Changeset 4244 for branches/DataAnalysis/HeuristicLab.Problems.DataAnalysis.Regression/3.3/Symbolic/Analyzers/FixedValidationBestScaledSymbolicRegressionSolutionAnalyzer.cs

Timestamp:

08/17/10 16:39:11 (14 years ago)

Author:

gkronber

Message:

Use FastRandom instead of Mersenne twister for partial evaluation of training samples. #1082

File:

• branches/DataAnalysis/HeuristicLab.Problems.DataAnalysis.Regression/3.3/Symbolic/Analyzers/FixedValidationBestScaledSymbolicRegressionSolutionAnalyzer.cs (modified) (1 diff)

branches/DataAnalysis/HeuristicLab.Problems.DataAnalysis.Regression/3.3/Symbolic/Analyzers/FixedValidationBestScaledSymbolicRegressionSolutionAnalyzer.cs

@@ -256 +256 @@
       int validationStart = ValidiationSamplesStart.Value;
       int validationEnd = ValidationSamplesEnd.Value;
-      uint seed = (uint)Random.Next();
+      int seed = Random.Next();
       int count = (int)((validationEnd - validationStart) * RelativeNumberOfEvaluatedSamples.Value);
       if (count == 0) count = 1;