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.Map;
20
21 /**
22 * Measures the cosine distance between two character sequences.
23 *
24 * <p>It utilizes the {@link CosineSimilarity} to compute the distance. Character sequences
25 * are converted into vectors through a simple tokenizer that works with a regular expression
26 * to split words in a sentence.</p>
27 *
28 * <p>
29 * For further explanation about Cosine Similarity and Cosine Distance, refer to
30 * https://en.wikipedia.org/wiki/Cosine_similarity.
31 * </p>
32 *
33 * @since 1.0
34 * @see CosineSimilarity
35 */
36 public class CosineDistance implements EditDistance<Double> {
37
38 /**
39 * Construct a new instance.
40 */
41 public CosineDistance() {
42 // empty
43 }
44
45 @Override
46 public Double apply(final CharSequence left, final CharSequence right) {
47 final CharSequence[] leftTokens = RegexTokenizer.INSTANCE.apply(left);
48 final CharSequence[] rightTokens = RegexTokenizer.INSTANCE.apply(right);
49
50 final Map<CharSequence, Integer> leftVector = Counter.of(leftTokens);
51 final Map<CharSequence, Integer> rightVector = Counter.of(rightTokens);
52 final double similarity = CosineSimilarity.INSTANCE.cosineSimilarity(leftVector, rightVector);
53 return 1.0 - similarity;
54 }
55
56 }