wiki</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=74539">
+ <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=74539">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=74539">
+ <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=74539">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=74539">
+ <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=74539">Add News</A>
+ </DIV>
+ </DIV>
+
+ <DIV class="pagecontent">
+ <DIV class="wiki-content">
+ <P>Apache Mahout is a new Apache TLP project to create scalable, machine learning algorithms under the Apache license. </P>
+
+<STYLE type="text/css">/*<![CDATA[*/
+div.rbtoc1325524744313 {margin-left: 1.5em;padding: 0px;}
+div.rbtoc1325524744313 ul {list-style: disc;margin-left: 0px;}
+div.rbtoc1325524744313 li {margin-left: 0px;padding-left: 0px;}
+
+/*]]>*/</STYLE><DIV class="rbtoc1325524744313">
+<UL>
+ <LI><A href="#MahoutWiki-General">General</A></LI>
+ <LI><A href="#MahoutWiki-Community">Community</A></LI>
+ <LI><A href="#MahoutWiki-Installation%252FSetup">Installation/Setup</A></LI>
+ <LI><A href="#MahoutWiki-Examples">Examples</A></LI>
+ <LI><A href="#MahoutWiki-ImplementationBackground">Implementation Background</A></LI>
+<UL>
+ <LI><A href="#MahoutWiki-RequirementsandDesign">Requirements and Design</A></LI>
+ <LI><A href="#MahoutWiki-CollectionsandAlgorithms">Collections and Algorithms</A></LI>
+ <LI><A href="#MahoutWiki-Utilities">Utilities</A></LI>
+ <LI><A href="#MahoutWiki-Data">Data</A></LI>
+ <LI><A href="#MahoutWiki-Benchmarks">Benchmarks</A></LI>
+</UL>
+ <LI><A href="#MahoutWiki-Committer%2527sResources">Committer's Resources</A></LI>
+<UL>
+ <LI><A href="#MahoutWiki-ProjectResources">Project Resources</A></LI>
+ <LI><A href="#MahoutWiki-AdditionalResources">Additional Resources</A></LI>
+</UL>
+ <LI><A href="#MahoutWiki-HowToEditThisWiki">How To Edit This Wiki</A></LI>
+</UL></DIV>
+
+<H2><A name="MahoutWiki-General"></A>General</H2>
+<P><A href="overview.html" title="Overview">Overview</A> – Mahout? What's that supposed to be?</P>
+
+<P><A href="quickstart.html" title="Quickstart">Quickstart</A> – learn how to quickly setup Apache Mahout for your project.</P>
+
+<P><A href="faq.html" title="FAQ">FAQ</A> – Frequent questions encountered on the mailing lists.</P>
+
+<P><A href="developer-resources.html" title="Developer Resources">Developer Resources</A> – overview of the Mahout development infrastructure.</P>
+
+<P><A href="how-to-contribute.html" title="How To Contribute">How To Contribute</A> – get involved with the Mahout community.</P>
+
+<P><A href="how-to-become-a-committer.html" title="How To Become A Committer">How To Become A Committer</A> – become a member of the Mahout development community.</P>
+
+<P><A href="http://hadoop.apache.org/" class="external-link" rel="nofollow">Hadoop</A> – several of our implementations depend on Hadoop.</P>
+
+<P><A href="http://mloss.org/software/" class="external-link" rel="nofollow">Machine Learning Open Source Software</A> – other projects implementing Open Source Machine Learning libraries.</P>
+
+<P><A href="mahoutname.html" title="MahoutName">Mahout – The name, history and its pronunciation</A></P>
+
+<H2><A name="MahoutWiki-Community"></A>Community</H2>
+
+<P><A href="who-we-are.html" title="Who We Are">Who we are</A> – who are the developers behind Apache Mahout?</P>
+
+<P><A href="books-tutorials-and-talks.html" title="Books Tutorials and Talks">Books, Tutorials, Talks, Articles, News, Background Reading, etc. on Mahout</A></P>
+
+<P><A href="issue-tracker.html" title="Issue Tracker">Issue Tracker</A> – see what features people are working on, submit patches and file bugs.</P>
+
+<P><A href="https://svn.apache.org/repos/asf/mahout/" class="external-link" rel="nofollow">Source Code (SVN)</A> – <A href="http://fisheye6.atlassian.com/browse/mahout" class="external-link" rel="nofollow">Fisheye</A> – download the Mahout source code from svn.</P>
+
+<P><A href="mailing-lists-irc-and-archives.html" title="Mailing Lists, IRC and Archives">Mailing lists and IRC</A> – links to our mailing lists, IRC channel and archived design and algorithm discussions, maybe your questions was answered there already?</P>
+
+<P><A href="version-control.html" title="Version Control">Version Control</A> – where we track our code.</P>
+
+<P><A href="powered-by-mahout.html" title="Powered By Mahout">Powered By Mahout</A> – who is using Mahout in production?</P>
+
+<P><A href="professional-support.html" title="Professional Support">Professional Support</A> – who is offering professional support for Mahout?</P>
+
+<P><A href="gsoc.html" title="GSOC">Mahout and Google Summer of Code</A> – All you need to know about Mahout and GSoC.</P>
+
+
+<P><A href="glossary.html" title="Glossary">Glossary of commonly used terms and abbreviations</A></P>
+
+<H2><A name="MahoutWiki-Installation%2FSetup"></A>Installation/Setup</H2>
+
+<P><A href="system-requirements.html" title="System Requirements">System Requirements</A> – what do you need to run Mahout?</P>
+
