Uploaded image for project: 'Mahout'
  1. Mahout
  2. MAHOUT-825

Canopies grouping records outside t1

    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Closed
    • Major
    • Resolution: Won't Fix
    • 0.6
    • 0.6
    • classic
    • windows, linux

    Description

      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.

      Attachments

        1. canopy-clusterFilter-t1
          7 kB
          Paritosh Ranjan
        2. canopy-outlier-elimination
          20 kB
          Paritosh Ranjan
        3. canopy-outside-t1-points-patch-1
          5 kB
          Paritosh Ranjan
        4. canopy-radius-based-outlier-elimination
          14 kB
          Paritosh Ranjan
        5. canopy-strict-clustering-flag
          13 kB
          Paritosh Ranjan
        6. Clustering Remote Points - Two Big, Useless Clusters.txt
          403 kB
          Paritosh Ranjan
        7. MAHOUT-825.patch
          79 kB
          Jeff Eastman
        8. Not Clustering Remote Points - Two Meaningful Clusters.txt
          4 kB
          Paritosh Ranjan

        Activity

          People

            jeastman Jeff Eastman
            paritoshranjan Paritosh Ranjan
            Votes:
            0 Vote for this issue
            Watchers:
            0 Start watching this issue

            Dates

              Created:
              Updated:
              Resolved: