Package elki.clustering.kmeans.spherical

Class SphericalKMeans.Instance

java.lang.Object

elki.clustering.kmeans.AbstractKMeans.Instance

elki.clustering.kmeans.spherical.SphericalKMeans.Instance

Direct Known Subclasses:

EuclideanSphericalHamerlyKMeans.Instance, EuclideanSphericalSimplifiedElkanKMeans.Instance, SphericalHamerlyKMeans.Instance, SphericalSimplifiedElkanKMeans.Instance, SphericalSimplifiedHamerlyKMeans.Instance, SphericalSingleAssignmentKMeans.Instance

Enclosing class:

SphericalKMeans<V extends NumberVector>

public static class SphericalKMeans.Instance
extends AbstractKMeans.Instance

Instance for a particular data set.

Author:

Alexander Voß

Field Summary

Fields inherited from class elki.clustering.kmeans.AbstractKMeans.Instance

assignment, clusters, diststat, isSquared, k, key, means, relation, varsum

Constructor Summary

Constructors

Constructor	Description
Instance(Relation<? extends NumberVector> relation, double[][] means)	Constructor.

Method Summary

Modifier and Type	Method	Description
protected int	assignToNearestCluster()	Assign each object to the nearest cluster.
protected double	distance(double[] x, double[] y)	Compute the squared distance (and count the distance computations).
protected double	distance(NumberVector x, double[] y)	Compute the squared distance (and count the distance computations).
protected double	distance(NumberVector x, NumberVector y)	Compute the squared distance (and count the distance computations).
protected Logging	getLogger()	Get the class logger.
protected void	initialSeparation(double[][] ccsim)	Initial separation of means.
int	iterate(int iteration)	Main loop function.
protected static double[][]	means(java.util.List<? extends DBIDs> clusters, double[][] means, Relation<? extends NumberVector> relation)	Returns the mean vectors of the given clusters in the given database.
protected void	meansFromSums(double[][] dst, double[][] sums, double[][] prev)	Compute means from cluster sums by adding and normalizing.
protected void	movedSimilarity(double[][] means, double[][] newmeans, double[] sims)	Similarity to previous locations.
protected void	recomputeVariance(Relation<? extends NumberVector> relation)	Recompute the cluster variances.
protected double	similarity(double[] vec1, double[] vec2)	Compute the similarity of two objects (and count this operation).
protected double	similarity(NumberVector vec1, double[] vec2)	Compute the similarity of two objects (and count this operation).
protected double	sqrtdistance(NumberVector x, double[] y)	Compute the distance (and count the distance computations).
protected double	sqrtdistance(NumberVector x, NumberVector y)	Compute the distance (and count the distance computations).

Methods inherited from class elki.clustering.kmeans.AbstractKMeans.Instance

buildResult, buildResult, computeSquaredSeparation, copyMeans, initialSeperation, movedDistance, recomputeSeperation, run, sqrtdistance

Methods inherited from class java.lang.Object

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

Constructor Detail

Instance

public Instance(Relation<? extends NumberVector> relation,
                double[][] means)

Constructor.

Parameters:

relation - Data relation

means - Initial cluster means

Method Detail

iterate

public int iterate(int iteration)

Description copied from class: AbstractKMeans.Instance

Main loop function.

Specified by:

iterate in class AbstractKMeans.Instance

Parameters:

iteration - Iteration number (beginning at 1)

Returns:

Number of reassigned points

assignToNearestCluster

protected int assignToNearestCluster()

Description copied from class: AbstractKMeans.Instance

Assign each object to the nearest cluster.

Overrides:

assignToNearestCluster in class AbstractKMeans.Instance

Returns:

number of objects reassigned

similarity

protected double similarity(NumberVector vec1,
                            double[] vec2)

Compute the similarity of two objects (and count this operation).

Parameters:

vec1 - First vector

vec2 - Second vector

Returns:

Similarity (dot product)

similarity

protected double similarity(double[] vec1,
                            double[] vec2)

Compute the similarity of two objects (and count this operation).

Parameters:

vec1 - First vector

vec2 - Second vector

Returns:

Similarity (dot product)

distance

protected double distance(double[] x,
                          double[] y)

Description copied from class: AbstractKMeans.Instance

Compute the squared distance (and count the distance computations).

Overrides:

distance in class AbstractKMeans.Instance

Parameters:

x - First object

y - Second object

Returns:

Distance

distance

protected double distance(NumberVector x,
                          double[] y)

Description copied from class: AbstractKMeans.Instance

Compute the squared distance (and count the distance computations).

Overrides:

distance in class AbstractKMeans.Instance

Parameters:

x - First object

y - Second object

Returns:

Distance

distance

protected double distance(NumberVector x,
                          NumberVector y)

Description copied from class: AbstractKMeans.Instance

Compute the squared distance (and count the distance computations).

Overrides:

distance in class AbstractKMeans.Instance

Parameters:

x - First object

y - Second object

Returns:

Distance

sqrtdistance

protected double sqrtdistance(NumberVector x,
                              double[] y)

Description copied from class: AbstractKMeans.Instance

Compute the distance (and count the distance computations). If the distance is squared, also compute the square root.

Overrides:

sqrtdistance in class AbstractKMeans.Instance

Parameters:

x - First object

y - Second object

Returns:

Distance

sqrtdistance

protected double sqrtdistance(NumberVector x,
                              NumberVector y)

Description copied from class: AbstractKMeans.Instance

Compute the distance (and count the distance computations). If the distance is squared, also compute the square root.

Overrides:

sqrtdistance in class AbstractKMeans.Instance

Parameters:

x - First object

y - Second object

Returns:

Distance

initialSeparation

protected void initialSeparation(double[][] ccsim)

Initial separation of means. Used by Elkan and Hamerly.

Parameters:

ccsim - Output square root of pairwise separation

movedSimilarity

protected void movedSimilarity(double[][] means,
                               double[][] newmeans,
                               double[] sims)

Similarity to previous locations.

Used by Hamerly, (Simplified)Elkan.

Parameters:

means - Old means

newmeans - New means

sims - Similarities moved (output)

meansFromSums

protected void meansFromSums(double[][] dst,
                             double[][] sums,
                             double[][] prev)

Compute means from cluster sums by adding and normalizing.

Overrides:

meansFromSums in class AbstractKMeans.Instance

Parameters:

dst - Output means

sums - Input sums

prev - Previous means (to handle empty clusters)

recomputeVariance

protected void recomputeVariance(Relation<? extends NumberVector> relation)

Description copied from class: AbstractKMeans.Instance

Recompute the cluster variances.

Overrides:

recomputeVariance in class AbstractKMeans.Instance

Parameters:

relation - Data relation

getLogger

protected Logging getLogger()

Description copied from class: AbstractKMeans.Instance

Get the class logger.

Specified by:

getLogger in class AbstractKMeans.Instance

Returns:

Logger

means

protected static double[][] means(java.util.List<? extends DBIDs> clusters,
                                  double[][] means,
                                  Relation<? extends NumberVector> relation)

Returns the mean vectors of the given clusters in the given database.

Parameters:

clusters - the clusters to compute the means

means - the recent means

relation - the database containing the vectors

Returns:

the mean vectors of the given clusters in the given database