+<P><A href="quickstart.html" title="Quickstart">Quickstart</A> – get started with Mahout, run the examples and get pointers to further resources.</P>
+
+<P><A href="downloads.html" title="Downloads">Downloads</A> – a list of Mahout releases.</P>
+
+<P><A href="buildingmahout.html" title="BuildingMahout">Download and installation</A> – build Mahout from the sources.</P>
+
+<P><A href="mahout-on-amazon-ec2.html" title="Mahout on Amazon EC2">Mahout on Amazon's EC2 Service</A> – run Mahout on Amazon's EC2.</P>
+
+<P><A href="mahout-on-elastic-mapreduce.html" title="Mahout on Elastic MapReduce">Mahout on Amazon's EMR</A> – Run Mahout on Amazon's Elastic Map Reduce</P>
+
+<P><A href="mahoutintegration.html" title="MahoutIntegration">Integrating Mahout into an Application</A> – integrate Mahout's capabilities in your application.</P>
+
+<H2><A name="MahoutWiki-Examples"></A>Examples</H2>
+
+<OL>
+ <LI><A href="asfemail.html" title="ASFEmail">ASF Email Examples</A> – Examples of recommenders, clustering and classification all using a public domain collection of 7 million emails.</LI>
+</OL>
+
+
+<H2><A name="MahoutWiki-ImplementationBackground"></A>Implementation Background</H2>
+
+<H3><A name="MahoutWiki-RequirementsandDesign"></A>Requirements and Design</H3>
+
+<P><A href="matrix-and-vector-needs.html" title="Matrix and Vector Needs">Matrix and Vector Needs</A> – requirements for Mahout vectors.</P>
+
+<P><A href="collectionde-serialization.html" title="Collection(De-)Serialization">Collection(De-)Serialization</A></P>
+
+<H3><A name="MahoutWiki-CollectionsandAlgorithms"></A>Collections and Algorithms</H3>
+
+<P>Learn more about <A href="mahout-collections.html" title="mahout-collections">mahout-collections</A>, containers for efficient storage of primitive-type data and open hash tables.</P>
+
+<P>Learn more about the <A href="algorithms.html" title="Algorithms">Algorithms</A> discussed and employed by Mahout.</P>
+
+<P>Learn more about the <A href="recommender-documentation.html" title="Recommender Documentation">Mahout recommender implementation</A>.</P>
+
+<H3><A name="MahoutWiki-Utilities"></A>Utilities</H3>
+
+<P>This section describes tools that might be useful for working with Mahout.</P>
+
+<P><A href="converting-content.html" title="Converting Content">Converting Content</A> – Mahout has some utilities for converting content such as logs to formats more amenable for consumption by Mahout.<BR>
+<A href="creating-vectors.html" title="Creating Vectors">Creating Vectors</A> – Mahout's algorithms operate on vectors. Learn more on how to generate these from raw data.<BR>
+<A href="viewing-result.html" title="Viewing Result">Viewing Result</A> – How to visualize the result of your trained algorithms.</P>
+
+<H3><A name="MahoutWiki-Data"></A>Data</H3>
+
+<P><A href="collections.html" title="Collections">Collections</A> – To try out and test Mahout's algorithms you need training data. We are always looking for new training data collections.</P>
+
+<H3><A name="MahoutWiki-Benchmarks"></A>Benchmarks</H3>
+
+<P><A href="mahout-benchmarks.html" title="Mahout Benchmarks">Mahout Benchmarks</A></P>
+
+<H2><A name="MahoutWiki-Committer%27sResources"></A>Committer's Resources</H2>
+
+<UL>
+ <LI><A href="testing.html" title="Testing">Testing</A> – Information on test plans and ideas for testing</LI>
+</UL>
+
+
+<H3><A name="MahoutWiki-ProjectResources"></A>Project Resources</H3>
+
+<UL>
+ <LI><A href="thirdparty-dependencies.html" title="Thirdparty Dependencies">Dealing with Third Party Dependencies not in Maven</A></LI>
+ <LI><A href="how-to-update-the-website.html" title="How To Update The Website">How To Update The Website</A></LI>
+ <LI><A href="patch-check-list.html" title="Patch Check List">Patch Check List</A></LI>
+ <LI><A href="http://cwiki.apache.org/confluence/display/MAHOUT/How%20to%20release" class="external-link" rel="nofollow">How To Release</A></LI>
+ <LI><A href="https://analysis.apache.org/dashboard/index/63921" class="external-link" rel="nofollow">Sonar Code Quality Analysis</A></LI>
+</UL>
+
+
+<H3><A name="MahoutWiki-AdditionalResources"></A>Additional Resources</H3>
+
+<UL>
+ <LI><A href="http://monitoring.apache.org/status/" class="external-link" rel="nofollow">Apache Machine Status</A> - Check to see if SVN, other resources are available.</LI>
+ <LI><A href="http://www.apache.org/dev/committers.html" class="external-link" rel="nofollow">Committer's FAQ</A></LI>
+ <LI><A href="http://www.apache.org/dev/" class="external-link" rel="nofollow">Apache Dev</A></LI>
+</UL>
+
+
+
+<H2><A name="MahoutWiki-HowToEditThisWiki"></A>How To Edit This Wiki</H2>
+
+<P>How to edit this Wiki</P>
+
+<P>This Wiki is a collaborative site, anyone can contribute and share:</P>
+
+<UL>
+ <LI>Create an account by clicking the "Login" link at the top of any page, and picking a username and password.</LI>
+ <LI>Edit any page by pressing Edit at the top of the page</LI>
+</UL>
+
+
+<P>There are some conventions used on the Mahout wiki:</P>
+
+<UL>
+ <LI><DIV class="preformatted panel" style="border-width: 1px;"><DIV class="preformattedContent panelContent">
