Changeset 14530 for stable/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolutionVariableImpactsCalculator.cs

Timestamp:

12/25/16 17:09:04 (7 years ago)

Author:

gkronber

Message:

#2673: merged r14348 and 14463 from trunk to stable

Location:

stable

Files:

• . (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis (modified) (1 prop)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolutionVariableImpactsCalculator.cs (modified) (3 diffs)

stable/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolutionVariableImpactsCalculator.cs

@@ -122 +122 @@
       }
 
-
       var impacts = new Dictionary<string, double>();
       var modifiableDataset = ((Dataset)dataset).ToModifiable();
 
-      foreach (var inputVariable in problemData.AllowedInputVariables) {
+      var inputvariables = new HashSet<string>(problemData.AllowedInputVariables.Union(solution.Model.VariablesUsedForPrediction));
+      var allowedInputVariables = dataset.VariableNames.Where(v => inputvariables.Contains(v)).ToList();
+
+      foreach (var inputVariable in allowedInputVariables) {
         var newEstimates = EvaluateModelWithReplacedVariable(solution.Model, inputVariable, modifiableDataset, rows, replacement);
         var newR2 = OnlinePearsonsRCalculator.Calculate(targetValues, newEstimates, out error);
@@ -156 +158 @@
           // new var has same empirical distribution but the relation to y is broken
           rand = new FastRandom(31415);
-          replacementValues = rows.Select(r => originalValues[r]).Shuffle(rand).ToList();
+          // prepare a complete column for the dataset
+          replacementValues = Enumerable.Repeat(double.NaN, dataset.Rows).ToList();
+          // shuffle only the selected rows
+          var shuffledValues = rows.Select(r => originalValues[r]).Shuffle(rand).ToList();
+          int i = 0;
+          // update column values 
+          foreach (var r in rows) {
+            replacementValues[r] = shuffledValues[i++];
+          }
           break;
         case ReplacementMethodEnum.Noise:
@@ -162 +172 @@
           var stdDev = rows.Select(r => originalValues[r]).StandardDeviation();
           rand = new FastRandom(31415);
-          replacementValues = rows.Select(_ => NormalDistributedRandom.NextDouble(rand, avg, stdDev)).ToList();
+          // prepare a complete column for the dataset
+          replacementValues = Enumerable.Repeat(double.NaN, dataset.Rows).ToList();
+          // update column values 
+          foreach (var r in rows) {
+            replacementValues[r] = NormalDistributedRandom.NextDouble(rand, avg, stdDev);
+          }
           break;