Changeset 8664 for trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectiveBoundedMeanSquaredErrorEvaluator.cs

Timestamp:

09/17/12 11:18:40 (12 years ago)

Author:

mkommend

Message:

#1951:

• Added linear scaling parameter to data analysis problems.
• Adapted interfaces, evaluators and analyzers accordingly.
• Added OnlineBoundedMeanSquaredErrorCalculator.
• Adapted symbolic regression sample unit test.

File:

• trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectiveBoundedMeanSquaredErrorEvaluator.cs (modified) (2 diffs)

trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective/SymbolicClassificationSingleObjectiveBoundedMeanSquaredErrorEvaluator.cs

@@ -47 +47 @@
       IEnumerable<int> rows = GenerateRowsToEvaluate();
       var solution = SymbolicExpressionTreeParameter.ActualValue;
-      double quality = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, ProblemDataParameter.ActualValue, rows);
+      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();
     }
 
-    public static double Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IClassificationProblemData problemData, IEnumerable<int> rows) {
+    public static double Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IClassificationProblemData problemData, IEnumerable<int> rows, bool applyLinearScaling) {
       IEnumerable<double> estimatedValues = interpreter.GetSymbolicExpressionTreeValues(solution, problemData.Dataset, rows);
-      IEnumerable<double> originalValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
-      IEnumerable<double> boundedEstimationValues = estimatedValues.LimitToRange(lowerEstimationLimit, upperEstimationLimit);
+      IEnumerable<double> targetValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
+      OnlineCalculatorError errorState;
 
-      double minClassValue = problemData.ClassValues.OrderBy(x => x).First();
-      double maxClassValue = problemData.ClassValues.OrderBy(x => x).Last();
+      double lowestClassValue = problemData.ClassValues.OrderBy(x => x).First();
+      double upmostClassValue = problemData.ClassValues.OrderByDescending(x => x).First();
 
-      IEnumerator<double> originalEnumerator = originalValues.GetEnumerator();
-      IEnumerator<double> estimatedEnumerator = estimatedValues.GetEnumerator();
-      double errorSum = 0.0;
-      int n = 0;
-
-      // always move forward both enumerators (do not use short-circuit evaluation!)
-      while (originalEnumerator.MoveNext() & estimatedEnumerator.MoveNext()) {
-        double estimated = estimatedEnumerator.Current;
-        double original = originalEnumerator.Current;
-        double error = estimated - original;
-
-        if (estimated < minClassValue || estimated > maxClassValue)
-          errorSum += Math.Abs(error);
-        else
-          errorSum += Math.Pow(error, 2);
-        n++;
+      double boundedMse;
+      if (applyLinearScaling) {
+        var boundedMseCalculator = new OnlineBoundedMeanSquaredErrorCalculator(lowestClassValue, upmostClassValue);
+        CalculateWithScaling(targetValues, estimatedValues, lowerEstimationLimit, upperEstimationLimit, boundedMseCalculator, problemData.Dataset.Rows);
+        errorState = boundedMseCalculator.ErrorState;
+        boundedMse = boundedMseCalculator.BoundedMeanSquaredError;
+      } else {
+        IEnumerable<double> boundedEstimatedValues = estimatedValues.LimitToRange(lowerEstimationLimit, upperEstimationLimit);
+        boundedMse = OnlineBoundedMeanSquaredErrorCalculator.Calculate(targetValues, boundedEstimatedValues, lowestClassValue, upmostClassValue, out errorState);
       }
-
-      // check if both enumerators are at the end to make sure both enumerations have the same length
-      if (estimatedEnumerator.MoveNext() || originalEnumerator.MoveNext()) {
-        throw new ArgumentException("Number of elements in first and second enumeration doesn't match.");
-      } else {
-        return errorSum / n;
-      }
+      if (errorState != OnlineCalculatorError.None) return Double.NaN;
+      return boundedMse;
     }
 
@@ -89 +77 @@
       SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = context;
       EstimationLimitsParameter.ExecutionContext = context;
+      ApplyLinearScalingParameter.ExecutionContext = context;
 
-      double mse = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, tree, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, problemData, rows);
+      double mse = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, tree, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, problemData, rows, ApplyLinearScalingParameter.ActualValue.Value);
 
       SymbolicDataAnalysisTreeInterpreterParameter.ExecutionContext = null;
       EstimationLimitsParameter.ExecutionContext = null;
+      ApplyLinearScalingParameter.ExecutionContext = null;
 
       return mse;