Changeset 17226 for branches/2521_ProblemRefactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest

Timestamp:

08/29/19 15:57:35 (5 years ago)

Author:

mkommend

Message:

#2521: Merged trunk changes into problem refactoring branch.

Location:

branches/2521_ProblemRefactoring

Files:

• . (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4 (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/ModelCreation.cs (copied) (copied from trunk/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/ModelCreation.cs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestClassification.cs (modified) (11 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestClassificationSolution.cs (modified) (1 diff)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModel.cs (modified) (9 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModelFull.cs (copied) (copied from trunk/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModelFull.cs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModelSurrogate.cs (copied) (copied from trunk/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModelSurrogate.cs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestRegression.cs (modified) (10 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestRegressionSolution.cs (modified) (1 diff)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestUtil.cs (modified) (3 diffs)

branches/2521_ProblemRefactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestClassification.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2019 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -20 +20 @@
 #endregion
 
+using System.Collections.Generic;
+using System.Linq;
 using System.Threading;
+using HEAL.Attic;
+using HeuristicLab.Algorithms.DataAnalysis.RandomForest;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -26 +30 @@
 using HeuristicLab.Optimization;
 using HeuristicLab.Parameters;
-using HEAL.Attic;
 using HeuristicLab.Problems.DataAnalysis;
 
@@ -43 +46 @@
     private const string SeedParameterName = "Seed";
     private const string SetSeedRandomlyParameterName = "SetSeedRandomly";
-    private const string CreateSolutionParameterName = "CreateSolution";
+    private const string ModelCreationParameterName = "ModelCreation";
 
     #region parameter properties
@@ -61 +64 @@
       get { return (IFixedValueParameter<BoolValue>)Parameters[SetSeedRandomlyParameterName]; }
     }
-    public IFixedValueParameter<BoolValue> CreateSolutionParameter {
-      get { return (IFixedValueParameter<BoolValue>)Parameters[CreateSolutionParameterName]; }
+    private IFixedValueParameter<EnumValue<ModelCreation>> ModelCreationParameter {
+      get { return (IFixedValueParameter<EnumValue<ModelCreation>>)Parameters[ModelCreationParameterName]; }
     }
     #endregion
@@ -86 +89 @@
       set { SetSeedRandomlyParameter.Value.Value = value; }
     }
-    public bool CreateSolution {
-      get { return CreateSolutionParameter.Value.Value; }
-      set { CreateSolutionParameter.Value.Value = value; }
+    public ModelCreation ModelCreation {
+      get { return ModelCreationParameter.Value.Value; }
+      set { ModelCreationParameter.Value.Value = value; }
     }
     #endregion
@@ -105 +108 @@
       Parameters.Add(new FixedValueParameter<IntValue>(SeedParameterName, "The random seed used to initialize the new pseudo random number generator.", new IntValue(0)));
       Parameters.Add(new FixedValueParameter<BoolValue>(SetSeedRandomlyParameterName, "True if the random seed should be set to a random value, otherwise false.", new BoolValue(true)));
-      Parameters.Add(new FixedValueParameter<BoolValue>(CreateSolutionParameterName, "Flag that indicates if a solution should be produced at the end of the run", new BoolValue(true)));
-      Parameters[CreateSolutionParameterName].Hidden = true;
+      Parameters.Add(new FixedValueParameter<EnumValue<ModelCreation>>(ModelCreationParameterName, "Defines the results produced at the end of the run (Surrogate => Less disk space, lazy recalculation of model)", new EnumValue<ModelCreation>(ModelCreation.Model)));
+      Parameters[ModelCreationParameterName].Hidden = true;
 
