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

Class KMeansPlusPlusInitialMeans<V,D extends NumberDistance<D,?>>

java.lang.Object

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

de.lmu.ifi.dbs.elki.algorithm.clustering.kmeans.KMeansPlusPlusInitialMeans<V,D>

Type Parameters:

V - Vector type

D - Distance type

All Implemented Interfaces:

KMeansInitialization<V>, KMedoidsInitialization<V>

@Reference(authors="D. Arthur, S. Vassilvitskii",
           title="k-means++: the advantages of careful seeding",
           booktitle="Proc. of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 2007",
           url="http://dx.doi.org/10.1145/1283383.1283494")
public class KMeansPlusPlusInitialMeans<V,D extends NumberDistance<D,?>>
extends AbstractKMeansInitialization<V>
implements KMedoidsInitialization<V>

K-Means++ initialization for k-means. Reference:

D. Arthur, S. Vassilvitskii
k-means++: the advantages of careful seeding
In: Proc. of the Eighteenth Annual ACM-SIAM Symposium on Discrete Algorithms, SODA 2007

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	KMeansPlusPlusInitialMeans.Parameterizer<V,D extends NumberDistance<D,?>> Parameterization class.

Field Summary

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

rnd

Constructor Summary

Constructors

Constructor and Description
KMeansPlusPlusInitialMeans(RandomFactory rnd) Constructor.

Method Summary

Methods

Modifier and Type	Method and Description
List<V>	chooseInitialMeans(Relation<V> relation, int k, PrimitiveDistanceFunction<? super V,?> distanceFunction) Choose initial means
DBIDs	chooseInitialMedoids(int k, DistanceQuery<? super V,?> distQ2) Choose initial means
protected double	initialWeights(double[] weights, ArrayDBIDs ids, DBID latest, DistanceQuery<? super V,D> distQ) Initialize the weight list.
protected double	updateWeights(double[] weights, ArrayDBIDs ids, DBID latest, DistanceQuery<? super V,D> distQ) Update the weight list.
protected double	updateWeights(double[] weights, ArrayDBIDs ids, DBID latest, PrimitiveDoubleDistanceFunction<V> distF, Relation<V> rel) Update the weight list.

Methods inherited from class java.lang.Object

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

Constructor Detail

KMeansPlusPlusInitialMeans

public KMeansPlusPlusInitialMeans(RandomFactory rnd)

Constructor.

Parameters:

rnd - Random generator.

Method Detail

chooseInitialMeans

public List<V> chooseInitialMeans(Relation<V> relation,
                         int k,
                         PrimitiveDistanceFunction<? super V,?> distanceFunction)

Description copied from interface: KMeansInitialization

Choose initial means

Specified by:

chooseInitialMeans in interface KMeansInitialization<V>

Parameters:

relation - Relation

k - Parameter k

distanceFunction - Distance function

Returns:

List of chosen means for k-means

chooseInitialMedoids

public DBIDs chooseInitialMedoids(int k,
                         DistanceQuery<? super V,?> distQ2)

Description copied from interface: KMedoidsInitialization

Choose initial means

Specified by:

chooseInitialMedoids in interface KMedoidsInitialization<V>

Parameters:

k - Parameter k

distQ2 - Distance function

Returns:

List of chosen means for k-means

initialWeights

protected double initialWeights(double[] weights,
                    ArrayDBIDs ids,
                    DBID latest,
                    DistanceQuery<? super V,D> distQ)

Initialize the weight list.

Parameters:

weights - Weight list

ids - IDs

latest - Added ID

distQ - Distance query

Returns:

Weight sum

updateWeights

protected double updateWeights(double[] weights,
                   ArrayDBIDs ids,
                   DBID latest,
                   DistanceQuery<? super V,D> distQ)

Update the weight list.

Parameters:

weights - Weight list

ids - IDs

latest - Added ID

distQ - Distance query

Returns:

Weight sum

updateWeights

protected double updateWeights(double[] weights,
                   ArrayDBIDs ids,
                   DBID latest,
                   PrimitiveDoubleDistanceFunction<V> distF,
                   Relation<V> rel)

Update the weight list.

Parameters:

weights - Weight list

ids - IDs

latest - Added ID

distF - Distance function

Returns:

Weight sum