Changeset 4309 for branches/DataAnalysis/HeuristicLab.Problems.DataAnalysis

Timestamp:

08/24/10 19:25:11 (14 years ago)

Author:

gkronber

Message:

Exploring overfitting countermeasures. #1142

Location:

branches/DataAnalysis/HeuristicLab.Problems.DataAnalysis/3.3

Files:

• HeuristicLab.Problems.DataAnalysis-3.3.csproj (modified) (1 diff)
• Operators/CovariantParsimonyPressure.cs (modified) (8 diffs)
• Operators/CovariantParsimonyPressureAdder.cs (added)

branches/DataAnalysis/HeuristicLab.Problems.DataAnalysis/3.3/HeuristicLab.Problems.DataAnalysis-3.3.csproj

@@ -133 +133 @@
     <Compile Include="Interfaces\IOnlineEvaluator.cs" />
     <Compile Include="MatrixExtensions.cs" />
+    <Compile Include="Operators\CovariantParsimonyPressureAdder.cs" />
     <Compile Include="Operators\CovariantParsimonyPressure.cs" />
     <Compile Include="Operators\DynamicDepthLimitInitializer.cs" />

branches/DataAnalysis/HeuristicLab.Problems.DataAnalysis/3.3/Operators/CovariantParsimonyPressure.cs

@@ -47 +47 @@
       get { return (IScopeTreeLookupParameter<DoubleValue>)Parameters["AdjustedQuality"]; }
     }
-
     public ILookupParameter<BoolValue> MaximizationParameter {
       get { return (ILookupParameter<BoolValue>)Parameters["Maximization"]; }
@@ -54 +53 @@
       get { return (IValueLookupParameter<DoubleValue>)Parameters["K"]; }
     }
+    public ILookupParameter<DoubleValue> CParameter {
+      get { return (ILookupParameter<DoubleValue>)Parameters["C"]; }
+    }
     public ILookupParameter<IntValue> GenerationsParameter {
       get { return (ILookupParameter<IntValue>)Parameters["Generations"]; }
@@ -63 +65 @@
       get { return (IValueLookupParameter<BoolValue>)Parameters["ApplyParsimonyPressure"]; }
     }
-    public ILookupParameter<DataTable> ValidationQualityParameter {
-      get { return (ILookupParameter<DataTable>)Parameters["Validation Quality"]; }
-    }
-    //public ILookupParameter<DoubleValue> CurrentBestValidationQualityParameter {
-    //  get { return (ILookupParameter<DoubleValue>)Parameters["Current best validation quality"]; }
-    //}
-    //public ILookupParameter<DoubleValue> BestValidationQualityParameter {
-    //  get { return (ILookupParameter<DoubleValue>)Parameters["Best solution quality (validation)"]; }
-    //}
     public ILookupParameter<DoubleValue> LengthCorrelationParameter {
       get { return (ILookupParameter<DoubleValue>)Parameters["Correlation(Length, AdjustedFitness)"]; }
@@ -78 +71 @@
       get { return (ILookupParameter<DoubleValue>)Parameters["Correlation(Fitness, AdjustedFitness)"]; }
     }
-    //public IValueLookupParameter<IntValue> GenerationSpanParameter {
-    //  get { return (IValueLookupParameter<IntValue>)Parameters["GenerationSpan"]; }
-    //}
-    //public IValueLookupParameter<PercentValue> OverfittingLimitParameter {
-    //  get { return (IValueLookupParameter<PercentValue>)Parameters["OverfittingLimit"]; }
-    //}
     public IValueLookupParameter<PercentValue> ComplexityAdaptionParameter {
       get { return (IValueLookupParameter<PercentValue>)Parameters["ComplexityAdaption"]; }
-    }
-    public ILookupParameter<DataTable> QualitiesParameter {
-      get { return (ILookupParameter<DataTable>)Parameters["Qualities"]; }
     }
     public IValueLookupParameter<DoubleValue> MinAverageSizeParameter {
@@ -103 +87 @@
       Parameters.Add(new ValueLookupParameter<DoubleValue>("K", new DoubleValue(1.0)));
       Parameters.Add(new LookupParameter<IntValue>("Generations"));
-      Parameters.Add(new ValueLookupParameter<IntValue>("FirstGenerationParameter", new IntValue(5)));
+      Parameters.Add(new ValueLookupParameter<IntValue>("FirstGenerationParameter", new IntValue(1)));
       Parameters.Add(new ValueLookupParameter<BoolValue>("ApplyParsimonyPressure"));
-      //Parameters.Add(new LookupParameter<DoubleValue>("Current best validation quality"));
-      //Parameters.Add(new LookupParameter<DoubleValue>("Best solution quality (validation)"));
-      Parameters.Add(new LookupParameter<DataTable>("Validation Quality"));
-      Parameters.Add(new LookupParameter<DataTable>("Qualities"));
-      //Parameters.Add(new ValueLookupParameter<IntValue>("GenerationSpan", new IntValue(5)));
-      //Parameters.Add(new ValueLookupParameter<PercentValue>("OverfittingLimit", new PercentValue(5)));
-      Parameters.Add(new ValueLookupParameter<PercentValue>("ComplexityAdaption", new PercentValue(-5)));
+      Parameters.Add(new ValueLookupParameter<PercentValue>("ComplexityAdaption", new PercentValue(-0.01)));
       Parameters.Add(new LookupParameter<DoubleValue>("Correlation(Length, AdjustedFitness)"));
       Parameters.Add(new LookupParameter<DoubleValue>("Correlation(Fitness, AdjustedFitness)"));
       Parameters.Add(new ValueLookupParameter<DoubleValue>("MinAverageSize", new DoubleValue(15)));
+      Parameters.Add(new LookupParameter<DoubleValue>("C"));
     }
 
