1 /*
2 * Licensed to the Apache Software Foundation (ASF) under one or more
3 * contributor license agreements. See the NOTICE file distributed with
4 * this work for additional information regarding copyright ownership.
5 * The ASF licenses this file to You under the Apache License, Version 2.0
6 * (the "License"); you may not use this file except in compliance with
7 * the License. You may obtain a copy of the License at
8 *
9 * https://www.apache.org/licenses/LICENSE-2.0
10 *
11 * Unless required by applicable law or agreed to in writing, software
12 * distributed under the License is distributed on an "AS IS" BASIS,
13 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 * See the License for the specific language governing permissions and
15 * limitations under the License.
16 */
17 package org.apache.commons.text.similarity;
18
19 import java.util.HashSet;
20 import java.util.Set;
21
22 /**
23 * Measures the Jaccard similarity (aka Jaccard index) of two sets of character sequence. Jaccard similarity is the size of the intersection divided by the size
24 * of the union of the two sets.
25 *
26 * <p>
27 * For further explanation about Jaccard Similarity, refer https://en.wikipedia.org/wiki/Jaccard_index
28 * </p>
29 *
30 * @since 1.0
31 */
32 public class JaccardSimilarity implements SimilarityScore<Double> {
33
34 /**
35 * The singleton instance.
36 */
37 static final JaccardSimilarity INSTANCE = new JaccardSimilarity();
38
39 /**
40 * Creates a new instance.
41 */
42 public JaccardSimilarity() {
43 // empty
44 }
45
46 /**
47 * Computes the Jaccard Similarity of two set character sequence passed as input.
48 *
49 * @param left first input sequence.
50 * @param right second input sequence.
51 * @return The Jaccard Similarity of two set character sequence passed as input.
52 * @throws IllegalArgumentException if either String input {@code null}.
53 */
54 @Override
55 public Double apply(final CharSequence left, final CharSequence right) {
56 return apply(SimilarityInput.input(left), SimilarityInput.input(right));
57 }
58
59 /**
60 * Computes the Jaccard Similarity of two character sequences passed as input. Does the calculation by identifying the union (characters in at least one of
61 * the two sets) of the two sets and intersection (characters which are present in set one which are present in set two)
62 *
63 * @param <E> The type of similarity score unit.
64 * @param left first input sequence.
65 * @param right second input sequence.
66 * @return The Jaccard Similarity of two set character sequence passed as input.
67 * @since 1.13.0
68 */
69 public <E> Double apply(final SimilarityInput<E> left, final SimilarityInput<E> right) {
70 if (left == null || right == null) {
71 throw new IllegalArgumentException("Input cannot be null");
72 }
73 final int leftLength = left.length();
74 final int rightLength = right.length();
75 if (leftLength == 0 && rightLength == 0) {
76 return 1d;
77 }
78 if (leftLength == 0 || rightLength == 0) {
79 return 0d;
80 }
81 final Set<E> leftSet = new HashSet<>();
82 for (int i = 0; i < leftLength; i++) {
83 leftSet.add(left.at(i));
84 }
85 final Set<E> rightSet = new HashSet<>();
86 for (int i = 0; i < rightLength; i++) {
87 rightSet.add(right.at(i));
88 }
89 final Set<E> unionSet = new HashSet<>(leftSet);
90 unionSet.addAll(rightSet);
91 final int intersectionSize = leftSet.size() + rightSet.size() - unionSet.size();
92 return 1.0d * intersectionSize / unionSet.size();
93 }
94 }