source: branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/WeightCalculators/MedianThresholdCalculator.cs @ 8534

Last change on this file since 8534 was 8534, checked in by sforsten, 8 years ago

#1776:

  • merged r8508:8533 from trunk into branch
  • AverageThresholdCalculator and MedianThresholdCalculator can now handle multi class classification
  • changed combo boxes in ClassificationEnsembleSolutionView to drop down list
File size: 5.2 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2012 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.Collections;
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  [StorableClass]
31  [Item("MedianThresholdCalculator", "")]
32  public class MedianThresholdCalculator : DiscriminantClassificationWeightCalculator {
33
34    public MedianThresholdCalculator()
35      : base() {
36    }
37    [StorableConstructor]
38    protected MedianThresholdCalculator(bool deserializing) : base(deserializing) { }
39    protected MedianThresholdCalculator(MedianThresholdCalculator original, Cloner cloner)
40      : base(original, cloner) {
41    }
42    public override IDeepCloneable Clone(Cloner cloner) {
43      return new MedianThresholdCalculator(this, cloner);
44    }
45
46    protected double[] threshold;
47    protected double[] classValues;
48
49    protected override IEnumerable<double> DiscriminantCalculateWeights(IEnumerable<IDiscriminantFunctionClassificationSolution> discriminantSolutions) {
50      classValues = discriminantSolutions.First().Model.ClassValues.ToArray();
51      var modelThresholds = discriminantSolutions.Select(x => x.Model.Thresholds.ToArray());
52      threshold = new double[modelThresholds.First().GetLength(0)];
53      for (int i = 0; i < modelThresholds.First().GetLength(0); i++) {
54        threshold[i] = GetMedian(modelThresholds.Select(x => x[i]).ToList());
55      }
56      return Enumerable.Repeat<double>(1, discriminantSolutions.Count());
57    }
58
59    protected override double GetDiscriminantConfidence(IEnumerable<IDiscriminantFunctionClassificationSolution> solutions, int index, double estimatedClassValue) {
60
61      Dataset dataset = solutions.First().ProblemData.Dataset;
62      IList<double> values = solutions.Select(s => s.Model.GetEstimatedValues(dataset, Enumerable.Repeat(index, 1)).First()).ToList();
63      if (values.Count <= 0)
64        return double.NaN;
65      double median = GetMedian(values);
66      return GetMedianConfidence(median, estimatedClassValue);
67    }
68
69    public override IEnumerable<double> GetDiscriminantConfidence(IEnumerable<IDiscriminantFunctionClassificationSolution> solutions, IEnumerable<int> indices, IEnumerable<double> estimatedClassValue) {
70
71      Dataset dataset = solutions.First().ProblemData.Dataset;
72      double[][] values = solutions.Select(s => s.Model.GetEstimatedValues(dataset, indices).ToArray()).ToArray();
73      double[] confidences = new double[indices.Count()];
74      double[] estimatedClassValueArr = estimatedClassValue.ToArray();
75
76      for (int i = 0; i < indices.Count(); i++) {
77        double avg = values.Select(x => x[i]).Average();
78        confidences[i] = GetMedianConfidence(avg, estimatedClassValueArr[i]);
79      }
80
81      return confidences;
82    }
83
84    protected double GetMedianConfidence(double median, double estimatedClassValue) {
85      for (int i = 0; i < classValues.Length; i++) {
86        if (estimatedClassValue.Equals(classValues[i])) {
87          //special case: avgerage is higher than value of highest class
88          if (i == classValues.Length - 1 && median > estimatedClassValue) {
89            return 1;
90          }
91          //special case: average is lower than value of lowest class
92          if (i == 0 && median < estimatedClassValue) {
93            return 1;
94          }
95          //special case: average is not between threshold of estimated class value
96          if ((i < classValues.Length - 1 && median >= threshold[i + 1]) || median <= threshold[i]) {
97            return 0;
98          }
99
100          double thresholdToClassDistance, thresholdToAverageValueDistance;
101          if (median >= classValues[i]) {
102            thresholdToClassDistance = threshold[i + 1] - classValues[i];
103            thresholdToAverageValueDistance = threshold[i + 1] - median;
104          } else {
105            thresholdToClassDistance = classValues[i] - threshold[i];
106            thresholdToAverageValueDistance = median - threshold[i];
107          }
108          return (1 / thresholdToClassDistance) * thresholdToAverageValueDistance;
109        }
110      }
111      return double.NaN;
112    }
113
114    protected double GetMedian(IList<double> estimatedValues) {
115      int count = estimatedValues.Count;
116      if (count % 2 == 0)
117        return 0.5 * (estimatedValues[count / 2 - 1] + estimatedValues[count / 2]);
118      else
119        return estimatedValues[count / 2];
120    }
121  }
122}
Note: See TracBrowser for help on using the repository browser.