Added: mahout/site/new_website/MAHOUT/tastecommandline.html URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/tastecommandline.html?rev=1243022&view=auto ============================================================================== --- mahout/site/new_website/MAHOUT/tastecommandline.html (added) +++ mahout/site/new_website/MAHOUT/tastecommandline.html Sat Feb 11 10:22:15 2012 @@ -0,0 +1,160 @@ + +<!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>TasteCommandLine</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="TasteCommandLine">TasteCommandLine</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">TasteCommandLine</DIV> + + <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;"> + <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=4587975";> + <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=4587975";>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=4587975";> + <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=4587975";>Add Page</A> + + <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=4587975";> + <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=4587975";>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="TasteCommandLine-Introduction"></A>Introduction </H1> + +<P>This quick start page describes how to run the hadoop based recommendation jobs of Mahout Taste on a Hadoop cluster. </P> + +<H1><A name="TasteCommandLine-Steps"></A>Steps </H1> + +<H2><A name="TasteCommandLine-Testingitononesinglemachinew%2Focluster"></A>Testing it on one single machine w/o cluster </H2> + +<P>In the examples directory type, for example: </P> +<DIV class="code panel" style="border-width: 1px;"><DIV class="codeContent panelContent"> +<PRE class="code-java"> +mvn -q exec:java -Dexec.mainClass=<SPAN class="code-quote">"org.apache.mahout.cf.taste.hadoop.pseudo.RecommenderJob"</SPAN> -Dexec.args=<SPAN class="code-quote">"<OPTIONS>"</SPAN> +</PRE> +</DIV></DIV> + +<H2><A name="TasteCommandLine-Runningitonthecluster"></A>Running it on the cluster </H2> + +<UL> + <LI>In $MAHOUT_HOME/, build the jar containing the job (mvn install) The job will be generated in $MAHOUT_HOME/core/target/ and it's name will contain the Mahout version number. For example, when using Mahout 0.3 release, the job will be mahout-core-0.3.jar</LI> + <LI>(Optional) 1 Start up Hadoop: $HADOOP_HOME/bin/start-all.sh</LI> + <LI>Put the data: $HADOOP_HOME/bin/hadoop fs -put <PATH TO DATA> testdata</LI> + <LI>Run the Job: $HADOOP_HOME/bin/hadoop jar $MAHOUT_HOME/core/target/mahout-core-<MAHOUT VERSION>.job org.apache.mahout.cf.taste.hadoop.<JOB> <OPTIONS></LI> + <LI>Get the data out of HDFS and have a look. Use bin/hadoop fs -lsr output to view all outputs.</LI> +</UL> + + +<H1><A name="TasteCommandLine-Commandlineoptions"></A>Command line options </H1> + +<P>Specify only the command line option "--help" for a complete summary of available command line options. Or, refer to the javadoc for the "Job" class being run.</P> + </DIV> + + + </DIV> + </DIV> + <DIV class="footer"> + Generated by + <A href="http://www.atlassian.com/confluence/";>Atlassian Confluence</A> (Version: 3.2 Build: 1810 Mar 16, 2010) + <A href="http://could.it/autoexport/";>Auto Export Plugin</A> (Version: 1.0.0-dkulp) + </DIV> +<SCRIPT type="text/javascript"> + + var _gaq = _gaq || []; + _gaq.push(['_setAccount', 'UA-17359171-1']); + _gaq.push(['_setDomainName', 'none']); + _gaq.push(['_setAllowLinker', true]); + _gaq.push(['_trackPageview']); + + (function() { + var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; + ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; + var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); + })(); + +</SCRIPT> + </BODY> +</HTML> \ No newline at end of file
Added: mahout/site/new_website/MAHOUT/testing.html URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/testing.html?rev=1243022&view=auto ============================================================================== --- mahout/site/new_website/MAHOUT/testing.html (added) +++ mahout/site/new_website/MAHOUT/testing.html Sat Feb 11 10:22:15 2012 @@ -0,0 +1,184 @@ + +<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/html4/loose.dtd";> +<HTML> + <HEAD> +<LINK type="text/css" rel="stylesheet" href="https://cwiki.apache.org/confluence/display/MAHOUT/$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>Testing</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="Testing">Testing</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">Testing</DIV> + + <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;"> + <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=26119486";> + <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=26119486";>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=26119486";> + <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=26119486";>Add Page</A> + + <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=26119486";> + <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=26119486";>Add News</A> + </DIV> + </DIV> + + <DIV class="pagecontent"> + <DIV class="wiki-content"> + <H1><A name="Testing-Intro"></A>Intro</H1> + +<P>As Mahout matures, solid testing procedures are needed. This page and its children capture test plans along with ideas for improving our testing.