Changeset 17416

Timestamp:

01/31/20 16:21:00 (4 years ago)

Author:

pfleck

Message:

#3040 enabled variable impacts for vectorial data (if vectors have the same length)

Location:

branches/3040_VectorBasedGP

Files:

• HeuristicLab.Problems.DataAnalysis.Views/3.4/Regression/RegressionSolutionVariableImpactsView.cs (modified) (1 diff)
• HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolutionVariableImpactsCalculator.cs (modified) (2 diffs)

branches/3040_VectorBasedGP/HeuristicLab.Problems.DataAnalysis.Views/3.4/Regression/RegressionSolutionVariableImpactsView.cs

@@ -141 +141 @@
         var originalVariableOrdering = problemData.Dataset.VariableNames
           .Where(v => inputvariables.Contains(v))
-          .Where(v => problemData.Dataset.VariableHasType<double>(v) || problemData.Dataset.VariableHasType<string>(v))
+          //.Where(v => problemData.Dataset.VariableHasType<double>(v) || problemData.Dataset.VariableHasType<string>(v))
           .ToList();
 

branches/3040_VectorBasedGP/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolutionVariableImpactsCalculator.cs

@@ -195 +195 @@
         originalValues = modifiableDataset.GetReadOnlyStringValues(variableName).ToList();
         replacementValues = GetReplacementValuesForString(model, modifiableDataset, variableName, rows, (List<string>)originalValues, targetValues, factorReplacementMethod);
+      } else if (modifiableDataset.VariableHasType<DoubleVector>(variableName)) {
+        originalValues = modifiableDataset.GetReadOnlyDoubleVectorValues(variableName).ToList();
+        replacementValues = GetReplacementValuesForDoubleVector(modifiableDataset, rows, (List<DoubleVector>)originalValues, replacementMethod);
       } else {
         throw new NotSupportedException("Variable not supported");
@@ -303 +306 @@
     }
 
+    private static IList GetReplacementValuesForDoubleVector(ModifiableDataset modifiableDataset,
+      IEnumerable<int> rows,
+      List<DoubleVector> originalValues,
+      ReplacementMethodEnum replacementMethod = ReplacementMethodEnum.Shuffle) {
+
+      IRandom random = new FastRandom(31415);
+      List<DoubleVector> replacementValues;
+      DoubleVector replacementValue;
+
+      switch (replacementMethod) {
+        case ReplacementMethodEnum.Shuffle:
+          // new var has same empirical distribution but the relation to y is broken
+          // prepare a complete column for the dataset
+          replacementValues = Enumerable.Repeat(new DoubleVector(new[] { double.NaN }), modifiableDataset.Rows).ToList();
+          // shuffle only the selected rows
+          var shuffledValues = rows.Select(r => originalValues[r]).Shuffle(random).ToList();
+          int i = 0;
+          // update column values 
+          foreach (var r in rows) {
+            replacementValues[r] = shuffledValues[i++];
+          }
+          break;
+
+        default:
+          throw new ArgumentException(string.Format("ReplacementMethod {0} cannot be handled.", replacementMethod));
+      }
+
+      return replacementValues;
+    }
+
     private static double CalculateQualityForReplacement(
       IRegressionModel model,