Changeset 6740 for trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Classification/3.4/SingleObjective

Timestamp:

09/12/11 13:48:31 (13 years ago)

Author:

mkommend

Message:

#1597, #1609, #1640:

• Corrected TableFileParser to handle empty rows correctly.
• Refactored DataSet to store values in List<List> instead of a two-dimensional array.
• Enable importing and storing string and datetime values.
• Changed data access methods in dataset and adapted all concerning classes.
• Changed interpreter to store the variable values for all rows during the compilation step.

Location:

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

Files:

• SymbolicClassificationSingleObjectiveBoundedMeanSquaredErrorEvaluator.cs (modified) (1 diff)
• SymbolicClassificationSingleObjectiveMeanSquaredErrorEvaluator.cs (modified) (1 diff)
• SymbolicClassificationSingleObjectivePearsonRSquaredEvaluator.cs (modified) (1 diff)
• SymbolicClassificationSingleObjectiveProblem.cs (modified) (1 diff)

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

@@ -54 +54 @@
     public static double Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IClassificationProblemData problemData, IEnumerable<int> rows) {
       IEnumerable<double> estimatedValues = interpreter.GetSymbolicExpressionTreeValues(solution, problemData.Dataset, rows);
-      IEnumerable<double> originalValues = problemData.Dataset.GetEnumeratedVariableValues(problemData.TargetVariable, rows);
+      IEnumerable<double> originalValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
       IEnumerable<double> boundedEstimationValues = estimatedValues.LimitToRange(lowerEstimationLimit, upperEstimationLimit);
 

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

@@ -54 +54 @@
     public static double Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IClassificationProblemData problemData, IEnumerable<int> rows) {
       IEnumerable<double> estimatedValues = interpreter.GetSymbolicExpressionTreeValues(solution, problemData.Dataset, rows);
-      IEnumerable<double> originalValues = problemData.Dataset.GetEnumeratedVariableValues(problemData.TargetVariable, rows);
+      IEnumerable<double> originalValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
       IEnumerable<double> boundedEstimationValues = estimatedValues.LimitToRange(lowerEstimationLimit, upperEstimationLimit);
       OnlineCalculatorError errorState;

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

@@ -54 +54 @@
     public static double Calculate(ISymbolicDataAnalysisExpressionTreeInterpreter interpreter, ISymbolicExpressionTree solution, double lowerEstimationLimit, double upperEstimationLimit, IClassificationProblemData problemData, IEnumerable<int> rows) {
       IEnumerable<double> estimatedValues = interpreter.GetSymbolicExpressionTreeValues(solution, problemData.Dataset, rows);
-      IEnumerable<double> originalValues = problemData.Dataset.GetEnumeratedVariableValues(problemData.TargetVariable, rows);
+      IEnumerable<double> originalValues = problemData.Dataset.GetDoubleValues(problemData.TargetVariable, rows);
       OnlineCalculatorError errorState;
       double r2 = OnlinePearsonsRSquaredCalculator.Calculate(estimatedValues, originalValues, out errorState);

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

@@ -73 +73 @@
     private void UpdateEstimationLimits() {
       if (ProblemData.TrainingPartition.Start < ProblemData.TrainingPartition.End) {
-        var targetValues = ProblemData.Dataset.GetVariableValues(ProblemData.TargetVariable, ProblemData.TrainingPartition.Start, ProblemData.TrainingPartition.End);
+        var targetValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes).ToList();
         var mean = targetValues.Average();
         var range = targetValues.Max() - targetValues.Min();