Changeset 13211 for branches/DataAnalysis.ComplexityAnalyzer

Timestamp:

11/17/15 13:55:11 (9 years ago)

Author:

mkommend

Message:

#2175: Added parameter for constant optimization iterations.

Location:

branches/DataAnalysis.ComplexityAnalyzer/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/MultiObjective

Files:

• PearsonRSquaredNestedTreeSizeEvaluator.cs (modified) (1 diff)
• PearsonRSquaredNumberOfVariablesEvaluator.cs (modified) (1 diff)
• PearsonRSquaredTreeComplexityEvaluator.cs (modified) (1 diff)
• SymbolicRegressionMultiObjectiveEvaluator.cs (modified) (5 diffs)
• SymbolicRegressionMultiObjectiveMeanSquaredErrorTreeSizeEvaluator.cs (modified) (1 diff)
• SymbolicRegressionMultiObjectivePearsonRSquaredTreeSizeEvaluator.cs (modified) (1 diff)
• SymbolicRegressionMultiObjectiveTrainingBestSolutionAnalyzer.cs (modified) (5 diffs)

branches/DataAnalysis.ComplexityAnalyzer/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/MultiObjective/PearsonRSquaredNestedTreeSizeEvaluator.cs

@@ -55 +55 @@
 
       if (UseConstantOptimization) {
-        SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, solution, problemData, rows, applyLinearScaling, 5, estimationLimits.Upper, estimationLimits.Lower);
+        SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, solution, problemData, rows, applyLinearScaling, ConstantOptimizationIterations, estimationLimits.Upper, estimationLimits.Lower);
       }
 

branches/DataAnalysis.ComplexityAnalyzer/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/MultiObjective/PearsonRSquaredNumberOfVariablesEvaluator.cs

@@ -55 +55 @@
 
       if (UseConstantOptimization) {
-        SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, solution, problemData, rows, applyLinearScaling, 5, estimationLimits.Upper, estimationLimits.Lower);
+        SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, solution, problemData, rows, applyLinearScaling, ConstantOptimizationIterations, estimationLimits.Upper, estimationLimits.Lower);
       }
       double[] qualities = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, ProblemDataParameter.ActualValue, rows, ApplyLinearScalingParameter.ActualValue.Value, DecimalPlaces);

branches/DataAnalysis.ComplexityAnalyzer/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/MultiObjective/PearsonRSquaredTreeComplexityEvaluator.cs

@@ -54 +54 @@
 
       if (UseConstantOptimization) {
-        SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, solution, problemData, rows, applyLinearScaling, 5, estimationLimits.Upper, estimationLimits.Lower);
+        SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, solution, problemData, rows, applyLinearScaling, ConstantOptimizationIterations, estimationLimits.Upper, estimationLimits.Lower);
       }
       double[] qualities = Calculate(interpreter, solution, estimationLimits.Lower, estimationLimits.Upper, problemData, rows, applyLinearScaling, DecimalPlaces);

branches/DataAnalysis.ComplexityAnalyzer/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/MultiObjective/SymbolicRegressionMultiObjectiveEvaluator.cs

@@ -32 +32 @@
     private const string DecimalPlacesParameterName = "Decimal Places";
     private const string UseConstantOptimizationParameterName = "Use constant optimization";
+    private const string ConstantOptimizationIterationsParameterName = "Constant optimization iterations";
 
     public IFixedValueParameter<IntValue> DecimalPlacesParameter {
@@ -40 +41 @@
     }
 
+    public IFixedValueParameter<IntValue> ConstantOptimizationIterationsParameter {
+      get { return (IFixedValueParameter<IntValue>)Parameters[ConstantOptimizationIterationsParameterName]; }
+    }
+
+
     public int DecimalPlaces {
       get { return DecimalPlacesParameter.Value.Value; }
@@ -47 +53 @@
       get { return UseConstantOptimizationParameter.Value.Value; }
       set { UseConstantOptimizationParameter.Value.Value = value; }
+    }
+    public int ConstantOptimizationIterations {
+      get { return ConstantOptimizationIterationsParameter.Value.Value; }
+      set { ConstantOptimizationIterationsParameter.Value.Value = value; }
     }
 