+<PRE>+*TODO:*+</PRE>
+</DIV></DIV>
+<P> (<INS><B>TODO:</B></INS> ) is used to denote sections that definitely need to be cleaned up.</P></LI>
+ <LI><DIV class="preformatted panel" style="border-width: 1px;"><DIV class="preformattedContent panelContent">
+<PRE>+*Mahout_(version)*+</PRE>
+</DIV></DIV>
+<P> (<INS><B>Mahout_0.2</B></INS>) is used to draw attention to which version of Mahout a feature was (or will be) added to Mahout.</P></LI>
+</UL>
+
+
+ </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="mailing-lists-irc-and-archives.html" title="Mailing Lists, IRC and Archives">Mailing Lists, IRC and Archives</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="collections.html" title="Collections">Collections</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="powered-by-mahout.html" title="Powered By Mahout">Powered By Mahout</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="issue-tracker.html" title="Issue Tracker">Issue Tracker</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="books-tutorials-and-talks.html" title="Books Tutorials and Talks">Books Tutorials and Talks</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="what-when-where-why-but-not-how-or-who.html" title="What, When, Where, Why (but not How or Who)">What, When, Where, Why (but not How or Who)</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="quickstart.html" title="Quickstart">Quickstart</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="mahout-on-amazon-ec2.html" title="Mahout on Amazon EC2">Mahout on Amazon EC2</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="reference-reading.html" title="Reference Reading">Reference Reading</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="algorithms.html" title="Algorithms">Algorithms</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="creating-vectors.html" title="Creating Vectors">Creating Vectors</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="glossary.html" title="Glossary">Glossary</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="gsoc.html" title="GSOC">GSOC</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="mahout-benchmarks.html" title="Mahout Benchmarks">Mahout Benchmarks</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="who-we-are.html" title="Who We Are">Who We Are</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="overview.html" title="Overview">Overview</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="system-requirements.html" title="System Requirements">System Requirements</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="downloads.html" title="Downloads">Downloads</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="developer-resources.html" title="Developer Resources">Developer Resources</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="version-control.html" title="Version Control">Version Control</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="privacy-policy.html" title="Privacy Policy">Privacy Policy</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="professional-support.html" title="Professional Support">Professional Support</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="mahoutintegration.html" title="MahoutIntegration">MahoutIntegration</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="using-mahout-with-python-via-jpype.html" title="Using Mahout with Python via JPype">Using Mahout with Python via JPype</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="viewing-result.html" title="Viewing Result">Viewing Result</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="testing.html" title="Testing">Testing</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="algorithm-summary-table.html" title="Algorithm summary table">Algorithm summary table</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="mahoutname.html" title="MahoutName">MahoutName</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="converting-content.html" title="Converting Content">Converting Content</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="database-integrations.html" title="Database Integrations">Database Integrations</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="file-format-integrations.html" title="File Format Integrations">File Format Integrations</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="data-processing.html" title="Data Processing">Data Processing</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="data-formats.html" title="Data Formats">Data Formats</A>
+ <SPAN class="smalltext">(Apache Mahout)</SPAN>
+ <BR>
+ <A href="asfemail.html" title="ASFEmail">ASFEmail</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/mahoutbenchmarks.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/mahoutbenchmarks.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/mahoutbenchmarks.html (added)
+++ mahout/site/new_website/MAHOUT/mahoutbenchmarks.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,179 @@
+
