Changeset 12702 for stable/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest

Timestamp:

07/10/15 11:51:51 (9 years ago)

Author:

mkommend

Message:

#2276: Merged changes to stable.

Location:

stable

Files:

• . (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModel.cs (modified) (4 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestUtil.cs (modified) (9 diffs)

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestModel.cs

@@ -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);
@@ -205 +205 @@
       outOfBagRmsError = rep.oobrmserror;
 
-      return new RandomForestModel(dForest,seed, problemData,nTrees, r, m);
+      return new RandomForestModel(dForest, seed, problemData, nTrees, r, m);
     }
 
@@ -242 +242 @@
       outOfBagRelClassificationError = rep.oobrelclserror;
 
-      return new RandomForestModel(dForest,seed, problemData,nTrees, r, m, classValues);
+      return new RandomForestModel(dForest, seed, problemData, nTrees, r, m, classValues);
     }
 

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/RandomForest/RandomForestUtil.cs

@@ -90 +90 @@
 
   public static class RandomForestUtil {
-    private static readonly object locker = new object();
-
     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;
@@ -132 +130 @@
     }
 
-    // grid search without cross-validation since in the case of random forests, the out-of-bag estimate is unbiased
+    /// <summary>
+    /// Grid search without crossvalidation (since for random forests the out-of-bag estimate is unbiased)
+    /// </summary>
+    /// <param name="problemData">The regression problem data</param>
+    /// <param name="parameterRanges">The ranges for each parameter in the grid search</param>
+    /// <param name="seed">The random seed (required by the random forest model)</param>
+    /// <param name="maxDegreeOfParallelism">The maximum allowed number of threads (to parallelize the grid search)</param>
     public static RFParameter GridSearch(IRegressionProblemData problemData, Dictionary<string, IEnumerable<double>> parameterRanges, int seed = 12345, int maxDegreeOfParallelism = 1) {
       var setters = parameterRanges.Keys.Select(GenerateSetter).ToList();
@@ -139 +143 @@
       RFParameter bestParameters = new RFParameter();
 
+      var locker = new object();
       Parallel.ForEach(crossProduct, new ParallelOptions { MaxDegreeOfParallelism = maxDegreeOfParallelism }, parameterCombination => {
         var parameterValues = parameterCombination.ToList();
@@ -156 +161 @@
     }
 
+    /// <summary>
+    /// Grid search without crossvalidation (since for random forests the out-of-bag estimate is unbiased)
+    /// </summary>
+    /// <param name="problemData">The classification problem data</param>
+    /// <param name="parameterRanges">The ranges for each parameter in the grid search</param>
+    /// <param name="seed">The random seed (required by the random forest model)</param>
+    /// <param name="maxDegreeOfParallelism">The maximum allowed number of threads (to parallelize the grid search)</param>
     public static RFParameter GridSearch(IClassificationProblemData problemData, Dictionary<string, IEnumerable<double>> parameterRanges, int seed = 12345, int maxDegreeOfParallelism = 1) {
       var setters = parameterRanges.Keys.Select(GenerateSetter).ToList();
@@ -163 +175 @@
       RFParameter bestParameters = new RFParameter();
 
+      var locker = new object();
       Parallel.ForEach(crossProduct, new ParallelOptions { MaxDegreeOfParallelism = maxDegreeOfParallelism }, parameterCombination => {
         var parameterValues = parameterCombination.ToList();
@@ -181 +194 @@
     }
 
+    /// <summary>
+    /// Grid search with crossvalidation
+    /// </summary>
+    /// <param name="problemData">The regression problem data</param>
+    /// <param name="numberOfFolds">The number of folds for crossvalidation</param>
+    /// <param name="shuffleFolds">Specifies whether the folds should be shuffled</param>
+    /// <param name="parameterRanges">The ranges for each parameter in the grid search</param>
+    /// <param name="seed">The random seed (required by the random forest model)</param>
+    /// <param name="maxDegreeOfParallelism">The maximum allowed number of threads (to parallelize the grid search)</param>
+    /// <returns>The best parameter values found by the grid search</returns>
     public static RFParameter GridSearch(IRegressionProblemData problemData, int numberOfFolds, bool shuffleFolds, Dictionary<string, IEnumerable<double>> parameterRanges, int seed = 12345, int maxDegreeOfParallelism = 1) {
       DoubleValue mse = new DoubleValue(Double.MaxValue);
@@ -189 +212 @@
       var crossProduct = parameterRanges.Values.CartesianProduct();
 
+      var locker = new object();
       Parallel.ForEach(crossProduct, new ParallelOptions { MaxDegreeOfParallelism = maxDegreeOfParallelism }, parameterCombination => {
         var parameterValues = parameterCombination.ToList();
@@ -208 +232 @@
     }
 
+    /// <summary>
+    /// Grid search with crossvalidation
+    /// </summary>
+    /// <param name="problemData">The classification problem data</param>
+    /// <param name="numberOfFolds">The number of folds for crossvalidation</param>
+    /// <param name="shuffleFolds">Specifies whether the folds should be shuffled</param>
+    /// <param name="parameterRanges">The ranges for each parameter in the grid search</param>
+    /// <param name="seed">The random seed (for shuffling)</param>
+    /// <param name="maxDegreeOfParallelism">The maximum allowed number of threads (to parallelize the grid search)</param>
     public static RFParameter GridSearch(IClassificationProblemData problemData, int numberOfFolds, bool shuffleFolds, Dictionary<string, IEnumerable<double>> parameterRanges, int seed = 12345, int maxDegreeOfParallelism = 1) {
       DoubleValue accuracy = new DoubleValue(0);
@@ -216 +249 @@
       var partitions = GenerateRandomForestPartitions(problemData, numberOfFolds, shuffleFolds);
 
+      var locker = new object();
       Parallel.ForEach(crossProduct, new ParallelOptions { MaxDegreeOfParallelism = maxDegreeOfParallelism }, parameterCombination => {
         var parameterValues = parameterCombination.ToList();