source: trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/DiscriminantFunctionClassificationModel.cs @ 6604

Last change on this file since 6604 was 6604, checked in by mkommend, 11 years ago

#1600: Added possibility to create classification solutions from classification models.

File size: 4.3 KB
Line 
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
22using System;
23using System.Collections.Generic;
24using System.Linq;
25using HeuristicLab.Common;
26using HeuristicLab.Core;
27using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
28
29namespace HeuristicLab.Problems.DataAnalysis {
30  /// <summary>
31  /// Represents discriminant function classification data analysis models.
32  /// </summary>
33  [StorableClass]
34  [Item("DiscriminantFunctionClassificationModel", "Represents a classification model that uses a discriminant function and classification thresholds.")]
35  public abstract class DiscriminantFunctionClassificationModel : NamedItem, IDiscriminantFunctionClassificationModel {
36    [Storable]
37    private IRegressionModel model;
38
39    [Storable]
40    private double[] classValues;
41    public IEnumerable<double> ClassValues {
42      get { return (double[])classValues.Clone(); }
43      private set { classValues = value.ToArray(); }
44    }
45
46    [Storable]
47    private double[] thresholds;
48    public IEnumerable<double> Thresholds {
49      get { return (IEnumerable<double>)thresholds.Clone(); }
50      private set { thresholds = value.ToArray(); }
51    }
52
53
54    [StorableConstructor]
55    protected DiscriminantFunctionClassificationModel(bool deserializing) : base(deserializing) { }
56    protected DiscriminantFunctionClassificationModel(DiscriminantFunctionClassificationModel original, Cloner cloner)
57      : base(original, cloner) {
58      model = cloner.Clone(original.model);
59      classValues = (double[])original.classValues.Clone();
60      thresholds = (double[])original.thresholds.Clone();
61    }
62
63    public DiscriminantFunctionClassificationModel(IRegressionModel model)
64      : base() {
65      this.name = ItemName;
66      this.description = ItemDescription;
67      this.model = model;
68      this.classValues = new double[] { 0.0 };
69      this.thresholds = new double[] { double.NegativeInfinity };
70    }
71
72    public void SetThresholdsAndClassValues(IEnumerable<double> thresholds, IEnumerable<double> classValues) {
73      var classValuesArr = classValues.ToArray();
74      var thresholdsArr = thresholds.ToArray();
75      if (thresholdsArr.Length != classValuesArr.Length) throw new ArgumentException();
76
77      this.classValues = classValuesArr;
78      this.thresholds = thresholdsArr;
79      OnThresholdsChanged(EventArgs.Empty);
80    }
81
82    public IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows) {
83      return model.GetEstimatedValues(dataset, rows);
84    }
85
86    public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
87      foreach (var x in GetEstimatedValues(dataset, rows)) {
88        int classIndex = 0;
89        // find first threshold value which is larger than x => class index = threshold index + 1
90        for (int i = 0; i < thresholds.Length; i++) {
91          if (x > thresholds[i]) classIndex++;
92          else break;
93        }
94        yield return classValues.ElementAt(classIndex - 1);
95      }
96    }
97    #region events
98    public event EventHandler ThresholdsChanged;
99    protected virtual void OnThresholdsChanged(EventArgs e) {
100      var listener = ThresholdsChanged;
101      if (listener != null) listener(this, e);
102    }
103    #endregion
104
105    public abstract IDiscriminantFunctionClassificationSolution CreateDiscriminantFunctionClassificationSolution(IClassificationProblemData problemData);
106    public abstract IClassificationSolution CreateClassificationSolution(IClassificationProblemData problemData);
107  }
108}
Note: See TracBrowser for help on using the repository browser.