+<!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>MahoutBenchmarks</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="MahoutBenchmarks">MahoutBenchmarks</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">MahoutBenchmarks</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="http://cwiki.apache.org/confluence/pages/editpage.action?pageId=21791409">
+ <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=21791409">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=21791409">
+ <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=21791409">Add Page</A>
+
+ <A href="http://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=21791409">
+ <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=21791409">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="MahoutBenchmarks-Introduction"></A>Introduction</H1>
+
+<P>TODO: YMMV</P>
+
+<H1><A name="MahoutBenchmarks-Recommenders"></A>Recommenders</H1>
+
+<H2><A name="MahoutBenchmarks-ARuleofThumb"></A>A Rule of Thumb</H2>
+
+<P>100M preferences are about the data set size where non-distributed recommenders will outgrow a normal-sized machine (32-bit, <= 4GB RAM). Your mileage will vary significantly with the nature of the data.</P>
+
+<H2><A name="MahoutBenchmarks-Distributedrecommendervs.Wikipedialinks%28May272010%29"></A>Distributed recommender vs. Wikipedia links (May 27 2010)</H2>
+
+<P>From the mailing list:</P>
+
+<P>I just finished running a set of recommendations based on the Wikipedia link graph, for book purposes (yeah, it's unconventional). I ran on my laptop, but it ought to be crudely representative of how it runs in a real cluster.</P>
+
+<P>The input is 1058MB as a text file, and contains, 130M article-article associations, from 5.7M articles to 3.8M distinct articles ("users" and "items", respectively). I estimate cost based on Amazon's North<BR>
+American small Linux-based instance pricing of $0.085/hour. I ran on a dual-core laptop with plenty of RAM, allowing 1GB per worker, so this is valid.</P>
+
+<P>In this run, I run recommendations for all 5.7M "users". You can certainly run for any subset of all users of course.</P>
+
+<P>Phase 1 (Item ID to item index mapping)<BR>
+29 minutes CPU time<BR>
+$0.05<BR>
+60MB output</P>
+
+<P>Phase 2 (Create user vectors)<BR>
+88 minutes CPU time<BR>
+$0.13<BR>
+Output: 1159MB</P>
+
+<P>Phase 3 (Count co-occurrence)<BR>
+77 hours CPU time<BR>
+$6.54<BR>
+Output: 23.6GB</P>
+
+<P>Phase 4 (Partial multiply prep)<BR>
+10.5 hours CPU time<BR>
+$0.90<BR>
+Output: 24.6GB</P>
+
+<P>Phase 5 (Aggregate and recommend)<BR>
+about 600 hours<BR>
+about $51.00<BR>
+about 10GB<BR>
+(I estimated these rather than let it run at home for days!)</P>
+
+
+<P>Note that phases 1 and 3 may be run less frequently, and need not be run every time. But the cost is dominated by the last step, which is most of the work. I've ignored storage costs.</P>
+
+<P>This implies a cost of $0.01 (or about 8 instance-minutes) per 1,000 user recommendations. That's not bad if, say, you want to update recs for you site's 100,000 daily active users for a dollar.</P>
+
+<P>There are several levers one could pull internally to sacrifice accuracy for speed, but it's currently set to pretty normal values. So this is just one possibility.</P>
+
+<P>Now that's not terrible, but it is about 8x more computing than would be needed by a non-distributed implementation <B>if</B> you could fit the whole data set into a very large instance's memory, which is still possible at this scale but needs a pretty big instance. That's a very apples-to-oranges comparison of course; different algorithms, entirely different environments. This is about the amount of overhead I'd expect from distributing – interesting to note how non-trivial it is.</P>
+
+
+<H1><A name="MahoutBenchmarks-Clustering"></A>Clustering</H1>
+
+<H1><A name="MahoutBenchmarks-Classification"></A>Classification</H1>
+
+<H1><A name="MahoutBenchmarks-FrequentPatternsetMining"></A>Frequent Patternset Mining</H1>
+
+ </DIV>
+
+
+ </DIV>
+ </DIV>
+ <DIV class="footer">
+ Generated by
+ <A href="http://www.atlassian.com/confluence/">Atlassian Confluence</A> (Version: 3.2 Build: 1810 Mar 16, 2010)
+ <A href="http://could.it/autoexport/">Auto Export Plugin</A> (Version: 1.0.0-dkulp)
+ </DIV>
+ </BODY>
+</HTML>
\ No newline at end of file
Added: mahout/site/new_website/MAHOUT/mahoutec2.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/mahoutec2.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/mahoutec2.html (added)
+++ mahout/site/new_website/MAHOUT/mahoutec2.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,344 @@
+
+<!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>MahoutEC2</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="MahoutEC2">MahoutEC2</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">MahoutEC2</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=98346">
+ <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=98346">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=98346">
+ <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=98346">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=98346">
