Changeset 14869 for branches/RBFRegression/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees

Timestamp:

04/14/17 08:58:45 (8 years ago)

Author:

gkronber

Message:

#2699: merged changesets from trunk to branch

Location:

branches/RBFRegression/HeuristicLab.Algorithms.DataAnalysis/3.4

Files:

• . (modified) (1 prop)
• GradientBoostedTrees/GradientBoostedTreesAlgorithm.cs (modified) (4 diffs)
• GradientBoostedTrees/GradientBoostedTreesAlgorithmStatic.cs (modified) (1 diff)

branches/RBFRegression/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesAlgorithm.cs

@@ -21 +21 @@
 #endregion
 
-using System;
 using System.Linq;
 using System.Threading;
@@ -38 +37 @@
   [StorableClass]
   [Creatable(CreatableAttribute.Categories.DataAnalysisRegression, Priority = 125)]
-  public class GradientBoostedTreesAlgorithm : BasicAlgorithm {
-    public override Type ProblemType {
-      get { return typeof(IRegressionProblem); }
-    }
-    public new IRegressionProblem Problem {
-      get { return (IRegressionProblem)base.Problem; }
-      set { base.Problem = value; }
-    }
-
+  public class GradientBoostedTreesAlgorithm : FixedDataAnalysisAlgorithm<IRegressionProblem> {
     #region ParameterNames
     private const string IterationsParameterName = "Iterations";
@@ -204 +195 @@
       table.Rows.Add(new DataRow("Loss (train)"));
       table.Rows.Add(new DataRow("Loss (test)"));
+      table.Rows["Loss (train)"].VisualProperties.StartIndexZero = true;
+      table.Rows["Loss (test)"].VisualProperties.StartIndexZero = true;
+
       Results.Add(new Result("Qualities", table));
       var curLoss = new DoubleValue();
@@ -263 +257 @@
           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);

branches/RBFRegression/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/GradientBoostedTreesAlgorithmStatic.cs

@@ -148 +148 @@
     // for custom stepping & termination
     public static IGbmState CreateGbmState(IRegressionProblemData problemData, ILossFunction lossFunction, uint randSeed, int maxSize = 3, double r = 0.66, double m = 0.5, double nu = 0.01) {
+      // check input variables. Only double variables are allowed.
+      var invalidInputs =
+        problemData.AllowedInputVariables.Where(name => !problemData.Dataset.VariableHasType<double>(name));
+      if (invalidInputs.Any())
+        throw new NotSupportedException("Gradient tree boosting only supports real-valued variables. Unsupported inputs: " + string.Join(", ", invalidInputs));
+
       return new GbmState(problemData, lossFunction, randSeed, maxSize, r, m, nu);
     }