Free cookie consent management tool by TermsFeed Policy Generator

source: trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationSolutionBase.cs @ 15583

Last change on this file since 15583 was 15583, checked in by swagner, 6 years ago

#2640: Updated year of copyrights in license headers

File size: 10.1 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2018 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.Generic;
23using System.Linq;
24using HeuristicLab.Common;
25using HeuristicLab.Data;
26using HeuristicLab.Optimization;
27using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
28using HeuristicLab.Problems.DataAnalysis.OnlineCalculators;
29
30namespace HeuristicLab.Problems.DataAnalysis {
31  [StorableClass]
32  public abstract class ClassificationSolutionBase : DataAnalysisSolution, IClassificationSolution {
33    private const string TrainingAccuracyResultName = "Accuracy (training)";
34    private const string TestAccuracyResultName = "Accuracy (test)";
35    private const string TrainingNormalizedGiniCoefficientResultName = "Normalized Gini Coefficient (training)";
36    private const string TestNormalizedGiniCoefficientResultName = "Normalized Gini Coefficient (test)";
37    private const string ClassificationPerformanceMeasuresResultName = "Classification Performance Measures";
38
39    public new IClassificationModel Model {
40      get { return (IClassificationModel)base.Model; }
41      protected set { base.Model = value; }
42    }
43
44    public new IClassificationProblemData ProblemData {
45      get { return (IClassificationProblemData)base.ProblemData; }
46      set { base.ProblemData = value; }
47    }
48
49    #region Results
50    public double TrainingAccuracy {
51      get { return ((DoubleValue)this[TrainingAccuracyResultName].Value).Value; }
52      private set { ((DoubleValue)this[TrainingAccuracyResultName].Value).Value = value; }
53    }
54    public double TestAccuracy {
55      get { return ((DoubleValue)this[TestAccuracyResultName].Value).Value; }
56      private set { ((DoubleValue)this[TestAccuracyResultName].Value).Value = value; }
57    }
58    public double TrainingNormalizedGiniCoefficient {
59      get { return ((DoubleValue)this[TrainingNormalizedGiniCoefficientResultName].Value).Value; }
60      protected set { ((DoubleValue)this[TrainingNormalizedGiniCoefficientResultName].Value).Value = value; }
61    }
62    public double TestNormalizedGiniCoefficient {
63      get { return ((DoubleValue)this[TestNormalizedGiniCoefficientResultName].Value).Value; }
64      protected set { ((DoubleValue)this[TestNormalizedGiniCoefficientResultName].Value).Value = value; }
65    }
66    public ClassificationPerformanceMeasuresResultCollection ClassificationPerformanceMeasures {
67      get { return ((ClassificationPerformanceMeasuresResultCollection)this[ClassificationPerformanceMeasuresResultName].Value); }
68      protected set { (this[ClassificationPerformanceMeasuresResultName].Value) = value; }
69    }
70    #endregion
71
72    [StorableConstructor]
73    protected ClassificationSolutionBase(bool deserializing) : base(deserializing) { }
74    protected ClassificationSolutionBase(ClassificationSolutionBase original, Cloner cloner)
75      : base(original, cloner) {
76    }
77    protected ClassificationSolutionBase(IClassificationModel model, IClassificationProblemData problemData)
78      : base(model, problemData) {
79      Add(new Result(TrainingAccuracyResultName, "Accuracy of the model on the training partition (percentage of correctly classified instances).", new PercentValue()));
80      Add(new Result(TestAccuracyResultName, "Accuracy of the model on the test partition (percentage of correctly classified instances).", new PercentValue()));
81      Add(new Result(TrainingNormalizedGiniCoefficientResultName, "Normalized Gini coefficient of the model on the training partition.", new DoubleValue()));
82      Add(new Result(TestNormalizedGiniCoefficientResultName, "Normalized Gini coefficient of the model on the test partition.", new DoubleValue()));
83      Add(new Result(ClassificationPerformanceMeasuresResultName, @"Classification performance measures.\n
84                              In a multiclass classification all misclassifications of the negative class will be treated as true negatives except on positive class estimations.",
85                            new ClassificationPerformanceMeasuresResultCollection()));
86    }
87
88    [StorableHook(HookType.AfterDeserialization)]
89    private void AfterDeserialization() {
90      if (string.IsNullOrEmpty(Model.TargetVariable))
91        Model.TargetVariable = this.ProblemData.TargetVariable;
92
93      if (!this.ContainsKey(TrainingNormalizedGiniCoefficientResultName))
94        Add(new Result(TrainingNormalizedGiniCoefficientResultName, "Normalized Gini coefficient of the model on the training partition.", new DoubleValue()));
95      if (!this.ContainsKey(TestNormalizedGiniCoefficientResultName))
