Changeset 15371 for trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic

Timestamp:

09/19/17 10:49:02 (7 years ago)

Author:

pfleck

Message:

#1666: Merged into trunk

Location:

trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic

Files:

• . (modified) (1 prop)
• 3.4/SymbolicDataAnalysisSolutionImpactValuesCalculator.cs (modified) (1 diff)

trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic/3.4/SymbolicDataAnalysisSolutionImpactValuesCalculator.cs

@@ -32 +32 @@
   public abstract class SymbolicDataAnalysisSolutionImpactValuesCalculator : Item, ISymbolicDataAnalysisSolutionImpactValuesCalculator {
     protected SymbolicDataAnalysisSolutionImpactValuesCalculator() { }
-
     protected SymbolicDataAnalysisSolutionImpactValuesCalculator(SymbolicDataAnalysisSolutionImpactValuesCalculator original, Cloner cloner)
       : base(original, cloner) { }
     [StorableConstructor]
     protected SymbolicDataAnalysisSolutionImpactValuesCalculator(bool deserializing) : base(deserializing) { }
-    public abstract void CalculateImpactAndReplacementValues(ISymbolicDataAnalysisModel model, ISymbolicExpressionTreeNode node, IDataAnalysisProblemData problemData, IEnumerable<int> rows, out double impactValue, out double replacementValue, out double newQualityForImpactsCalculation, double qualityForImpactsCalculation = double.NaN);
+
+    public virtual void CalculateImpactAndReplacementValues(ISymbolicDataAnalysisModel model, ISymbolicExpressionTreeNode node, IDataAnalysisProblemData problemData, IEnumerable<int> rows,
+        out double impactValue, out double replacementValue, out double newQualityForImpactsCalculation,
+        double qualityForImpactsCalculation = double.NaN) {
+      if (double.IsNaN(qualityForImpactsCalculation))
+        qualityForImpactsCalculation = CalculateQualityForImpacts(model, problemData, rows);
+
+      var cloner = new Cloner();
+      var tempModel = cloner.Clone(model);
+      var tempModelNode = (ISymbolicExpressionTreeNode)cloner.GetClone(node);
+
+      var tempModelParentNode = tempModelNode.Parent;
+      int i = tempModelParentNode.IndexOfSubtree(tempModelNode);
+
+      double bestReplacementValue = 0.0;
+      double bestImpactValue = double.PositiveInfinity;
+      newQualityForImpactsCalculation = qualityForImpactsCalculation; // initialize
+      // try the potentially reasonable replacement values and use the best one
+      foreach (var repValue in CalculateReplacementValues(node, model.SymbolicExpressionTree, model.Interpreter, problemData.Dataset, problemData.TrainingIndices)) {
+        tempModelParentNode.RemoveSubtree(i);
+
+        var constantNode = new ConstantTreeNode(new Constant()) { Value = repValue };
+        tempModelParentNode.InsertSubtree(i, constantNode);
+
+        newQualityForImpactsCalculation = CalculateQualityForImpacts(tempModel, problemData, rows);
+
+        impactValue = qualityForImpactsCalculation - newQualityForImpactsCalculation;
+        if (impactValue < bestImpactValue) {
+          bestImpactValue = impactValue;
+          bestReplacementValue = repValue;
+        }
+      }
+
+      replacementValue = bestReplacementValue;
+      impactValue = bestImpactValue;
+    }
+
+    protected abstract double CalculateQualityForImpacts(ISymbolicDataAnalysisModel model, IDataAnalysisProblemData problemData, IEnumerable<int> rows);
 
     protected IEnumerable<double> CalculateReplacementValues(ISymbolicExpressionTreeNode node, ISymbolicExpressionTree sourceTree, ISymbolicDataAnalysisExpressionTreeInterpreter interpreter,