Changeset 4038 for trunk

Timestamp:

07/15/10 14:01:09 (14 years ago)

Author:

mkommend

Message:

corrected bug in SymbolicRegressionEvaluator (ticket #1082)

File:

• trunk/sources/HeuristicLab.Problems.DataAnalysis.Regression/3.3/Symbolic/SymbolicRegressionEvaluator.cs (modified) (4 diffs)

trunk/sources/HeuristicLab.Problems.DataAnalysis.Regression/3.3/Symbolic/SymbolicRegressionEvaluator.cs

@@ -35 +35 @@
 using HeuristicLab.Operators;
 using HeuristicLab.Problems.DataAnalysis.Symbolic;
+using HeuristicLab.Random;
 
 namespace HeuristicLab.Problems.DataAnalysis.Regression.Symbolic {
@@ -131 +132 @@
 
     public override IOperation Apply() {
-      IEnumerable<int> rows = GenerateRowsToEvaluate(RelativeNumberOfEvaluatedSamples.Value, SamplesStart.Value, SamplesEnd.Value);
+      uint seed = (uint)Random.Next();
+      IEnumerable<int> rows = GenerateRowsToEvaluate(seed, RelativeNumberOfEvaluatedSamples.Value, SamplesStart.Value, SamplesEnd.Value);
       double quality = Evaluate(SymbolicExpressionTreeInterpreter, SymbolicExpressionTree, RegressionProblemData.Dataset,
         RegressionProblemData.TargetVariable, rows);
@@ -140 +142 @@
 
     //algorithm taken from progamming pearls page 127
-    private IEnumerable<int> GenerateRowsToEvaluate(double relativeAmount, int start, int end) {
+    //IMPORTANT because IEnumerables with yield are used the seed must best be specified to return always 
+    //the same sequence of numbers without caching the values.
+    private static IEnumerable<int> GenerateRowsToEvaluate(uint seed, double relativeAmount, int start, int end) {
       if (end < start) throw new ArgumentException("Start value is larger than end value.");
       int count = (int)((end - start) * relativeAmount);
@@ -146 +150 @@
 
       int remaining = end - start;
+      MersenneTwister random = new MersenneTwister(seed);
       for (int i = start; i < end && count > 0; i++) {
-        double probabilty = Random.NextDouble();
+        double probabilty = random.NextDouble();
         if (probabilty < ((double)count) / remaining) {
           count--;