       Problem = new ClassificationProblem();
@@ -121 +124 @@
       if (!Parameters.ContainsKey((SetSeedRandomlyParameterName)))
         Parameters.Add(new FixedValueParameter<BoolValue>(SetSeedRandomlyParameterName, "True if the random seed should be set to a random value, otherwise false.", new BoolValue(true)));
-      if (!Parameters.ContainsKey(CreateSolutionParameterName)) {
-        Parameters.Add(new FixedValueParameter<BoolValue>(CreateSolutionParameterName, "Flag that indicates if a solution should be produced at the end of the run", new BoolValue(true)));
-        Parameters[CreateSolutionParameterName].Hidden = true;
+
+      // parameter type has been changed
+      if (Parameters.ContainsKey("CreateSolution")) {
+        var createSolutionParam = Parameters["CreateSolution"] as FixedValueParameter<BoolValue>;
+        Parameters.Remove(createSolutionParam);
+
+        ModelCreation value = createSolutionParam.Value.Value ? ModelCreation.Model : ModelCreation.QualityOnly;
+        Parameters.Add(new FixedValueParameter<EnumValue<ModelCreation>>(ModelCreationParameterName, "Defines the results produced at the end of the run (Surrogate => Less disk space, lazy recalculation of model)", new EnumValue<ModelCreation>(value)));
+        Parameters[ModelCreationParameterName].Hidden = true;
+      } else if (!Parameters.ContainsKey(ModelCreationParameterName)) {
+        // very old version contains neither ModelCreationParameter nor CreateSolutionParameter
+        Parameters.Add(new FixedValueParameter<EnumValue<ModelCreation>>(ModelCreationParameterName, "Defines the results produced at the end of the run (Surrogate => Less disk space, lazy recalculation of model)", new EnumValue<ModelCreation>(ModelCreation.Model)));
+        Parameters[ModelCreationParameterName].Hidden = true;
       }
       #endregion
@@ -138 +151 @@
 
       var model = CreateRandomForestClassificationModel(Problem.ProblemData, NumberOfTrees, R, M, Seed, out rmsError, out relClassificationError, out outOfBagRmsError, out outOfBagRelClassificationError);
+
       Results.Add(new Result("Root mean square error", "The root of the mean of squared errors of the random forest regression solution on the training set.", new DoubleValue(rmsError)));
       Results.Add(new Result("Relative classification error", "Relative classification error of the random forest regression solution on the training set.", new PercentValue(relClassificationError)));
@@ -143 +157 @@
       Results.Add(new Result("Relative classification error (out-of-bag)", "The out-of-bag relative classification error  of the random forest regression solution.", new PercentValue(outOfBagRelClassificationError)));
 
-      if (CreateSolution) {
-        var solution = new RandomForestClassificationSolution(model, (IClassificationProblemData)Problem.ProblemData.Clone());
+
+      IClassificationSolution solution = null;
+      if (ModelCreation == ModelCreation.Model) {
+        solution = model.CreateClassificationSolution(Problem.ProblemData);
+      } else if (ModelCreation == ModelCreation.SurrogateModel) {
+        var problemData = Problem.ProblemData;
+        var surrogateModel = new RandomForestModelSurrogate(model, problemData.TargetVariable, problemData, Seed, NumberOfTrees, R, M, problemData.ClassValues.ToArray());
+
+        solution = surrogateModel.CreateClassificationSolution(problemData);
+      }
+
+      if (solution != null) {
         Results.Add(new Result(RandomForestClassificationModelResultName, "The random forest classification solution.", solution));
       }
@@ -157 +181 @@
     }
 
