[
https://issues.apache.org/jira/browse/MAHOUT-586?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12982606#action_12982606
]
Sean Owen commented on MAHOUT-586:
----------------------------------
It's a big change. It seems to remove some functionality (there is no
root-mean-square evaluation anymore?), tests, and replace with an
implementation of other existing functionality but in a different way.
More importantly this is also removing all of the logic to hold out test data;
this is most of what AbstractDifferenceRecommenderEvaluator does.
GroupLensRecommenderEvaluatorRunner does nothing but invoke an evalution; it's
like 5 lines of code. So I'm not sure I understand the comment.
A minor concern is that the book has just gone out with a writeup on the
current recommender system. That's not a reason to not change it, but one small
reason to think about whether API changes are needed.
What problem is being solved here?
> Redo RecommenderEvaluator for modularity
> ----------------------------------------
>
> Key: MAHOUT-586
> URL: https://issues.apache.org/jira/browse/MAHOUT-586
> Project: Mahout
> Issue Type: Improvement
> Components: Collaborative Filtering
> Reporter: Lance Norskog
> Attachments: MAHOUT-586.patch
>
>
> The RecommenderEvaluator implementation is hard-coded around one algorithm.
> This is a more flexible, modular rewrite.
--
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.
