org.openimaj.ml.clustering.random.RandomSetByteClusterer Maven / Gradle / Ivy

Go to download
Show more of this group Show more artifacts with this name
Show all versions of clustering Show documentation
Various clustering algorithm implementations for all primitive types including random, random forest, K-Means (Exact, Hierarchical and Approximate), ...
There is a newer version: 1.3.5
Show newest version
/*
	AUTOMATICALLY GENERATED BY jTemp FROM
	/Users/jon/Work/openimaj/tags/openimaj-1.3.1/machine-learning/clustering/src/main/jtemp/org/openimaj/ml/clustering/random/RandomSet#T#Clusterer.jtemp
*/
/**
 * Copyright (c) 2011, The University of Southampton and the individual contributors.
 * All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without modification,
 * are permitted provided that the following conditions are met:
 *
 *   * 	Redistributions of source code must retain the above copyright notice,
 * 	this list of conditions and the following disclaimer.
 *
 *   *	Redistributions in binary form must reproduce the above copyright notice,
 * 	this list of conditions and the following disclaimer in the documentation
 * 	and/or other materials provided with the distribution.
 *
 *   *	Neither the name of the University of Southampton nor the names of its
 * 	contributors may be used to endorse or promote products derived from this
 * 	software without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
 * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
 * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
 * DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR
 * ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
 * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
 * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
 * ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
 * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */
package org.openimaj.ml.clustering.random;

import java.util.Arrays;
import java.util.Random;

import org.openimaj.data.DataSource;
import org.openimaj.data.RandomData;
import org.openimaj.ml.clustering.ByteCentroidsResult;

/**
 * A similar strategy to {@link RandomSetByteClusterer} however it is 
 * guaranteed that the same training vector will not be sampled more than once. 
 * 
 * @author Jonathon Hare ([email protected])
 * @author Sina Samangooei ([email protected])
 */
public class RandomSetByteClusterer extends RandomByteClusterer {
	/**
	 * Creates a new random byte cluster used to create K centroids with data containing M elements.
	 *
	 * @param M number of elements in each data vector 
	 */
	public RandomSetByteClusterer(int M) {
		super(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.
	 *
	 * @param M number of elements in each data vector
	 * @param K number of centroids to be created
	 */
	public RandomSetByteClusterer(int M, int K) {
		super(M, K);
	}
	
	/**
	 * 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 guaranteed that the same data point will not be selected
	 * many times, though this is not the case if two seperate entries provided are identical.
	 * 
	 * @params data source of centroids
	 * @return the selected centroids
	 */
    @Override
	public ByteCentroidsResult cluster(byte[][] data) {
		ByteCentroidsResult result = new ByteCentroidsResult();
		
		if (K == -1) {
			result.centroids = data;
		} else {
			if (data.length < K) {
				throw new IllegalArgumentException("Not enough data");
			}
			
			result.centroids = new byte[K][];
			
			int[] indices;
			if(this.seed >= 0)
				indices = RandomData.getUniqueRandomInts(this.K, 0, data.length, new Random(this.seed));
			else
				indices = RandomData.getUniqueRandomInts(this.K, 0, data.length);
			
			for (int i = 0 ; i < indices.length; i++) {
				int dIndex = indices[i];
				
				result.centroids[i] = Arrays.copyOf(data[dIndex ], data[dIndex ].length);
			}
		}
		
		return result;
	}
	
	/**
	 * Selects K elements from the provided {@link DataSource} as the centroids of the clusters. 
	 * If K is -1 all provided data points will be selected. It is guaranteed that the same data 
	 * point will not be selected many times, though this is not the case if two seperate entries 
	 * provided are identical.
	 * 
	 * @params data a data source object
	 * @return the selected centroids
	 */
	@Override
	public ByteCentroidsResult cluster(DataSource data) {
		ByteCentroidsResult result = new ByteCentroidsResult();
		
		if(K == -1) {
			final int nc = data.numRows();
			result.centroids = new byte[nc][data.numDimensions()];
		} else {
			result.centroids = new byte[K][data.numDimensions()];
		}
		
		data.getRandomRows(result.centroids);
		
		return result;
	}
}