Package elki.clustering.kmeans.initialization

Class KMeansPlusPlus.NumberVectorInstance

java.lang.Object

elki.clustering.kmeans.initialization.KMeansPlusPlus.Instance<NumberVector>

elki.clustering.kmeans.initialization.KMeansPlusPlus.NumberVectorInstance

Direct Known Subclasses:

Ostrovsky.NumberVectorInstance

Enclosing class:

KMeansPlusPlus<O>

protected static class KMeansPlusPlus.NumberVectorInstance
extends KMeansPlusPlus.Instance<NumberVector>

Instance for k-means, number vector based.

Author:

Erich Schubert

Field Summary

Fields

Modifier and Type	Field	Description
protected NumberVectorDistance<?>	distance	Distance function
protected Relation<? extends NumberVector>	relation	Data relation.

Fields inherited from class elki.clustering.kmeans.initialization.KMeansPlusPlus.Instance

diststat, ids, random, weights

Constructor Summary

Constructors

Constructor	Description
NumberVectorInstance(Relation<? extends NumberVector> relation, NumberVectorDistance<?> distance, RandomFactory rnd)	Constructor.

Method Summary

Modifier and Type	Method	Description
protected void	chooseRemaining(int k, java.util.List<NumberVector> means, double weightsum)	Choose remaining means, weighted by distance.
protected double	distance(NumberVector a, DBIDRef b)	Compute the distance of two objects.
double[][]	run(int k)	Run k-means++ initialization for number vectors.

Methods inherited from class elki.clustering.kmeans.initialization.KMeansPlusPlus.Instance

initialWeights, nextDouble, updateWeights

Methods inherited from class java.lang.Object

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

Field Detail

distance

protected NumberVectorDistance<?> distance

Distance function

relation

protected Relation<? extends NumberVector> relation

Data relation.

Constructor Detail

NumberVectorInstance

public NumberVectorInstance(Relation<? extends NumberVector> relation,
                            NumberVectorDistance<?> distance,
                            RandomFactory rnd)

Constructor.

Parameters:

relation - Data relation to process

distance - Distance function

rnd - Random generator

Method Detail

run

public double[][] run(int k)

Run k-means++ initialization for number vectors.

Parameters:

k - K

Returns:

Vectors

distance

protected double distance(NumberVector a,
                          DBIDRef b)

Description copied from class: KMeansPlusPlus.Instance

Compute the distance of two objects.

Specified by:

distance in class KMeansPlusPlus.Instance<NumberVector>

Parameters:

a - First object

b - Second object

Returns:

Distance

chooseRemaining

protected void chooseRemaining(int k,
                               java.util.List<NumberVector> means,
                               double weightsum)

Choose remaining means, weighted by distance.

Parameters:

k - Number of means to choose

means - Means storage

weightsum - Sum of weights