You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@mahout.apache.org by Steve Chien <st...@gmail.com> on 2013/01/20 03:21:19 UTC

FuzzyKMeansDriver and the parameter emitMostLikely

 
  Lately, I am experimenting the features of Mahout Fuzzy K-Means algorithm. One thing I noticed in the FuzzyKMeansDriver.java of Mahout 0.7 is that the emitMostLikely parameter is always passed as "true" when the ClusterClassificationDriver.run method is invoked.

public static void clusterData(Path input,
                              Path clustersIn,
                              Path output,
                              DistanceMeasure measure,
                              double convergenceDelta,
                              float m,
                              boolean emitMostLikely,
                              double threshold,
                              boolean runSequential)
 throws IOException, ClassNotFoundException, InterruptedException {

 ClusterClassifier.writePolicy(new FuzzyKMeansClusteringPolicy(m, convergenceDelta), clustersIn);
 ClusterClassificationDriver.run(input, output, new Path(output, CLUSTERED_POINTS_DIRECTORY), threshold, true,
     runSequential);
}

  Is it a bug, or?
 
  Thanks for any insights!

Steve