1 | #region License Information
|
---|
2 | /* HeuristicLab
|
---|
3 | * Copyright (C) 2002-2011 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.Linq;
|
---|
24 | using HeuristicLab.Common;
|
---|
25 | using HeuristicLab.Core;
|
---|
26 | using HeuristicLab.Data;
|
---|
27 | using HeuristicLab.Optimization;
|
---|
28 | using HeuristicLab.Parameters;
|
---|
29 | using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
|
---|
30 | using HeuristicLab.Problems.DataAnalysis;
|
---|
31 | using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
|
---|
32 | using System.Collections.Generic;
|
---|
33 | using HeuristicLab.Problems.DataAnalysis.Symbolic;
|
---|
34 | using HeuristicLab.Problems.DataAnalysis.Symbolic.Regression;
|
---|
35 |
|
---|
36 | namespace HeuristicLab.Algorithms.DataAnalysis {
|
---|
37 | /// <summary>
|
---|
38 | /// k-Means clustering algorithm data analysis algorithm.
|
---|
39 | /// </summary>
|
---|
40 | [Item("k-Means", "The k-Means clustering algorithm.")]
|
---|
41 | [Creatable("Data Analysis")]
|
---|
42 | [StorableClass]
|
---|
43 | public sealed class KMeansClustering : FixedDataAnalysisAlgorithm<IClusteringProblem> {
|
---|
44 | private const string KParameterName = "k";
|
---|
45 | private const string RestartsParameterName = "Restarts";
|
---|
46 | private const string KMeansSolutionResultName = "k-Means clustering solution";
|
---|
47 | #region parameter properties
|
---|
48 | public IValueParameter<IntValue> KParameter {
|
---|
49 | get { return (IValueParameter<IntValue>)Parameters[KParameterName]; }
|
---|
50 | }
|
---|
51 | public IValueParameter<IntValue> RestartsParameter {
|
---|
52 | get { return (IValueParameter<IntValue>)Parameters[RestartsParameterName]; }
|
---|
53 | }
|
---|
54 | #endregion
|
---|
55 | #region properties
|
---|
56 | public IntValue K {
|
---|
57 | get { return KParameter.Value; }
|
---|
58 | }
|
---|
59 | public IntValue Restarts {
|
---|
60 | get { return RestartsParameter.Value; }
|
---|
61 | }
|
---|
62 | #endregion
|
---|
63 | [StorableConstructor]
|
---|
64 | private KMeansClustering(bool deserializing) : base(deserializing) { }
|
---|
65 | private KMeansClustering(KMeansClustering original, Cloner cloner)
|
---|
66 | : base(original, cloner) {
|
---|
67 | }
|
---|
68 | public KMeansClustering()
|
---|
69 | : base() {
|
---|
70 | Parameters.Add(new ValueParameter<IntValue>(KParameterName, "The number of clusters.", new IntValue(3)));
|
---|
71 | Parameters.Add(new ValueParameter<IntValue>(RestartsParameterName, "The number of restarts.", new IntValue(0)));
|
---|
72 | Problem = new ClusteringProblem();
|
---|
73 | }
|
---|
74 | [StorableHook(HookType.AfterDeserialization)]
|
---|
75 | private void AfterDeserialization() { }
|
---|
76 |
|
---|
77 | public override IDeepCloneable Clone(Cloner cloner) {
|
---|
78 | return new KMeansClustering(this, cloner);
|
---|
79 | }
|
---|
80 |
|
---|
81 | #region k-Means clustering
|
---|
82 | protected override void Run() {
|
---|
83 | var solution = CreateKMeansSolution(Problem.ProblemData, K.Value, Restarts.Value);
|
---|
84 | Results.Add(new Result(KMeansSolutionResultName, "The linear regression solution.", solution));
|
---|
85 | }
|
---|
86 |
|
---|
87 | public static KMeansClusteringSolution CreateKMeansSolution(IClusteringProblemData problemData, int k, int restarts) {
|
---|
88 | Dataset dataset = problemData.Dataset;
|
---|
89 | IEnumerable<string> allowedInputVariables = problemData.AllowedInputVariables;
|
---|
90 | int start = problemData.TrainingPartitionStart.Value;
|
---|
91 | int end = problemData.TrainingPartitionEnd.Value;
|
---|
92 | IEnumerable<int> rows = Enumerable.Range(start, end - start);
|
---|
93 | int info;
|
---|
94 | double[,] centers;
|
---|
95 | int[] xyc;
|
---|
96 | double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
|
---|
97 | alglib.kmeansgenerate(inputMatrix, inputMatrix.GetLength(0), inputMatrix.GetLength(1), k, restarts + 1, out info, out centers, out xyc);
|
---|
98 | if (info != 1) throw new ArgumentException("Error in calculation of k-Means clustering solution");
|
---|
99 |
|
---|
100 | KMeansClusteringSolution solution = new KMeansClusteringSolution(new KMeansClusteringModel(centers, allowedInputVariables), problemData);
|
---|
101 | return solution;
|
---|
102 | }
|
---|
103 | #endregion
|
---|
104 | }
|
---|
105 | }
|
---|