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

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/Regression

Files:

• RegressionProblemData.cs (modified) (1 diff)
• RegressionSolutionBase.cs (modified) (3 diffs)

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionProblemData.cs

@@ -144 +144 @@
       dataset.Name = Path.GetFileName(fileName);
 
-      RegressionProblemData problemData = new RegressionProblemData(dataset, dataset.VariableNames.Skip(1), dataset.VariableNames.First());
+      RegressionProblemData problemData = new RegressionProblemData(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/Regression/RegressionSolutionBase.cs

@@ -127 +127 @@
         OnlineCalculatorError errorState;
         Add(new Result(TrainingMeanAbsoluteErrorResultName, "Mean of absolute errors of the model on the training partition", new DoubleValue()));
-        double trainingMAE = OnlineMeanAbsoluteErrorCalculator.Calculate(EstimatedTrainingValues, ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes), out errorState);
+        double trainingMAE = OnlineMeanAbsoluteErrorCalculator.Calculate(EstimatedTrainingValues, ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes), out errorState);
         TrainingMeanAbsoluteError = errorState == OnlineCalculatorError.None ? trainingMAE : double.NaN;
       }
@@ -134 +134 @@
         OnlineCalculatorError errorState;
         Add(new Result(TestMeanAbsoluteErrorResultName, "Mean of absolute errors of the model on the test partition", new DoubleValue()));
-        double testMAE = OnlineMeanAbsoluteErrorCalculator.Calculate(EstimatedTestValues, ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TestIndizes), out errorState);
+        double testMAE = OnlineMeanAbsoluteErrorCalculator.Calculate(EstimatedTestValues, ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TestIndizes), out errorState);
         TestMeanAbsoluteError = errorState == OnlineCalculatorError.None ? testMAE : double.NaN;
       }
@@ -142 +142 @@
     protected void CalculateResults() {
       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;