org.openimaj.ml.clustering.kmeans

Class FeatureVectorKMeansInit<T>

java.lang.Object

org.openimaj.ml.clustering.kmeans.FeatureVectorKMeansInit<T>

Type Parameters:

T - Type of object being clustered

Direct Known Subclasses:

FeatureVectorKMeansInit.RANDOM

public abstract class FeatureVectorKMeansInit<T>
extends Object

Initialisation for K-Means clustering. Given a data source of samples and a set of clusters to fill, implementations of this class should initialise the KMeans algorithm. A default RANDOM implementation is provided which uses DataSource.getRandomRows(DATATYPE[])

Author:

Jonathon Hare (jsh2@ecs.soton.ac.uk), Sina Samangooei (ss@ecs.soton.ac.uk)

Nested Class Summary

Nested Classes

Modifier and Type	Class and Description
static class	FeatureVectorKMeansInit.RANDOM<T> Simple kmeans initialized on randomly selected samples.

Constructor Summary

Constructors

Constructor and Description
FeatureVectorKMeansInit()

Method Summary

Modifier and Type	Method and Description
abstract void	initKMeans(DataSource<T> bds, T[] clusters) Initialise the centroids based on the given data.

Methods inherited from class java.lang.Object

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

Constructor Detail

FeatureVectorKMeansInit

public FeatureVectorKMeansInit()

Method Detail

initKMeans

public abstract void initKMeans(DataSource<T> bds,
                                T[] clusters)
                         throws IOException

Initialise the centroids based on the given data.

Parameters:

bds - the data source of samples

clusters - the clusters to init

Throws:

IOException - problem reading samples