org.ddogleg.clustering.kmeans

Class InitializePlusPlus

java.lang.Object

org.ddogleg.clustering.kmeans.InitializePlusPlus

All Implemented Interfaces:

InitializeKMeans_F64

public class InitializePlusPlus
extends java.lang.Object
implements InitializeKMeans_F64

Implementation of the seeding strategy described in [1]. A point is randomly selected from the list as the first seed. The remaining seeds are selected randomly based on the distance of each seed from their closest cluster.

[1] David Arthur and Sergei Vassilvitskii. 2007. k-means++: the advantages of careful seeding. In Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms (SODA '07). Society for Industrial and Applied Mathematics, Philadelphia, PA, USA, 1027-1035.

Constructor Summary

Constructors

Constructor and Description
InitializePlusPlus()

Method Summary

Modifier and Type	Method and Description
void	init(int pointDimension, long randomSeed) Initializes internal data structures.
void	selectSeeds(java.util.List<double[]> points, java.util.List<double[]> seeds)

Methods inherited from class java.lang.Object

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

Constructor Detail

InitializePlusPlus

public InitializePlusPlus()

Method Detail

init

public void init(int pointDimension,
                 long randomSeed)

Description copied from interface: InitializeKMeans_F64

Initializes internal data structures. Must be called first.

Specified by:

init in interface InitializeKMeans_F64

Parameters:

pointDimension - NUmber of degrees of freedom in each point.

randomSeed - Seed for any random number generators used internally.

selectSeeds

public void selectSeeds(java.util.List<double[]> points,
                        java.util.List<double[]> seeds)

Specified by:

selectSeeds in interface InitializeKMeans_F64

Parameters:

points - Set of points which is to be clustered.

seeds - List full of points which will act as the initial seed for k-means.