org.openimaj.ml.clustering.random

Class RandomShortClusterer

java.lang.Object

org.openimaj.ml.clustering.random.RandomShortClusterer

All Implemented Interfaces:

Clusterer<short[][]>, SpatialClusterer<ShortCentroidsResult,short[]>

Direct Known Subclasses:

RandomSetShortClusterer

public class RandomShortClusterer
extends Object
implements SpatialClusterer<ShortCentroidsResult,short[]>

A simple (yet apparently quite effective in high dimensions) clustering technique trained used randomly sampled data points. A configurable number of data points are selected from the training data to represent the centroids.

Author:

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

Field Summary

Fields

Modifier and Type	Field and Description
protected int	K
protected int	M
protected Random	random
protected long	seed

Constructor Summary

Constructors

Constructor and Description
RandomShortClusterer(int M) Creates a new random byte cluster used to create centroids with data containing M elements.
RandomShortClusterer(int M, int K) Creates a new random byte cluster used to create K centroids with data containing M elements.

Method Summary

Modifier and Type	Method and Description
ShortCentroidsResult	cluster(DataSource<short[]> data) Selects K elements from the provided DataSource as the centroids of the clusters.
ShortCentroidsResult	cluster(short[][] data) Selects K elements from the provided data as the centroids of the clusters.
int[][]	performClustering(short[][] data)
void	setSeed(long seed)

Methods inherited from class java.lang.Object

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

Field Detail

M

protected int M

K

protected int K

random

protected Random random

seed

protected long seed

Constructor Detail

RandomShortClusterer

public RandomShortClusterer(int M,
                            int K)

Creates a new random byte cluster used to create K centroids with data containing M elements.

Parameters:

M - number of elements in each data vector

K - number of centroids to be created

RandomShortClusterer

public RandomShortClusterer(int M)

Creates a new random byte cluster used to create centroids with data containing M elements. The number of clusters will be equal to the number of data points provided in training.

Parameters:

M - number of elements in each data vector

Method Detail

setSeed

public void setSeed(long seed)

Parameters:

seed - the seed for the Random object used to select random data points.

cluster

public ShortCentroidsResult cluster(short[][] data)

Selects K elements from the provided data as the centroids of the clusters. If K is -1 all provided data points will be selected. It is not guaranteed that the same data point will not be selected many times.

Specified by:

cluster in interface SpatialClusterer<ShortCentroidsResult,short[]>

Parameters:

data - the data.

Returns:

the selected centroids

performClustering

public int[][] performClustering(short[][] data)

Specified by:

performClustering in interface Clusterer<short[][]>

Returns:

Given data items, cluster them by index

cluster

public ShortCentroidsResult cluster(DataSource<short[]> data)

Selects K elements from the provided DataSource as the centroids of the clusters. If K is -1 all provided data points will be selected. It is not guaranteed that the same data point will not be selected many times.

Specified by:

cluster in interface SpatialClusterer<ShortCentroidsResult,short[]>

Parameters:

data - the data.

Returns:

the selected centroids