Changeset 12720 for trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression

Timestamp:

07/10/15 15:41:09 (9 years ago)

Author:

bburlacu

Message:

#2359: Changed the impact calculators so that the quality value necessary for impacts calculation is calculated with a separate method. Refactored the CalculateImpactAndReplacementValues method to return the new quality in an out-parameter (adjusted method signature in interface accordingly). Added Evaluate method to the regression and classification pruning operators that re-evaluates the tree using the problem evaluator after pruning was performed.

Location:

trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4

Files:

• SymbolicRegressionPruningOperator.cs (modified) (7 diffs)
• SymbolicRegressionSolutionImpactValuesCalculator.cs (modified) (3 diffs)

trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SymbolicRegressionPruningOperator.cs

@@ -27 +27 @@
 using HeuristicLab.Core;
 using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
+using HeuristicLab.Parameters;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
 
@@ -33 +34 @@
   [Item("SymbolicRegressionPruningOperator", "An operator which prunes symbolic regression trees.")]
   public class SymbolicRegressionPruningOperator : SymbolicDataAnalysisExpressionPruningOperator {
+    private const string EvaluatorParameterName = "Evaluator";
+
+    #region parameter properties
+    public ILookupParameter<ISymbolicRegressionSingleObjectiveEvaluator> EvaluatorParameter {
+      get { return (ILookupParameter<ISymbolicRegressionSingleObjectiveEvaluator>)Parameters[EvaluatorParameterName]; }
+    }
+    #endregion
+
     protected SymbolicRegressionPruningOperator(SymbolicRegressionPruningOperator original, Cloner cloner)
       : base(original, cloner) {
@@ -45 +54 @@
     public SymbolicRegressionPruningOperator(ISymbolicDataAnalysisSolutionImpactValuesCalculator impactValuesCalculator)
       : base(impactValuesCalculator) {
+      Parameters.Add(new LookupParameter<ISymbolicRegressionSingleObjectiveEvaluator>(EvaluatorParameterName));
     }
 
@@ -52 +62 @@
 
     protected override double Evaluate(IDataAnalysisModel model) {
-      var regressionModel = (IRegressionModel)model;
+      var regressionModel = (ISymbolicRegressionModel)model;
       var regressionProblemData = (IRegressionProblemData)ProblemDataParameter.ActualValue;
-      var rows = Enumerable.Range(FitnessCalculationPartitionParameter.ActualValue.Start, FitnessCalculationPartitionParameter.ActualValue.Size);
-      return Evaluate(regressionModel, regressionProblemData, rows);
-    }
-
-    private static double Evaluate(IRegressionModel model, IRegressionProblemData problemData,
-      IEnumerable<int> rows) {
-      var estimatedValues = model.GetEstimatedValues(problemData.Dataset, rows); // also bounds the values
-      var targetValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
-      OnlineCalculatorError errorState;
-      var quality = OnlinePearsonsRCalculator.Calculate(targetValues, estimatedValues, out errorState);
-      if (errorState != OnlineCalculatorError.None) return double.NaN;
-      return quality*quality;
+      var evaluator = EvaluatorParameter.ActualValue;
+      var fitnessEvaluationPartition = FitnessCalculationPartitionParameter.ActualValue;
+      var rows = Enumerable.Range(fitnessEvaluationPartition.Start, fitnessEvaluationPartition.Size);
+      return evaluator.Evaluate(this.ExecutionContext, regressionModel.SymbolicExpressionTree, regressionProblemData, rows);
     }
 
@@ -72 +74 @@
       var model = new SymbolicRegressionModel(clonedTree, interpreter, estimationLimits.Lower, estimationLimits.Upper);
       var nodes = clonedTree.Root.GetSubtree(0).GetSubtree(0).IterateNodesPrefix().ToList(); // skip the nodes corresponding to the ProgramRootSymbol and the StartSymbol
-      double quality = Evaluate(model, problemData, rows);
+
+      double qualityForImpactsCalculation = double.NaN; // pass a NaN value initially so the impact calculator will calculate the quality
 
       for (int i = 0; i < nodes.Count; ++i) {
@@ -79 +82 @@
 
         double impactValue, replacementValue;
-        impactValuesCalculator.CalculateImpactAndReplacementValues(model, node, problemData, rows, out impactValue, out replacementValue, quality);
+        double newQualityForImpactsCalculation;
+        impactValuesCalculator.CalculateImpactAndReplacementValues(model, node, problemData, rows, out impactValue, out replacementValue, out newQualityForImpactsCalculation, qualityForImpactsCalculation);
 
         if (pruneOnlyZeroImpactNodes && !impactValue.IsAlmost(0.0)) continue;
@@ -90 +94 @@
         i += node.GetLength() - 1; // skip subtrees under the node that was folded
 
