Changeset 12694 for branches/HeuristicLab.Problems.Orienteering/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest

Timestamp:

07/09/15 13:07:30 (10 years ago)

Author:

abeham

Message:

#2208: merged trunk changes

Location:

branches/HeuristicLab.Problems.Orienteering

Files:

• . (modified) (2 props)
• HeuristicLab.Algorithms.DataAnalysis (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestClassification.cs (modified) (3 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestClassificationSolution.cs (modified) (1 diff)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModel.cs (modified) (8 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestRegression.cs (modified) (3 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestRegressionSolution.cs (modified) (1 diff)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestUtil.cs (copied) (copied from trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestUtil.cs)

branches/HeuristicLab.Problems.Orienteering/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestClassification.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2015 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -20 +20 @@
 #endregion
 
-using System;
-using System.Collections.Generic;
-using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -36 +33 @@
   /// </summary>
   [Item("Random Forest Classification", "Random forest classification data analysis algorithm (wrapper for ALGLIB).")]
-  [Creatable("Data Analysis")]
+  [Creatable(CreatableAttribute.Categories.DataAnalysisClassification, Priority = 120)]
   [StorableClass]
   public sealed class RandomForestClassification : FixedDataAnalysisAlgorithm<IClassificationProblem> {

branches/HeuristicLab.Problems.Orienteering/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestClassificationSolution.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2015 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.

branches/HeuristicLab.Problems.Orienteering/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModel.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2015 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -76 +76 @@
       // we assume that the trees array (double[]) is immutable in alglib
       randomForest.innerobj.trees = original.randomForest.innerobj.trees;
-      
+
       // allowedInputVariables is immutable so we don't need to clone
       allowedInputVariables = original.allowedInputVariables;
@@ -129 +129 @@
     }
 
-    public IEnumerable<double> GetEstimatedValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedValues(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, AllowedInputVariables, rows);
       AssertInputMatrix(inputData);
@@ -147 +147 @@
     }
 
-    public IEnumerable<double> GetEstimatedClassValues(Dataset dataset, IEnumerable<int> rows) {
+    public IEnumerable<double> GetEstimatedClassValues(IDataset dataset, IEnumerable<int> rows) {
       double[,] inputData = AlglibUtil.PrepareInputMatrix(dataset, AllowedInputVariables, rows);
       AssertInputMatrix(inputData);
@@ -188 +188 @@
 
     public static RandomForestModel CreateRegressionModel(IRegressionProblemData problemData, int nTrees, double r, double m, int seed,
-      out double rmsError, out double avgRelError, out double outOfBagAvgRelError, out double outOfBagRmsError) {
-
+      out double rmsError, out double outOfBagRmsError, out double avgRelError, out double outOfBagAvgRelError) {
+      return CreateRegressionModel(problemData, problemData.TrainingIndices, nTrees, r, m, seed, out rmsError, out avgRelError, out outOfBagAvgRelError, out outOfBagRmsError);
+    }
+
+    public static RandomForestModel CreateRegressionModel(IRegressionProblemData problemData, IEnumerable<int> trainingIndices, int nTrees, double r, double m, int seed,
+      out double rmsError, out double outOfBagRmsError, out double avgRelError, out double outOfBagAvgRelError) {
       var variables = problemData.AllowedInputVariables.Concat(new string[] { problemData.TargetVariable });
-      double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(problemData.Dataset, variables, problemData.TrainingIndices);
+      double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(problemData.Dataset, variables, trainingIndices);
 
       alglib.dfreport rep;
@@ -201 +205 @@
       outOfBagRmsError = rep.oobrmserror;
 
-      return new RandomForestModel(dForest,
-        seed, problemData,
-        nTrees, r, m);
+      return new RandomForestModel(dForest, seed, problemData, nTrees, r, m);
     }
 
     public static RandomForestModel CreateClassificationModel(IClassificationProblemData problemData, int nTrees, double r, double m, int seed,
       out double rmsError, out double outOfBagRmsError, out double relClassificationError, out double outOfBagRelClassificationError) {
+      return CreateClassificationModel(problemData, problemData.TrainingIndices, nTrees, r, m, seed, out rmsError, out outOfBagRmsError, out relClassificationError, out outOfBagRelClassificationError);
+    }
+
+    public static RandomForestModel CreateClassificationModel(IClassificationProblemData problemData, IEnumerable<int> trainingIndices, int nTrees, double r, double m, int seed,
+      out double rmsError, out double outOfBagRmsError, out double relClassificationError, out double outOfBagRelClassificationError) {
 
       var variables = problemData.AllowedInputVariables.Concat(new string[] { problemData.TargetVariable });
-      double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(problemData.Dataset, variables, problemData.TrainingIndices);
+      double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(problemData.Dataset, variables, trainingIndices);
 
       var classValues = problemData.ClassValues.ToArray();
@@ -235 +242 @@
       outOfBagRelClassificationError = rep.oobrelclserror;
 
-      return new RandomForestModel(dForest,
-        seed, problemData,
-        nTrees, r, m, classValues);
+      return new RandomForestModel(dForest, seed, problemData, nTrees, r, m, classValues);
     }
 
@@ -264 +269 @@
 
     private static void AssertInputMatrix(double[,] inputMatrix) {
-      if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
+      if (inputMatrix.Cast<double>().Any(x => Double.IsNaN(x) || Double.IsInfinity(x)))
         throw new NotSupportedException("Random forest modeling does not support NaN or infinity values in the input dataset.");
     }

branches/HeuristicLab.Problems.Orienteering/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestRegression.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2015 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -20 +20 @@
 #endregion
 
-using System;
-using System.Collections.Generic;
-using System.Linq;
 using HeuristicLab.Common;
 using HeuristicLab.Core;
@@ -36 +33 @@
   /// </summary>
   [Item("Random Forest Regression", "Random forest regression data analysis algorithm (wrapper for ALGLIB).")]
-  [Creatable("Data Analysis")]
+  [Creatable(CreatableAttribute.Categories.DataAnalysisRegression, Priority = 120)]
   [StorableClass]
   public sealed class RandomForestRegression : FixedDataAnalysisAlgorithm<IRegressionProblem> {

branches/HeuristicLab.Problems.Orienteering/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestRegressionSolution.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2014 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2015 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.