+ <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=98346">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="MahoutEC2-MahoutonAmazonEC2"></A>Mahout on Amazon EC2</H1>
+
+<P>Amazon EC2 is a compute-on-demand platform sold by Amazon.com that allows users to purchase one or more host machines on an hourly basis and execute applications. Since Hadoop can run on EC2, it is also possible to run Mahout on EC2. The following sections will detail how to do this.</P>
+
+
+<H1><A name="MahoutEC2-Prerequisites"></A>Prerequisites</H1>
+
+<P>To run Mahout on EC2 you need to start up a Hadoop cluster on one or more instances of a Hadoop-0.20.2 compatible Amazon Machine Instance (AMI). Unfortunately, there do not currently exist any public AMIs that support Hadoop-0.20.2; you will have to create one. The following steps begin with a public Cloudera Ubuntu AMI that comes with Java installed on it. You could use any other AMI with Java installed or you could use a clean AMI and install Java yourself. These instructions assume some familiarity with Amazon EC2 concepts and terminology. See the Amazon EC2 User Guide, in References below.</P>
+
+<OL>
+ <LI>From the <A href="https://console.aws.amazon.com/ec2/home#c=EC2&s=Home" class="external-link" rel="nofollow">AWS Management Console</A>/AMIs, start the following AMI (<EM>ami-8759bfee</EM>)
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+cloudera-ec2-hadoop-images/cloudera-hadoop-ubuntu-20090623-x86_64.manifest.xml
+</PRE>
+</DIV></DIV></LI>
+ <LI>From the AWS Console/Instances, select the instance and right-click 'Connect" to get the connect string which contains your <instance public DNS name>
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+> ssh -i <gsg-keypair.pem> root@<instance <SPAN class="code-keyword">public</SPAN> DNS name>
+</PRE>
+</DIV></DIV></LI>
+ <LI>In the root home directory evaluate:
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+# apt-get install python-setuptools
+# easy_install <SPAN class="code-quote">"simplejson==2.0.9"</SPAN>
+# easy_install <SPAN class="code-quote">"boto==1.8d"</SPAN>
+# apt-get install ant
+# apt-get install subversion
+# apt-get install maven2
+</PRE>
+</DIV></DIV></LI>
+ <LI>Add the following to your .profile
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+export JAVA_HOME=/usr/lib/jvm/java-6-sun
+export HADOOP_HOME=/usr/local/hadoop-0.20.2
+export HADOOP_CONF_DIR=/usr/local/hadoop-0.20.2/conf
+export MAHOUT_HOME=/usr/local/mahout-0.4
+export MAHOUT_VERSION=0.4-SNAPSHOT
+export MAVEN_OPTS=-Xmx1024m
+</PRE>
+</DIV></DIV></LI>
+ <LI>Upload the Hadoop distribution and configure it. This distribution is not available on the Hadoop site. You can download a beta version from <A href="http://archive.cloudera.com/cdh/3/" class="external-link" rel="nofollow">Cloudera's CH3 distribution</A>
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+> scp -i <gsg-keypair.pem> <where>/hadoop-0.20.2.tar.gz root@<instance <SPAN class="code-keyword">public</SPAN> DNS name>:.
+
+# tar -xzf hadoop-0.20.2.tar.gz
+# mv hadoop-0.20.2 /usr/local/.
+</PRE>
+</DIV></DIV></LI>
+ <LI>Configure Hadoop for temporary single node operation
+ <OL>
+ <LI>add the following to $HADOOP_HOME/conf/hadoop-env.sh
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+# The java implementation to use. Required.
+export JAVA_HOME=/usr/lib/jvm/java-6-sun
+
+# The maximum amount of heap to use, in MB. Default is 1000.
+export HADOOP_HEAPSIZE=2000
+</PRE>
+</DIV></DIV></LI>
+ <LI>add the following to $HADOOP_HOME/conf/core-site.xml and also $HADOOP_HOME/conf/mapred-site.xml
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+<configuration>
+ <property>
+ <name>fs.<SPAN class="code-keyword">default</SPAN>.name</name>
+ <value>hdfs:<SPAN class="code-comment">//localhost:9000</value>
+</SPAN> </property>
+
+ <property>
+ <name>mapred.job.tracker</name>
+ <value>localhost:9001</value>
+ </property>
+
+ <property>
+ <name>dfs.replication</name>
+ <value>1</value>
+ <!-- set to 1 to reduce warnings when
+ running on a single node -->
+ </property>
+</configuration>
+</PRE>
+</DIV></DIV></LI>
+ <LI>set up authorized keys for localhost login w/o passwords and format your name node
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+# ssh-keygen -t dsa -P '' -f ~/.ssh/id_dsa
+# cat ~/.ssh/id_dsa.pub >> ~/.ssh/authorized_keys
+# $HADOOP_HOME/bin/hadoop namenode -format
+</PRE>
+</DIV></DIV></LI>
+ </OL>
+ </LI>
+ <LI>Checkout and build Mahout from trunk. Alternatively, you can upload a Mahout release tarball and install it as we did with the Hadoop tarball (Don't forget to update your .profile accordingly).
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+# svn co http:<SPAN class="code-comment">//svn.apache.org/repos/asf/mahout/trunk mahout
+</SPAN># cd mahout
+# mvn install
+# cd ..
+# mv mahout /usr/local/mahout-0.4
+</PRE>
+</DIV></DIV></LI>
+ <LI>Run Hadoop, just to prove you can, and test Mahout by building the Reuters dataset on it. Finally, delete the files and shut it down.
