Changeset 10538 for branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification

Timestamp:

03/05/14 14:48:13 (11 years ago)

Author:

pfleck

Message:

• merged trunk

Location:

branches/DataPreprocessing

Files:

• . (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification-3.4.csproj (modified) (2 diffs)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/MultiObjective/SymbolicClassificationMultiObjectiveMeanSquaredErrorTreeSizeEvaluator.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/MultiObjective/SymbolicClassificationMultiObjectivePearsonRSquaredTreeSizeEvaluator.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectiveBoundedMeanSquaredErrorEvaluator.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectiveMeanSquaredErrorEvaluator.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectivePearsonRSquaredEvaluator.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectivePenaltyScoreEvaluator.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicClassificationPruningAnalyzer.cs (copied) (copied from trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicClassificationPruningAnalyzer.cs)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicClassificationPruningOperator.cs (copied) (copied from trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicClassificationPruningOperator.cs)
• HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicClassificationSolutionImpactValuesCalculator.cs (modified) (4 diffs)

branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification-3.4.csproj

@@ -120 +120 @@
     <Compile Include="ModelCreators\NormalDistributedThresholdsModelCreator.cs" />
     <Compile Include="MultiObjective\SymbolicClassificationMultiObjectiveValidationBestSolutionAnalyzer.cs" />
+    <Compile Include="SymbolicClassificationPruningAnalyzer.cs" />
     <Compile Include="SymbolicClassificationSolutionImpactValuesCalculator.cs" />
     <Compile Include="SymbolicNearestNeighbourClassificationModel.cs" />
@@ -149 +150 @@
       <SubType>Code</SubType>
     </Compile>
+    <Compile Include="SymbolicClassificationPruningOperator.cs" />
     <None Include="HeuristicLab.snk" />
     <None Include="Plugin.cs.frame" />

branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/MultiObjective/SymbolicClassificationMultiObjectiveMeanSquaredErrorTreeSizeEvaluator.cs

@@ -44 +44 @@
     public override IEnumerable<bool> Maximization { get { return new bool[2] { false, false }; } }
 
-    public override IOperation Apply() {
+    public override IOperation InstrumentedApply() {
       IEnumerable<int> rows = GenerateRowsToEvaluate();
       var solution = SymbolicExpressionTreeParameter.ActualValue;
       double[] qualities = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, ProblemDataParameter.ActualValue, rows);
       QualitiesParameter.ActualValue = new DoubleArray(qualities);
-      return base.Apply();
+      return base.InstrumentedApply();
     }
 

branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/MultiObjective/SymbolicClassificationMultiObjectivePearsonRSquaredTreeSizeEvaluator.cs

@@ -44 +44 @@
     public override IEnumerable<bool> Maximization { get { return new bool[2] { true, false }; } }
 
-    public override IOperation Apply() {
+    public override IOperation InstrumentedApply() {
       IEnumerable<int> rows = GenerateRowsToEvaluate();
       var solution = SymbolicExpressionTreeParameter.ActualValue;
       double[] qualities = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, ProblemDataParameter.ActualValue, rows, ApplyLinearScalingParameter.ActualValue.Value);
       QualitiesParameter.ActualValue = new DoubleArray(qualities);
-      return base.Apply();
+      return base.InstrumentedApply();
     }
 

branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectiveBoundedMeanSquaredErrorEvaluator.cs

@@ -44 +44 @@
     public override bool Maximization { get { return false; } }
 
-    public override IOperation Apply() {
+    public override IOperation InstrumentedApply() {
       IEnumerable<int> rows = GenerateRowsToEvaluate();
       var solution = SymbolicExpressionTreeParameter.ActualValue;
       double quality = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, ProblemDataParameter.ActualValue, rows, ApplyLinearScalingParameter.ActualValue.Value);
       QualityParameter.ActualValue = new DoubleValue(quality);
-      return base.Apply();
+      return base.InstrumentedApply();
     }
 

branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectiveMeanSquaredErrorEvaluator.cs

