View Javadoc
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  
18  /*
19   * This is not the original file distributed by the Apache Software Foundation
20   * It has been modified by the Hipparchus project
21   */
22  
23  package org.hipparchus.clustering.evaluation;
24  
25  import java.util.List;
26  
27  import org.hipparchus.clustering.Cluster;
28  import org.hipparchus.clustering.Clusterable;
29  import org.hipparchus.clustering.distance.DistanceMeasure;
30  import org.hipparchus.stat.descriptive.moment.Variance;
31  
32  /**
33   * Computes the sum of intra-cluster distance variances according to the formula:
34   * \] score = \sum\limits_{i=1}^n \sigma_i^2 \]
35   * where n is the number of clusters and \( \sigma_i^2 \) is the variance of
36   * intra-cluster distances of cluster \( c_i \).
37   *
38   * @param <T> the type of the clustered points
39   */
40  public class SumOfClusterVariances<T extends Clusterable> extends ClusterEvaluator<T> {
41  
42      /** Simple constructor.
43       * @param measure the distance measure to use
44       */
45      public SumOfClusterVariances(final DistanceMeasure measure) {
46          super(measure);
47      }
48  
49      /** {@inheritDoc} */
50      @Override
51      public double score(final List<? extends Cluster<T>> clusters) {
52          double varianceSum = 0.0;
53          for (final Cluster<T> cluster : clusters) {
54              if (!cluster.getPoints().isEmpty()) {
55  
56                  final Clusterable center = centroidOf(cluster);
57  
58                  // compute the distance variance of the current cluster
59                  final Variance stat = new Variance();
60                  for (final T point : cluster.getPoints()) {
61                      stat.increment(distance(point, center));
62                  }
63                  varianceSum += stat.getResult();
64  
65              }
66          }
67          return varianceSum;
68      }
69  
70  }