marytts.machinelearning
Class KMeansClusteringTrainer

java.lang.Object
  extended by marytts.machinelearning.KMeansClusteringTrainer

public class KMeansClusteringTrainer
extends java.lang.Object

K-Means clustering training algorithm Reference: J. MacQueen, 1967, "Some methods for classification and analysis of multivariate observations", Proc. Fifth Berkeley Symp. on Math. Statist. and Prob., Vol. 1 (Univ. of Calif. Press, 1967), pp. 281-297.

Author:
Oytun Türk

Field Summary
 int[] clusterIndices
           
 Cluster[] clusters
           
 double[][] covMatrixGlobal
           
 double[][] invCovMatrixGlobal
           
 int[] totalObservationsInClusters
           
 
Constructor Summary
KMeansClusteringTrainer()
           
 
Method Summary
 int getFeatureDimension()
           
 int getTotalClusters()
           
 boolean isDiagonalCovariance()
           
 void train(double[][] x, KMeansClusteringTrainerParams kmeansParams)
           
 
Methods inherited from class java.lang.Object
clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait
 

Field Detail

clusters

public Cluster[] clusters

totalObservationsInClusters

public int[] totalObservationsInClusters

clusterIndices

public int[] clusterIndices

covMatrixGlobal

public double[][] covMatrixGlobal

invCovMatrixGlobal

public double[][] invCovMatrixGlobal
Constructor Detail

KMeansClusteringTrainer

public KMeansClusteringTrainer()
Method Detail

train

public void train(double[][] x,
                  KMeansClusteringTrainerParams kmeansParams)

getFeatureDimension

public int getFeatureDimension()

getTotalClusters

public int getTotalClusters()

isDiagonalCovariance

public boolean isDiagonalCovariance()