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

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/RandomForestRegression.cs (modified) (10 diffs)

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);
     }