mahout-dev mailing list archives

Site index · List index
Message view « Date » · « Thread »
Top « Date » · « Thread »
From "Pat Ferrel (JIRA)" <j...@apache.org>
Subject [jira] [Commented] (MAHOUT-1464) Cooccurrence Analysis on Spark
Date Tue, 03 Jun 2014 00:54:02 GMT

    [ https://issues.apache.org/jira/browse/MAHOUT-1464?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=14016102#comment-14016102
] 

Pat Ferrel commented on MAHOUT-1464:
------------------------------------

My problem is that my cluster is 1.2.1 and to upgrade everything I run on it has to go to
H2. Oh bother.

I think the best thing is commit this and see it someone will run one of the several included
tests on a cluster. It works local and seems to work clustered but the write fails. The write
is not part of the core code.

Anyway unless someone vetos I'll commit it once I get at least one build integrated test included.

> Cooccurrence Analysis on Spark
> ------------------------------
>
>                 Key: MAHOUT-1464
>                 URL: https://issues.apache.org/jira/browse/MAHOUT-1464
>             Project: Mahout
>          Issue Type: Improvement
>          Components: Collaborative Filtering
>         Environment: hadoop, spark
>            Reporter: Pat Ferrel
>            Assignee: Sebastian Schelter
>             Fix For: 1.0
>
>         Attachments: MAHOUT-1464.patch, MAHOUT-1464.patch, MAHOUT-1464.patch, MAHOUT-1464.patch,
MAHOUT-1464.patch, MAHOUT-1464.patch, run-spark-xrsj.sh
>
>
> Create a version of Cooccurrence Analysis (RowSimilarityJob with LLR) that runs on Spark.
This should be compatible with Mahout Spark DRM DSL so a DRM can be used as input. 
> Ideally this would extend to cover MAHOUT-1422. This cross-cooccurrence has several applications
including cross-action recommendations. 



--
This message was sent by Atlassian JIRA
(v6.2#6252)

Mime
View raw message