Changeset 13156 for stable/HeuristicLab.Problems.DataAnalysis/3.4/Implementation

Timestamp:

11/13/15 21:19:15 (9 years ago)

Author:

gkronber

Message:

#1998: merged changes from trunk to stable branch

Location:

stable

Files:

• . (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationPerformanceMeasures.cs (modified) (8 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationSolutionBase.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ConstantClassificationSolution.cs (copied) (copied from trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ConstantClassificationSolution.cs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/ConstantModel.cs (copied) (copied from trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/ConstantModel.cs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/ConstantRegressionModel.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/ConstantRegressionSolution.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/TimeSeriesPrognosis/Models/ConstantTimeSeriesPrognosisModel.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/TimeSeriesPrognosis/TimeSeriesPrognosisResults.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/TimeSeriesPrognosis/TimeSeriesPrognosisSolutionBase.cs (modified) (1 diff)

stable/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationPerformanceMeasures.cs

@@ -37 +37 @@
     protected const string TrainingFalsePositiveRateResultName = "False positive rate (training)";
     protected const string TrainingFalseDiscoveryRateResultName = "False discovery rate (training)";
+    protected const string TrainingF1ScoreResultName = "F1 score (training)";
+    protected const string TrainingMatthewsCorrelationResultName = "Matthews Correlation (training)";
     protected const string TestTruePositiveRateResultName = "True positive rate (test)";
     protected const string TestTrueNegativeRateResultName = "True negative rate (test)";
@@ -43 +45 @@
     protected const string TestFalsePositiveRateResultName = "False positive rate (test)";
     protected const string TestFalseDiscoveryRateResultName = "False discovery rate (test)";
+    protected const string TestF1ScoreResultName = "F1 score (test)";
+    protected const string TestMatthewsCorrelationResultName = "Matthews Correlation (test)";
     #endregion
 
@@ -89 +93 @@
       set { ((DoubleValue)this[TrainingFalseDiscoveryRateResultName].Value).Value = value; }
     }
+    public double TrainingF1Score {
+      get { return ((DoubleValue)this[TrainingF1ScoreResultName].Value).Value; }
+      set { ((DoubleValue)this[TrainingF1ScoreResultName].Value).Value = value; }
+    }
+    public double TrainingMatthewsCorrelation {
+      get { return ((DoubleValue)this[TrainingMatthewsCorrelationResultName].Value).Value; }
+      set { ((DoubleValue)this[TrainingMatthewsCorrelationResultName].Value).Value = value; }
+    }
     public double TestTruePositiveRate {
       get { return ((DoubleValue)this[TestTruePositiveRateResultName].Value).Value; }
@@ -113 +125 @@
       set { ((DoubleValue)this[TestFalseDiscoveryRateResultName].Value).Value = value; }
     }
+    public double TestF1Score {
+      get { return ((DoubleValue)this[TestF1ScoreResultName].Value).Value; }
+      set { ((DoubleValue)this[TestF1ScoreResultName].Value).Value = value; }
+    }
+    public double TestMatthewsCorrelation {
+      get { return ((DoubleValue)this[TestMatthewsCorrelationResultName].Value).Value; }
+      set { ((DoubleValue)this[TestMatthewsCorrelationResultName].Value).Value = value; }
+    }
     #endregion
 
@@ -123 +143 @@
       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()));
       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()));
+      Add(new Result(TrainingF1ScoreResultName, "The F1 score of the model on the training partition.", new DoubleValue()));
+      Add(new Result(TrainingMatthewsCorrelationResultName, "The Matthews correlation value of the model on the training partition.", new DoubleValue()));
       Add(new Result(TestTruePositiveRateResultName, "Sensitivity/True positive rate of the model on the test partition\n(TP/(TP+FN)).", new PercentValue()));
       Add(new Result(TestTrueNegativeRateResultName, "Specificity/True negative rate of the model on the test partition\n(TN/(FP+TN)).", new PercentValue()));
@@ -129 +151 @@
       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()));
       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()));
+      Add(new Result(TestF1ScoreResultName, "The F1 score of the model on the test partition.", new DoubleValue()));
+      Add(new Result(TestMatthewsCorrelationResultName, "The Matthews correlation value of the model on the test partition.", new DoubleValue()));
       TrainingTruePositiveRate = double.NaN;
       TrainingTrueNegativeRate = double.NaN;
@@ -135 +159 @@
       TrainingFalsePositiveRate = double.NaN;
       TrainingFalseDiscoveryRate = double.NaN;
+      TrainingF1Score = double.NaN;
+      TrainingMatthewsCorrelation = double.NaN;
       TestTruePositiveRate = double.NaN;
       TestTrueNegativeRate = double.NaN;
@@ -141 +167 @@
       TestFalsePositiveRate = double.NaN;
       TestFalseDiscoveryRate = double.NaN;
+      TestF1Score = double.NaN;
+      TestMatthewsCorrelation = double.NaN;
     }
 