-    public static RandomForestModel CreateRandomForestClassificationModel(IClassificationProblemData problemData, int nTrees, double r, double m, int seed,
+    public static RandomForestModelFull CreateRandomForestClassificationModel(IClassificationProblemData problemData, int nTrees, double r, double m, int seed,
+ out double rmsError, out double avgRelError, out double outOfBagRmsError, out double outOfBagAvgRelError) {
+      var model = CreateRandomForestClassificationModel(problemData, problemData.TrainingIndices, nTrees, r, m, seed, out rmsError, out avgRelError, out outOfBagRmsError, out outOfBagAvgRelError);
+      return model;
+    }
+
+    public static RandomForestModelFull CreateRandomForestClassificationModel(IClassificationProblemData problemData, IEnumerable<int> trainingIndices, int nTrees, double r, double m, int seed,
       out double rmsError, out double relClassificationError, out double outOfBagRmsError, out double outOfBagRelClassificationError) {
-      return RandomForestModel.CreateClassificationModel(problemData, nTrees, r, m, seed,
-       rmsError: out rmsError, relClassificationError: out relClassificationError, outOfBagRmsError: out outOfBagRmsError, outOfBagRelClassificationError: out outOfBagRelClassificationError);
+
+      var variables = problemData.AllowedInputVariables.Concat(new string[] { problemData.TargetVariable });
+      double[,] inputMatrix = problemData.Dataset.ToArray(variables, trainingIndices);
+
+      var classValues = problemData.ClassValues.ToArray();
+      int nClasses = classValues.Length;
+
+      // map original class values to values [0..nClasses-1]
+      var classIndices = new Dictionary<double, double>();
+      for (int i = 0; i < nClasses; i++) {
+        classIndices[classValues[i]] = i;
+      }
+
+      int nRows = inputMatrix.GetLength(0);
+      int nColumns = inputMatrix.GetLength(1);
+      for (int row = 0; row < nRows; row++) {
+        inputMatrix[row, nColumns - 1] = classIndices[inputMatrix[row, nColumns - 1]];
+      }
+
+      alglib.dfreport rep;
+      var dForest = RandomForestUtil.CreateRandomForestModel(seed, inputMatrix, nTrees, r, m, nClasses, out rep);
+
+      rmsError = rep.rmserror;
+      outOfBagRmsError = rep.oobrmserror;
+      relClassificationError = rep.relclserror;
+      outOfBagRelClassificationError = rep.oobrelclserror;
+
+      return new RandomForestModelFull(dForest, problemData.TargetVariable, problemData.AllowedInputVariables, classValues);
     }
     #endregion

branches/2521_ProblemRefactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestClassificationSolution.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2019 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/2521_ProblemRefactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModel.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2019 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -23 +23 @@
 using System.Collections.Generic;
 using System.Linq;
+using HEAL.Attic;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
 using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
-using HEAL.Attic;
 using HeuristicLab.Problems.DataAnalysis;
 using HeuristicLab.Problems.DataAnalysis.Symbolic;
@@ -34 +34 @@
   /// Represents a random forest model for regression and classification
   /// </summary>
-  [StorableType("A4F688CD-1F42-4103-8449-7DE52AEF6C69")]
+  [Obsolete("This class only exists for backwards compatibility reasons for stored models with the XML Persistence. Use RFModelSurrogate or RFModelFull instead.")]
+  [StorableType("9AA4CCC2-CD75-4471-8DF6-949E5B783642")]
   [Item("RandomForestModel", "Represents a random forest for regression and classification.")]
   public sealed class RandomForestModel : ClassificationModel, IRandomForestModel {
@@ -139 +140 @@
     public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = dataset.ToArray(AllowedInputVariables, rows);
-      AssertInputMatrix(inputData);
+      RandomForestUtil.AssertInputMatrix(inputData);
 
       int n = inputData.GetLength(0);
@@ -157 +158 @@
     public IEnumerable<double> GetEstimatedVariances(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = dataset.ToArray(AllowedInputVariables, rows);
-      AssertInputMatrix(inputData);
+      RandomForestUtil.AssertInputMatrix(inputData);
 
       int n = inputData.GetLength(0);
@@ -175 +176 @@
     public override IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = dataset.ToArray(AllowedInputVariables, rows);
-      AssertInputMatrix(inputData);
+      RandomForestUtil.AssertInputMatrix(inputData);
 
       int n = inputData.GetLength(0);
@@ -315 +316 @@
 
       alglib.dfreport rep;
-      var dForest = CreateRandomForestModel(seed, inputMatrix, nTrees, r, m, 1, out rep);
+      var dForest = RandomForestUtil.CreateRandomForestModel(seed, inputMatrix, nTrees, r, m, 1, out rep);
 
       rmsError = rep.rmserror;
@@ -353 +354 @@
 
       alglib.dfreport rep;
-      var dForest = CreateRandomForestModel(seed, inputMatrix, nTrees, r, m, nClasses, out rep);
+      var dForest = RandomForestUtil.CreateRandomForestModel(seed, inputMatrix, nTrees, r, m, nClasses, out rep);
 
