info.debatty.java.stringsimilarity.Jaccard Maven / Gradle / Ivy

Go to download

Show more of this group Show more artifacts with this name
Show all versions of java-string-similarity Show documentation

Implementation of various string similarity and distance algorithms: Levenshtein, Jaro-winkler, n-Gram, Q-Gram, Jaccard index, Longest Common Subsequence edit distance, cosine similarity...

There is a newer version: 2.0.0

Show newest version

/*
 * The MIT License
 *
 * Copyright 2015 Thibault Debatty.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a copy
 * of this software and associated documentation files (the "Software"), to deal
 * in the Software without restriction, including without limitation the rights
 * to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
 * copies of the Software, and to permit persons to whom the Software is
 * furnished to do so, subject to the following conditions:
 *
 * The above copyright notice and this permission notice shall be included in
 * all copies or substantial portions of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
 * THE SOFTWARE.
 */

package info.debatty.java.stringsimilarity;

import info.debatty.java.stringsimilarity.interfaces.MetricStringDistance;
import info.debatty.java.stringsimilarity.interfaces.NormalizedStringSimilarity;
import info.debatty.java.stringsimilarity.interfaces.NormalizedStringDistance;
import java.util.HashSet;
import java.util.Map;
import java.util.Set;

import net.jcip.annotations.Immutable;

/**
 * Each input string is converted into a set of n-grams, the Jaccard index is
 * then computed as |V1 inter V2| / |V1 union V2|.
 * Like Q-Gram distance, the input strings are first converted into sets of
 * n-grams (sequences of n characters, also called k-shingles), but this time
 * the cardinality of each n-gram is not taken into account.
 * Distance is computed as 1 - cosine similarity.
 * Jaccard index is a metric distance.
 * @author Thibault Debatty
 */
@Immutable
public class Jaccard extends ShingleBased implements
        MetricStringDistance, NormalizedStringDistance,
        NormalizedStringSimilarity {

    /**
     * The strings are first transformed into sets of k-shingles (sequences of k
     * characters), then Jaccard index is computed as |A inter B| / |A union B|.
     * The default value of k is 3.
     *
     * @param k
     */
    public Jaccard(final int k) {
        super(k);
    }

    /**
     * The strings are first transformed into sets of k-shingles (sequences of k
     * characters), then Jaccard index is computed as |A inter B| / |A union B|.
     * The default value of k is 3.
     */
    public Jaccard() {
        super();
    }

    /**
     * Compute Jaccard index: |A inter B| / |A union B|.
     * @param s1 The first string to compare.
     * @param s2 The second string to compare.
     * @return The Jaccard index in the range [0, 1]
     * @throws NullPointerException if s1 or s2 is null.
     */
    public final double similarity(final String s1, final String s2) {
        if (s1 == null) {
            throw new NullPointerException("s1 must not be null");
        }

        if (s2 == null) {
            throw new NullPointerException("s2 must not be null");
        }

        if (s1.equals(s2)) {
            return 1;
        }

        Map profile1 = getProfile(s1);
        Map profile2 = getProfile(s2);


        Set union = new HashSet();
        union.addAll(profile1.keySet());
        union.addAll(profile2.keySet());

        int inter = profile1.keySet().size() + profile2.keySet().size()
                - union.size();

        return 1.0 * inter / union.size();
    }


    /**
     * Distance is computed as 1 - similarity.
     * @param s1 The first string to compare.
     * @param s2 The second string to compare.
     * @return 1 - the Jaccard similarity.
     * @throws NullPointerException if s1 or s2 is null.
     */
    public final double distance(final String s1, final String s2) {
        return 1.0 - similarity(s1, s2);
    }
}