Free cookie consent management tool by TermsFeed Policy Generator

source: branches/ClassificationEnsembleVoting/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/WeightCalculators/MedianThresholdCalculator.cs @ 8297

Last change on this file since 8297 was 8297, checked in by sforsten, 10 years ago

#1776:

  • Corrected namespace of IClassificationEnsembleSolutionWeightCalculator interface
  • Corrected calculation of confidence for test and training samples in ClassificationEnsembleSolutionEstimatedClassValuesView
  • Added overload method GetConfidence to IClassificationEnsembleSolutionWeightCalculator to calculate more than one point at a time (maybe additional methods for training and test confidence could improve the performance remarkably)
  • Added ClassificationEnsembleSolutionConfidenceAccuracyDependence to see how accuracy would behave, if only samples with high confidence would be classified
File size: 4.9 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      // only works with binary classification
61      if (!classValues.Count().Equals(2))
62        return double.NaN;
63      Dataset dataset = solutions.First().ProblemData.Dataset;
64      IList<double> values = solutions.Select(s => s.Model.GetEstimatedValues(dataset, Enumerable.Repeat(index, 1)).First()).ToList();
65      if (values.Count <= 0)
66        return double.NaN;
67      double median = GetMedian(values);
68      return GetMedianConfidence(median, estimatedClassValue);
69    }
70
71    public override IEnumerable<double> GetDiscriminantConfidence(IEnumerable<IDiscriminantFunctionClassificationSolution> solutions, IEnumerable<int> indices, IEnumerable<double> estimatedClassValue) {
72      if (!classValues.Count().Equals(2))
73        return Enumerable.Repeat(double.NaN, indices.Count());
74
75      Dataset dataset = solutions.First().ProblemData.Dataset;
76      double[][] values = solutions.Select(s => s.Model.GetEstimatedValues(dataset, indices).ToArray()).ToArray();
77      double[] confidences = new double[indices.Count()];
78      double[] estimatedClassValueArr = estimatedClassValue.ToArray();
79
80      for (int i = 0; i < indices.Count(); i++) {
81        double avg = values.Select(x => x[i]).Average();
82        confidences[i] = GetMedianConfidence(avg, estimatedClassValueArr[i]);
83      }
84
85      return confidences;
86    }
87
88    protected double GetMedianConfidence(double median, double estimatedClassValue) {
89      if (estimatedClassValue.Equals(classValues[0])) {
90        if (median < estimatedClassValue)
91          return 1;
92        else if (median >= threshold[1])
93          return 0;
94        else {
95          double distance = threshold[1] - classValues[0];
96          return (1 / distance) * (threshold[1] - median);
97        }
98      } else if (estimatedClassValue.Equals(classValues[1])) {
99        if (median > estimatedClassValue)
100          return 1;
101        else if (median <= threshold[1])
102          return 0;
103        else {
104          double distance = classValues[1] - threshold[1];
105          return (1 / distance) * (median - threshold[1]);
106        }
107      } else
108        return double.NaN;
109    }
110
111    protected double GetMedian(IList<double> estimatedValues) {
112      int count = estimatedValues.Count;
113      if (count % 2 == 0)
114        return 0.5 * (estimatedValues[count / 2 - 1] + estimatedValues[count / 2]);
115      else
116        return estimatedValues[count / 2];
117    }
118  }
119}
Note: See TracBrowser for help on using the repository browser.