Changeset 15833 for branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/GBM/GradientBoostingRegressionAlgorithm.cs

Timestamp:

03/08/18 10:57:03 (6 years ago)

Author:

bwerth

Message:

#2847: added handling of empty and underdetermined data sets

File:

• branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/GBM/GradientBoostingRegressionAlgorithm.cs (modified) (12 diffs)

branches/M5Regression/HeuristicLab.Algorithms.DataAnalysis/3.4/GBM/GradientBoostingRegressionAlgorithm.cs

@@ -45 +45 @@
   [Creatable(CreatableAttribute.Categories.DataAnalysisRegression, Priority = 350)]
   public class GradientBoostingRegressionAlgorithm : FixedDataAnalysisAlgorithm<IRegressionProblem> {
-
     #region ParameterNames
-
     private const string IterationsParameterName = "Iterations";
     private const string NuParameterName = "Nu";
@@ -58 +56 @@
     private const string StoreRunsParameterName = "StoreRuns";
     private const string RegressionAlgorithmSolutionResultParameterName = "RegressionAlgorithmResult";
-
     #endregion
 
     #region ParameterProperties
-
     public IFixedValueParameter<IntValue> IterationsParameter {
       get { return (IFixedValueParameter<IntValue>)Parameters[IterationsParameterName]; }
@@ -102 +98 @@
       get { return (IFixedValueParameter<BoolValue>)Parameters[StoreRunsParameterName]; }
     }
-
     #endregion
 
     #region Properties
-
     public int Iterations {
       get { return IterationsParameter.Value.Value; }
@@ -155 +149 @@
       set { RegressionAlgorithmSolutionResultParameter.Value.Value = value; }
     }
-
     #endregion
 
     [StorableConstructor]
     protected GradientBoostingRegressionAlgorithm(bool deserializing)
-      : base(deserializing) {
-    }
+      : base(deserializing) { }
 
     protected GradientBoostingRegressionAlgorithm(GradientBoostingRegressionAlgorithm original, Cloner cloner)
-      : base(original, cloner) {
-    }
+      : base(original, cloner) { }
 
     public override IDeepCloneable Clone(Cloner cloner) {
@@ -232 +223 @@
       var problemData = Problem.ProblemData;
       var targetVarName = problemData.TargetVariable;
-      var activeVariables = problemData.AllowedInputVariables.Concat(new string[] { problemData.TargetVariable });
+      var activeVariables = problemData.AllowedInputVariables.Concat(new string[] {problemData.TargetVariable});
       var modifiableDataset = new ModifiableDataset(
         activeVariables,
@@ -252 +243 @@
       List<IRegressionModel> models = new List<IRegressionModel>();
       try {
-
         // Loop until iteration limit reached or canceled.
         for (int i = 0; i < Iterations; i++) {
@@ -258 +248 @@
 
           modifiableDataset.RemoveVariable(targetVarName);
-          modifiableDataset.AddVariable(targetVarName, curY.Concat(curYTest));
+          modifiableDataset.AddVariable(targetVarName, curY.Concat(curYTest).ToList());
 
           SampleTrainingData(rand, modifiableDataset, rRows, problemData.Dataset, curY, problemData.TargetVariable, problemData.TrainingIndices); // all training indices from the original problem data are allowed 
@@ -301 +291 @@
 
             models.Add(model);
-
-
           }
 
@@ -363 +351 @@
       alglib.lrunpack(lm, out coefficients, out features);
 
-      var ensembleModel = new RegressionEnsembleModel(models, coefficients.Take(models.Count)) { AverageModelEstimates = false };
+      var ensembleModel = new RegressionEnsembleModel(models, coefficients.Take(models.Count)) {AverageModelEstimates = false};
       var ensembleSolution = (IRegressionEnsembleSolution)ensembleModel.CreateRegressionSolution(problemData);
       return ensembleSolution;
@@ -442 +430 @@
         prob.ProblemDataParameter.Value = problemData;
         return true;
-      } else return false;
+      }
+      else return false;
     }
 
@@ -478 +467 @@
           // NaN evaluations would not be critical but are problematic if we want to combine all symbolic models into a single symbolic model 
           if (symbRegSol == null ||
-            (symbRegSol.TrainingLowerEstimationLimitHits == 0 && symbRegSol.TrainingUpperEstimationLimitHits == 0 &&
-             symbRegSol.TestLowerEstimationLimitHits == 0 && symbRegSol.TestUpperEstimationLimitHits == 0) &&
-            symbRegSol.TrainingNaNEvaluations == 0 && symbRegSol.TestNaNEvaluations == 0) {
+              (symbRegSol.TrainingLowerEstimationLimitHits == 0 && symbRegSol.TrainingUpperEstimationLimitHits == 0 &&
+               symbRegSol.TestLowerEstimationLimitHits == 0 && symbRegSol.TestUpperEstimationLimitHits == 0) &&
+              symbRegSol.TrainingNaNEvaluations == 0 && symbRegSol.TestNaNEvaluations == 0) {
             model = sol.Model;
           }
@@ -499 +488 @@
         ((BoolValue)paramItem.Parameters["SetSeedRandomly"].ActualValue).Value = false;
         ((IntValue)paramItem.Parameters["Seed"].ActualValue).Value = seed;
-      } else {
+      }
+      else {
         throw new ArgumentException("Base learner does not have a seed parameter (algorithm {0})", alg.Name);
       }
-
     }
   }