[jira] Updated: (MAHOUT-563) CanopyEstimator - Estimate T1/T2 for CanopyClusterer

["Lance Norskog (JIRA)" <ji...@apache.org>]

     [ https://issues.apache.org/jira/browse/MAHOUT-563?page=com.atlassian.jira.plugin.system.issuetabpanels:all-tabpanel ]

Lance Norskog updated MAHOUT-563:
---------------------------------

    Attachment: MAHOUT-563.patch

First cut. 

CanopyEstimator does three things: 
# Makes a random subsample of a given vector set
# Estimated initial T1/T2 numbers from the maximum and minimum distances between vectors in the subsample
# Iteratively hunts for T1/T2 values will create a list of canopies within a given minimum and maximum size

The algorithm for the latter is lame, but it does something useful in small and medium-scale tests.

> CanopyEstimator - Estimate T1/T2 for CanopyClusterer
> ----------------------------------------------------
>
>                 Key: MAHOUT-563
>                 URL: https://issues.apache.org/jira/browse/MAHOUT-563
>             Project: Mahout
>          Issue Type: New Feature
>          Components: Clustering
>            Reporter: Lance Norskog
>            Priority: Minor
>         Attachments: MAHOUT-563.patch
>
>
> Hunting for T1/T2 values that make an interesting Canopy set is a singularly unsatisfying task. This class estimates T1 and T2 numbers given the original set.

-- 
This message is automatically generated by JIRA.
-
You can reply to this email to add a comment to the issue online.