Changeset 17050 for branches/2952_RF-ModelStorage/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest

Timestamp:

06/28/19 13:58:06 (6 years ago)

Author:

mkommend

Message:

#2952: Finished implemenation of different RF models.

Location:

branches/2952_RF-ModelStorage/HeuristicLab.Algorithms.DataAnalysis

Files:

• . (modified) (1 prop)
• 3.4 (modified) (1 prop)
• 3.4/RandomForest/ModelCreation.cs (copied) (copied from branches/2952_RF-ModelStorage/HeuristicLab.Algorithms.DataAnalysis/3.4/GradientBoostedTrees/ModelCreation.cs) (2 diffs)
• 3.4/RandomForest/RandomForestClassification.cs (modified) (9 diffs)
• 3.4/RandomForest/RandomForestModel.cs (modified) (1 diff)
• 3.4/RandomForest/RandomForestModelFull.cs (modified) (1 diff)
• 3.4/RandomForest/RandomForestModelSurrogate.cs (modified) (1 diff)
• 3.4/RandomForest/RandomForestRegression.cs (modified) (9 diffs)

branches/2952_RF-ModelStorage/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/ModelCreation.cs

@@ -23 +23 @@
 using HEAL.Attic;
 
-namespace HeuristicLab.Algorithms.DataAnalysis.GradientBoostedTrees {
+namespace HeuristicLab.Algorithms.DataAnalysis.RandomForest {
 
   /// <summary>
@@ -31 +31 @@
   /// Model - the complete model will be stored (consider the amount of memory needed)
   /// </summary>
-  [StorableType("EE55C357-C4B3-4662-B40B-D1D06A851809")]
+  [StorableType("3869899B-1848-4628-AF27-3B6FDE5840D6")]
   public enum ModelCreation {
     QualityOnly,

branches/2952_RF-ModelStorage/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestClassification.cs

@@ -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;
@@ -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;
       }
       #endregion
@@ -138 +147 @@
 
       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 +153 @@
       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 = model.CreateClassificationSolution(Problem.ProblemData);
+
+      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 +177 @@
     }
 
-    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/2952_RF-ModelStorage/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModel.cs

@@ -34 +34 @@
   /// Represents a random forest model for regression and classification
   /// </summary>
-  [Obsolete("This class only exists for backwards compatibility reasons. Use RFModelSurrogate or RFModelFull instead.")]
+  [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.")]

branches/2952_RF-ModelStorage/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModelFull.cs

@@ -100 +100 @@
 
     public RandomForestModelFull(alglib.decisionforest decisionForest, string targetVariable, IEnumerable<string> inputVariables, IEnumerable<double> classValues = null) : base(targetVariable) {
+      this.name = ItemName;
+      this.description = ItemDescription;
+
       randomForest = decisionForest;
 

branches/2952_RF-ModelStorage/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModelSurrogate.cs

@@ -115 +115 @@
       IRandomForestModel randomForestModel = null;
 
-      //TODO Refactor to new methods
       double rmsError, oobRmsError, relClassError, oobRelClassError;
       var classificationProblemData = originalTrainingData as IClassificationProblemData;
 
       if (originalTrainingData is IRegressionProblemData regressionProblemData) {
-        randomForestModel = RandomForestModel.CreateRegressionModel(regressionProblemData,
+        randomForestModel = RandomForestRegression.CreateRandomForestRegressionModel(regressionProblemData,
                                               nTrees, r, m, seed, out rmsError, out oobRmsError,
                                               out relClassError, out oobRelClassError);
       } else if (classificationProblemData != null) {
-        randomForestModel = RandomForestModel.CreateClassificationModel(classificationProblemData,
+        randomForestModel = RandomForestClassification.CreateRandomForestClassificationModel(classificationProblemData,
                                               nTrees, r, m, seed, out rmsError, out oobRmsError,
                                               out relClassError, out oobRelClassError);

branches/2952_RF-ModelStorage/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestRegression.cs

@@ -24 +24 @@
 using System.Threading;
 using HEAL.Attic;
+using HeuristicLab.Algorithms.DataAnalysis.RandomForest;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -45 +46 @@
     private const string SeedParameterName = "Seed";
     private const string SetSeedRandomlyParameterName = "SetSeedRandomly";
-    private const string CreateSolutionParameterName = "CreateSolution";
+    private const string ModelCreationParameterName = "ModelCreation";
 
     #region parameter properties
@@ -63 +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
@@ -88 +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
@@ -106 +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();
@@ -122 +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;
       }
       #endregion
@@ -145 +152 @@
       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 = model.CreateRegressionSolution(Problem.ProblemData);
+      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));
       }
@@ -163 +178 @@
      double r, double m, int seed,
      out double rmsError, out double avgRelError, out double outOfBagRmsError, out double outOfBagAvgRelError) {
-      return CreateRandomForestRegressionModel(problemData, problemData.TrainingIndices, nTrees, r, m, seed, out rmsError, out avgRelError, out outOfBagRmsError, out outOfBagAvgRelError);
+      var model = CreateRandomForestRegressionModel(problemData, problemData.TrainingIndices, nTrees, r, m, seed, out rmsError, out avgRelError, out outOfBagRmsError, out outOfBagAvgRelError);
+      return model;
     }
 
@@ -181 +197 @@
 
       return new RandomForestModelFull(dForest, problemData.TargetVariable, problemData.AllowedInputVariables);
-
-      //return RandomForestModel.CreateRegressionModel(problemData, nTrees, r, m, seed,
-      //rmsError: out rmsError, avgRelError: out avgRelError, outOfBagRmsError: out outOfBagRmsError, outOfBagAvgRelError: out outOfBagAvgRelError);
     }