jminhep.algorithms

Class KMeansExchangeAlg

java.lang.Object

jminhep.algorithms.KMeansExchangeAlg

public class KMeansExchangeAlg
extends java.lang.Object

K-means partitioning using exchange method.

Based on Jama Matrix class package, "JAMA: A Java Matrix Package" is used.
See: http://math.nist.gov/javanumerics/jama

Field Summary

Fields

Modifier and Type	Field and Description
double	MAXVAL
double	R

Constructor Summary

Constructors

Constructor and Description
KMeansExchangeAlg(DataHolder data)

Method Summary

Modifier and Type	Method and Description
DataHolder	getCenters() Returns cluster centers
int	getClusters() Get number of clusters.
double	getCompactness() This method returns the Compactness and Separation measure of cluster validity (see Fuzzy Algorithms With Applications to Image Processing and Pattern Recognition, Zheru Chi, Hong Yan, Tuan Pham, World Scientific, pp.
int	getError()
java.lang.String	getName()
int[]	getNumberPoints() Returns the number of points in each cluster
DataHolder	getSeedHolder() Returns seed centers
void	run()
void	runBest()
void	setClusters(int Nclu)
void	setEpochMax(int N)

Methods inherited from class java.lang.Object

equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Field Detail

MAXVAL

public final double MAXVAL

See Also:

Constant Field Values

R

public final double R

See Also:

Constant Field Values

Constructor Detail

KMeansExchangeAlg

public KMeansExchangeAlg(DataHolder data)

Method Detail

setEpochMax

public void setEpochMax(int N)

getError

public int getError()

setClusters

public void setClusters(int Nclu)

getClusters

public int getClusters()

Get number of clusters.

getCenters

public DataHolder getCenters()

Returns cluster centers

Returns:

DataHolder

getSeedHolder

public DataHolder getSeedHolder()

Returns seed centers

Returns:

DataHolder

getNumberPoints

public int[] getNumberPoints()

Returns the number of points in each cluster

Returns:

int[] getNumberPoints

getCompactness

public double getCompactness()

This method returns the Compactness and Separation measure of cluster validity (see Fuzzy Algorithms With Applications to Image Processing and Pattern Recognition, Zheru Chi, Hong Yan, Tuan Pham, World Scientific, pp. 93)

runBest

public void runBest()

run

public void run()

getName

public java.lang.String getName()