</P> + +<H1><A name="Testing-TestPlans"></A>Test Plans</H1> + +<UL> + <LI><A href="https://cwiki.apache.org/confluence/pages/createpage.action?spaceKey=MAHOUT&title=0.6&linkCreation=true&fromPageId=26119486"; class="createlink">0.6</A> - Test Plans for the 0.6 release<BR> +There are no special plans except for unit tests, and user testing of the Hadoop jobs.</LI> +</UL> + + +<H1><A name="Testing-TestIdeas"></A>Test Ideas</H1> + +<H2><A name="Testing-Regressions%2FBenchmarks%2FIntegrations"></A>Regressions/Benchmarks/Integrations</H2> +<UL> + <LI>Algorithmic quality and speed are not tested, except in a few instances. Such tests often require much longer run times (minutes to hours), a running Hadoop cluster, and downloads of large datasets (in the megabytes).</LI> + <LI>Standardized speed tests are difficult on different hardware.</LI> + <LI>Unit tests of external integrations require access to externals: HDFS, S3, JDBC, Cassandra, etc.</LI> +</UL> + + +<P>Apache Jenkins is not able to support these environments. Commercial donations would help. </P> + +<H2><A name="Testing-UnitTests"></A>Unit Tests</H2> +<P>Mahout's current tests are almost entirely unit tests. Algorithm tests generally supply a few numbers to code paths and verify that expected numbers come out. 'mvn test' runs these tests. There is "positive" coverage of a great many utilities and algorithms. A much smaller percent include "negative" coverage (bogus setups, inputs, combinations).</P> + +<H2><A name="Testing-Other"></A>Other</H2> + + </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="05.html" title="0.5">0.5</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/tf-idf-term-frequency-inverse-document-frequency.html URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/tf-idf-term-frequency-inverse-document-frequency.html?rev=1243022&view=auto ============================================================================== --- mahout/site/new_website/MAHOUT/tf-idf-term-frequency-inverse-document-frequency.html (added) +++ mahout/site/new_website/MAHOUT/tf-idf-term-frequency-inverse-document-frequency.html Sat Feb 11 10:22:15 2012 @@ -0,0 +1,140 @@ + +<!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>TF-IDF - Term Frequency-Inverse Document Frequency</TITLE> + <META http-equiv="Content-Type" content="text/html;charset=UTF-8"></HEAD> + <BODY onload="init()"> + <TABLE border="0" cellpadding="2" cellspacing="0" width="100%"> + <TR class="topBar"> + <TD align="left" valign="middle" class="topBarDiv" align="left" nowrap=""> + <A href="mahout-wiki.html" title="Apache Mahout">Apache Mahout</A> > <A href="mahout-wiki.html" title="Mahout Wiki">Mahout Wiki</A> > <A href="glossary.html" title="Glossary">Glossary</A> > <A href="" title="TF-IDF - Term Frequency-Inverse Document Frequency">TF-IDF - Term Frequency-Inverse Document Frequency</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">TF-IDF - Term Frequency-Inverse Document Frequency</DIV> + + <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;"> + <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=10846330";> + <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=10846330";>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=10846330";> + <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=10846330";>Add Page</A> + + <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=10846330";> + <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=10846330";>Add News</A> + </DIV> + </DIV> + <DIV class="pagesubheading" style="margin: 0px 10px 0px 10px;"> + #editReport() + </DIV> + + <DIV class="pagecontent"> + <DIV class="wiki-content"> + <P>Is a weight measure often used in information retrieval and text mining. This weight is a statistical measure used to evaluate how important a word is to a document in a collection or corpus. The importance increases proportionally to the number of times a word appears in the document but is offset by the frequency of the word in the corpus. In other words if a term/word appears lots in a document but also appears lots in the corpus/collection as a whole it will get a lower score. An example of this would be "the", "and", "it" but depending on your source material it maybe other words that are very common to the source matter.