[13794] | 1 | #region License Information
|
---|
| 2 | /* HeuristicLab
|
---|
| 3 | * Copyright (C) 2002-2016 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
|
---|
| 4 | *
|
---|
| 5 | * This file is part of HeuristicLab.
|
---|
| 6 | *
|
---|
| 7 | * HeuristicLab is free software: you can redistribute it and/or modify
|
---|
| 8 | * it under the terms of the GNU General Public License as published by
|
---|
| 9 | * the Free Software Foundation, either version 3 of the License, or
|
---|
| 10 | * (at your option) any later version.
|
---|
| 11 | *
|
---|
| 12 | * HeuristicLab is distributed in the hope that it will be useful,
|
---|
| 13 | * but WITHOUT ANY WARRANTY; without even the implied warranty of
|
---|
| 14 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
|
---|
| 15 | * GNU General Public License for more details.
|
---|
| 16 | *
|
---|
| 17 | * You should have received a copy of the GNU General Public License
|
---|
| 18 | * along with HeuristicLab. If not, see <http://www.gnu.org/licenses/>.
|
---|
| 19 | */
|
---|
| 20 | #endregion
|
---|
| 21 |
|
---|
| 22 | using System;
|
---|
| 23 | using System.Collections.Generic;
|
---|
| 24 | using System.Linq;
|
---|
| 25 |
|
---|
| 26 | namespace HeuristicLab.Analysis {
|
---|
| 27 | public class ClusteringHelper<T> {
|
---|
| 28 | private readonly int k;
|
---|
| 29 |
|
---|
| 30 | private List<KeyValuePair<T, double>> instances;
|
---|
| 31 | private List<KeyValuePair<T, double>> excluded;
|
---|
| 32 | private int[] clusterValues;
|
---|
[13797] | 33 | private int[] rankedMap;
|
---|
[13794] | 34 |
|
---|
| 35 | private ClusteringHelper(int K) {
|
---|
| 36 | this.k = K;
|
---|
| 37 | }
|
---|
| 38 |
|
---|
| 39 | /// <summary>
|
---|
| 40 | /// Helps in clustering data which is available as key-value pairs.
|
---|
| 41 | /// It is possible to specify an exclude function to omit certain points from clustering.
|
---|
| 42 | /// These points will be assigned cluster with id k. All other points will be assigned a
|
---|
| 43 | /// cluster id in the range [0;k-1].
|
---|
| 44 | /// </summary>
|
---|
| 45 | /// <param name="k">The maximum number of clusters that should be created.</param>
|
---|
| 46 | /// <param name="values">The data which links a certain item with a double value that is to be clustered.</param>
|
---|
| 47 | /// <param name="excludeFunc">The function that allows excluding certing data points which will receive cluster id k.</param>
|
---|
| 48 | /// <returns>A reference to the helper class to allow fluent calls.</returns>
|
---|
| 49 | public static ClusteringHelper<T> Cluster(int k, IEnumerable<KeyValuePair<T, double>> values, Func<KeyValuePair<T, double>, bool> excludeFunc = null) {
|
---|
| 50 | if (excludeFunc == null) excludeFunc = _ => false;
|
---|
| 51 | var helper = new ClusteringHelper<T>(k);
|
---|
| 52 | helper.Initialize(values, excludeFunc);
|
---|
[13797] | 53 | if (helper.instances.Count == 0) {
|
---|
[13794] | 54 | helper.clusterValues = new int[0];
|
---|
[13797] | 55 | helper.rankedMap = new int[k + 1];
|
---|
| 56 | } else {
|
---|
| 57 | var centroids = CkMeans1D.Cluster(helper.instances.Select(x => x.Value).ToArray(), k, out helper.clusterValues);
|
---|
| 58 | helper.rankedMap = new int[k + 1];
|
---|
| 59 | var rank = 0;
|
---|
| 60 | foreach (var c in centroids) helper.rankedMap[c.Value] = rank++;
|
---|
| 61 | }
|
---|
| 62 | // excluded are always ranked last
|
---|
| 63 | helper.rankedMap[k] = k;
|
---|
[13794] | 64 | return helper;
|
---|
| 65 | }
|
---|
| 66 |
|
---|
| 67 | /// <summary>
|
---|
| 68 | /// Returns the clustered data by
|
---|
| 69 | /// </summary>
|
---|
| 70 | /// <returns></returns>
|
---|
| 71 | public IEnumerable<KeyValuePair<T, Tuple<double, int>>> GetByInstance() {
|
---|
[13797] | 72 | return GetClustered().Select(x => new KeyValuePair<T, Tuple<double, int>>(x.Item1.Key, Tuple.Create(x.Item1.Value, rankedMap[x.Item2])));
|
---|
[13794] | 73 | }
|
---|
| 74 |
|
---|
| 75 | public IEnumerable<KeyValuePair<int, List<KeyValuePair<T, double>>>> GetByCluster() {
|
---|
| 76 | return GetClustered().GroupBy(x => x.Item2)
|
---|
[13797] | 77 | .Select(x => new KeyValuePair<int, List<KeyValuePair<T, double>>>(rankedMap[x.Key], x.Select(y => y.Item1).ToList()));
|
---|
[13794] | 78 | }
|
---|
| 79 |
|
---|
| 80 | private void Initialize(IEnumerable<KeyValuePair<T, double>> values, Func<KeyValuePair<T, double>, bool> excludeFunc) {
|
---|
| 81 | instances = new List<KeyValuePair<T, double>>();
|
---|
| 82 | excluded = new List<KeyValuePair<T, double>>();
|
---|
| 83 | foreach (var v in values) {
|
---|
| 84 | if (!excludeFunc(v)) instances.Add(v);
|
---|
| 85 | else excluded.Add(v);
|
---|
| 86 | }
|
---|
| 87 | }
|
---|
| 88 |
|
---|
| 89 | private IEnumerable<Tuple<KeyValuePair<T, double>, int>> GetClustered() {
|
---|
| 90 | for (var i = 0; i < clusterValues.Length; i++) {
|
---|
| 91 | yield return Tuple.Create(instances[i], clusterValues[i]);
|
---|
| 92 | }
|
---|
| 93 | foreach (var ex in excluded)
|
---|
| 94 | yield return Tuple.Create(ex, k);
|
---|
| 95 | }
|
---|
| 96 | }
|
---|
| 97 | }
|
---|