Package org.ddogleg.clustering.kmeans

Class StandardKMeans_MT<P>

java.lang.Object

org.ddogleg.clustering.kmeans.StandardKMeans<P>

org.ddogleg.clustering.kmeans.StandardKMeans_MT<P>

All Implemented Interfaces:

ComputeClusters<P>

public class StandardKMeans_MT<P>
extends StandardKMeans<P>

Concurrent implementation of StandardKMeans

Field Summary

Fields inherited from class org.ddogleg.clustering.kmeans.StandardKMeans

convergeTol, maxIterations, maxReSeed, reseedAfterIterations, seedSelector, updateMeans

Constructor Summary

Constructors

Constructor	Description
StandardKMeans_MT(ComputeMeanClusters<P> updateMeans, InitializeKMeans<P> seedSelector, PointDistance<P> distancer, DogLambdas.NewInstance<P> factory)	Configures k-means parameters

Method Summary

Modifier and Type	Method	Description
protected int	findBestMatch(P p, DogArray<P> clusters, StandardKMeans_MT<P>.org.ddogleg.clustering.kmeans.StandardKMeans_MT.MatchData match)	Searches for this cluster which is the closest to p
protected void	matchPointsToClusters(LArrayAccessor<P> points, DogArray<P> clusters)	Finds the cluster which is the closest to each point.
ComputeClusters<P>	newInstanceThread()	Creates a new instance which has the same configuration and can be run in parallel.

Methods inherited from class org.ddogleg.clustering.kmeans.StandardKMeans

findBestMatch, getAssignment, getDistanceMeasure, initialize, process, setVerbose

Methods inherited from class java.lang.Object

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

Constructor Details

StandardKMeans_MT

public StandardKMeans_MT(ComputeMeanClusters<P> updateMeans,
 InitializeKMeans<P> seedSelector,
 PointDistance<P> distancer,
 DogLambdas.NewInstance<P> factory)

Configures k-means parameters

Parameters:

seedSelector - Used to select initial seeds for the clusters

Method Details

matchPointsToClusters

protected void matchPointsToClusters(LArrayAccessor<P> points,
 DogArray<P> clusters)

Finds the cluster which is the closest to each point. The point is the added to the sum for the cluster and its member count incremented

Overrides:

matchPointsToClusters in class StandardKMeans<P>

findBestMatch

protected int findBestMatch(P p,
 DogArray<P> clusters,
 StandardKMeans_MT<P>.org.ddogleg.clustering.kmeans.StandardKMeans_MT.MatchData match)

Searches for this cluster which is the closest to p

newInstanceThread

public ComputeClusters<P> newInstanceThread()

Description copied from interface: ComputeClusters

Creates a new instance which has the same configuration and can be run in parallel. Some components can be shared as long as they are read only and thread safe.

Specified by:

newInstanceThread in interface ComputeClusters<P>

Overrides:

newInstanceThread in class StandardKMeans<P>