[
https://issues.apache.org/jira/browse/MAHOUT-1030?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13678847#comment-13678847
]
Pat Ferrel commented on MAHOUT-1030:
------------------------------------
+1 to Lance's point.
My point of 01/Jul/12 was that the membership for kmeans should be 1 or 0 (it
was prior to Jeff's patch I believe) and so can't be used to calculate the
distance to the centroid. The membership is being overloaded and so I was
voting to return to the old method for storing the distance in a
WeightedPropertyVectorWritable and leaving the membership 0 or 1.
Since I was voting to not use the membership I implemented a recalc of the
distance during ingest of the clustered vectors so that my code would continue
to work either way. I rather expected someone to complain that membership was
now fuzzy in some sense and dependent on the distance metric. Lance and Jeff
also point out the problem with normalization expectations.
In general there are lots of places a WeightedPropertyVectorWritable would be
nice, even nicer than a NamedVectorWritable. Using them seems like a good way
to add properties without breaking backward compatibility.
> Regression: Clustered Points Should be WeightedPropertyVectorWritable not
> WeightedVectorWritable
> ------------------------------------------------------------------------------------------------
>
> Key: MAHOUT-1030
> URL: https://issues.apache.org/jira/browse/MAHOUT-1030
> Project: Mahout
> Issue Type: Bug
> Components: Clustering, Integration
> Affects Versions: 0.7
> Reporter: Jeff Eastman
> Assignee: Suneel Marthi
> Fix For: 0.8
>
> Attachments: MAHOUT-1030.patch, MAHOUT-1030.patch, MAHOUT-1030.patch
>
>
> Looks like this won't make it into this build. Pretty widespread impact on
> code and tests and I don't know which properties were implemented in the old
> version. I will create a JIRA and post my interim results.
> On 6/8/12 12:21 PM, Jeff Eastman wrote:
> > That's a reversion that evidently got in when the new
> > ClusterClassificationDriver was introduced. It should be a pretty easy fix
> > and I will see if I can make the change before Paritosh cuts the release
> > bits tonight.
> >
> > On 6/7/12 1:00 PM, Pat Ferrel wrote:
> >> It appears that in kmeans the clusteredPoints are now written as
> >> WeightedVectorWritable where in mahout 0.6 they were
> >> WeightedPropertyVectorWritable? This means that the distance from the
> >> centroid is no longer stored here? Why? I hope I'm wrong because that is
> >> not a welcome change. How is one to order clustered docs by distance from
> >> cluster centroid?
> >>
> >> I'm sure I could calculate the distance but that would mean looking up the
> >> centroid for the cluster id given in the above WeightedVectorWritable,
> >> which means iterating through all the clusters for each clustered doc. In
> >> my case the number of clusters could be fairly large.
> >>
> >> Am I missing something?
> >>
> >>
> >
--
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