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+# $HADOOP_HOME/bin/hadoop namenode -format
+# $HADOOP_HOME/bin/start-all.sh
+# jps <SPAN class="code-comment">// you should see all 5 Hadoop processes (NameNode, SecondaryNameNode, DataNode, JobTracker, TaskTracker)
+</SPAN># cd $MAHOUT_HOME
+# ./examples/bin/build-reuters.sh
+
+# $HADOOP_HOME/bin/stop-all.sh
+# rm -rf /tmp/* <SPAN class="code-comment">// delete the Hadoop files</SPAN>
+</PRE>
+</DIV></DIV></LI>
+ <LI>Remove the single-host stuff you added to $HADOOP_HOME/conf/core-site.xml and $HADOOP_HOME/conf/mapred-site.xml in step #6b and verify you are happy with the other conf file settings. The Hadoop startup scripts will not make any changes to them. In particular, upping the Java heap size is required for many of the Mahout jobs.
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+ <SPAN class="code-comment">// $HADOOP_HOME/conf/mapred-site.xml
+</SPAN> <property>
+ <name>mapred.child.java.opts</name>
+ <value>-Xmx2000m</value>
+ </property>
+</PRE>
+</DIV></DIV></LI>
+ <LI>Bundle your image into a new AMI, upload it to S3 and register it so it can be launched multiple times to construct a Mahout-ready Hadoop cluster. (See Amazon's <A href="http://docs.amazonwebservices.com/AWSEC2/latest/UserGuide/index.html?PreparingAndCreatingAMIs.html" class="external-link" rel="nofollow">Preparing And Creating AMIs</A> for details).
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+<SPAN class="code-comment">// copy your AWS <SPAN class="code-keyword">private</SPAN> key file and certificate file to /mnt on your instance (you don't want to leave these around in the AMI).
+</SPAN>> scp -i <gsg-keypair.pem> <your AWS cert directory>/*.pem root@<instance <SPAN class="code-keyword">public</SPAN> DNS name>:/mnt/.
+
+# ec2-bundle-vol -k /mnt/pk*.pem -c /mnt/cert*.pem -u <your-AWS-user_id> -d /mnt -p mahout
+# ec2-upload-bundle -b <your-s3-bucket> -m /mnt/mahout.manifest.xml -a <your-AWS-access_key> -s <your-AWS-secret_key>
+# ec2-register -K /mnt/pk-*.pem -C /mnt/cert-*.pem <your-s3-bucket>/mahout.manifest.xml
+</PRE>
+</DIV></DIV>
+<H1><A name="MahoutEC2-GettingStarted"></A>Getting Started</H1></LI>
+</OL>
+
+
+<OL>
+ <LI>Now you can go back to your AWS Management Console and try launching a single instance of your image. Once this launches, make sure you can connect to it and test it by running (again):
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+# $HADOOP_HOME/hadoop namenode -format
+# $HADOOP_HOME/bin/start-all.sh
+# jps <SPAN class="code-comment">// you should see all 5 Hadoop processes (NameNode, SecondaryNameNode, DataNode, JobTracker, TaskTracker)
+</SPAN># cd $MAHOUT_HOME
+# ./examples/bin/build-reuters.sh
+
+# $HADOOP_HOME/bin/stop-all.sh
+# rm -rf /tmp/* <SPAN class="code-comment">// delete the Hadoop files</SPAN>
+</PRE>
+</DIV></DIV></LI>
+ <LI>Now that you have a working Mahout-ready AMI, follow <A href="http://wiki.apache.org/hadoop/AmazonEC2" class="external-link" rel="nofollow">Hadoop's instructions</A> to configure their scripts for your environment.
+ <OL>
+ <LI>edit bin/hadoop-ec2-env.sh, setting the following environment variables:
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+AWS_ACCOUNT_ID
+AWS_ACCESS_KEY_ID
+AWS_SECRET_ACCESS_KEY
+S3_BUCKET
+(and perhaps others depending upon your environment)
+</PRE>
+</DIV></DIV></LI>
+ <LI>edit bin/launch-hadoop-master and bin/launch-hadoop-slaves, setting:
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+AMI_IMAGE
+</PRE>
+</DIV></DIV></LI>
+ <LI>finally, launch your cluster and log in
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+> bin/hadoop-ec2 launch-cluster test-cluster 2
+> bin/hadoop-ec2 login test-cluster
+# ...
