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 /**
20 * Measures the Jaccard distance of two sets of character sequence. Jaccard distance is the dissimilarity between two sets. It is the complementary of Jaccard
21 * similarity.
22 *
23 * <p>
24 * For further explanation about Jaccard Distance, refer https://en.wikipedia.org/wiki/Jaccard_index
25 * </p>
26 *
27 * @since 1.0
28 */
29 public class JaccardDistance implements EditDistance<Double> {
30
31 /**
32 * Creates a new instance.
33 */
34 public JaccardDistance() {
35 // empty
36 }
37
38 /**
39 * Computes the Jaccard distance of two set character sequence passed as input. Calculates Jaccard similarity and returns the complement of it.
40 *
41 * @param left first input sequence.
42 * @param right second input sequence.
43 * @return The Jaccard distance.
44 * @throws IllegalArgumentException if either String input {@code null}.
45 */
46 @Override
47 public Double apply(final CharSequence left, final CharSequence right) {
48 return apply(SimilarityInput.input(left), SimilarityInput.input(right));
49 }
50
51 /**
52 * Computes the Jaccard distance of two set character sequence passed as input. Calculates Jaccard similarity and returns the complement of it.
53 *
54 * @param <E> The type of similarity score unit.
55 * @param left first input sequence.
56 * @param right second input sequence.
57 * @return index.
58 * @throws IllegalArgumentException if either String input {@code null}.
59 */
60 public <E> Double apply(final SimilarityInput<E> left, final SimilarityInput<E> right) {
61 return 1.0 - JaccardSimilarity.INSTANCE.apply(left, right).doubleValue();
62 }
63
64 }