org.apache.commons.math3.ml.clustering
Class Clusterer<T extends Clusterable>

java.lang.Object
  org.apache.commons.math3.ml.clustering.Clusterer<T>

Type Parameters:

T - the type of points that can be clustered

Direct Known Subclasses:

DBSCANClusterer, KMeansPlusPlusClusterer, MultiKMeansPlusPlusClusterer

public abstract class Clusterer<T extends Clusterable>
extends Object

Base class for clustering algorithms.

Since:

3.2

Version:

$Id $

Clusterer

protected Clusterer(DistanceMeasure measure)

Build a new clusterer with the given DistanceMeasure.

Parameters:

measure - the distance measure to use

cluster

public abstract List<? extends Cluster<T>> cluster(Collection<T> points)
                                                                throws MathIllegalArgumentException,
                                                                       ConvergenceException

Perform a cluster analysis on the given set of Clusterable instances.

Parameters:

points - the set of Clusterable instances

Returns:

a List of clusters

Throws:

MathIllegalArgumentException - if points are null or the number of data points is not compatible with this clusterer

ConvergenceException - if the algorithm has not yet converged after the maximum number of iterations has been exceeded

getDistanceMeasure

public DistanceMeasure getDistanceMeasure()

Returns the DistanceMeasure instance used by this clusterer.

Returns:

the distance measure

distance

protected double distance(Clusterable p1,
                          Clusterable p2)

Calculates the distance between two Clusterable instances with the configured DistanceMeasure.

Parameters:

p1 - the first clusterable

p2 - the second clusterable

Returns:

the distance between the two clusterables