Changeset 8531 for trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicDiscriminantFunctionClassificationModel.cs

Timestamp:

08/28/12 13:11:15 (12 years ago)

Author:

mkommend

Message:

#1919: Refactored calculation of thresholds for SymbolicDiscriminantFunctionClassficationModels and removed the automatic recalculation of thresholds during solution creation.

File:

• trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicDiscriminantFunctionClassificationModel.cs (modified) (3 diffs)

trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicDiscriminantFunctionClassificationModel.cs

@@ -67 +67 @@
       double lowerEstimationLimit = double.MinValue, double upperEstimationLimit = double.MaxValue)
       : base(tree, interpreter) {
-      thresholds = new double[] { double.NegativeInfinity };
-      classValues = new double[] { 0.0 };
+      this.thresholds = new double[0];
+      this.classValues = new double[0];
       this.lowerEstimationLimit = lowerEstimationLimit;
       this.upperEstimationLimit = upperEstimationLimit;
@@ -88 +88 @@
 
     public IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows) {
-      return Interpreter.GetSymbolicExpressionTreeValues(SymbolicExpressionTree, dataset, rows)
-        .LimitToRange(lowerEstimationLimit, upperEstimationLimit);
+      return Interpreter.GetSymbolicExpressionTreeValues(SymbolicExpressionTree, dataset, rows).LimitToRange(lowerEstimationLimit, upperEstimationLimit);
     }
 
     public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
+      if (!Thresholds.Any() && !ClassValues.Any()) throw new ArgumentException("No thresholds and class values were set for the current symbolic classification model.");
       foreach (var x in GetEstimatedValues(dataset, rows)) {
         int classIndex = 0;
@@ -121 +121 @@
     }
     #endregion
+
+    public static void SetAccuracyMaximizingThresholds(IDiscriminantFunctionClassificationModel model, IClassificationProblemData problemData) {
+      double[] classValues;
+      double[] thresholds;
+      var targetClassValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TrainingIndices);
+      var estimatedTrainingValues = model.GetEstimatedValues(problemData.Dataset, problemData.TrainingIndices);
+      AccuracyMaximizationThresholdCalculator.CalculateThresholds(problemData, estimatedTrainingValues, targetClassValues, out classValues, out thresholds);
+
+      model.SetThresholdsAndClassValues(thresholds, classValues);
+    }
+
+    public static void SetClassDistibutionCutPointThresholds(IDiscriminantFunctionClassificationModel model, IClassificationProblemData problemData) {
+      double[] classValues;
+      double[] thresholds;
+      var targetClassValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, problemData.TrainingIndices);
+      var estimatedTrainingValues = model.GetEstimatedValues(problemData.Dataset, problemData.TrainingIndices);
+      NormalDistributionCutPointsThresholdCalculator.CalculateThresholds(problemData, estimatedTrainingValues, targetClassValues, out classValues, out thresholds);
+
+      model.SetThresholdsAndClassValues(thresholds, classValues);
+    }
 
     public static void Scale(SymbolicDiscriminantFunctionClassificationModel model, IClassificationProblemData problemData) {