Changeset 6784 for branches/GP.Grammar.Editor/HeuristicLab.Problems.DataAnalysis/3.4/Implementation

Timestamp:

09/16/11 12:00:36 (13 years ago)

Author:

mkommend

Message:

#1479: Integrated trunk changes.

Location:

branches/GP.Grammar.Editor/HeuristicLab.Problems.DataAnalysis/3.4/Implementation

Files:

• Classification/ClassificationProblemData.cs (modified) (3 diffs)
• Classification/ClassificationSolutionBase.cs (modified) (1 diff)
• Classification/DiscriminantFunctionClassificationSolutionBase.cs (modified) (3 diffs)
• Clustering/ClusteringProblemData.cs (modified) (2 diffs)
• DataAnalysisProblemData.cs (modified) (1 diff)
• Regression/RegressionProblemData.cs (modified) (1 diff)
• Regression/RegressionSolutionBase.cs (modified) (3 diffs)

branches/GP.Grammar.Editor/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;

branches/GP.Grammar.Editor/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;

branches/GP.Grammar.Editor/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);
 

branches/GP.Grammar.Editor/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Clustering/ClusteringProblemData.cs

@@ -20 +20 @@
 #endregion
 
-using System;
 using System.Collections.Generic;
 using System.IO;
-using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
-using HeuristicLab.Data;
-using HeuristicLab.Parameters;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
 
@@ -103 +99 @@
       dataset.Name = Path.GetFileName(fileName);
 
-      ClusteringProblemData problemData = new ClusteringProblemData(dataset, dataset.VariableNames);
+      ClusteringProblemData problemData = new ClusteringProblemData(dataset, dataset.DoubleVariables);
       problemData.Name = "Data imported from " + Path.GetFileName(fileName);
       return problemData;

branches/GP.Grammar.Editor/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/DataAnalysisProblemData.cs

@@ -116 +116 @@
       if (allowedInputVariables == null) throw new ArgumentNullException("The allowedInputVariables must not be null.");
 
-      if (allowedInputVariables.Except(dataset.VariableNames).Any())
-        throw new ArgumentException("All allowed input variables must be present in the dataset.");
+      if (allowedInputVariables.Except(dataset.DoubleVariables).Any())
+        throw new ArgumentException("All allowed input variables must be present in the dataset and of type double.");
 
-      var inputVariables = new CheckedItemList<StringValue>(dataset.VariableNames.Select(x => new StringValue(x)));
+      var inputVariables = new CheckedItemList<StringValue>(dataset.DoubleVariables.Select(x => new StringValue(x)));
       foreach (StringValue x in inputVariables)
         inputVariables.SetItemCheckedState(x, allowedInputVariables.Contains(x.Value));

branches/GP.Grammar.Editor/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;

branches/GP.Grammar.Editor/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;