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

Files:

• RegressionSolutionErrorCharacteristicsCurveView.cs (modified) (2 diffs)
• RegressionSolutionEstimatedValuesView.cs (modified) (1 diff)
• RegressionSolutionLineChartView.cs (modified) (1 diff)
• RegressionSolutionScatterPlotView.cs (modified) (2 diffs)

trunk/sources/HeuristicLab.Problems.DataAnalysis.Views/3.4/Regression/RegressionSolutionErrorCharacteristicsCurveView.cs

@@ -164 +164 @@
       switch (cmbSamples.SelectedItem.ToString()) {
         case TrainingSamples:
-          originalValues = ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes);
+          originalValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes);
           break;
         case TestSamples:
-          originalValues = ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TestIndizes);
+          originalValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TestIndizes);
           break;
         case AllSamples:
-          originalValues = ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable);
+          originalValues = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable);
           break;
         default:
@@ -197 +197 @@
 
     protected IEnumerable<double> GetMeanModelEstimatedValues(IEnumerable<double> originalValues) {
-      double averageTrainingTarget = ProblemData.Dataset.GetEnumeratedVariableValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes).Average();
+      double averageTrainingTarget = ProblemData.Dataset.GetDoubleValues(ProblemData.TargetVariable, ProblemData.TrainingIndizes).Average();
       return Enumerable.Repeat(averageTrainingTarget, originalValues.Count());
     }

trunk/sources/HeuristicLab.Problems.DataAnalysis.Views/3.4/Regression/RegressionSolutionEstimatedValuesView.cs

@@ -88 +88 @@
           string[,] values = new string[Content.ProblemData.Dataset.Rows, 7];
 
-          double[] target = Content.ProblemData.Dataset.GetVariableValues(Content.ProblemData.TargetVariable);
+          double[] target = Content.ProblemData.Dataset.GetDoubleValues(Content.ProblemData.TargetVariable).ToArray();
           var estimated = Content.EstimatedValues.GetEnumerator();
           var estimated_training = Content.EstimatedTrainingValues.GetEnumerator();

trunk/sources/HeuristicLab.Problems.DataAnalysis.Views/3.4/Regression/RegressionSolutionLineChartView.cs

@@ -67 +67 @@
         this.chart.Series[TARGETVARIABLE_SERIES_NAME].ChartType = SeriesChartType.FastLine;
         this.chart.Series[TARGETVARIABLE_SERIES_NAME].Points.DataBindXY(Enumerable.Range(0, Content.ProblemData.Dataset.Rows).ToArray(),
-          Content.ProblemData.Dataset.GetVariableValues(Content.ProblemData.TargetVariable));
+          Content.ProblemData.Dataset.GetDoubleValues(Content.ProblemData.TargetVariable).ToArray());
 
         this.chart.Series.Add(ESTIMATEDVALUES_TRAINING_SERIES_NAME);

trunk/sources/HeuristicLab.Problems.DataAnalysis.Views/3.4/Regression/RegressionSolutionScatterPlotView.cs

@@ -130 +130 @@
         if (this.chart.Series[ALL_SERIES].Points.Count > 0)
           this.chart.Series[ALL_SERIES].Points.DataBindXY(Content.EstimatedValues.ToArray(), "",
-            dataset.GetVariableValues(targetVariableName), "");
+            dataset.GetDoubleValues(targetVariableName).ToArray(), "");
         if (this.chart.Series[TRAINING_SERIES].Points.Count > 0)
           this.chart.Series[TRAINING_SERIES].Points.DataBindXY(Content.EstimatedTrainingValues.ToArray(), "",
-            dataset.GetEnumeratedVariableValues(targetVariableName, Content.ProblemData.TrainingIndizes).ToArray(), "");
+            dataset.GetDoubleValues(targetVariableName, Content.ProblemData.TrainingIndizes).ToArray(), "");
         if (this.chart.Series[TEST_SERIES].Points.Count > 0)
           this.chart.Series[TEST_SERIES].Points.DataBindXY(Content.EstimatedTestValues.ToArray(), "",
-           dataset.GetEnumeratedVariableValues(targetVariableName, Content.ProblemData.TestIndizes).ToArray(), "");
-
-        double max = Content.EstimatedTrainingValues.Concat(Content.EstimatedTestValues.Concat(Content.EstimatedValues.Concat(dataset.GetVariableValues(targetVariableName)))).Max();
-        double min = Content.EstimatedTrainingValues.Concat(Content.EstimatedTestValues.Concat(Content.EstimatedValues.Concat(dataset.GetVariableValues(targetVariableName)))).Min();
+           dataset.GetDoubleValues(targetVariableName, Content.ProblemData.TestIndizes).ToArray(), "");
+
+        double max = Content.EstimatedTrainingValues.Concat(Content.EstimatedTestValues.Concat(Content.EstimatedValues.Concat(dataset.GetDoubleValues(targetVariableName)))).Max();
+        double min = Content.EstimatedTrainingValues.Concat(Content.EstimatedTestValues.Concat(Content.EstimatedValues.Concat(dataset.GetDoubleValues(targetVariableName)))).Min();
 
         max = max + 0.2 * Math.Abs(max);
@@ -177 +177 @@
           case ALL_SERIES:
             predictedValues = Content.EstimatedValues.ToArray();
-            targetValues = Content.ProblemData.Dataset.GetVariableValues(targetVariableName);
+            targetValues = Content.ProblemData.Dataset.GetDoubleValues(targetVariableName).ToArray();
             break;
           case TRAINING_SERIES:
             predictedValues = Content.EstimatedTrainingValues.ToArray();
-            targetValues = Content.ProblemData.Dataset.GetEnumeratedVariableValues(targetVariableName, Content.ProblemData.TrainingIndizes).ToArray();
+            targetValues = Content.ProblemData.Dataset.GetDoubleValues(targetVariableName, Content.ProblemData.TrainingIndizes).ToArray();
             break;
           case TEST_SERIES:
             predictedValues = Content.EstimatedTestValues.ToArray();
-            targetValues = Content.ProblemData.Dataset.GetEnumeratedVariableValues(targetVariableName, Content.ProblemData.TestIndizes).ToArray();
+            targetValues = Content.ProblemData.Dataset.GetDoubleValues(targetVariableName, Content.ProblemData.TestIndizes).ToArray();
             break;
         }