You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@mahout.apache.org by "Saleem Ansari (JIRA)" <ji...@apache.org> on 2013/07/13 12:49:52 UTC
[jira] [Comment Edited] (MAHOUT-1004) Distributed User-based
Collaborative Filtering
[ https://issues.apache.org/jira/browse/MAHOUT-1004?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13704407#comment-13704407 ]
Saleem Ansari edited comment on MAHOUT-1004 at 7/13/13 10:49 AM:
-----------------------------------------------------------------
To understand how the user-based recommender would work, I have re-based the user-based recommender patch against trunk codebase. Now it compiles fine. However the tests are failing.
What I basically changed?
* Use the latest API e.g. PriorityQueue instead of TopK, nonZeros.iterator() instead of iterateNonZero().
-Test failures-: http://pastebin.com/PxdQ4qw2
Test failures updated: http://pastebin.com/sQWcG2Ya
* -I think my ( Cygwin ) environment is not setup properly, hence the permission issues, due to which some tests are failing.-
* Now ran the tests on Fedora 19 with a sane environment, so lesser tests fail.
Please have a look at the updated patch: [^MAHOUT-1004-trunk-rebased-but-tests-fail.patch]. In the meantime I will understand what would need to be re-factored and try to fix the test cases.
was (Author: tuxdna):
To understand how the user-based recommender would work, I have re-based the user-based recommender patch against trunk codebase. Now it compiles fine. However the tests are failing.
What I basically changed?
* Use the latest API e.g. PriorityQueue instead of TopK, nonZeros.iterator() instead of iterateNonZero().
Test failures: http://pastebin.com/PxdQ4qw2
* I think my ( Cygwin ) environment is not setup properly, hence the permission issues, due to which some tests are failing.
Please have a look at the updated patch: [^MAHOUT-1004-trunk-rebased-but-tests-fail.patch]. In the meantime I will understand what would need to be re-factored and try to fix the test cases.
> Distributed User-based Collaborative Filtering
> ----------------------------------------------
>
> Key: MAHOUT-1004
> URL: https://issues.apache.org/jira/browse/MAHOUT-1004
> Project: Mahout
> Issue Type: New Feature
> Components: Collaborative Filtering
> Affects Versions: 0.7
> Reporter: Kris Jack
> Priority: Minor
> Labels: Recommender, User-based
> Fix For: Backlog
>
> Attachments: MAHOUT-1004.patch, MAHOUT-1004-trunk-rebased-but-tests-fail.patch
>
> Original Estimate: 336h
> Remaining Estimate: 336h
>
> I'd like to contribute code that implements a distributed user-based collaborative filtering algorithm.
> In brief, so far I've taken the code for the existing org.apache.mahout.cf.taste.hadoop.item.RecommenderJob and created a new org.apache.mahout.cf.taste.hadoop.user.RecommenderJob. With help from Sean Owen, I followed a similar approach to the item-based implementation, but multiplied a user-user matrix with a user-item vector rather than an item-item matrix with an item-user vector. The result of the multiplication then needs to be transposed in order to output recommendations by user id.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators
For more information on JIRA, see: http://www.atlassian.com/software/jira