Package org.ddogleg.clustering

Class ConfigKMeans

java.lang.Object

org.ddogleg.clustering.ConfigKMeans

public class ConfigKMeans
extends Object

Configuration for K-Means clustering

Field Summary

Fields

Modifier and Type	Field	Description
double	convergeTol	Change in distance criteria when testing for convergence
KMeansInitializers	initializer	Which initialization algorithm
int	maxIterations	Maximum number of iterations, across all seeds combined
int	maxReSeed	Maximum number of times it will reseed before stopping.
int	reseedAfterIterations	If it doesn't converge within this many iterations a new seed is created

Constructor Summary

Constructors

Constructor	Description
ConfigKMeans()

Method Summary

Modifier and Type	Method	Description
void	checkValidity()
void	setTo(ConfigKMeans src)

Methods inherited from class java.lang.Object

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

Field Details

initializer

public KMeansInitializers initializer

Which initialization algorithm

maxIterations

public int maxIterations

Maximum number of iterations, across all seeds combined

reseedAfterIterations

public int reseedAfterIterations

If it doesn't converge within this many iterations a new seed is created

maxReSeed

public int maxReSeed

Maximum number of times it will reseed before stopping. If %le; then there is no limit.

convergeTol

public double convergeTol

Change in distance criteria when testing for convergence

Constructor Details

ConfigKMeans

public ConfigKMeans()

Method Details

setTo

public void setTo(ConfigKMeans src)

checkValidity

public void checkValidity()