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

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/3.4/Implementation/Classification

Files:

• ClassificationProblemData.cs (modified) (3 diffs)
• ClassificationSolutionBase.cs (modified) (1 diff)
• DiscriminantFunctionClassificationSolutionBase.cs (modified) (3 diffs)

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblemData.cs

@@ -226 +226 @@
       get {
         if (classValues == null) {
-          classValues = Dataset.GetEnumeratedVariableValues(TargetVariableParameter.Value.Value).Distinct().ToList();
+          classValues = Dataset.GetDoubleValues(TargetVariableParameter.Value.Value).Distinct().ToList();
           classValues.Sort();
         }
@@ -291 +291 @@
     private static IEnumerable<string> CheckVariablesForPossibleTargetVariables(Dataset dataset) {
       int maxSamples = Math.Min(InspectedRowsToDetermineTargets, dataset.Rows);
-      var validTargetVariables = (from v in dataset.VariableNames
-                                  let distinctValues = dataset.GetEnumeratedVariableValues(v)
+      var validTargetVariables = (from v in dataset.DoubleVariables
+                                  let distinctValues = dataset.GetDoubleValues(v)
                                     .Take(maxSamples)
                                     .Distinct()
@@ -410 +410 @@
       dataset.Name = Path.GetFileName(fileName);
 
-      ClassificationProblemData problemData = new ClassificationProblemData(dataset, dataset.VariableNames.Skip(1), dataset.VariableNames.First());
+      ClassificationProblemData problemData = new ClassificationProblemData(dataset, dataset.DoubleVariables.Skip(1), dataset.DoubleVariables.First());
       problemData.Name = "Data imported from " + Path.GetFileName(fileName);
       return problemData;

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationSolutionBase.cs

@@ -67 +67 @@
     protected void CalculateResults() {
       double[] estimatedTrainingClassValues = EstimatedTrainingClassValues.ToArray(); // cache values
-      double[] originalTrainingClassValues = ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes).ToArray();
+      double[] originalTrainingClassValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes).ToArray();
       double[] estimatedTestClassValues = EstimatedTestClassValues.ToArray(); // cache values
-      double[] originalTestClassValues = ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TestIndizes).ToArray();
+      double[] originalTestClassValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TestIndizes).ToArray();
 
       OnlineCalculatorError errorState;

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/DiscriminantFunctionClassificationSolutionBase.cs

@@ -103 +103 @@
     protected void CalculateRegressionResults() {
       double[] estimatedTrainingValues = EstimatedTrainingValues.ToArray(); // cache values
-      double[] originalTrainingValues = ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes).ToArray();
+      double[] originalTrainingValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes).ToArray();
       double[] estimatedTestValues = EstimatedTestValues.ToArray(); // cache values
-      double[] originalTestValues = ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TestIndizes).ToArray();
+      double[] originalTestValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TestIndizes).ToArray();
 
       OnlineCalculatorError errorState;
@@ -132 +132 @@
       double[] classValues;
       double[] thresholds;
-      var targetClassValues = ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes);
+      var targetClassValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes);
       AccuracyMaximizationThresholdCalculator.CalculateThresholds(ProblemData, EstimatedTrainingValues, targetClassValues, out classValues, out thresholds);
 
@@ -141 +141 @@
       double[] classValues;
       double[] thresholds;
-      var targetClassValues = ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes);
+      var targetClassValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes);
       NormalDistributionCutPointsThresholdCalculator.CalculateThresholds(ProblemData, EstimatedTrainingValues, targetClassValues, out classValues, out thresholds);