001/* 002 * Licensed to the Apache Software Foundation (ASF) under one or more 003 * contributor license agreements. See the NOTICE file distributed with 004 * this work for additional information regarding copyright ownership. 005 * The ASF licenses this file to You under the Apache License, Version 2.0 006 * (the "License"); you may not use this file except in compliance with 007 * the License. You may obtain a copy of the License at 008 * 009 * http://www.apache.org/licenses/LICENSE-2.0 010 * 011 * Unless required by applicable law or agreed to in writing, software 012 * distributed under the License is distributed on an "AS IS" BASIS, 013 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. 014 * See the License for the specific language governing permissions and 015 * limitations under the License. 016 */ 017package org.apache.commons.text.similarity; 018 019import java.util.HashSet; 020import java.util.Set; 021 022/** 023 * Measures the Jaccard similarity (aka Jaccard index) of two sets of character 024 * sequence. Jaccard similarity is the size of the intersection divided by the 025 * size of the union of the two sets. 026 * 027 * <p> 028 * For further explanation about Jaccard Similarity, refer 029 * https://en.wikipedia.org/wiki/Jaccard_index 030 * </p> 031 * 032 * @since 1.0 033 */ 034public class JaccardSimilarity implements SimilarityScore<Double> { 035 036 /** 037 * Singleton instance. 038 */ 039 static final JaccardSimilarity INSTANCE = new JaccardSimilarity(); 040 041 /** 042 * Calculates Jaccard Similarity of two set character sequence passed as 043 * input. 044 * 045 * @param left first character sequence 046 * @param right second character sequence 047 * @return index 048 * @throws IllegalArgumentException 049 * if either String input {@code null} 050 */ 051 @Override 052 public Double apply(final CharSequence left, final CharSequence right) { 053 if (left == null || right == null) { 054 throw new IllegalArgumentException("Input cannot be null"); 055 } 056 return calculateJaccardSimilarity(left, right); 057 } 058 059 /** 060 * Calculates Jaccard Similarity of two character sequences passed as 061 * input. Does the calculation by identifying the union (characters in at 062 * least one of the two sets) of the two sets and intersection (characters 063 * which are present in set one which are present in set two) 064 * 065 * @param left first character sequence 066 * @param right second character sequence 067 * @return index 068 */ 069 private Double calculateJaccardSimilarity(final CharSequence left, final CharSequence right) { 070 final int leftLength = left.length(); 071 final int rightLength = right.length(); 072 if (leftLength == 0 && rightLength == 0) { 073 return 1d; 074 } 075 if (leftLength == 0 || rightLength == 0) { 076 return 0d; 077 } 078 final Set<Character> leftSet = new HashSet<>(); 079 for (int i = 0; i < leftLength; i++) { 080 leftSet.add(left.charAt(i)); 081 } 082 final Set<Character> rightSet = new HashSet<>(); 083 for (int i = 0; i < rightLength; i++) { 084 rightSet.add(right.charAt(i)); 085 } 086 final Set<Character> unionSet = new HashSet<>(leftSet); 087 unionSet.addAll(rightSet); 088 final int intersectionSize = leftSet.size() + rightSet.size() - unionSet.size(); 089 return 1.0d * intersectionSize / unionSet.size(); 090 } 091}