Uploaded image for project: 'Spark'
  1. Spark
  2. SPARK-13226

MLLib PowerIteration Clustering depends on deprecated KMeans setRuns API

    XMLWordPrintableJSON

Details

    • Improvement
    • Status: Resolved
    • Trivial
    • Resolution: Duplicate
    • None
    • None
    • MLlib
    • None

    Description

      The current MLLib PowerIteration clustering implementation sets the number of parallel runs inside of the kmeans call to 5. This deprecated.

      The reference implementation also appears to either sex max iterations or a tolerance, both of which are currently left to our kmeans defaults ( http://www.cs.cmu.edu/~wcohen/ )

      Attachments

        Issue Links

          Activity

            People

              Unassigned Unassigned
              holden Holden Karau
              Votes:
              0 Vote for this issue
              Watchers:
              2 Start watching this issue

              Dates

                Created:
                Updated:
                Resolved: