[
https://issues.apache.org/jira/browse/MAHOUT-825?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13122944#comment-13122944
]
Paritosh Ranjan commented on MAHOUT-825:
----------------------------------------
I experimented on Canopy generation phase as Ted suggested it. And the results
are positive, and it can be switched on/off using a flag, and, the default is
off.
The radius is being calculated. I think you missed it :
{code}
private double computeCanopyNeighbourhoodDistance(Canopy canopy) {
canopy.computeParameters();
double radius = canopy.getRadius().getLengthSquared();
return radius*clusterStrictness;
}
{code}
I don't see any harm in having an outlier elimination mechanism in Canopy if we
don't have it in other clustering mechanisms. As, there is a flag to control
that, and, its off by default.
Its evolving from some time. And, I think, all the doubts mentioned earlier
have been fixed. Its controlled by a flag, and, its not dependent on t1 anymore.
> Canopies grouping records outside t1
> ------------------------------------
>
> Key: MAHOUT-825
> URL: https://issues.apache.org/jira/browse/MAHOUT-825
> Project: Mahout
> Issue Type: Bug
> Components: Clustering
> Affects Versions: 0.6
> Environment: windows, linux
> Reporter: Paritosh Ranjan
> Labels: features, newbie, patch
> Fix For: 0.6
>
> Attachments: Clustering Remote Points - Two Big, Useless
> Clusters.txt, Not Clustering Remote Points - Two Meaningful Clusters.txt,
> canopy-clusterFilter-t1, canopy-outlier-elimination,
> canopy-outside-t1-points-patch-1, canopy-strict-clustering-flag
>
>
> While finding closest canopy, there is no check to ensure that it returns
> canopies which are within distance t1 from the point. This results in
> incorrect result i.e. Points outside t1 are grouped in canopies.
--
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