+# exit
+> bin/hadoop-ec2 terminate-cluster test-cluster <SPAN class="code-comment">// when you are done with it</SPAN>
+</PRE>
+</DIV></DIV></LI>
+ </OL>
+ </LI>
+</OL>
+
+
+<H1><A name="MahoutEC2-RunningtheExamples"></A>Running the Examples</H1>
+<OL>
+ <LI>Submit the Reuters test job
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+# cd $MAHOUT_HOME
+# ./examples/bin/build-reuters.sh
+<SPAN class="code-comment">// the warnings about configuration files <SPAN class="code-keyword">do</SPAN> not seem to matter</SPAN>
+</PRE>
+</DIV></DIV></LI>
+ <LI>See the Mahout <A href="quickstart.html" title="QuickStart">QuickStart</A> page for more examples
+<H1><A name="MahoutEC2-References"></A>References</H1></LI>
+</OL>
+
+
+<P><A href="http://docs.amazonwebservices.com/AWSEC2/latest/UserGuide/index.html" class="external-link" rel="nofollow">Amazon EC2 User Guide</A><BR>
+<A href="http://wiki.apache.org/hadoop/AmazonEC2" class="external-link" rel="nofollow">Hadoop's instructions</A></P>
+
+
+
+<H1><A name="MahoutEC2-Recognition"></A>Recognition</H1>
+
+<P>Some of the information available here was possible through the "Amazon Web Services Apache Projects Testing Program".</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="mahout-on-elastic-mapreduce.html" title="Mahout on Elastic MapReduce">Mahout on Elastic MapReduce</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
Added: mahout/site/new_website/MAHOUT/mahoutgatutorial.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/mahoutgatutorial.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/mahoutgatutorial.html (added)
+++ mahout/site/new_website/MAHOUT/mahoutgatutorial.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,155 @@
+
+<!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>Mahout.GA.Tutorial</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="Mahout.GA.Tutorial">Mahout.GA.Tutorial</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">Mahout.GA.Tutorial</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=93002">
+ <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=93002">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=93002">
+ <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=93002">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=93002">
+ <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=93002">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="Mahout.GA.Tutorial-HowtodistributethefitnessevaluationusingMahout.GA"></A>How to distribute the fitness evaluation using Mahout.GA</H1>
+
+<P>In any Watchmaker program, you'll have to create an instance of a StandaloneEvolutionEngine. For the TSP example this is done in the EvolutionaryTravellingSalesman class:</P>
+
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+<SPAN class="code-keyword">private</SPAN> EvolutionEngine<List<<SPAN class="code-object">String</SPAN>>> getEngine(CandidateFactory<List<<SPAN class="code-object">String</SPAN>>> candidateFactory, EvolutionaryOperator<List<?>> pipeline, Random rng) {
+ <SPAN class="code-keyword">return</SPAN> <SPAN class="code-keyword">new</SPAN> StandaloneEvolutionEngine<List<<SPAN class="code-object">String</SPAN>>>(candidateFactory, pipeline, <SPAN class="code-keyword">new</SPAN> RouteEvaluator(distances), selectionStrategy, rng);
+}
+</PRE>
+</DIV></DIV>
+
+<P>The RouteEvaluator class is where the fitness of each individual is evaluated, if we want to distribute the evaluation over a Hadoop Cluster, all we have to is wrap the evaluator in a MahoutFitnessEvaluator, and instead of a StandaloneEvolutionEngine we'll use a STEvolutionEngine :</P>
+
+<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent">
+<PRE class="code-java">
+<SPAN class="code-keyword">private</SPAN> EvolutionEngine<List<<SPAN class="code-object">String</SPAN>>> getEngine(CandidateFactory<List<<SPAN class="code-object">String</SPAN>>> candidateFactory, EvolutionaryOperator<List<?>> pipeline, Random rng) {
+ MahoutFitnessEvaluator<List<<SPAN class="code-object">String</SPAN>>> evaluator = <SPAN class="code-keyword">new</SPAN> MahoutFitnessEvaluator<List<<SPAN class="code-object">String</SPAN>>>(<SPAN class="code-keyword">new</SPAN> RouteEvaluator(distances));
+ <SPAN class="code-keyword">return</SPAN> <SPAN class="code-keyword">new</SPAN> STEvolutionEngine<List<<SPAN class="code-object">String</SPAN>>>(candidateFactory, pipeline, evaluator, selectionStrategy, rng);
+}
+</PRE>
+</DIV></DIV>
+
+<P>And voila! your code is ready to run on Hadoop. The complete running example is available with the examples in the org/apache/mahout/ga/watchmaker/travellingsalesman directory</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/mahoutintegration.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/mahoutintegration.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/mahoutintegration.html (added)
+++ mahout/site/new_website/MAHOUT/mahoutintegration.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>MahoutIntegration</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="MahoutIntegration">MahoutIntegration</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">MahoutIntegration</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=24184880">
+ <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=24184880">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=24184880">
+ <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=24184880">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=24184880">
+ <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=24184880">Add News</A>
+ </DIV>
+ </DIV>
+
+ <DIV class="pagecontent">
+ <DIV class="wiki-content">
+
