Changeset 15321 for branches/SimplifierViewsProgress/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression

Timestamp:

08/10/17 17:16:07 (7 years ago)

Author:

pfleck

Message:

#1666

• Moved CalculateImpactAndReplacementValues into base-class.
• Use SymRegImpactCalculator for SymTimeSeriesPrognosis.
• Unified CalculateImpactAndReplacementValues for all SimplifierViews.

File:

• branches/SimplifierViewsProgress/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SymbolicRegressionSolutionImpactValuesCalculator.cs (modified) (3 diffs)

branches/SimplifierViewsProgress/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SymbolicRegressionSolutionImpactValuesCalculator.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;
 
@@ -32 +30 @@
   public class SymbolicRegressionSolutionImpactValuesCalculator : SymbolicDataAnalysisSolutionImpactValuesCalculator {
     public SymbolicRegressionSolutionImpactValuesCalculator() { }
-
     protected SymbolicRegressionSolutionImpactValuesCalculator(SymbolicRegressionSolutionImpactValuesCalculator original, Cloner cloner)
       : base(original, cloner) { }
@@ -38 +35 @@
       return new SymbolicRegressionSolutionImpactValuesCalculator(this, cloner);
     }
-
     [StorableConstructor]
     protected SymbolicRegressionSolutionImpactValuesCalculator(bool deserializing) : base(deserializing) { }
 
-    public override void CalculateImpactAndReplacementValues(ISymbolicDataAnalysisModel model, ISymbolicExpressionTreeNode node,
-      IDataAnalysisProblemData problemData, IEnumerable<int> rows, out double impactValue, out double replacementValue, out double newQualityForImpactsCalculation,
-      double qualityForImpactsCalculation = double.NaN) {
+    protected override double CalculateQualityForImpacts(ISymbolicDataAnalysisModel model, IDataAnalysisProblemData problemData, IEnumerable<int> rows) {
       var regressionModel = (ISymbolicRegressionModel)model;
       var regressionProblemData = (IRegressionProblemData)problemData;
-
-      var dataset = regressionProblemData.Dataset;
-      var targetValues = dataset.GetDoubleValues(regressionProblemData.TargetVariable, rows);
-
-      if (double.IsNaN(qualityForImpactsCalculation))
-        qualityForImpactsCalculation = CalculateQualityForImpacts(regressionModel, regressionProblemData, rows);
-
-      var cloner = new Cloner();
-      var tempModel = cloner.Clone(regressionModel);
-      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, regressionModel.SymbolicExpressionTree, regressionModel.Interpreter, regressionProblemData.Dataset, regressionProblemData.TrainingIndices)) {
-
-        tempModelParentNode.RemoveSubtree(i);
-
-        var constantNode = new ConstantTreeNode(new Constant()) { Value = repValue };
-
-        tempModelParentNode.InsertSubtree(i, constantNode);
-
-        var estimatedValues = tempModel.GetEstimatedValues(dataset, rows);
-        OnlineCalculatorError errorState;
-        double r = OnlinePearsonsRCalculator.Calculate(targetValues, estimatedValues, out errorState);
-        if (errorState != OnlineCalculatorError.None) r = 0.0;
-        newQualityForImpactsCalculation = r * r;
-
-        impactValue = qualityForImpactsCalculation - newQualityForImpactsCalculation;
-        if (impactValue < bestImpactValue) {
-          bestImpactValue = impactValue;
-          bestReplacementValue = repValue;
-        }
-      }
-      replacementValue = bestReplacementValue;
-      impactValue = bestImpactValue;
-    }
-
-    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);
+      var estimatedValues = regressionModel.GetEstimatedValues(problemData.Dataset, rows); // also bounds the values
+      var targetValues = problemData.Dataset.GetDoubleValues(regressionProblemData.TargetVariable, rows);
       OnlineCalculatorError errorState;
       var r = OnlinePearsonsRCalculator.Calculate(targetValues, estimatedValues, out errorState);