stable/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationSolutionBase.cs

@@ -26 +26 @@
 using HeuristicLab.Optimization;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
+using HeuristicLab.Problems.DataAnalysis.OnlineCalculators;
 
 namespace HeuristicLab.Problems.DataAnalysis {
@@ -135 +136 @@
       if (testPerformanceCalculator.ErrorState == OnlineCalculatorError.None)
         ClassificationPerformanceMeasures.SetTestResults(testPerformanceCalculator);
+
+      if (ProblemData.Classes == 2) {
+        var f1Training = FOneScoreCalculator.Calculate(originalTrainingClassValues, estimatedTrainingClassValues, out errorState);
+        if (errorState == OnlineCalculatorError.None) ClassificationPerformanceMeasures.TrainingF1Score = f1Training;
+        var f1Test = FOneScoreCalculator.Calculate(originalTestClassValues, estimatedTestClassValues, out errorState);
+        if (errorState == OnlineCalculatorError.None) ClassificationPerformanceMeasures.TestF1Score = f1Test;
+      }
+
+      var mccTraining = MatthewsCorrelationCoefficientCalculator.Calculate(originalTrainingClassValues, estimatedTrainingClassValues, out errorState);
+      if (errorState == OnlineCalculatorError.None) ClassificationPerformanceMeasures.TrainingMatthewsCorrelation = mccTraining;
+      var mccTest = MatthewsCorrelationCoefficientCalculator.Calculate(originalTestClassValues, estimatedTestClassValues, out errorState);
+      if (errorState == OnlineCalculatorError.None) ClassificationPerformanceMeasures.TestMatthewsCorrelation = mccTest;
     }
 

stable/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/ConstantRegressionModel.cs

@@ -31 +31 @@
   [StorableClass]
   [Item("Constant Regression Model", "A model that always returns the same constant value regardless of the presented input data.")]
+  [Obsolete]
   public class ConstantRegressionModel : NamedItem, IRegressionModel, IStringConvertibleValue {
     [Storable]
@@ -60 +61 @@
 
     public IRegressionSolution CreateRegressionSolution(IRegressionProblemData problemData) {
-      return new ConstantRegressionSolution(this, new RegressionProblemData(problemData));
+      return new ConstantRegressionSolution(new ConstantModel(constant), new RegressionProblemData(problemData));
     }
 

stable/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/ConstantRegressionSolution.cs

@@ -28 +28 @@
   [Item(Name = "Constant Regression Solution", Description = "Represents a constant regression solution (model + data).")]
   public class ConstantRegressionSolution : RegressionSolution {
-    public new ConstantRegressionModel Model {
-      get { return (ConstantRegressionModel)base.Model; }
+    public new ConstantModel Model {
+      get { return (ConstantModel)base.Model; }
       set { base.Model = value; }
     }
@@ -36 +36 @@
     protected ConstantRegressionSolution(bool deserializing) : base(deserializing) { }
     protected ConstantRegressionSolution(ConstantRegressionSolution original, Cloner cloner) : base(original, cloner) { }
-    public ConstantRegressionSolution(ConstantRegressionModel model, IRegressionProblemData problemData)
+    public ConstantRegressionSolution(ConstantModel model, IRegressionProblemData problemData)
       : base(model, problemData) {
       RecalculateResults();

stable/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/TimeSeriesPrognosis/Models/ConstantTimeSeriesPrognosisModel.cs

@@ -20 +20 @@
 #endregion
 
+using System;
 using System.Collections.Generic;
 using System.Linq;
@@ -29 +30 @@
   [StorableClass]
   [Item("Constant TimeSeries Model", "A time series model that returns for all prediciton the same constant value.")]
+  [Obsolete]
   public class ConstantTimeSeriesPrognosisModel : ConstantRegressionModel, ITimeSeriesPrognosisModel {
     [StorableConstructor]

stable/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/TimeSeriesPrognosis/TimeSeriesPrognosisResults.cs

@@ -373 +373 @@
       //mean model
       double trainingMean = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TrainingIndices).Average();
-      var meanModel = new ConstantTimeSeriesPrognosisModel(trainingMean);
+      var meanModel = new ConstantModel(trainingMean);
 
       //AR1 model
@@ -448 +448 @@
         //mean model
         double trainingMean = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TrainingIndices).Average();
-        var meanModel = new ConstantTimeSeriesPrognosisModel(trainingMean);
+        var meanModel = new ConstantModel(trainingMean);
 
         //AR1 model

stable/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/TimeSeriesPrognosis/TimeSeriesPrognosisSolutionBase.cs

@@ -150 +150 @@
       OnlineCalculatorError errorState;
       double trainingMean = ProblemData.TrainingIndices.Any() ? ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndices).Average() : double.NaN;
-      var meanModel = new ConstantTimeSeriesPrognosisModel(trainingMean);
+      var meanModel = new ConstantModel(trainingMean);
 
       double alpha, beta;