+ </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/mahoutname.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/mahoutname.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/mahoutname.html (added)
+++ mahout/site/new_website/MAHOUT/mahoutname.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,168 @@
+
+<!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>MahoutName</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="MahoutName">MahoutName</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">MahoutName</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=27827430">
+ <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=27827430">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=27827430">
+ <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=27827430">Add Page</A>
+
+ <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=27827430">
+ <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=27827430">Add News</A>
+ </DIV>
+ </DIV>
+
+ <DIV class="pagecontent">
+ <DIV class="wiki-content">
+ <DIV>
+<UL>
+ <LI><A href="#MahoutName-What%2527sinaName%253F">What's in a Name?</A></LI>
+ <LI><A href="#MahoutName-Pronunciation">Pronunciation</A></LI>
+ <LI><A href="#MahoutName-History">History</A></LI>
+</UL></DIV>
+
+<H1><A name="MahoutName-What%27sinaName%3F"></A>What's in a Name?</H1>
+
+<P>A Mahout is a keeper/driver of elephants (<A href="http://en.wikipedia.org/wiki/Mahout" class="external-link" rel="nofollow">http://en.wikipedia.org/wiki/Mahout</A>). Since many of Mahout's algorithms are implemented in MapReduce on Hadoop, we thought it appropriate to come up with a name that was:</P>
+
+<P>1. Related to Hadoop<BR>
+2. Easily findable on the web since it is a relatively uncommon word in US/Europe circles</P>
+
+<P>Prior to coming to the ASF, those of us working on the project plan voted between Howdah (<A href="http://en.wikipedia.org/wiki/Howdah" class="external-link" rel="nofollow">http://en.wikipedia.org/wiki/Howdah</A> – the carriage on top of an elephant) and Mahout.</P>
+
+<H1><A name="MahoutName-Pronunciation"></A>Pronunciation</H1>
+
+<P>There are some disagreements about how to pronounce the name. Webster's has it as muh-hout (as in "out" – <A href="http://dictionary.reference.com/browse/mahout" class="external-link" rel="nofollow">http://dictionary.reference.com/browse/mahout</A>), but the Sanskrit/Hindi origins pronounce it as "muh-hoot". The second pronunciation suggests a nice pun on the Hebrew word ×××ת meaning "essence or truth".</P>
+
+<H1><A name="MahoutName-History"></A>History</H1>
+
+<P>Mahout was started by <A href="http://web.archive.org/web/20071228055210/http:/ml-site.grantingersoll.com/index.php?title=Main_Page" class="external-link" rel="nofollow">Isabel Drost, Grant Ingersoll and Karl Wettin</A>. It <A href="http://web.archive.org/web/20080201093120/http:/lucene.apache.org/#22%2BJanuary%2B2008%2B-%2BLucene%2BPMC%2BApproves%2BMahout%2BMachine%2BLearning%2BProject" class="external-link" rel="nofollow">started</A> as part of the <A href="http://lucene.apache.org/" class="external-link" rel="nofollow">Lucene</A> project (see the <A href="http://web.archive.org/web/20080102151102/http:/ml-site.grantingersoll.com/index.php?title=Incubator_proposal" class="external-link" rel="nofollow">original proposal</A>) and went on to become a top level project in April of 2010.</P>
+
+<P>The original goal was to implement all 10 algorithms from Andrew Ng's paper title "<A href="http://www.google.com/url?sa=t&source=web&cd=1&ved=0CB8QFjAA&url=http:%2F%2Fwww.cs.stanford.edu%2Fpeople%2Fang%2Fpapers%2Fnips06-mapreducemulticore.pdf&ei=iaR8TvKYK_DTiALCq7GODg&usg=AFQjCNFaW8ZuT6xuAz61ZaoKaQ7mpmIv2w&sig2=KVaGbhPFI3rKgjtxg4yIjg" class="external-link" rel="nofollow">Map-Reduce for Machine Learning on Multicore</A>"</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/mahoutreleases.html
URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/mahoutreleases.html?rev=1243022&view=auto
==============================================================================
--- mahout/site/new_website/MAHOUT/mahoutreleases.html (added)
+++ mahout/site/new_website/MAHOUT/mahoutreleases.html Sat Feb 11 10:22:15 2012
@@ -0,0 +1,118 @@
+
+<!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>MahoutReleases</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="MahoutReleases">MahoutReleases</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">MahoutReleases</DIV>
+
+ <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;">
+ <A href="http://cwiki.apache.org/confluence/pages/editpage.action?pageId=96707">
+ <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=96707">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=96707">
+ <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=96707">Add Page</A>
+
+ <A href="http://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=96707">
+ <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=96707">Add News</A>
+ </DIV>
+ </DIV>
+ <DIV class="pagesubheading" style="margin: 0px 10px 0px 10px;">
+ Added by <A href="http://cwiki.apache.org/confluence/users/viewuserprofile.action?username=zhao_yangang@yahoo.com.cn">zhaoyg</A>, last edited by <A href="http://cwiki.apache.org/confluence/users/viewuserprofile.action?username=zhao_yangang@yahoo.com.cn">zhaoyg</A> on Sep 08, 2008
+
+ </DIV>
+
+ <DIV class="pagecontent">
+ <DIV class="wiki-content">
+
+ </DIV>
+
+
+ </DIV>
+ </DIV>
+ <DIV class="footer">
+ Generated by
+ <A href="http://www.atlassian.com/confluence/">Atlassian Confluence</A> (Version: 2.10.4 Build: 1520 Jul 24, 2009)
+ <A href="http://could.it/autoexport/">Auto Export Plugin</A> (Version: 1.0.0.beta1)
+ </DIV>
+ </BODY>
+</HTML>