       rmsError = rep.rmserror;
@@ -361 +362 @@
 
       return new RandomForestModel(problemData.TargetVariable, dForest, seed, problemData, nTrees, r, m, classValues);
-    }
-
-    private static alglib.decisionforest CreateRandomForestModel(int seed, double[,] inputMatrix, int nTrees, double r, double m, int nClasses, out alglib.dfreport rep) {
-      AssertParameters(r, m);
-      AssertInputMatrix(inputMatrix);
-
-      int info = 0;
-      alglib.math.rndobject = new System.Random(seed);
-      var dForest = new alglib.decisionforest();
-      rep = new alglib.dfreport();
-      int nRows = inputMatrix.GetLength(0);
-      int nColumns = inputMatrix.GetLength(1);
-      int sampleSize = Math.Max((int)Math.Round(r * nRows), 1);
-      int nFeatures = Math.Max((int)Math.Round(m * (nColumns - 1)), 1);
-
-      alglib.dforest.dfbuildinternal(inputMatrix, nRows, nColumns - 1, nClasses, nTrees, sampleSize, nFeatures, alglib.dforest.dfusestrongsplits + alglib.dforest.dfuseevs, ref info, dForest.innerobj, rep.innerobj);
-      if (info != 1) throw new ArgumentException("Error in calculation of random forest model");
-      return dForest;
-    }
-
-    private static void AssertParameters(double r, double m) {
-      if (r <= 0 || r > 1) throw new ArgumentException("The R parameter for random forest modeling must be between 0 and 1.");
-      if (m <= 0 || m > 1) throw new ArgumentException("The M parameter for random forest modeling must be between 0 and 1.");
-    }
-
-    private static void AssertInputMatrix(double[,] inputMatrix) {
-      if (inputMatrix.ContainsNanOrInfinity())
-        throw new NotSupportedException("Random forest modeling does not support NaN or infinity values in the input dataset.");
     }
 

branches/2521_ProblemRefactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestRegression.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2019 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -20 +20 @@
 #endregion
 
+using System.Collections.Generic;
+using System.Linq;
 using System.Threading;
+using HEAL.Attic;
+using HeuristicLab.Algorithms.DataAnalysis.RandomForest;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -26 +30 @@
 using HeuristicLab.Optimization;
 using HeuristicLab.Parameters;
-using HEAL.Attic;
 using HeuristicLab.Problems.DataAnalysis;
 
@@ -43 +46 @@
     private const string SeedParameterName = "Seed";
     private const string SetSeedRandomlyParameterName = "SetSeedRandomly";
-    private const string CreateSolutionParameterName = "CreateSolution";
+    private const string ModelCreationParameterName = "ModelCreation";
 
     #region parameter properties
@@ -61 +64 @@
       get { return (IFixedValueParameter<BoolValue>)Parameters[SetSeedRandomlyParameterName]; }
     }
-    public IFixedValueParameter<BoolValue> CreateSolutionParameter {
-      get { return (IFixedValueParameter<BoolValue>)Parameters[CreateSolutionParameterName]; }
+    private IFixedValueParameter<EnumValue<ModelCreation>> ModelCreationParameter {
+      get { return (IFixedValueParameter<EnumValue<ModelCreation>>)Parameters[ModelCreationParameterName]; }
     }
     #endregion
@@ -86 +89 @@
       set { SetSeedRandomlyParameter.Value.Value = value; }
     }
-    public bool CreateSolution {
-      get { return CreateSolutionParameter.Value.Value; }
-      set { CreateSolutionParameter.Value.Value = value; }
+    public ModelCreation ModelCreation {
+      get { return ModelCreationParameter.Value.Value; }
+      set { ModelCreationParameter.Value.Value = value; }
     }
     #endregion
@@ -104 +107 @@
       Parameters.Add(new FixedValueParameter<IntValue>(SeedParameterName, "The random seed used to initialize the new pseudo random number generator.", new IntValue(0)));
       Parameters.Add(new FixedValueParameter<BoolValue>(SetSeedRandomlyParameterName, "True if the random seed should be set to a random value, otherwise false.", new BoolValue(true)));
-      Parameters.Add(new FixedValueParameter<BoolValue>(CreateSolutionParameterName, "Flag that indicates if a solution should be produced at the end of the run", new BoolValue(true)));
-      Parameters[CreateSolutionParameterName].Hidden = true;
+      Parameters.Add(new FixedValueParameter<EnumValue<ModelCreation>>(ModelCreationParameterName, "Defines the results produced at the end of the run (Surrogate => Less disk space, lazy recalculation of model)", new EnumValue<ModelCreation>(ModelCreation.Model)));
+      Parameters[ModelCreationParameterName].Hidden = true;
 