</P> + + +<P> See Also:</P> +<UL> + <LI><A href="http://en.wikipedia.org/wiki/Tf%E2%80%93idf"; class="external-link" rel="nofollow">http://en.wikipedia.org/wiki/Tf%E2%80%93idf</A></LI> + <LI><A href="http://nlp.stanford.edu/IR-book/html/htmledition/tf-idf-weighting-1.html"; class="external-link" rel="nofollow">http://nlp.stanford.edu/IR-book/html/htmledition/tf-idf-weighting-1.html</A></LI> +</UL> + + </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/thirdparty-dependencies.html URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/thirdparty-dependencies.html?rev=1243022&view=auto ============================================================================== --- mahout/site/new_website/MAHOUT/thirdparty-dependencies.html (added) +++ mahout/site/new_website/MAHOUT/thirdparty-dependencies.html Sat Feb 11 10:22:15 2012 @@ -0,0 +1,158 @@ + +<!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>Thirdparty Dependencies</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="system-requirements.html" title="System Requirements">System Requirements</A> > <A href="" title="Thirdparty Dependencies">Thirdparty Dependencies</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">Thirdparty Dependencies</DIV> + + <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;"> + <A href="https://cwiki.apache.org/confluence/pages/editpage.action?pageId=5964501";> + <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=5964501";>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=5964501";> + <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=5964501";>Add Page</A> + + <A href="https://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=5964501";> + <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=5964501";>Add News</A> + </DIV> + </DIV> + + <DIV class="pagecontent"> + <DIV class="wiki-content"> + <P>If you have a dependency on a third party artifact that is not in Maven, you should:</P> + +<OL> + <LI>Ask the project to add it if at all possible. Most open source projects want wider adoption, so this kind of request is often well received.</LI> + <LI>If they won't add it, we may be able to add it to our Maven repo, assuming it can be published at the ASF at all (no GPL code, for instance). Please ask on the mailing list first.</LI> + <LI>Assuming it can be, then you need to sign and deploy the artifacts, as described below:<BR> + mvn gpg:sign-and-deploy-file -Durl=<A href="https://repository.apache.org/service/local/staging/deploy/maven2"; class="external-link" rel="nofollow">https://repository.apache.org/service/local/staging/deploy/maven2</A> -DrepositoryId=apache.releases.https -DgroupId=org.apache.mahout.foobar -DartifactId=foobar -Dversion=x.y -Dpackaging=jar -Dfile=foobar-x.y.jar</LI> + <LI>Once it is deployed, go into <A href="http://repository.apache.org/"; class="external-link" rel="nofollow">http://repository.apache.org/</A> (use your SVN credentials to login in)</LI> + <LI>Select Staging</LI> + <LI>Find your repository artifacts</LI> + <LI>Close them (this makes them publicly available, since you are closing the staging repo)</LI> + <LI>Promote them. This adds them to the public Maven repo.</LI> +</OL> + + + </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/thirdpartydependencies.html URL: http://svn.apache.org/viewvc/mahout/site/new_website/MAHOUT/thirdpartydependencies.html?rev=1243022&view=auto ============================================================================== --- mahout/site/new_website/MAHOUT/thirdpartydependencies.html (added) +++ mahout/site/new_website/MAHOUT/thirdpartydependencies.html Sat Feb 11 10:22:15 2012 @@ -0,0 +1,138 @@ + +<!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>ThirdPartyDependencies</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="ThirdPartyDependencies">ThirdPartyDependencies</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">ThirdPartyDependencies</DIV> + + <DIV class="greynavbar" align="right" style="padding: 2px 10px; margin: 0px;"> + <A href="http://cwiki.apache.org/confluence/pages/editpage.action?pageId=5964501";> + <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=5964501";>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=5964501";> + <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=5964501";>Add Page</A> + + <A href="http://cwiki.apache.org/confluence/pages/createblogpost.action?spaceKey=MAHOUT&fromPageId=5964501";> + <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=5964501";>Add News</A> + </DIV> + </DIV> + <DIV class="pagesubheading" style="margin: 0px 10px 0px 10px;"> + Added by <A href="../~gsingers/index.html">Grant Ingersoll</A>, last edited by <A href="../~gsingers/index.html">Grant Ingersoll</A> on Nov 11, 2009 + + </DIV> + + <DIV class="pagecontent"> + <DIV class="wiki-content"> + <P>If you have a dependency on a third party artifact that is not in Maven, you should:</P> + +<OL> + <LI>Ask the project to add it if at all possible. Most open source projects want wider adoption, so this kind of request is often well received.