-        quality -= impactValue;
+        qualityForImpactsCalculation = newQualityForImpactsCalculation;
       }
       return model.SymbolicExpressionTree;

trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SymbolicRegressionSolutionImpactValuesCalculator.cs

@@ -48 +48 @@
     }
 
-    public override double CalculateImpactValue(ISymbolicDataAnalysisModel model, ISymbolicExpressionTreeNode node, IDataAnalysisProblemData problemData, IEnumerable<int> rows, double originalQuality = double.NaN) {
-      double impactValue, replacementValue;
-      CalculateImpactAndReplacementValues(model, node, problemData, rows, out impactValue, out replacementValue, originalQuality);
+    public override double CalculateImpactValue(ISymbolicDataAnalysisModel model, ISymbolicExpressionTreeNode node, IDataAnalysisProblemData problemData, IEnumerable<int> rows, double qualityForImpactsCalculation = double.NaN) {
+      double impactValue, replacementValue, newQualityForImpactsCalculation;
+      CalculateImpactAndReplacementValues(model, node, problemData, rows, out impactValue, out replacementValue, out newQualityForImpactsCalculation, qualityForImpactsCalculation);
       return impactValue;
     }
 
     public override void CalculateImpactAndReplacementValues(ISymbolicDataAnalysisModel model, ISymbolicExpressionTreeNode node,
-      IDataAnalysisProblemData problemData, IEnumerable<int> rows, out double impactValue, out double replacementValue,
-      double originalQuality = Double.NaN) {
+      IDataAnalysisProblemData problemData, IEnumerable<int> rows, out double impactValue, out double replacementValue, out double newQualityForImpactsCalculation,
+      double qualityForImpactsCalculation = Double.NaN) {
       var regressionModel = (ISymbolicRegressionModel)model;
       var regressionProblemData = (IRegressionProblemData)problemData;
@@ -64 +64 @@
 
       OnlineCalculatorError errorState;
-      if (double.IsNaN(originalQuality)) {
-        var originalValues = regressionModel.GetEstimatedValues(dataset, rows);
-        originalQuality = OnlinePearsonsRCalculator.Calculate(targetValues, originalValues, out errorState);
-        if (errorState != OnlineCalculatorError.None) originalQuality = 0.0;
-      }
+      if (double.IsNaN(qualityForImpactsCalculation))
+        qualityForImpactsCalculation = CalculateQualityForImpacts(regressionModel, regressionProblemData, rows);
 
       replacementValue = CalculateReplacementValue(regressionModel, node, regressionProblemData, rows);
@@ -83 +80 @@
 
       var estimatedValues = tempModel.GetEstimatedValues(dataset, rows);
-      double newQuality = OnlinePearsonsRCalculator.Calculate(targetValues, estimatedValues, out errorState);
-      if (errorState != OnlineCalculatorError.None) newQuality = 0.0;
+      double r = OnlinePearsonsRCalculator.Calculate(targetValues, estimatedValues, out errorState);
+      if (errorState != OnlineCalculatorError.None) r = 0.0;
+      newQualityForImpactsCalculation = r * r;
 
-      impactValue = (originalQuality*originalQuality) - (newQuality*newQuality);
+      impactValue = qualityForImpactsCalculation - newQualityForImpactsCalculation;
+    }
+
+    public static double CalculateQualityForImpacts(ISymbolicRegressionModel model, IRegressionProblemData problemData, IEnumerable<int> rows) {
+      var estimatedValues = model.GetEstimatedValues(problemData.Dataset, rows); // also bounds the values
+      var targetValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
+      OnlineCalculatorError errorState;
+      var r = OnlinePearsonsRCalculator.Calculate(targetValues, estimatedValues, out errorState);
+      var quality = r * r;
+      if (errorState != OnlineCalculatorError.None) return double.NaN;
+      return quality;
     }
   }