Changeset 11315 for trunk/sources/HeuristicLab.Algorithms.DataAnalysis

Timestamp:

08/27/14 14:02:05 (10 years ago)

Author:

bburlacu

Message:

#2237: Added RandomForestUtil class implementing fold generation, cross-validation and grid search. Overloaded CreateRegressionModel method to accept a user-specified data partition.

Location:

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest

Files:

• RandomForestModel.cs (modified) (2 diffs)
• RandomForestUtil.cs (added)

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModel.cs

@@ -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;
@@ -189 +189 @@
     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) {
-
+      return CreateRegressionModel(problemData, nTrees, r, m, seed, out rmsError, out avgRelError, out outOfBagAvgRelError, out outOfBagRmsError, problemData.TrainingIndices);
+    }
+
+    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, IEnumerable<int> trainingIndices) {
       var variables = problemData.AllowedInputVariables.Concat(new string[] { problemData.TargetVariable });
       double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(problemData.Dataset, variables, problemData.TrainingIndices);