Package org.apache.commons.math4.legacy.ml.clustering.evaluation

Class CalinskiHarabasz

java.lang.Object

org.apache.commons.math4.legacy.ml.clustering.evaluation.CalinskiHarabasz

All Implemented Interfaces:

ClusterEvaluator

public class CalinskiHarabasz
extends Object
implements ClusterEvaluator

Compute the Calinski and Harabasz score.

It is also known as the Variance Ratio Criterion.

The score is defined as ratio between the within-cluster dispersion and the between-cluster dispersion.

See Also:

A dendrite method for cluster analysis

Constructor Summary

Constructors

Constructor	Description
CalinskiHarabasz()

Method Summary

Modifier and Type	Method	Description
boolean	isBetterScore(double a, double b)	Provides a means to interpret the score value.
double	score(List<? extends Cluster<? extends Clusterable>> clusters)

Methods inherited from class java.lang.Object

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

Constructor Detail

CalinskiHarabasz

public CalinskiHarabasz()

Method Detail

score

public double score(List<? extends Cluster<? extends Clusterable>> clusters)

Specified by:

score in interface ClusterEvaluator

Parameters:

clusters - List of clusters.

Returns:

the score attributed by the evaluator.

isBetterScore

public boolean isBetterScore(double a,
                             double b)

Provides a means to interpret the score value.

Specified by:

isBetterScore in interface ClusterEvaluator

Parameters:

a - Score computed by this evaluator.

b - Score computed by this evaluator.

Returns:

true if the evaluator considers that score a is better than score b.