[11685] | 1 | #region License Information
|
---|
| 2 | /* HeuristicLab
|
---|
[17181] | 3 | * Copyright (C) Heuristic and Evolutionary Algorithms Laboratory (HEAL)
|
---|
[11685] | 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;
|
---|
[11872] | 23 | using HeuristicLab.Common;
|
---|
[11685] | 24 | using HeuristicLab.Data;
|
---|
| 25 | using HeuristicLab.Optimization;
|
---|
[17097] | 26 | using HEAL.Attic;
|
---|
[11685] | 27 |
|
---|
| 28 | namespace HeuristicLab.Problems.DataAnalysis {
|
---|
[17097] | 29 | [StorableType("6F44E140-22CF-48D3-B100-B6013F2B6608")]
|
---|
[11685] | 30 | public class ClassificationPerformanceMeasuresResultCollection : ResultCollection {
|
---|
| 31 | #region result names
|
---|
| 32 | protected const string ClassificationPositiveClassNameResultName = "Classification positive class";
|
---|
| 33 | protected const string TrainingTruePositiveRateResultName = "True positive rate (training)";
|
---|
| 34 | protected const string TrainingTrueNegativeRateResultName = "True negative rate (training)";
|
---|
| 35 | protected const string TrainingPositivePredictiveValueResultName = "Positive predictive value (training)";
|
---|
| 36 | protected const string TrainingNegativePredictiveValueResultName = "Negative predictive value (training)";
|
---|
| 37 | protected const string TrainingFalsePositiveRateResultName = "False positive rate (training)";
|
---|
| 38 | protected const string TrainingFalseDiscoveryRateResultName = "False discovery rate (training)";
|
---|
[13156] | 39 | protected const string TrainingF1ScoreResultName = "F1 score (training)";
|
---|
| 40 | protected const string TrainingMatthewsCorrelationResultName = "Matthews Correlation (training)";
|
---|
[11685] | 41 | protected const string TestTruePositiveRateResultName = "True positive rate (test)";
|
---|
| 42 | protected const string TestTrueNegativeRateResultName = "True negative rate (test)";
|
---|
| 43 | protected const string TestPositivePredictiveValueResultName = "Positive predictive value (test)";
|
---|
| 44 | protected const string TestNegativePredictiveValueResultName = "Negative predictive value (test)";
|
---|
| 45 | protected const string TestFalsePositiveRateResultName = "False positive rate (test)";
|
---|
| 46 | protected const string TestFalseDiscoveryRateResultName = "False discovery rate (test)";
|
---|
[13156] | 47 | protected const string TestF1ScoreResultName = "F1 score (test)";
|
---|
| 48 | protected const string TestMatthewsCorrelationResultName = "Matthews Correlation (test)";
|
---|
[11685] | 49 | #endregion
|
---|
| 50 |
|
---|
| 51 | public ClassificationPerformanceMeasuresResultCollection()
|
---|
| 52 | : base() {
|
---|
| 53 | AddMeasures();
|
---|
| 54 | }
|
---|
| 55 | [StorableConstructor]
|
---|
[17097] | 56 | protected ClassificationPerformanceMeasuresResultCollection(StorableConstructorFlag _) : base(_) {
|
---|
[11685] | 57 | }
|
---|
| 58 |
|
---|
[11872] | 59 | protected ClassificationPerformanceMeasuresResultCollection(ClassificationPerformanceMeasuresResultCollection original, Cloner cloner)
|
---|
| 60 | : base(original, cloner) { }
|
---|
| 61 | public override IDeepCloneable Clone(Cloner cloner) {
|
---|
| 62 | return new ClassificationPerformanceMeasuresResultCollection(this, cloner);
|
---|
| 63 | }
|
---|
| 64 |
|
---|
[11685] | 65 | #region result properties
|
---|
| 66 | public string ClassificationPositiveClassName {
|
---|
| 67 | get { return ((StringValue)this[ClassificationPositiveClassNameResultName].Value).Value; }
|
---|
| 68 | set { ((StringValue)this[ClassificationPositiveClassNameResultName].Value).Value = value; }
