Package smile.clustering

Class GMeans

java.lang.Object

smile.clustering.PartitionClustering

smile.clustering.CentroidClustering<double[],double[]>

smile.clustering.GMeans

All Implemented Interfaces:

Serializable, Comparable<CentroidClustering<double[],double[]>>

public class GMeans
extends CentroidClustering<double[],double[]>

G-Means clustering algorithm, an extended K-Means which tries to automatically determine the number of clusters by normality test. The G-means algorithm is based on a statistical test for the hypothesis that a subset of data follows a Gaussian distribution. G-means runs k-means with increasing k in a hierarchical fashion until the test accepts the hypothesis that the data assigned to each k-means center are Gaussian.

References

1. G. Hamerly and C. Elkan. Learning the k in k-means. NIPS, 2003.

See Also:

• KMeans
• XMeans
• Serialized Form

Field Summary

Fields inherited from class smile.clustering.CentroidClustering

centroids, distortion

Fields inherited from class smile.clustering.PartitionClustering

k, OUTLIER, size, y

Constructor Summary

Constructors

Constructor	Description
GMeans(double distortion, double[][] centroids, int[] y)	Constructor.

Method Summary

Modifier and Type	Method	Description
protected double	distance(double[] x, double[] y)	The distance function.
static GMeans	fit(double[][] data, int kmax)	Clustering data with the number of clusters determined by G-Means algorithm automatically.
static GMeans	fit(double[][] data, int kmax, int maxIter, double tol)	Clustering data with the number of clusters determined by G-Means algorithm automatically.

Methods inherited from class smile.clustering.CentroidClustering

compareTo, predict, toString

Methods inherited from class smile.clustering.PartitionClustering

run, seed

Methods inherited from class java.lang.Object

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

Constructor Details

GMeans

public GMeans(double distortion,
 double[][] centroids,
 int[] y)

Constructor.

Parameters:

distortion - the total distortion.

centroids - the centroids of each cluster.

y - the cluster labels.

Method Details

distance

protected double distance(double[] x,
 double[] y)

Description copied from class: CentroidClustering

The distance function.

Specified by:

distance in class CentroidClustering<double[],double[]>

Parameters:

x - an observation.

y - the other observation.

Returns:

the distance.

fit

public static GMeans fit(double[][] data,
 int kmax)

Clustering data with the number of clusters determined by G-Means algorithm automatically.

Parameters:

data - the input data of which each row is an observation.

kmax - the maximum number of clusters.

Returns:

the model.

fit

public static GMeans fit(double[][] data,
 int kmax,
 int maxIter,
 double tol)

Clustering data with the number of clusters determined by G-Means algorithm automatically.

Parameters:

data - the input data of which each row is an observation.

kmax - the maximum number of clusters.

maxIter - the maximum number of iterations for k-means.

tol - the tolerance of k-means convergence test.

Returns:

the model.