       Problem = new RegressionProblem();
@@ -120 +123 @@
       if (!Parameters.ContainsKey((SetSeedRandomlyParameterName)))
         Parameters.Add(new FixedValueParameter<BoolValue>(SetSeedRandomlyParameterName, "True if the random seed should be set to a random value, otherwise false.", new BoolValue(true)));
-      if (!Parameters.ContainsKey(CreateSolutionParameterName)) {
-        Parameters.Add(new FixedValueParameter<BoolValue>(CreateSolutionParameterName, "Flag that indicates if a solution should be produced at the end of the run", new BoolValue(true)));
-        Parameters[CreateSolutionParameterName].Hidden = true;
+
+      // parameter type has been changed
+      if (Parameters.ContainsKey("CreateSolution")) {
+        var createSolutionParam = Parameters["CreateSolution"] as FixedValueParameter<BoolValue>;
+        Parameters.Remove(createSolutionParam);
+
+        ModelCreation value = createSolutionParam.Value.Value ? ModelCreation.Model : ModelCreation.QualityOnly;
+        Parameters.Add(new FixedValueParameter<EnumValue<ModelCreation>>(ModelCreationParameterName, "Defines the results produced at the end of the run (Surrogate => Less disk space, lazy recalculation of model)", new EnumValue<ModelCreation>(value)));
+        Parameters[ModelCreationParameterName].Hidden = true;
+      } else if (!Parameters.ContainsKey(ModelCreationParameterName)) {
+        // very old version contains neither ModelCreationParameter nor CreateSolutionParameter
+        Parameters.Add(new FixedValueParameter<EnumValue<ModelCreation>>(ModelCreationParameterName, "Defines the results produced at the end of the run (Surrogate => Less disk space, lazy recalculation of model)", new EnumValue<ModelCreation>(ModelCreation.Model)));
+        Parameters[ModelCreationParameterName].Hidden = true;
       }
       #endregion
@@ -143 +156 @@
       Results.Add(new Result("Average relative error (out-of-bag)", "The out-of-bag average of relative errors of the random forest regression solution.", new PercentValue(outOfBagAvgRelError)));
 
-      if (CreateSolution) {
-        var solution = new RandomForestRegressionSolution(model, (IRegressionProblemData)Problem.ProblemData.Clone());
+      IRegressionSolution solution = null;
+      if (ModelCreation == ModelCreation.Model) {
+        solution = model.CreateRegressionSolution(Problem.ProblemData);
+      } else if (ModelCreation == ModelCreation.SurrogateModel) {
+        var problemData = Problem.ProblemData;
+        var surrogateModel = new RandomForestModelSurrogate(model, problemData.TargetVariable, problemData, Seed, NumberOfTrees, R, M);
+        solution = surrogateModel.CreateRegressionSolution(problemData);
+      }
+
+      if (solution != null) {
         Results.Add(new Result(RandomForestRegressionModelResultName, "The random forest regression solution.", solution));
       }
     }
+
 
