mahout-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Hudson (Commented) (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (MAHOUT-920) Remove a mapreduce job from parallel FPGrowth workflow
Date Sun, 15 Jan 2012 17:59:40 GMT

    [ https://issues.apache.org/jira/browse/MAHOUT-920?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13186542#comment-13186542
] 

Hudson commented on MAHOUT-920:
-------------------------------

Integrated in Mahout-Quality #1307 (See [https://builds.apache.org/job/Mahout-Quality/1307/])
    MAHOUT-890 MAHOUT-920 MAHOUT-921 MAHOUT-927 FpGrowth2 Implementation and fixes to existing
Mapreduce classes in pfpgrowth

robinanil : http://svn.apache.org/viewcvs.cgi/?root=Apache-SVN&view=rev&rev=1231700
Files : 
* /mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/FPGrowthDriver.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/MultiTransactionTreeIterator.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/PFPGrowth.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/ParallelFPGrowthCombiner.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/ParallelFPGrowthMapper.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/ParallelFPGrowthReducer.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/TransactionSortingMapper.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/TransactionSortingReducer.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/TransactionTree.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/TransactionTreeIterator.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/fpgrowth/FrequentPatternMaxHeap.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/fpgrowth/Pattern.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/fpgrowth2
* /mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/fpgrowth2/FPGrowthIds.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/fpgrowth2/FPGrowthObj.java
* /mahout/trunk/core/src/main/java/org/apache/mahout/fpm/pfpgrowth/fpgrowth2/FPTree.java
* /mahout/trunk/core/src/test/java/org/apache/mahout/fpm/pfpgrowth/FPGrowthRetailDataTest2.java
* /mahout/trunk/core/src/test/java/org/apache/mahout/fpm/pfpgrowth/FPGrowthRetailDataTestVs.java
* /mahout/trunk/core/src/test/java/org/apache/mahout/fpm/pfpgrowth/FPGrowthSyntheticDataTest.java
* /mahout/trunk/core/src/test/java/org/apache/mahout/fpm/pfpgrowth/FPGrowthTest2.java
* /mahout/trunk/core/src/test/java/org/apache/mahout/fpm/pfpgrowth/PFPGrowthRetailDataTest.java
* /mahout/trunk/core/src/test/java/org/apache/mahout/fpm/pfpgrowth/PFPGrowthRetailDataTest2.java
* /mahout/trunk/core/src/test/java/org/apache/mahout/fpm/pfpgrowth/PFPGrowthRetailDataTestVs.java
* /mahout/trunk/core/src/test/java/org/apache/mahout/fpm/pfpgrowth/PFPGrowthSynthDataTest2.java
* /mahout/trunk/core/src/test/java/org/apache/mahout/fpm/pfpgrowth/PFPGrowthTest.java
* /mahout/trunk/core/src/test/java/org/apache/mahout/fpm/pfpgrowth/PFPGrowthTest2.java
* /mahout/trunk/core/src/test/java/org/apache/mahout/fpm/pfpgrowth/TransactionTreeTest.java
* /mahout/trunk/core/src/test/resources/FPGsynth.dat

                
> Remove a mapreduce job from parallel FPGrowth workflow
> ------------------------------------------------------
>
>                 Key: MAHOUT-920
>                 URL: https://issues.apache.org/jira/browse/MAHOUT-920
>             Project: Mahout
>          Issue Type: Improvement
>          Components: Frequent Itemset/Association Rule Mining
>    Affects Versions: 0.6
>            Reporter: tom pierce
>            Assignee: Robin Anil
>            Priority: Minor
>             Fix For: 0.6
>
>         Attachments: MAHOUT-890.patch, MAHOUT-920.patch
>
>
> The transaction sorting job could have been made map-only, and another mapreduce job
follows, so it made sense to combine them.  It would have been possible to use a ChainMapper
approach, but it seemed simpler to fold the functionality into the following mapper (ParallelFPGrowthMapper).
 The attached patch does just that.

--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira

        

Mime
View raw message