de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.initialization

Class AbstractKMeansInitialization

java.lang.Object

de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.initialization.AbstractKMeansInitialization

All Implemented Interfaces:

KMeansInitialization

Direct Known Subclasses:

FarthestPointsInitialMeans, KMeansPlusPlusInitialMeans, OstrovskyInitialMeans, PredefinedInitialMeans, RandomlyChosenInitialMeans, RandomNormalGeneratedInitialMeans, RandomUniformGeneratedInitialMeans, SampleKMeansInitialization

public abstract class AbstractKMeansInitialization
extends java.lang.Object
implements KMeansInitialization

Abstract base class for common k-means initializations.

Since:

0.5.0

Author:

Erich Schubert

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	AbstractKMeansInitialization.Parameterizer Parameterization class.

Field Summary

Fields

Modifier and Type	Field and Description
protected RandomFactory	rnd Random number generator

Constructor Summary

Constructors

Constructor and Description
AbstractKMeansInitialization(RandomFactory rnd) Constructor.

Method Summary

Modifier and Type	Method and Description
static double[][]	unboxVectors(java.util.List<? extends NumberVector> means) Unbox database means to primitive means.

Methods inherited from class java.lang.Object

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

Methods inherited from interface de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.initialization.KMeansInitialization

chooseInitialMeans

Field Detail

rnd

protected RandomFactory rnd

Random number generator

Constructor Detail

AbstractKMeansInitialization

public AbstractKMeansInitialization(RandomFactory rnd)

Constructor.

Parameters:

rnd - Random number generator.

Method Detail

unboxVectors

public static double[][] unboxVectors(java.util.List<? extends NumberVector> means)

Unbox database means to primitive means.

Parameters:

means - Database means

Returns:

List of primitive double[] means