Changeset 14825 for branches/symbreg-factors-2650/HeuristicLab.Algorithms.DataAnalysis

Timestamp:

04/04/17 16:57:45 (7 years ago)

Author:

gkronber

Message:

#2650: merged r14769:14820 from trunk to branch to prepare for branch reintegration

Location:

branches/symbreg-factors-2650

Files:

• . (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4/CrossValidation.cs (modified) (1 diff)
• HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesAlgorithm.cs (modified) (1 diff)

branches/symbreg-factors-2650/HeuristicLab.Algorithms.DataAnalysis/3.4/CrossValidation.cs

@@ -451 +451 @@
       var aggregatedResults = new List<IResult>();
       foreach (KeyValuePair<string, List<IClassificationSolution>> solutions in resultSolutions) {
-        // clone manually to correctly clone references between cloned root objects 
-        Cloner cloner = new Cloner();
-        var problemDataClone = (IClassificationProblemData)cloner.Clone(Problem.ProblemData);
+        // at least one algorithm (GBT with logistic regression loss) produces a classification solution even though the original problem is a regression problem.
+        var targetVariable = solutions.Value.First().ProblemData.TargetVariable;
+        var problemDataClone = new ClassificationProblemData(Problem.ProblemData.Dataset,
+          Problem.ProblemData.AllowedInputVariables, targetVariable);
         // set partitions of problem data clone correctly
         problemDataClone.TrainingPartition.Start = SamplesStart.Value; problemDataClone.TrainingPartition.End = SamplesEnd.Value;

branches/symbreg-factors-2650/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesAlgorithm.cs

@@ -255 +255 @@
           var classificationProblemData = new ClassificationProblemData(problemData.Dataset,
             problemData.AllowedInputVariables, problemData.TargetVariable, problemData.Transformations);
-          classificationModel.RecalculateModelParameters(classificationProblemData, classificationProblemData.TrainingIndices);
+          classificationProblemData.TrainingPartition.Start = Problem.ProblemData.TrainingPartition.Start;
+          classificationProblemData.TrainingPartition.End = Problem.ProblemData.TrainingPartition.End;
+          classificationProblemData.TestPartition.Start = Problem.ProblemData.TestPartition.Start;
+          classificationProblemData.TestPartition.End = Problem.ProblemData.TestPartition.End;
+
+          classificationModel.SetThresholdsAndClassValues(new double[] { double.NegativeInfinity, 0.0 }, new []{ 0.0, 1.0 });
+
 
           var classificationSolution = new DiscriminantFunctionClassificationSolution(classificationModel, classificationProblemData);