org.openimaj.ml.clustering.random.RandomIntClusterer 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/Random#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.ml.clustering.IntCentroidsResult;
import org.openimaj.ml.clustering.IndexClusters;
import org.openimaj.ml.clustering.SpatialClusterer;

/**
 * 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 ([email protected])
 * @author Sina Samangooei ([email protected])
 *
 */
public class RandomIntClusterer implements SpatialClusterer {
	protected int M;
	protected int K;
	protected Random random;
	protected long seed;
	
	/**
	 * 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
	 * @param K number of centroids to be created
	 */
	public RandomIntClusterer(int M, int K) {
		this.M = M;
		this.K = K;
		this.random = new Random();
		this.seed = -1;
	}
	
	/**
	 * 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
	 */
	public RandomIntClusterer(int M) {
		this(M, -1);
	}
		
	/**
	 * @param seed the seed for the {@link Random} object used to select random data points.
	 */
	public void setSeed(long seed) {
		this.random = new Random();
		random.setSeed(seed);
		this.seed = seed;
	}
	
	/***
	 * 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.
	 * 
	 * @params data source of centroids
	 * @return the selected centroids
	 */
	@Override
	public IntCentroidsResult cluster(int[][] data) {
		int nc = this.K;
		
		if (nc == -1) {
			nc = data.length;
		}
		
		IntCentroidsResult result = new IntCentroidsResult();
		result.centroids = new int[nc][];
		
		for (int i = 0; i < nc; i++) {
			int dIndex = this.random.nextInt(data.length);
			
			result.centroids[i] = Arrays.copyOf(data[dIndex], data[dIndex].length);
		}
		
		return result;
	}
	
	@Override
	public int[][] performClustering(int[][] data) {
		IntCentroidsResult res = this.cluster(data);
		return new IndexClusters(res.defaultHardAssigner().assign(data)).clusters();
	}
	
	/**
	 * 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 not guaranteed that the same data 
	 * point will not be selected many times.
	 * 
	 * @params data a data source object
	 * @return the selected centroids
	 */
	@Override
	public IntCentroidsResult cluster(DataSource data) {
		int nc = this.K;
		
		if (nc == -1) {
			nc = data.numRows();
		}
		
		IntCentroidsResult result = new IntCentroidsResult();
		result.centroids = new int[nc][M];
		int[][] dataRow = new int[1][];
		
		for (int i = 0; i < nc; i++) {
			int dIndex = this.random.nextInt(data.numRows());
			dataRow[0] = result.centroids[i];
			
			data.getData(dIndex, dIndex+1, dataRow);
		}
		
		return result;
	}
}