[jira] [Updated] (MAHOUT-1464) RowSimilarityJob on Spark

["Sebastian Schelter (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/MAHOUT-1464?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Sebastian Schelter updated MAHOUT-1464:
---------------------------------------

    Attachment: MAHOUT-1464.patch

Luckily, Dmitriy's latest commit solved most of my problems as it provides the machinery to compute column sums and broadcast drms. Awesome work, Dmitriy.

Here is a first hacky version of cooccurrence analysis with downsampling and LLR using Dmitriy's new DSL.

Successfully tested on the movielens1M dataset on my laptop :)

> RowSimilarityJob on Spark
> -------------------------
>
>                 Key: MAHOUT-1464
>                 URL: https://issues.apache.org/jira/browse/MAHOUT-1464
>             Project: Mahout
>          Issue Type: Improvement
>          Components: Collaborative Filtering
>    Affects Versions: 0.9
>         Environment: hadoop, spark
>            Reporter: Pat Ferrel
>              Labels: performance
>             Fix For: 0.9
>
>         Attachments: MAHOUT-1464.patch
>
>
> Create a version of RowSimilarityJob that runs on Spark. Ssc has a prototype here: https://gist.github.com/sscdotopen/8314254. 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 which is a feature request for RSJ on two inputs to calculate the similarity of rows of one DRM with those of another. This cross-similarity has several applications including cross-action recommendations. 



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