@@ -130 +109 @@
       }
       if (!Parameters.ContainsKey("FirstGenerationParameter")) {
-        Parameters.Add(new ValueLookupParameter<IntValue>("FirstGenerationParameter", new IntValue(5)));
+        Parameters.Add(new ValueLookupParameter<IntValue>("FirstGenerationParameter", new IntValue(1)));
       }
       if (!Parameters.ContainsKey("ApplyParsimonyPressure")) {
         Parameters.Add(new ValueLookupParameter<BoolValue>("ApplyParsimonyPressure"));
       }
-      //if (!Parameters.ContainsKey("Current best validation quality")) {
-      //  Parameters.Add(new LookupParameter<DoubleValue>("Current best validation quality"));
-      //}
-      //if (!Parameters.ContainsKey("Best solution quality (validation)")) {
-      //  Parameters.Add(new LookupParameter<DoubleValue>("Best solution quality (validation)"));
-      //}
-      if (!Parameters.ContainsKey("Correlation(Length, AdjustedFitness)")) {
-        Parameters.Add(new LookupParameter<DoubleValue>("Correlation(Length, AdjustedFitness)"));
-      }
-      if (!Parameters.ContainsKey("Correlation(Fitness, AdjustedFitness)")) {
-        Parameters.Add(new LookupParameter<DoubleValue>("Correlation(Fitness, AdjustedFitness)"));
-      }
-      if (!Parameters.ContainsKey("Validation Quality")) {
-        Parameters.Add(new LookupParameter<DataTable>("Validation Quality"));
-      }
-      if (!Parameters.ContainsKey("Qualities")) {
-        Parameters.Add(new LookupParameter<DataTable>("Qualities"));
-      }
       if (!Parameters.ContainsKey("ComplexityAdaption")) {
-        Parameters.Add(new ValueLookupParameter<PercentValue>("ComplexityAdaption", new PercentValue(-5)));
+        Parameters.Add(new ValueLookupParameter<PercentValue>("ComplexityAdaption", new PercentValue(-0.01)));
       }
       if (!Parameters.ContainsKey("MinAverageSize")) {
         Parameters.Add(new ValueLookupParameter<DoubleValue>("MinAverageSize", new DoubleValue(15)));
+      }
+      if (!Parameters.ContainsKey("C")) {
+        Parameters.Add(new LookupParameter<DoubleValue>("C"));
       }
     }
@@ -194 +158 @@
 
         double sizeAdaption = lengthMeanCalculator.Mean * ComplexityAdaptionParameter.ActualValue.Value;
-        if (sizeAdaption < 0) sizeAdaption = Math.Floor(sizeAdaption);
-        else sizeAdaption = Math.Ceiling(sizeAdaption);
-        double g = lengthMeanCalculator.Mean + sizeAdaption;
-        if (g < MinAverageSizeParameter.ActualValue.Value)
-          g = MinAverageSizeParameter.ActualValue.Value;
+        if (lengthMeanCalculator.Mean + sizeAdaption < MinAverageSizeParameter.ActualValue.Value)
+          sizeAdaption = 0.0;
 
         //            cov(l, f) - (g(t+1) - mu(t)) avgF
         // c(t) =  --------------------------------------------
         //           cov(l, l^k) - (g(t+1) - mu(t)) E[l^k]
-        double c = lengthFitnessCovEvaluator.Covariance - (g - lengthMeanCalculator.Mean) * fitnessMeanCalculator.Mean;
-        c /= lengthAdjLengthCovEvaluator.Covariance - (g - lengthMeanCalculator.Mean) * adjLengthMeanCalculator.Mean;
+        double c = lengthFitnessCovEvaluator.Covariance - sizeAdaption * fitnessMeanCalculator.Mean;
+        c /= lengthAdjLengthCovEvaluator.Covariance - sizeAdaption * adjLengthMeanCalculator.Mean;
+
+        CParameter.ActualValue = new DoubleValue(c);
 
         // adjust fitness
@@ -230 +193 @@
 
       } else {
+        CParameter.ActualValue = new DoubleValue(0.0);
         // adjusted fitness is equal to fitness
         AdjustedQualityParameter.ActualValue = (ItemArray<DoubleValue>)QualityParameter.ActualValue.Clone();