     // keep for compatibility with old API
@@ -157 +179 @@
     }
 
-    public static RandomForestModel CreateRandomForestRegressionModel(IRegressionProblemData problemData, int nTrees,
-      double r, double m, int seed,
-      out double rmsError, out double avgRelError, out double outOfBagRmsError, out double outOfBagAvgRelError) {
-      return RandomForestModel.CreateRegressionModel(problemData, nTrees, r, m, seed,
-        rmsError: out rmsError, avgRelError: out avgRelError, outOfBagRmsError: out outOfBagRmsError, outOfBagAvgRelError: out outOfBagAvgRelError);
+    public static RandomForestModelFull CreateRandomForestRegressionModel(IRegressionProblemData problemData, int nTrees,
+     double r, double m, int seed,
+     out double rmsError, out double avgRelError, out double outOfBagRmsError, out double outOfBagAvgRelError) {
+      var model = CreateRandomForestRegressionModel(problemData, problemData.TrainingIndices, nTrees, r, m, seed, out rmsError, out avgRelError, out outOfBagRmsError, out outOfBagAvgRelError);
+      return model;
+    }
+
+    public static RandomForestModelFull CreateRandomForestRegressionModel(IRegressionProblemData problemData, IEnumerable<int> trainingIndices, int nTrees, double r, double m, int seed,
+    out double rmsError, out double avgRelError, out double outOfBagRmsError, out double outOfBagAvgRelError) {
+
+      var variables = problemData.AllowedInputVariables.Concat(new string[] { problemData.TargetVariable });
+      double[,] inputMatrix = problemData.Dataset.ToArray(variables, trainingIndices);
+
+      alglib.dfreport rep;
+      var dForest = RandomForestUtil.CreateRandomForestModel(seed, inputMatrix, nTrees, r, m, 1, out rep);
+
+      rmsError = rep.rmserror;
+      outOfBagRmsError = rep.oobrmserror;
+      avgRelError = rep.avgrelerror;
+      outOfBagAvgRelError = rep.oobavgrelerror;
+
+      return new RandomForestModelFull(dForest, problemData.TargetVariable, problemData.AllowedInputVariables);
     }
 

branches/2521_ProblemRefactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestRegressionSolution.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2019 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/2521_ProblemRefactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestUtil.cs

@@ -2 +2 @@
 
 /* HeuristicLab
- * Copyright (C) 2002-2019 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -27 +27 @@
 using System.Linq.Expressions;
 using System.Threading.Tasks;
+using HEAL.Attic;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
 using HeuristicLab.Data;
 using HeuristicLab.Parameters;
-using HEAL.Attic;
 using HeuristicLab.Problems.DataAnalysis;
 using HeuristicLab.Random;
@@ -89 +89 @@
 
   public static class RandomForestUtil {
+    public static void AssertParameters(double r, double m) {
+      if (r <= 0 || r > 1) throw new ArgumentException("The R parameter for random forest modeling must be between 0 and 1.");
+      if (m <= 0 || m > 1) throw new ArgumentException("The M parameter for random forest modeling must be between 0 and 1.");
+    }
+
+    public static void AssertInputMatrix(double[,] inputMatrix) {
+      if (inputMatrix.ContainsNanOrInfinity())
+        throw new NotSupportedException("Random forest modeling does not support NaN or infinity values in the input dataset.");
+    }
+
+    internal static alglib.decisionforest CreateRandomForestModel(int seed, double[,] inputMatrix, int nTrees, double r, double m, int nClasses, out alglib.dfreport rep) {
+      RandomForestUtil.AssertParameters(r, m);
+      RandomForestUtil.AssertInputMatrix(inputMatrix);
+
+      int info = 0;
+      alglib.math.rndobject = new System.Random(seed);
+      var dForest = new alglib.decisionforest();
+      rep = new alglib.dfreport();
+      int nRows = inputMatrix.GetLength(0);
+      int nColumns = inputMatrix.GetLength(1);
+      int sampleSize = Math.Max((int)Math.Round(r * nRows), 1);
+      int nFeatures = Math.Max((int)Math.Round(m * (nColumns - 1)), 1);
+
+      alglib.dforest.dfbuildinternal(inputMatrix, nRows, nColumns - 1, nClasses, nTrees, sampleSize, nFeatures, alglib.dforest.dfusestrongsplits + alglib.dforest.dfuseevs, ref info, dForest.innerobj, rep.innerobj);
+      if (info != 1) throw new ArgumentException("Error in calculation of random forest model");
+      return dForest;
+    }
+
+
     private static void CrossValidate(IRegressionProblemData problemData, Tuple<IEnumerable<int>, IEnumerable<int>>[] partitions, int nTrees, double r, double m, int seed, out double avgTestMse) {
       avgTestMse = 0;