96        Add(new Result(TestNormalizedGiniCoefficientResultName, "Normalized Gini coefficient of the model on the test partition.", new DoubleValue()));
97      if (!this.ContainsKey(ClassificationPerformanceMeasuresResultName)) {
98        Add(new Result(ClassificationPerformanceMeasuresResultName, @"Classification performance measures.\n
99                              In a multiclass classification all misclassifications of the negative class will be treated as true negatives except on positive class estimations.",
100                              new ClassificationPerformanceMeasuresResultCollection()));
101        CalculateClassificationResults();
102      }
103    }
104
105    protected void CalculateClassificationResults() {
106      double[] estimatedTrainingClassValues = EstimatedTrainingClassValues.ToArray(); // cache values
107      double[] originalTrainingClassValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndices).ToArray();
108
109      double[] estimatedTestClassValues = EstimatedTestClassValues.ToArray(); // cache values
110      double[] originalTestClassValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TestIndices).ToArray();
111
112      var positiveClassName = ProblemData.PositiveClass;
113      double positiveClassValue = ProblemData.GetClassValue(positiveClassName);
114      ClassificationPerformanceMeasuresCalculator trainingPerformanceCalculator = new ClassificationPerformanceMeasuresCalculator(positiveClassName, positiveClassValue);
115      ClassificationPerformanceMeasuresCalculator testPerformanceCalculator = new ClassificationPerformanceMeasuresCalculator(positiveClassName, positiveClassValue);
116
117      OnlineCalculatorError errorState;
118      double trainingAccuracy = OnlineAccuracyCalculator.Calculate(originalTrainingClassValues, estimatedTrainingClassValues, out errorState);
119      if (errorState != OnlineCalculatorError.None) trainingAccuracy = double.NaN;
120      double testAccuracy = OnlineAccuracyCalculator.Calculate(originalTestClassValues, estimatedTestClassValues, out errorState);
121      if (errorState != OnlineCalculatorError.None) testAccuracy = double.NaN;
122
123      TrainingAccuracy = trainingAccuracy;
124      TestAccuracy = testAccuracy;
125
126      double trainingNormalizedGini = NormalizedGiniCalculator.Calculate(originalTrainingClassValues, estimatedTrainingClassValues, out errorState);
127      if (errorState != OnlineCalculatorError.None) trainingNormalizedGini = double.NaN;
128      double testNormalizedGini = NormalizedGiniCalculator.Calculate(originalTestClassValues, estimatedTestClassValues, out errorState);
129      if (errorState != OnlineCalculatorError.None) testNormalizedGini = double.NaN;
130
131      TrainingNormalizedGiniCoefficient = trainingNormalizedGini;
132      TestNormalizedGiniCoefficient = testNormalizedGini;
133
134      ClassificationPerformanceMeasures.Reset();
135
136      trainingPerformanceCalculator.Calculate(originalTrainingClassValues, estimatedTrainingClassValues);
137      if (trainingPerformanceCalculator.ErrorState == OnlineCalculatorError.None)
138        ClassificationPerformanceMeasures.SetTrainingResults(trainingPerformanceCalculator);
139
140      testPerformanceCalculator.Calculate(originalTestClassValues, estimatedTestClassValues);
141      if (testPerformanceCalculator.ErrorState == OnlineCalculatorError.None)
142        ClassificationPerformanceMeasures.SetTestResults(testPerformanceCalculator);
143
144      if (ProblemData.Classes == 2) {
145        var f1Training = FOneScoreCalculator.Calculate(originalTrainingClassValues, estimatedTrainingClassValues, out errorState);
146        if (errorState == OnlineCalculatorError.None) ClassificationPerformanceMeasures.TrainingF1Score = f1Training;
147        var f1Test = FOneScoreCalculator.Calculate(originalTestClassValues, estimatedTestClassValues, out errorState);
148        if (errorState == OnlineCalculatorError.None) ClassificationPerformanceMeasures.TestF1Score = f1Test;
149      }
150
151      var mccTraining = MatthewsCorrelationCoefficientCalculator.Calculate(originalTrainingClassValues, estimatedTrainingClassValues, out errorState);
152      if (errorState == OnlineCalculatorError.None) ClassificationPerformanceMeasures.TrainingMatthewsCorrelation = mccTraining;
153      var mccTest = MatthewsCorrelationCoefficientCalculator.Calculate(originalTestClassValues, estimatedTestClassValues, out errorState);
154      if (errorState == OnlineCalculatorError.None) ClassificationPerformanceMeasures.TestMatthewsCorrelation = mccTest;
155    }
156
157    public abstract IEnumerable<double> EstimatedClassValues { get; }
158    public abstract IEnumerable<double> EstimatedTrainingClassValues { get; }
159    public abstract IEnumerable<double> EstimatedTestClassValues { get; }
160
161    public abstract IEnumerable<double> GetEstimatedClassValues(IEnumerable<int> rows);
162
163    protected override void RecalculateResults() {
164      CalculateClassificationResults();
165    }
166  }
167}
Note: See TracBrowser for help on using the repository browser.