</LI> + <LI>If they won't add it, we may be able to add it to our Maven repo, assuming it can be published at the ASF at all (no GPL code, for instance). Please ask on the mailing list first.</LI> + <LI>Assuming it can be, then you need to sign and deploy the artifacts, as described below:<BR> + 1016 mvn gpg:sign-and-deploy-file -Durl=<A href="https://repository.apache.org/service/local/staging/deploy/maven2"; rel="nofollow">https://repository.apache.org/service/local/staging/deploy/maven2</A> -DrepositoryId=apache.releases.https -DgroupId=org.apache.mahout.kosmosfs -DartifactId=kfs -Dversion=0.3 -Dpackaging=jar -Dfile=kfs-0.3.jar<BR> + 1017 hg sign-and<BR> + 1018 mvn gpg:sign-and-deploy-file -Durl=<A href="https://repository.apache.org/service/local/staging/deploy/maven2"; rel="nofollow">https://repository.apache.org/service/local/staging/deploy/maven2</A> -DrepositoryId=apache.releases.https -DgroupId=org.apache.mahout.kosmosfs -DartifactId=kfs -Dversion=0.3 -Dpackaging=jar -Dfile=kfs-0.3.jar<BR> + 1019 mvn gpg:sign-and-deploy-file -Durl=<A href="https://repository.apache.org/service/local/staging/deploy/maven2"; rel="nofollow">https://repository.apache.org/service/local/staging/deploy/maven2</A> -DrepositoryId=apache.releases.https -DgroupId=org.apache.mahout.hbase -DartifactId=hbase -Dversion=0.20.0 -Dpackaging=jar -Dfile=hbase-0.20.0.jar<BR> + 1020 mvn gpg:sign-and-deploy-file -Durl=<A href="https://repository.apache.org/service/local/staging/deploy/maven2"; rel="nofollow">https://repository.apache.org/service/local/staging/deploy/maven2</A> -DrepositoryId=apache.releases.https -DgroupId=org.apache.mahout.jets3t -DartifactId=jets3t -Dversion=0.7.1 -Dpackaging=jar -Dfile=jets3t-0.7.1.jar<BR> + 1021 mvn gpg:sign-and-deploy-file -Durl=<A href="https://repository.apache.org/service/local/staging/deploy/maven2"; rel="nofollow">https://repository.apache.org/service/local/staging/deploy/maven2</A> -DrepositoryId=apache.releases.https -DgroupId=org.apache.mahout.hadoop -DartifactId=hadoop-core -Dversion=0.20.1 -Dpackaging=jar -Dfile=hadoop-core-0.20.1.jar <BR> + 1022 mvn gpg:sign-and-deploy-file -Durl=<A href="https://repository.apache.org/service/local/staging/deploy/maven2"; rel="nofollow">https://repository.apache.org/service/local/staging/deploy/maven2</A> -DrepositoryId=apache.releases.https -DgroupId=org.apache.mahout.kosmofs -DartifactId=kfs -Dversion=0.3 -Dpackaging=jar -Dfile=kfs-0.3.jar</LI> + <LI>Once it is deployed, go into <A href="http://repository.apache.org/"; rel="nofollow">http://repository.apache.org/</A> (use your SVN credentials to login in)</LI> + <LI>Select Staging</LI> + <LI>Find your repository artifacts</LI> + <LI>Close them (this makes them publicly available, since you are closing the staging repo)</LI> + <LI>Promote them. This adds them to the public Maven repo.</LI> +</OL> + + + </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>
![https://cwiki.apache.org/confluence/images/icons/notep_16.gif"](https://cwiki.apache.org/confluence/images/icons/notep_16.gif"){kind=link}
![https://cwiki.apache.org/confluence/images/icons/browse_space.gif"](https://cwiki.apache.org/confluence/images/icons/browse_space.gif"){kind=link}
![https://cwiki.apache.org/confluence/images/icons/add_page_16.gif"](https://cwiki.apache.org/confluence/images/icons/add_page_16.gif"){kind=link}
![https://cwiki.apache.org/confluence/images/icons/add_blogentry_16.gif"](https://cwiki.apache.org/confluence/images/icons/add_blogentry_16.gif"){kind=link}
![http://cwiki.apache.org/confluence/images/icons/notep_16.gif"](http://cwiki.apache.org/confluence/images/icons/notep_16.gif"){kind=link}
![http://cwiki.apache.org/confluence/images/icons/browse_space.gif"](http://cwiki.apache.org/confluence/images/icons/browse_space.gif"){kind=link}
![http://cwiki.apache.org/confluence/images/icons/add_page_16.gif"](http://cwiki.apache.org/confluence/images/icons/add_page_16.gif"){kind=link}
![http://cwiki.apache.org/confluence/images/icons/add_blogentry_16.gif"](http://cwiki.apache.org/confluence/images/icons/add_blogentry_16.gif"){kind=link}