Changeset 17045 for branches/2952_RF-ModelStorage/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest

Timestamp:

06/27/19 15:46:20 (6 years ago)

Author:

mkommend

Message:

#2952: Intermediate commit of refactoring RF models that is not yet finished.

Location:

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

Files:

• RandomForestClassification.cs (modified) (3 diffs)
• RandomForestModel.cs (modified) (8 diffs)
• RandomForestModelFull.cs (added)
• RandomForestModelSurrogate.cs (added)
• RandomForestRegression.cs (modified) (4 diffs)
• RandomForestUtil.cs (modified) (2 diffs)

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

@@ -21 +21 @@
 
 using System.Threading;
+using HEAL.Attic;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -26 +27 @@
 using HeuristicLab.Optimization;
 using HeuristicLab.Parameters;
-using HEAL.Attic;
 using HeuristicLab.Problems.DataAnalysis;
 
@@ -144 +144 @@
 
       if (CreateSolution) {
-        var solution = new RandomForestClassificationSolution(model, (IClassificationProblemData)Problem.ProblemData.Clone());
+        var solution = model.CreateClassificationSolution(Problem.ProblemData);
         Results.Add(new Result(RandomForestClassificationModelResultName, "The random forest classification solution.", solution));
       }

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

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

@@ -20 +20 @@
 #endregion
 
+using System.Collections.Generic;
+using System.Linq;
 using System.Threading;
+using HEAL.Attic;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -26 +29 @@
 using HeuristicLab.Optimization;
 using HeuristicLab.Parameters;
-using HEAL.Attic;
 using HeuristicLab.Problems.DataAnalysis;
 
@@ -144 +146 @@
 
       if (CreateSolution) {
-        var solution = new RandomForestRegressionSolution(model, (IRegressionProblemData)Problem.ProblemData.Clone());
+        var solution = model.CreateRegressionSolution(Problem.ProblemData);
         Results.Add(new Result(RandomForestRegressionModelResultName, "The random forest regression solution.", solution));
       }
     }
+
 
     // keep for compatibility with old API
@@ -157 +160 @@
     }
 
-    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) {
+      return CreateRandomForestRegressionModel(problemData, problemData.TrainingIndices, nTrees, r, m, seed, out rmsError, out avgRelError, out outOfBagRmsError, out outOfBagAvgRelError);
+    }
+
+    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);
+
+      //return RandomForestModel.CreateRegressionModel(problemData, nTrees, r, m, seed,
+      //rmsError: out rmsError, avgRelError: out avgRelError, outOfBagRmsError: out outOfBagRmsError, outOfBagAvgRelError: out outOfBagAvgRelError);
     }
 

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

@@ -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;