Changeset 8623 for trunk/sources/HeuristicLab.Problems.DataAnalysis

Timestamp:

09/10/12 17:13:46 (12 years ago)

Author:

gkronber

Message:

#1902 implemented LS Gaussian Process classification

Location:

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4

Files:

• Implementation/Classification/DiscriminantFunctionClassificationModel.cs (modified) (4 diffs)
• Implementation/Classification/ThresholdCalculators/NormalDistributionCutPointsThresholdCalculator.cs (modified) (2 diffs)
• Interfaces/Classification/IDiscriminantFunctionClassificationModel.cs (modified) (1 diff)

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/DiscriminantFunctionClassificationModel.cs

@@ -51 +51 @@
     }
 
+    private IDiscriminantFunctionThresholdCalculator thresholdCalculator;
+    [Storable]
+    public IDiscriminantFunctionThresholdCalculator ThresholdCalculator {
+      get { return thresholdCalculator; }
+      private set { thresholdCalculator = value; }
+    }
+
 
     [StorableConstructor]
@@ -61 +68 @@
     }
 
-    public DiscriminantFunctionClassificationModel(IRegressionModel model)
+    public DiscriminantFunctionClassificationModel(IRegressionModel model, IDiscriminantFunctionThresholdCalculator thresholdCalculator)
       : base() {
       this.name = ItemName;
       this.description = ItemDescription;
       this.model = model;
-      this.classValues = new double[] { 0.0 };
-      this.thresholds = new double[] { double.NegativeInfinity };
+      this.classValues = new double[0];
+      this.thresholds = new double[0];
+      this.thresholdCalculator = thresholdCalculator;
+    }
+
+    [StorableHook(HookType.AfterDeserialization)]
+    private void AfterDeserialization() {
+      if (ThresholdCalculator == null) ThresholdCalculator = new AccuracyMaximizationThresholdCalculator();
     }
 
@@ -80 +93 @@
     }
 
+    public virtual void RecalculateModelParameters(IClassificationProblemData problemData, IEnumerable<int> rows) {
+      double[] classValues;
+      double[] thresholds;
+      var targetClassValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
+      var estimatedTrainingValues = GetEstimatedValues(problemData.Dataset, rows);
+      thresholdCalculator.Calculate(problemData, estimatedTrainingValues, targetClassValues, out classValues, out thresholds);
+      SetThresholdsAndClassValues(thresholds, classValues);
+    }
+
+
     public IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows) {
       return model.GetEstimatedValues(dataset, rows);
@@ -85 +108 @@
 
     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 classification model.");
       foreach (var x in GetEstimatedValues(dataset, rows)) {
         int classIndex = 0;

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ThresholdCalculators/NormalDistributionCutPointsThresholdCalculator.cs

@@ -107 +107 @@
         double maxDensityClassValue = -1;
         foreach (var classValue in originalClasses) {
-          double density = NormalDensity(m, classMean[classValue], classStdDev[classValue]);
+          double density = LogNormalDensity(m, classMean[classValue], classStdDev[classValue]);
           if (density > maxDensity) {
             maxDensity = density;
@@ -139 +139 @@
     }
 
-    private static double NormalDensity(double x, double mu, double sigma) {
-      if (sigma.IsAlmost(0.0)) {
-        if (x.IsAlmost(mu)) return 1.0; else return 0.0;
-      } else {
-        return (1.0 / Math.Sqrt(2.0 * Math.PI * sigma * sigma)) * Math.Exp(-((x - mu) * (x - mu)) / (2.0 * sigma * sigma));
-      }
+    private static double LogNormalDensity(double x, double mu, double sigma) {
+      return -0.5 * Math.Log(2.0 * Math.PI * sigma * sigma) - ((x - mu) * (x - mu)) / (2.0 * sigma * sigma);
     }
 

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Interfaces/Classification/IDiscriminantFunctionClassificationModel.cs

@@ -26 +26 @@
     IEnumerable<double> Thresholds { get; }
     IEnumerable<double> ClassValues { get; }
+    IDiscriminantFunctionThresholdCalculator ThresholdCalculator { get; }
+    void RecalculateModelParameters(IClassificationProblemData problemData, IEnumerable<int> rows);
     // class values and thresholds can only be assigned simultanously
     void SetThresholdsAndClassValues(IEnumerable<double> thresholds, IEnumerable<double> classValues);