[
https://issues.apache.org/jira/browse/MAHOUT-939?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13182299#comment-13182299
]
Lance Norskog commented on MAHOUT-939:
--------------------------------------
SGD now does:
* 88% with just the subject,
* 98% with just the body, with and without quoted text
* 2% with body with quoted text
* 3% with subject and body without quoted text
* 2% with subject and body and quoted text
The subject-only test is the only believable output. One guess is that this
gives many fewer terms. Based on that guess, would hashing vectorization with a
small dimension give better results?
> ASF Email Classification Examples don't always produce good results
> -------------------------------------------------------------------
>
> Key: MAHOUT-939
> URL: https://issues.apache.org/jira/browse/MAHOUT-939
> Project: Mahout
> Issue Type: Bug
> Affects Versions: 0.6
> Reporter: Grant Ingersoll
> Assignee: Grant Ingersoll
> Labels: MAHOUT_INTRO_CONTRIBUTE
> Fix For: 0.7
>
> Attachments: MAHOUT-939.patch, MAHOUT-939.patch, MAHOUT-939.patch
>
>
> The classification examples for the ASF email don't work all that well
> currently in terms of quality when it comes to more than a few labels. Also,
> need to determine how much memory is required for vectors of cardinality size
> 100K.
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators:
https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira
