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

Class PredefinedInitialMeans

java.lang.Object

de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.initialization.AbstractKMeansInitialization<NumberVector>

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

All Implemented Interfaces:

KMeansInitialization<NumberVector>

public class PredefinedInitialMeans
extends AbstractKMeansInitialization<NumberVector>

Run k-means with prespecified initial means.

Author:

Erich Schubert

Nested Class Summary

Nested Classes

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

Field Summary

Fields

Modifier and Type	Field and Description
(package private) List<? extends NumberVector>	initialMeans Initial means to return.

Fields inherited from class de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.initialization.AbstractKMeansInitialization

rnd

Constructor Summary

Constructors

Constructor and Description
PredefinedInitialMeans(double[][] initialMeans) Constructor.
PredefinedInitialMeans(List<? extends NumberVector> initialMeans) Constructor.

Method Summary

Methods

Modifier and Type	Method and Description
<T extends NumberVector,O extends NumberVector> List<O>	chooseInitialMeans(Database database, Relation<T> relation, int k, NumberVectorDistanceFunction<? super T> distanceFunction, NumberVector.Factory<O> factory) Choose initial means
void	setInitialClusters(List<? extends Cluster<? extends MeanModel>> initialMeans) Set the initial means.
void	setInitialMeans(double[][] initialMeans) Set the initial means.
void	setInitialMeans(List<? extends NumberVector> initialMeans) Set the initial means.

Methods inherited from class java.lang.Object

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

Field Detail

initialMeans

List<? extends NumberVector> initialMeans

Initial means to return.

Constructor Detail

PredefinedInitialMeans

public PredefinedInitialMeans(List<? extends NumberVector> initialMeans)

Constructor.

Parameters:

initialMeans - Initial means

PredefinedInitialMeans

public PredefinedInitialMeans(double[][] initialMeans)

Constructor.

Parameters:

initialMeans - Initial means

Method Detail

setInitialMeans

public void setInitialMeans(List<? extends NumberVector> initialMeans)

Set the initial means. Important notice: Use with care - the means are not copied!

Parameters:

initialMeans - initial means.

setInitialClusters

public void setInitialClusters(List<? extends Cluster<? extends MeanModel>> initialMeans)

Set the initial means. Important notice: Use with care - the means are not copied!

Parameters:

initialMeans - initial means.

setInitialMeans

public void setInitialMeans(double[][] initialMeans)

Set the initial means. Important notice: Use with care - the means are not copied!

Parameters:

initialMeans - initial means.

chooseInitialMeans

public <T extends NumberVector,O extends NumberVector> List<O> chooseInitialMeans(Database database,
                                                                         Relation<T> relation,
                                                                         int k,
                                                                         NumberVectorDistanceFunction<? super T> distanceFunction,
                                                                         NumberVector.Factory<O> factory)

Description copied from interface: KMeansInitialization

Choose initial means

Type Parameters:

T - Input vector type

O - Output vector type

Parameters:

database - Database context

relation - Relation

k - Parameter k

distanceFunction - Distance function

factory - Factory for output vectors.

Returns:

List of chosen means for k-means