@@ -59 +69 @@
       Parameters.Add(new FixedValueParameter<IntValue>(DecimalPlacesParameterName, "The number of decimal places used for rounding the quality values.", new IntValue(5)) { Hidden = true });
       Parameters.Add(new FixedValueParameter<BoolValue>(UseConstantOptimizationParameterName, "", new BoolValue(false)));
+      Parameters.Add(new FixedValueParameter<IntValue>(ConstantOptimizationIterationsParameterName, "The number of iterations constant optimization should be applied.", new IntValue(5)));
     }
 
@@ -69 +80 @@
         Parameters.Add(new FixedValueParameter<IntValue>(DecimalPlacesParameterName, "The number of decimal places used for rounding the quality values.", new IntValue(-1)) { Hidden = true });
       }
+      if (!Parameters.ContainsKey(ConstantOptimizationIterationsParameterName)) {
+        Parameters.Add(new FixedValueParameter<IntValue>(ConstantOptimizationIterationsParameterName, "The number of iterations constant optimization should be applied.", new IntValue(5)));
+      }
     }
   }

branches/DataAnalysis.ComplexityAnalyzer/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/MultiObjective/SymbolicRegressionMultiObjectiveMeanSquaredErrorTreeSizeEvaluator.cs

@@ -54 +54 @@
 
       if (UseConstantOptimization) {
-        SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, solution, problemData, rows, applyLinearScaling, 5, estimationLimits.Upper, estimationLimits.Lower);
+        SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, solution, problemData, rows, applyLinearScaling, ConstantOptimizationIterations, estimationLimits.Upper, estimationLimits.Lower);
       }
 

branches/DataAnalysis.ComplexityAnalyzer/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/MultiObjective/SymbolicRegressionMultiObjectivePearsonRSquaredTreeSizeEvaluator.cs

@@ -54 +54 @@
 
       if (UseConstantOptimization) {
-        SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, solution, problemData, rows, applyLinearScaling, 5, estimationLimits.Upper, estimationLimits.Lower);
+        SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, solution, problemData, rows, applyLinearScaling, ConstantOptimizationIterations, estimationLimits.Upper, estimationLimits.Lower);
       }
       double[] qualities = Calculate(SymbolicDataAnalysisTreeInterpreterParameter.ActualValue, solution, EstimationLimitsParameter.ActualValue.Lower, EstimationLimitsParameter.ActualValue.Upper, ProblemDataParameter.ActualValue, rows, ApplyLinearScalingParameter.ActualValue.Value, DecimalPlaces);

branches/DataAnalysis.ComplexityAnalyzer/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/MultiObjective/SymbolicRegressionMultiObjectiveTrainingBestSolutionAnalyzer.cs

@@ -43 +43 @@
     private const string EstimationLimitsParameterName = "EstimationLimits";
     private const string MaximumSymbolicExpressionTreeLengthParameterName = "MaximumSymbolicExpressionTreeLength";
+    private const string ValidationPartitionParameterName = "ValidationPartition";
 
     #region parameter properties
@@ -57 +58 @@
       get { return (ILookupParameter<IntValue>)Parameters[MaximumSymbolicExpressionTreeLengthParameterName]; }
     }
+
+    public IValueLookupParameter<IntRange> ValidationPartitionParameter {
+      get { return (IValueLookupParameter<IntRange>)Parameters[ValidationPartitionParameterName]; }
+    }
     #endregion
 
