Changeset 13835

Timestamp:

05/04/16 16:56:49 (8 years ago)

Author:

bburlacu

Message:

#2288: Performance improvements in the SymbolicRegressionVariableImpactsAnalyzer.

File:

• branches/HeuristicLab.VariableInteractionNetworks/HeuristicLab.VariableInteractionNetworks/3.3/SymbolicDataAnalysisVariableImpactsAnalyzer.cs (modified) (4 diffs)

branches/HeuristicLab.VariableInteractionNetworks/HeuristicLab.VariableInteractionNetworks/3.3/SymbolicDataAnalysisVariableImpactsAnalyzer.cs

@@ -21 +21 @@
 
 using System;
+using System.Collections.Generic;
 using System.Linq;
 using HeuristicLab.Analysis;
@@ -225 +226 @@
       var variablesToTreeIndices = allowedInputVariables.ToDictionary(x => x, x => Enumerable.Range(0, simplifiedTrees.Count).Where(i => ContainsVariable(simplifiedTrees[i], x)).ToList());
 
-      foreach (var mapping in variablesToTreeIndices) {
-        var variableName = mapping.Key;
-        var median = problemData.Dataset.GetDoubleValues(variableName, problemData.TrainingIndices).Median();
-        var ds = new ModifiableDataset(problemData.Dataset.DoubleVariables, problemData.Dataset.DoubleVariables.Select(x => problemData.Dataset.GetReadOnlyDoubleValues(x).ToList()));
-        foreach (var i in problemData.TrainingIndices) {
-          ds.SetVariableValue(median, variableName, i);
-        }
-        var pd = new RegressionProblemData(ds, allowedInputVariables, problemData.TargetVariable);
-        pd.TrainingPartition.Start = problemData.TrainingPartition.Start;
-        pd.TrainingPartition.End = problemData.TrainingPartition.End;
-        pd.TestPartition.Start = problemData.TestPartition.Start;
-        pd.TestPartition.End = problemData.TestPartition.End;
-
-        var indices = mapping.Value;
+      // variable values used for restoring original values in the dataset
+      var variableValues = allowedInputVariables.Select(x => problemData.Dataset.GetReadOnlyDoubleValues(x).ToList()).ToList();
+      // the ds gets new variable values (not the above).
+      var variableNames = allowedInputVariables.Concat(new[] { problemData.TargetVariable }).ToList();
+      var ds = new ModifiableDataset(variableNames, variableNames.Select(x => problemData.Dataset.GetReadOnlyDoubleValues(x).ToList()));
+      var pd = new RegressionProblemData(ds, allowedInputVariables, problemData.TargetVariable);
+      pd.TrainingPartition.Start = problemData.TrainingPartition.Start;
+      pd.TrainingPartition.End = problemData.TrainingPartition.End;
+      pd.TestPartition.Start = problemData.TestPartition.Start;
+      pd.TestPartition.End = problemData.TestPartition.End;
+
+      for (int i = 0; i < allowedInputVariables.Count; ++i) {
+        var v = allowedInputVariables[i];
+        var median = problemData.Dataset.GetDoubleValues(v, problemData.TrainingIndices).Median();
+        var values = new List<double>(Enumerable.Repeat(median, problemData.Dataset.Rows));
+        // replace values with median
+        ds.ReplaceVariable(v, values);
+
+        var indices = variablesToTreeIndices[v];
+        if (!indices.Any()) {
+          dataTable.Rows[v].Values.Add(0);
+          continue;
+        }
+
         var averageImpact = 0d;
-        for (int i = 0; i < indices.Count; ++i) {
-          var tree = simplifiedTrees[i];
-          var originalQuality = qualities[i].Value;
+        for (int j = 0; j < indices.Count; ++j) {
+          var tree = simplifiedTrees[j];
+          var originalQuality = qualities[j].Value;
           double newQuality;
           if (optimizeConstants) {
@@ -253 +264 @@
         }
         averageImpact /= indices.Count;
-        dataTable.Rows[variableName].Values.Add(averageImpact);
+        dataTable.Rows[v].Values.Add(averageImpact);
+        // restore original values
+        ds.ReplaceVariable(v, variableValues[i]);
       }
 
@@ -275 +288 @@
   }
 }
+