You are viewing a plain text version of this content. The canonical link for it is here.
Posted to dev@mahout.apache.org by "Ted Dunning (JIRA)" <ji...@apache.org> on 2012/10/31 01:22:12 UTC
[jira] [Comment Edited] (MAHOUT-1107) OnlineLogisticRegression
doesn't seem to work for some people/problems
[ https://issues.apache.org/jira/browse/MAHOUT-1107?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13487396#comment-13487396 ]
Ted Dunning edited comment on MAHOUT-1107 at 10/31/12 12:21 AM:
----------------------------------------------------------------
Here is a plot of convergence versus number of passes on the data that Rajesh was using.
The plot is of the data from the commented printf in the test. The red line is a lowess smoothed average.
Also available at https://dl.dropbox.com/u/36863361/olr.png
Clearly this is converging just fine.
was (Author: tdunning):
Here is a plot of convergence versus number of passes on the data that Rajesh was using.
Also available at https://dl.dropbox.com/u/36863361/olr.png
Clearly this is converging just fine.
> OnlineLogisticRegression doesn't seem to work for some people/problems
> ----------------------------------------------------------------------
>
> Key: MAHOUT-1107
> URL: https://issues.apache.org/jira/browse/MAHOUT-1107
> Project: Mahout
> Issue Type: Bug
> Reporter: Ted Dunning
> Attachments: MAHOUT-1107-Test_case_for_OnlineLogisticRegression.patch, olr.png
>
>
> Rajesh reports that using the classic Iris dataset gives random guess results.
> This may be a bug in OLR or a bug in his code.
--
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
Re: [jira] [Comment Edited] (MAHOUT-1107) OnlineLogisticRegression
doesn't seem to work for some people/problems
Posted by Timothy Mann <ma...@gmail.com>.
Without more information, I don't think it will be possible to determine
whether or not a bug exists.
-Tim
On Tue, Oct 30, 2012 at 7:22 PM, Ted Dunning (JIRA) <ji...@apache.org> wrote:
>
> [
> https://issues.apache.org/jira/browse/MAHOUT-1107?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13487396#comment-13487396]
>
> Ted Dunning edited comment on MAHOUT-1107 at 10/31/12 12:21 AM:
> ----------------------------------------------------------------
>
> Here is a plot of convergence versus number of passes on the data that
> Rajesh was using.
>
> The plot is of the data from the commented printf in the test. The red
> line is a lowess smoothed average.
>
> Also available at https://dl.dropbox.com/u/36863361/olr.png
>
> Clearly this is converging just fine.
>
> was (Author: tdunning):
> Here is a plot of convergence versus number of passes on the data that
> Rajesh was using.
>
> Also available at https://dl.dropbox.com/u/36863361/olr.png
>
> Clearly this is converging just fine.
>
> > OnlineLogisticRegression doesn't seem to work for some people/problems
> > ----------------------------------------------------------------------
> >
> > Key: MAHOUT-1107
> > URL: https://issues.apache.org/jira/browse/MAHOUT-1107
> > Project: Mahout
> > Issue Type: Bug
> > Reporter: Ted Dunning
> > Attachments:
> MAHOUT-1107-Test_case_for_OnlineLogisticRegression.patch, olr.png
> >
> >
> > Rajesh reports that using the classic Iris dataset gives random guess
> results.
> > This may be a bug in OLR or a bug in his code.
>
> --
> 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
>