org.simmetrics.metrics.JaccardSimilarity Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of simmetrics-core Show documentation

There is a newer version: 4.1.1

/*
 * SimMetrics - SimMetrics is a java library of Similarity or Distance Metrics,
 * e.g. Levenshtein Distance, that provide float based similarity measures
 * between String Data. All metrics return consistent measures rather than
 * unbounded similarity scores.
 * 
 * Copyright (C) 2014 SimMetrics authors
 * 
 * This file is part of SimMetrics. This program is free software: you can
 * redistribute it and/or modify it under the terms of the GNU General Public
 * License as published by the Free Software Foundation, either version 3 of the
 * License, or (at your option) any later version.
 * 
 * This program is distributed in the hope that it will be useful, but WITHOUT
 * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
 * FOR A PARTICULAR PURPOSE. See the GNU General Public License for more
 * details.
 * 
 * You should have received a copy of the GNU General Public License along with
 * SimMetrics. If not, see .
 */
package org.simmetrics.metrics;

import java.util.HashSet;
import java.util.Set;

import org.simmetrics.SetMetric;

/**
 * Jaccard similarity algorithm providing a similarity measure between two sets
 * using the vector space of presented tokens.
 * 
 * 
 * jaccard index(a,b) = ( |a & b| ) / ( | a or b | )
 * 

 * 
 * This metric is identical to the matching coefficient which operates on lists.
 * 
 * This class is immutable and thread-safe.
 * 
 * @see Wikipedia - Jaccard
 *      index
 * 
 * 
 * @param 
 *            type of the token
 * 
 */
public final class JaccardSimilarity implements SetMetric {

	@Override
	public float compare(Set a, Set b) {

		if (a.isEmpty() && b.isEmpty()) {
			return 1.0f;
		}

		if (a.isEmpty() || b.isEmpty()) {
			return 0.0f;
		}

		final Set all = new HashSet<>();
		all.addAll(a);
		all.addAll(b);

		final int intersection = (a.size() + b.size()) - all.size();

		// return JaccardSimilarity
		return intersection / (float) all.size();
	}

	@Override
	public String toString() {
		return "JaccardSimilarity";
	}

}