Changeset 13986

Timestamp:

07/03/16 19:56:55 (8 years ago)

Author:

gkronber

Message:

#2595: added two new variants for variable impact calculation (shuffle and Gaussian noise)

Location:

trunk/sources

Files:

• HeuristicLab.Problems.DataAnalysis.Symbolic.Views/3.4/Plugin.cs.frame (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/HeuristicLab.Problems.DataAnalysis-3.4.csproj (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolutionVariableImpactsCalculator.cs (modified) (3 diffs)

trunk/sources/HeuristicLab.Problems.DataAnalysis.Symbolic.Views/3.4/Plugin.cs.frame

@@ -46 +46 @@
   [PluginDependency("HeuristicLab.Problems.DataAnalysis", "3.4")]
   [PluginDependency("HeuristicLab.Problems.DataAnalysis.Symbolic", "3.4")]
+  [PluginDependency("HeuristicLab.Random", "3.3")]
   public class HeuristicLabProblemsDataAnalysisSymbolicViewsPlugin : PluginBase {
   }

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/HeuristicLab.Problems.DataAnalysis-3.4.csproj

@@ -317 +317 @@
       <Private>False</Private>
     </ProjectReference>
+    <ProjectReference Include="..\..\HeuristicLab.Random\3.3\HeuristicLab.Random-3.3.csproj">
+      <Project>{F4539FB6-4708-40C9-BE64-0A1390AEA197}</Project>
+      <Name>HeuristicLab.Random-3.3</Name>
+    </ProjectReference>
   </ItemGroup>
   <ItemGroup />

trunk/sources/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolutionVariableImpactsCalculator.cs

@@ -30 +30 @@
 using HeuristicLab.Parameters;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
+using HeuristicLab.Random;
 
 namespace HeuristicLab.Problems.DataAnalysis {
@@ -37 +38 @@
     public enum ReplacementMethodEnum {
       Median,
-      Average
+      Average,
+      Shuffle,
+      Noise
     }
 
@@ -138 +141 @@
       var originalValues = dataset.GetReadOnlyDoubleValues(variable).ToList();
       double replacementValue;
+      List<double> replacementValues;
+      IRandom rand;
 
       switch (replacement) {
         case ReplacementMethodEnum.Median:
           replacementValue = rows.Select(r => originalValues[r]).Median();
+          replacementValues = Enumerable.Repeat(replacementValue, dataset.Rows).ToList();
           break;
         case ReplacementMethodEnum.Average:
           replacementValue = rows.Select(r => originalValues[r]).Average();
+          replacementValues = Enumerable.Repeat(replacementValue, dataset.Rows).ToList();
           break;
+        case ReplacementMethodEnum.Shuffle:
+          // 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();
+          break;
+        case ReplacementMethodEnum.Noise:
+          var avg = rows.Select(r => originalValues[r]).Average();
+          var stdDev = rows.Select(r => originalValues[r]).StandardDeviation();
+          rand = new FastRandom(31415);
+          replacementValues = rows.Select(_ => NormalDistributedRandom.NextDouble(rand, avg, stdDev)).ToList();
+          break;
+
         default:
           throw new ArgumentException(string.Format("ReplacementMethod {0} cannot be handled.", replacement));
       }
 
-      dataset.ReplaceVariable(variable, Enumerable.Repeat(replacementValue, dataset.Rows).ToList());
+      dataset.ReplaceVariable(variable, replacementValues);
       //mkommend: ToList is used on purpose to avoid lazy evaluation that could result in wrong estimates due to variable replacements
       var estimates = model.GetEstimatedValues(dataset, rows).ToList();