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

Class RandomlyChosenInitialMeans<O>

java.lang.Object

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

de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.initialization.RandomlyChosenInitialMeans<O>

Type Parameters:

O - Vector type

All Implemented Interfaces:

KMeansInitialization, KMedoidsInitialization<O>

@Reference(authors="D. J. McRae",title="MIKCA: A FORTRAN IV Iterative K-Means Cluster Analysis Program",booktitle="Behavioral Science 16(4)",bibkey="journals/misc/McRae71") @Reference(authors="E. W. Forgy",title="Cluster analysis of multivariate data: efficiency versus interpretability of classifications",booktitle="Biometrics 21(3)",bibkey="journals/biometrics/Forgy65") @Reference(authors="M. R. Anderberg",title="Nonhierarchical Clustering Methods",booktitle="Cluster Analysis for Applications",bibkey="books/academic/Anderberg73/Ch7")
 @Alias(value="de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.RandomlyChosenInitialMeans")
public class RandomlyChosenInitialMeans<O>
extends AbstractKMeansInitialization
implements KMedoidsInitialization<O>

Initialize K-means by randomly choosing k existing elements as initial cluster centers.

Reference:

D. J. McRae
MIKCA: A FORTRAN IV Iterative K-Means Cluster Analysis Program
Behavioral Science 16(4)

E. W. Forgy
Cluster analysis of multivariate data: efficiency versus interpretability of classifications
Abstract published in Biometrics 21(3)

M. R. Anderberg
Hierarchical Clustering Methods
Cluster Analysis for Applications

This initialization is often attributed to Forgy (but this is also debated), but we were unable to verify neither McRae (not available online?) nor Forgy so far (apparently, only an abstract is available in print, so we mostly can rely on indirect references, such as Anderberg).

Since:

0.5.0

Author:

Erich Schubert

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	RandomlyChosenInitialMeans.Parameterizer<V> Parameterization class.

Field Summary

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

rnd

Constructor Summary

Constructors

Constructor and Description
RandomlyChosenInitialMeans(RandomFactory rnd) Constructor.

Method Summary

Modifier and Type	Method and Description
double[][]	chooseInitialMeans(Database database, Relation<? extends NumberVector> relation, int k, NumberVectorDistanceFunction<?> distanceFunction) Choose initial means
DBIDs	chooseInitialMedoids(int k, DBIDs ids, DistanceQuery<? super O> distanceFunction) Choose initial means

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

unboxVectors

Methods inherited from class java.lang.Object

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

Constructor Detail

RandomlyChosenInitialMeans

public RandomlyChosenInitialMeans(RandomFactory rnd)

Constructor.

Parameters:

rnd - Random generator.

Method Detail

chooseInitialMeans

public double[][] chooseInitialMeans(Database database,
                                     Relation<? extends NumberVector> relation,
                                     int k,
                                     NumberVectorDistanceFunction<?> distanceFunction)

Description copied from interface: KMeansInitialization

Choose initial means

Specified by:

chooseInitialMeans in interface KMeansInitialization

Parameters:

database - Database context

relation - Relation

k - Parameter k

distanceFunction - Distance function

Returns:

List of chosen means for k-means

chooseInitialMedoids

public DBIDs chooseInitialMedoids(int k,
                                  DBIDs ids,
                                  DistanceQuery<? super O> distanceFunction)

Description copied from interface: KMedoidsInitialization

Choose initial means

Specified by:

chooseInitialMedoids in interface KMedoidsInitialization<O>

Parameters:

k - Parameter k

ids - Candidate IDs.

distanceFunction - Distance function

Returns:

List of chosen means for k-means