Package elki.clustering.kmeans.initialization

Class SphericalAFKMC2.Instance

java.lang.Object

elki.clustering.kmeans.initialization.KMC2.Instance

elki.clustering.kmeans.initialization.AFKMC2.Instance

elki.clustering.kmeans.initialization.SphericalAFKMC2.Instance

Enclosing class:

SphericalAFKMC2

protected static class SphericalAFKMC2.Instance
extends AFKMC2.Instance

Abstract instance implementing the weight handling.

Author:

Erich Schubert

Field Summary

Fields

Modifier and Type	Field	Description
protected double	alpha	Parameter to balance distance vs. uniform sampling.

Fields inherited from class elki.clustering.kmeans.initialization.KMC2.Instance

distance, diststat, m, random, relation, weights

Constructor Summary

Constructors

Constructor	Description
Instance(Relation<? extends NumberVector> relation, int m, double alpha, RandomFactory rnd)	Constructor.

Method Summary

Modifier and Type	Method	Description
protected double	distance(DBIDRef cand, java.util.List<NumberVector> means)	Minimum distance to the current means.
protected double	initialWeights(NumberVector first)	Initialize the weight list.
protected double	similarity(NumberVector a, DBIDRef b)	Compute the distance of two objects.

Methods inherited from class elki.clustering.kmeans.initialization.AFKMC2.Instance

getLogger, sample

Methods inherited from class elki.clustering.kmeans.initialization.KMC2.Instance

chooseRemaining, distance, run

Methods inherited from class java.lang.Object

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

Field Detail

alpha

protected double alpha

Parameter to balance distance vs. uniform sampling.

Constructor Detail

Instance

public Instance(Relation<? extends NumberVector> relation,
                int m,
                double alpha,
                RandomFactory rnd)

Constructor.

Parameters:

relation - Data relation

alpha - Alpha parameter

m - M parameter

rnd - Random generator

Method Detail

initialWeights

protected double initialWeights(NumberVector first)

Description copied from class: KMC2.Instance

Initialize the weight list.

Overrides:

initialWeights in class KMC2.Instance

Parameters:

first - Added ID

Returns:

Weight sum

similarity

protected double similarity(NumberVector a,
                            DBIDRef b)

Compute the distance of two objects.

Parameters:

a - First object

b - Second object

Returns:

Distance

distance

protected double distance(DBIDRef cand,
                          java.util.List<NumberVector> means)

Description copied from class: KMC2.Instance

Minimum distance to the current means.

Overrides:

distance in class KMC2.Instance

Parameters:

cand - Candidate

means - Current means

Returns:

Minimum distance