@@ -64 +69 @@
     public SymbolicRegressionMultiObjectiveTrainingBestSolutionAnalyzer()
       : base() {
-      Parameters.Add(new LookupParameter<IRegressionProblemData>(ProblemDataParameterName, "The problem data for the symbolic regression solution."));
-      Parameters.Add(new LookupParameter<ISymbolicDataAnalysisExpressionTreeInterpreter>(SymbolicDataAnalysisTreeInterpreterParameterName, "The symbolic data analysis tree interpreter for the symbolic expression tree."));
-      Parameters.Add(new ValueLookupParameter<DoubleLimit>(EstimationLimitsParameterName, "The lower and upper limit for the estimated values produced by the symbolic regression model."));
-      Parameters.Add(new LookupParameter<IntValue>(MaximumSymbolicExpressionTreeLengthParameterName, "Maximal length of the symbolic expression."));
+      Parameters.Add(new LookupParameter<IRegressionProblemData>(ProblemDataParameterName, "The problem data for the symbolic regression solution.") { Hidden = true });
+      Parameters.Add(new LookupParameter<ISymbolicDataAnalysisExpressionTreeInterpreter>(SymbolicDataAnalysisTreeInterpreterParameterName, "The symbolic data analysis tree interpreter for the symbolic expression tree.") { Hidden = true });
+      Parameters.Add(new ValueLookupParameter<DoubleLimit>(EstimationLimitsParameterName, "The lower and upper limit for the estimated values produced by the symbolic regression model.") { Hidden = true });
+      Parameters.Add(new LookupParameter<IntValue>(MaximumSymbolicExpressionTreeLengthParameterName, "Maximal length of the symbolic expression.") { Hidden = true });
+      Parameters.Add(new ValueLookupParameter<IntRange>(ValidationPartitionParameterName, "The validation partition."));
     }
 
@@ -73 +79 @@
     private void AfterDeserialization() {
       if (!Parameters.ContainsKey(MaximumSymbolicExpressionTreeLengthParameterName))
-        Parameters.Add(new LookupParameter<IntValue>(MaximumSymbolicExpressionTreeLengthParameterName, "Maximal length of the symbolic expression."));
+        Parameters.Add(new LookupParameter<IntValue>(MaximumSymbolicExpressionTreeLengthParameterName, "Maximal length of the symbolic expression.") { Hidden = true });
+      if (!Parameters.ContainsKey(ValidationPartitionParameterName))
+        Parameters.Add(new ValueLookupParameter<IntRange>(ValidationPartitionParameterName, "The validation partition."));
     }
 
@@ -123 +131 @@
       }
 
+
+
       qualityToTreeSize.Rows.Clear();
       var trainingRow = new ScatterPlotDataRow("Training NMSE", "", sizeParetoFront.Select(x => new Point2D<double>(x.Model.SymbolicExpressionTree.Length, x.TrainingNormalizedMeanSquaredError)));
       trainingRow.VisualProperties.PointSize = 5;
-      var testRow = new ScatterPlotDataRow("Test NMSE", "", sizeParetoFront.Select(x => new Point2D<double>(x.Model.SymbolicExpressionTree.Length, x.TestNormalizedMeanSquaredError)));
-      testRow.VisualProperties.PointSize = 5;
       qualityToTreeSize.Rows.Add(trainingRow);
-      qualityToTreeSize.Rows.Add(testRow);
+
+      var validationPartition = ValidationPartitionParameter.ActualValue;
+      if (validationPartition.Size != 0) {
+        var problemData = ProblemDataParameter.ActualValue;
+        var validationIndizes = Enumerable.Range(validationPartition.Start, validationPartition.Size).ToList();
+        var targetValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, validationIndizes).ToList();
+        OnlineCalculatorError error;
+        var validationRow = new ScatterPlotDataRow("Validation NMSE", "",
+          sizeParetoFront.Select(x => new Point2D<double>(x.Model.SymbolicExpressionTree.Length,
+          OnlineNormalizedMeanSquaredErrorCalculator.Calculate(targetValues, x.GetEstimatedValues(validationIndizes), out error))));
+        validationRow.VisualProperties.PointSize = 5;
+        qualityToTreeSize.Rows.Add(validationRow);
+      }
 
       double trainingArea = sizeParetoFront.Select(s => s.Model.SymbolicExpressionTree.Length * s.TrainingNormalizedMeanSquaredError).Average();