@@ -45 +45 @@
     public override bool Maximization { get { return false; } }
 
-    public override IOperation Apply() {
+    public override IOperation InstrumentedApply() {
       IEnumerable<int> rows = GenerateRowsToEvaluate();
       var solution = SymbolicExpressionTreeParameter.ActualValue;
       double quality = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, ProblemDataParameter.ActualValue, rows, ApplyLinearScalingParameter.ActualValue.Value);
       QualityParameter.ActualValue = new DoubleValue(quality);
-      return base.Apply();
+      return base.InstrumentedApply();
     }
 

branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectivePearsonRSquaredEvaluator.cs

@@ -44 +44 @@
     public override bool Maximization { get { return true; } }
 
-    public override IOperation Apply() {
+    public override IOperation InstrumentedApply() {
       IEnumerable<int> rows = GenerateRowsToEvaluate();
       var solution = SymbolicExpressionTreeParameter.ActualValue;
       double quality = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, ProblemDataParameter.ActualValue, rows, ApplyLinearScalingParameter.ActualValue.Value);
       QualityParameter.ActualValue = new DoubleValue(quality);
-      return base.Apply();
+      return base.InstrumentedApply();
     }
 

branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectivePenaltyScoreEvaluator.cs

@@ -64 +64 @@
 
 
-    public override IOperation Apply() {
+    public override IOperation InstrumentedApply() {
       double quality = Evaluate(ExecutionContext, SymbolicExpressionTreeParameter.ActualValue, ProblemDataParameter.ActualValue, GenerateRowsToEvaluate());
       QualityParameter.ActualValue = new DoubleValue(quality);
-      return base.Apply();
+      return base.InstrumentedApply();
     }
 

branches/DataPreprocessing/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SymbolicClassificationSolutionImpactValuesCalculator.cs

@@ -20 +20 @@
 #endregion
 
+using System;
 using System.Collections.Generic;
 using HeuristicLab.Common;
+using HeuristicLab.Core;
 using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
+using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
 
 namespace HeuristicLab.Problems.DataAnalysis.Symbolic.Classification {
+  [StorableClass]
+  [Item("SymbolicClassificationSolutionImpactValuesCalculator", "Calculate symbolic expression tree node impact values for classification problems.")]
   public class SymbolicClassificationSolutionImpactValuesCalculator : SymbolicDataAnalysisSolutionImpactValuesCalculator {
+    public SymbolicClassificationSolutionImpactValuesCalculator() { }
+    protected SymbolicClassificationSolutionImpactValuesCalculator(SymbolicClassificationSolutionImpactValuesCalculator original, Cloner cloner)
+      : base(original, cloner) { }
+    public override IDeepCloneable Clone(Cloner cloner) {
+      return new SymbolicClassificationSolutionImpactValuesCalculator(this, cloner);
+    }
+    [StorableConstructor]
+    protected SymbolicClassificationSolutionImpactValuesCalculator(bool deserializing) : base(deserializing) { }
+
     public override double CalculateReplacementValue(ISymbolicDataAnalysisModel model, ISymbolicExpressionTreeNode node, IDataAnalysisProblemData problemData, IEnumerable<int> rows) {
       var classificationModel = (ISymbolicClassificationModel)model;
@@ -34 +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);
+      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) {
       var classificationModel = (ISymbolicClassificationModel)model;
       var classificationProblemData = (IClassificationProblemData)problemData;
@@ -47 +69 @@
       }
 
-      var replacementValue = CalculateReplacementValue(classificationModel, node, classificationProblemData, rows);
+      replacementValue = CalculateReplacementValue(classificationModel, node, classificationProblemData, rows);
       var constantNode = new ConstantTreeNode(new Constant()) { Value = replacementValue };
+
       var cloner = new Cloner();
-      cloner.RegisterClonedObject(node, constantNode);
       var tempModel = cloner.Clone(classificationModel);
-      tempModel.RecalculateModelParameters(classificationProblemData, rows);
+      var tempModelNode = (ISymbolicExpressionTreeNode)cloner.GetClone(node);
+
+      var tempModelParentNode = tempModelNode.Parent;
+      int i = tempModelParentNode.IndexOfSubtree(tempModelNode);
+      tempModelParentNode.RemoveSubtree(i);
+      tempModelParentNode.InsertSubtree(i, constantNode);
 
       var estimatedClassValues = tempModel.GetEstimatedClassValues(dataset, rows);
@@ -58 +85 @@
       if (errorState != OnlineCalculatorError.None) newQuality = 0.0;
 
-      return originalQuality - newQuality;
+      impactValue = originalQuality - newQuality;
     }
-
   }
 }