|
---|
| 69 | }
|
---|
| 70 | public double TrainingTruePositiveRate {
|
---|
| 71 | get { return ((DoubleValue)this[TrainingTruePositiveRateResultName].Value).Value; }
|
---|
| 72 | set { ((DoubleValue)this[TrainingTruePositiveRateResultName].Value).Value = value; }
|
---|
| 73 | }
|
---|
| 74 | public double TrainingTrueNegativeRate {
|
---|
| 75 | get { return ((DoubleValue)this[TrainingTrueNegativeRateResultName].Value).Value; }
|
---|
| 76 | set { ((DoubleValue)this[TrainingTrueNegativeRateResultName].Value).Value = value; }
|
---|
| 77 | }
|
---|
| 78 | public double TrainingPositivePredictiveValue {
|
---|
| 79 | get { return ((DoubleValue)this[TrainingPositivePredictiveValueResultName].Value).Value; }
|
---|
| 80 | set { ((DoubleValue)this[TrainingPositivePredictiveValueResultName].Value).Value = value; }
|
---|
| 81 | }
|
---|
| 82 | public double TrainingNegativePredictiveValue {
|
---|
| 83 | get { return ((DoubleValue)this[TrainingNegativePredictiveValueResultName].Value).Value; }
|
---|
| 84 | set { ((DoubleValue)this[TrainingNegativePredictiveValueResultName].Value).Value = value; }
|
---|
| 85 | }
|
---|
| 86 | public double TrainingFalsePositiveRate {
|
---|
| 87 | get { return ((DoubleValue)this[TrainingFalsePositiveRateResultName].Value).Value; }
|
---|
| 88 | set { ((DoubleValue)this[TrainingFalsePositiveRateResultName].Value).Value = value; }
|
---|
| 89 | }
|
---|
| 90 | public double TrainingFalseDiscoveryRate {
|
---|
| 91 | get { return ((DoubleValue)this[TrainingFalseDiscoveryRateResultName].Value).Value; }
|
---|
| 92 | set { ((DoubleValue)this[TrainingFalseDiscoveryRateResultName].Value).Value = value; }
|
---|
| 93 | }
|
---|
[13156] | 94 | public double TrainingF1Score {
|
---|
| 95 | get { return ((DoubleValue)this[TrainingF1ScoreResultName].Value).Value; }
|
---|
| 96 | set { ((DoubleValue)this[TrainingF1ScoreResultName].Value).Value = value; }
|
---|
| 97 | }
|
---|
| 98 | public double TrainingMatthewsCorrelation {
|
---|
| 99 | get { return ((DoubleValue)this[TrainingMatthewsCorrelationResultName].Value).Value; }
|
---|
| 100 | set { ((DoubleValue)this[TrainingMatthewsCorrelationResultName].Value).Value = value; }
|
---|
| 101 | }
|
---|
[11685] | 102 | public double TestTruePositiveRate {
|
---|
| 103 | get { return ((DoubleValue)this[TestTruePositiveRateResultName].Value).Value; }
|
---|
| 104 | set { ((DoubleValue)this[TestTruePositiveRateResultName].Value).Value = value; }
|
---|
| 105 | }
|
---|
| 106 | public double TestTrueNegativeRate {
|
---|
| 107 | get { return ((DoubleValue)this[TestTrueNegativeRateResultName].Value).Value; }
|
---|
| 108 | set { ((DoubleValue)this[TestTrueNegativeRateResultName].Value).Value = value; }
|
---|
| 109 | }
|
---|
| 110 | public double TestPositivePredictiveValue {
|
---|
| 111 | get { return ((DoubleValue)this[TestPositivePredictiveValueResultName].Value).Value; }
|
---|
| 112 | set { ((DoubleValue)this[TestPositivePredictiveValueResultName].Value).Value = value; }
|
---|
| 113 | }
|
---|
| 114 | public double TestNegativePredictiveValue {
|
---|
| 115 | get { return ((DoubleValue)this[TestNegativePredictiveValueResultName].Value).Value; }
|
---|
| 116 | set { ((DoubleValue)this[TestNegativePredictiveValueResultName].Value).Value = value; }
|
---|
| 117 | }
|
---|
| 118 | public double TestFalsePositiveRate {
|
---|
| 119 | get { return ((DoubleValue)this[TestFalsePositiveRateResultName].Value).Value; }
|
---|
| 120 | set { ((DoubleValue)this[TestFalsePositiveRateResultName].Value).Value = value; }
|
---|
| 121 | }
|
---|
