Changeset 12843 for branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4

Timestamp:

08/11/15 10:11:47 (9 years ago)

Author:

ascheibe

Message:

#2388 merged trunk into branch

Location:

branches/HiveStatistics/sources

Files:

• . (modified) (2 props)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Regression (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/Plugin.cs.frame (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/Properties/AssemblyInfo.cs.frame (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SymbolicRegressionPruningAnalyzer.cs (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SymbolicRegressionPruningOperator.cs (modified) (7 diffs)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SymbolicRegressionSolutionImpactValuesCalculator.cs (modified) (3 diffs)

branches/HiveStatistics/sources

@@ -23 +23 @@
 bin
 protoc.exe
+obj

@@ -23 +23 @@
 bin
 protoc.exe
+obj

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/Plugin.cs.frame

@@ -26 +26 @@
 
 namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Regression {
-  [Plugin("HeuristicLab.Problems.DataAnalysis.Symbolic.Regression","Provides classes to perform symbolic regression (single- or multiobjective).", "3.4.7.$WCREV$")]
+  [Plugin("HeuristicLab.Problems.DataAnalysis.Symbolic.Regression","Provides classes to perform symbolic regression (single- or multiobjective).", "3.4.8.$WCREV$")]
   [PluginFile("HeuristicLab.Problems.DataAnalysis.Symbolic.Regression-3.4.dll", PluginFileType.Assembly)]
   [PluginDependency("HeuristicLab.ALGLIB", "3.7.0")]

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/Properties/AssemblyInfo.cs.frame

@@ -53 +53 @@
 // by using the '*' as shown below:
 [assembly: AssemblyVersion("3.4.0.0")]
-[assembly: AssemblyFileVersion("3.4.7.$WCREV$")]
+[assembly: AssemblyFileVersion("3.4.8.$WCREV$")]

branches/HiveStatistics/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SymbolicRegressionPruningAnalyzer.cs

@@ -24 +24 @@
 using HeuristicLab.Common;
 using HeuristicLab.Core;
+using HeuristicLab.Data;
 using HeuristicLab.Parameters;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
@@ -49 +50 @@
       Parameters.Add(new ValueParameter<SymbolicRegressionPruningOperator>(PruningOperatorParameterName, "The operator used to prune trees", new SymbolicRegressionPruningOperator(new SymbolicRegressionSolutionImpactValuesCalculator())));
     }
+
+    [StorableHook(HookType.AfterDeserialization)]
+    private void AfterDeserialization() {
+      // BackwardsCompatibility3.3
+
+      #region Backwards compatible code, remove with 3.4
+      if (Parameters.ContainsKey(PruningOperatorParameterName)) {
+        var oldParam = Parameters[PruningOperatorParameterName] as ValueParameter<SymbolicDataAnalysisExpressionPruningOperator>;
+        if (oldParam != null) {
+          Parameters.Remove(oldParam);
+          Parameters.Add(new ValueParameter<SymbolicRegressionPruningOperator>(PruningOperatorParameterName, "The operator used to prune trees", new SymbolicRegressionPruningOperator(new SymbolicRegressionSolutionImpactValuesCalculator())));
+        }
+      } else {
+        // not yet contained
+        Parameters.Add(new ValueParameter<SymbolicRegressionPruningOperator>(PruningOperatorParameterName, "The operator used to prune trees", new SymbolicRegressionPruningOperator(new SymbolicRegressionSolutionImpactValuesCalculator())));
+      }
+
+
+      if (Parameters.ContainsKey("PruneOnlyZeroImpactNodes")) {
+        PruningOperator.PruneOnlyZeroImpactNodes = ((IFixedValueParameter<BoolValue>)Parameters["PruneOnlyZeroImpactNodes"]).Value.Value;
+        Parameters.Remove(Parameters["PruneOnlyZeroImpactNodes"]);
+      }
+      if (Parameters.ContainsKey("ImpactThreshold")) {
+        PruningOperator.NodeImpactThreshold = ((IFixedValueParameter<DoubleValue>)Parameters["ImpactThreshold"]).Value.Value;
+        Parameters.Remove(Parameters["ImpactThreshold"]);
+      }
+      if (Parameters.ContainsKey("ImpactValuesCalculator")) {
+        PruningOperator.ImpactValuesCalculator = ((ValueParameter<SymbolicDataAnalysisSolutionImpactValuesCalculator>)Parameters["ImpactValuesCalculator"]).Value;
+        Parameters.Remove(Parameters["ImpactValuesCalculator"]);
+      }
+
+      #endregion
+    }
   }
 }

branches/HiveStatistics/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));
+    }
+
+    [StorableHook(HookType.AfterDeserialization)]
+    private void AfterDeserialization() {
+      // BackwardsCompatibility3.3
+      #region Backwards compatible code, remove with 3.4
+      base.ImpactValuesCalculator = new SymbolicRegressionSolutionImpactValuesCalculator();
+      if (!Parameters.ContainsKey(EvaluatorParameterName)) {
+        Parameters.Add(new LookupParameter<ISymbolicRegressionSingleObjectiveEvaluator>(EvaluatorParameterName));
+      }
+      #endregion
     }
 
@@ -52 +73 @@
 
     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 +85 @@
       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 +93 @@
 
         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 +105 @@
         i += node.GetLength() - 1; // skip subtrees under the node that was folded
 
-        quality -= impactValue;
+        qualityForImpactsCalculation = newQualityForImpactsCalculation;
       }
       return model.SymbolicExpressionTree;

branches/HiveStatistics/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;
     }
   }

@@ -23 +23 @@
 bin
 protoc.exe
+obj