[
https://issues.apache.org/jira/browse/MAHOUT-586?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=12982945#action_12982945
]
Lance Norskog commented on MAHOUT-586:
--------------------------------------
Other problems:
The SamplingDataModel is dense, and a sequential/sparse one would also help for
subsampling giant data models.
The old Sampling iterator really only has one problem: it is not repeatable.
There's a quote in some Yahoo slideshow for which I did not note the link: _To
get useable results it is hard to beat the performance of a single machine with
sampled data_.
> 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.