| 122 | public double TestFalseDiscoveryRate {
|
---|
| 123 | get { return ((DoubleValue)this[TestFalseDiscoveryRateResultName].Value).Value; }
|
---|
| 124 | set { ((DoubleValue)this[TestFalseDiscoveryRateResultName].Value).Value = value; }
|
---|
| 125 | }
|
---|
[13156] | 126 | public double TestF1Score {
|
---|
| 127 | get { return ((DoubleValue)this[TestF1ScoreResultName].Value).Value; }
|
---|
| 128 | set { ((DoubleValue)this[TestF1ScoreResultName].Value).Value = value; }
|
---|
| 129 | }
|
---|
| 130 | public double TestMatthewsCorrelation {
|
---|
| 131 | get { return ((DoubleValue)this[TestMatthewsCorrelationResultName].Value).Value; }
|
---|
| 132 | set { ((DoubleValue)this[TestMatthewsCorrelationResultName].Value).Value = value; }
|
---|
| 133 | }
|
---|
[11685] | 134 | #endregion
|
---|
| 135 |
|
---|
| 136 | protected void AddMeasures() {
|
---|
| 137 | Add(new Result(ClassificationPositiveClassNameResultName, "The positive class which is used for the performance measure calculations.", new StringValue()));
|
---|
| 138 | Add(new Result(TrainingTruePositiveRateResultName, "Sensitivity/True positive rate of the model on the training partition\n(TP/(TP+FN)).", new PercentValue()));
|
---|
| 139 | Add(new Result(TrainingTrueNegativeRateResultName, "Specificity/True negative rate of the model on the training partition\n(TN/(FP+TN)).", new PercentValue()));
|
---|
| 140 | Add(new Result(TrainingPositivePredictiveValueResultName, "Precision/Positive predictive value of the model on the training partition\n(TP/(TP+FP)).", new PercentValue()));
|
---|
| 141 | Add(new Result(TrainingNegativePredictiveValueResultName, "Negative predictive value of the model on the training partition\n(TN/(TN+FN)).", new PercentValue()));
|
---|
| 142 | Add(new Result(TrainingFalsePositiveRateResultName, "The false positive rate is the complement of the true negative rate of the model on the training partition.", new PercentValue()));
|
---|
| 143 | Add(new Result(TrainingFalseDiscoveryRateResultName, "The false discovery rate is the complement of the positive predictive value of the model on the training partition.", new PercentValue()));
|
---|
[13156] | 144 | Add(new Result(TrainingF1ScoreResultName, "The F1 score of the model on the training partition.", new DoubleValue()));
|
---|
| 145 | Add(new Result(TrainingMatthewsCorrelationResultName, "The Matthews correlation value of the model on the training partition.", new DoubleValue()));
|
---|
[11685] | 146 | Add(new Result(TestTruePositiveRateResultName, "Sensitivity/True positive rate of the model on the test partition\n(TP/(TP+FN)).", new PercentValue()));
|
---|
| 147 | Add(new Result(TestTrueNegativeRateResultName, "Specificity/True negative rate of the model on the test partition\n(TN/(FP+TN)).", new PercentValue()));
|
---|
| 148 | Add(new Result(TestPositivePredictiveValueResultName, "Precision/Positive predictive value of the model on the test partition\n(TP/(TP+FP)).", new PercentValue()));
|
---|
| 149 | Add(new Result(TestNegativePredictiveValueResultName, "Negative predictive value of the model on the test partition\n(TN/(TN+FN)).", new PercentValue()));
|
---|
| 150 | Add(new Result(TestFalsePositiveRateResultName, "The false positive rate is the complement of the true negative rate of the model on the test partition.", new PercentValue()));
|
---|
| 151 | Add(new Result(TestFalseDiscoveryRateResultName, "The false discovery rate is the complement of the positive predictive value of the model on the test partition.", new PercentValue()));
|
---|
[13156] | 152 | Add(new Result(TestF1ScoreResultName, "The F1 score of the model on the test partition.", new DoubleValue()));
|
---|
| 153 | Add(new Result(TestMatthewsCorrelationResultName, "The Matthews correlation value of the model on the test partition.", new DoubleValue()));
|
---|
[13880] | 154 |
|
---|
| 155 | Reset();
|
---|
| 156 | }
|
---|
| 157 |
|
---|
| 158 |
|
---|
| 159 | public void Reset() {
|
---|
[11685] | 160 | TrainingTruePositiveRate = double.NaN;
|
---|
| 161 | TrainingTrueNegativeRate = double.NaN;
|
---|
| 162 | TrainingPositivePredictiveValue = double.NaN;
|
---|
| 163 | TrainingNegativePredictiveValue = double.NaN;
|
---|
| 164 | TrainingFalsePositiveRate = double.NaN;
|
---|
| 165 | TrainingFalseDiscoveryRate = double.NaN;
|
---|
[13156] | 166 | TrainingF1Score = double.NaN;
|
---|
| 167 | TrainingMatthewsCorrelation = double.NaN;
|
---|
[11685] | 168 | TestTruePositiveRate = double.NaN;
|
---|
| 169 | TestTrueNegativeRate = double.NaN;
|
---|
| 170 | TestPositivePredictiveValue = double.NaN;
|
---|
| 171 | TestNegativePredictiveValue = double.NaN;
|
---|
| 172 | TestFalsePositiveRate = double.NaN;
|
---|
| 173 | TestFalseDiscoveryRate = double.NaN;
|
---|
[13156] | 174 | TestF1Score = double.NaN;
|
---|
| 175 | TestMatthewsCorrelation = double.NaN;
|
---|
[11685] | 176 | }
|
---|
| 177 |
|
---|
| 178 | public void SetTrainingResults(ClassificationPerformanceMeasuresCalculator trainingPerformanceCalculator) {
|
---|
| 179 | if (!string.IsNullOrWhiteSpace(ClassificationPositiveClassName)
|
---|
| 180 | && !ClassificationPositiveClassName.Equals(trainingPerformanceCalculator.PositiveClassName))
|
---|
[11686] | 181 | throw new ArgumentException("Classification positive class of the training data doesn't match with the data of test partition.");
|
---|
[11685] | 182 | ClassificationPositiveClassName = trainingPerformanceCalculator.PositiveClassName;
|
---|
| 183 | TrainingTruePositiveRate = trainingPerformanceCalculator.TruePositiveRate;
|
---|
| 184 | TrainingTrueNegativeRate = trainingPerformanceCalculator.TrueNegativeRate;
|
---|
| 185 | TrainingPositivePredictiveValue = trainingPerformanceCalculator.PositivePredictiveValue;
|
---|
| 186 | TrainingNegativePredictiveValue = trainingPerformanceCalculator.NegativePredictiveValue;
|
---|
| 187 | TrainingFalsePositiveRate = trainingPerformanceCalculator.FalsePositiveRate;
|
---|
| 188 | TrainingFalseDiscoveryRate = trainingPerformanceCalculator.FalseDiscoveryRate;
|
---|
| 189 | }
|
---|
| 190 |
|
---|
| 191 | public void SetTestResults(ClassificationPerformanceMeasuresCalculator testPerformanceCalculator) {
|
---|
| 192 | if (!string.IsNullOrWhiteSpace(ClassificationPositiveClassName)
|
---|
| 193 | && !ClassificationPositiveClassName.Equals(testPerformanceCalculator.PositiveClassName))
|
---|
[11686] | 194 | throw new ArgumentException("Classification positive class of the test data doesn't match with the data of training partition.");
|
---|
[11685] | 195 | ClassificationPositiveClassName = testPerformanceCalculator.PositiveClassName;
|
---|
| 196 | TestTruePositiveRate = testPerformanceCalculator.TruePositiveRate;
|
---|
| 197 | TestTrueNegativeRate = testPerformanceCalculator.TrueNegativeRate;
|
---|
| 198 | TestPositivePredictiveValue = testPerformanceCalculator.PositivePredictiveValue;
|
---|
| 199 | TestNegativePredictiveValue = testPerformanceCalculator.NegativePredictiveValue;
|
---|
| 200 | TestFalsePositiveRate = testPerformanceCalculator.FalsePositiveRate;
|
---|
| 201 | TestFalseDiscoveryRate = testPerformanceCalculator.FalseDiscoveryRate;
|
---|
| 202 | }
|
---|
| 203 | }
|
---|
| 204 | }
|
---|