Changeset 14238 for branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis/3.4

Timestamp:

08/05/16 17:34:16 (8 years ago)

Author:

gkronber

Message:

#2650:

• added weight for FactorVariable (necessary for LR)
• introduced VariableBase and VariableTreeNodeBase and IVariableSymbol
• support for factors in LR
• extended variable impacts in solution view
• fixed ERC view for regression
• support for FactorVariable in simplifier
• improved support for FactorVariable in constants optimizer
• multiple related changes and small fixes

Location:

branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis/3.4

Files:

• Implementation/Regression/RegressionSolutionVariableImpactsCalculator.cs (modified) (5 diffs)
• ModifiableDataset.cs (modified) (1 diff)

branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Regression/RegressionSolutionVariableImpactsCalculator.cs

@@ -90 +90 @@
     public static IEnumerable<Tuple<string, double>> CalculateImpacts(IRegressionSolution solution,
       DataPartitionEnum data = DataPartitionEnum.Training,
-      ReplacementMethodEnum replacement = ReplacementMethodEnum.Median) {
+      ReplacementMethodEnum replacementMethod = ReplacementMethodEnum.Median) {
 
       var problemData = solution.ProblemData;
@@ -126 +126 @@
       var modifiableDataset = ((Dataset)dataset).ToModifiable();
 
-      foreach (var inputVariable in problemData.AllowedInputVariables) {
-        var newEstimates = EvaluateModelWithReplacedVariable(solution.Model, inputVariable, modifiableDataset, rows, replacement);
+      // calculate impacts for double variables
+      foreach (var inputVariable in problemData.AllowedInputVariables.Where(problemData.Dataset.VariableHasType<double>)) {
+        var newEstimates = EvaluateModelWithReplacedVariable(solution.Model, inputVariable, modifiableDataset, rows, replacementMethod);
         var newR2 = OnlinePearsonsRCalculator.Calculate(targetValues, newEstimates, out error);
         if (error != OnlineCalculatorError.None) throw new InvalidOperationException("Error during R² calculation with replaced inputs.");
@@ -134 +135 @@
         var impact = originalR2 - newR2;
         impacts[inputVariable] = impact;
+      }
+      // calculate impacts for factor variables
+      foreach (var inputVariable in problemData.AllowedInputVariables.Where(problemData.Dataset.VariableHasType<string>)) {
+        var smallestImpact = double.PositiveInfinity;
+        foreach (var repl in problemData.Dataset.GetStringValues(inputVariable, rows).Distinct()) {
+          var newEstimates = EvaluateModelWithReplacedVariable(solution.Model, inputVariable, modifiableDataset, rows, Enumerable.Repeat(repl, dataset.Rows));
+          var newR2 = OnlinePearsonsRCalculator.Calculate(targetValues, newEstimates, out error);
+          if (error != OnlineCalculatorError.None) throw new InvalidOperationException("Error during R² calculation with replaced inputs.");
+
+          newR2 = newR2 * newR2;
+          var impact = originalR2 - newR2;
+          if (impact < smallestImpact) smallestImpact = impact;
+        }
+        impacts[inputVariable] = smallestImpact;
       }
       return impacts.OrderByDescending(i => i.Value).Select(i => Tuple.Create(i.Key, i.Value));
@@ -169 +184 @@
       }
 
-      dataset.ReplaceVariable(variable, replacementValues);
+      return EvaluateModelWithReplacedVariable(model, variable, dataset, rows, replacementValues);
+    }
+
+    private static IEnumerable<double> EvaluateModelWithReplacedVariable(IRegressionModel model, string variable, ModifiableDataset dataset, IEnumerable<int> rows, IEnumerable<double> replacementValues) {
+      var originalValues = dataset.GetReadOnlyDoubleValues(variable).ToList();
+      dataset.ReplaceVariable(variable, replacementValues.ToList());
       //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();
@@ -176 +196 @@
       return estimates;
     }
+    private static IEnumerable<double> EvaluateModelWithReplacedVariable(IRegressionModel model, string variable, ModifiableDataset dataset, IEnumerable<int> rows, IEnumerable<string> replacementValues) {
+      var originalValues = dataset.GetReadOnlyStringValues(variable).ToList();
+      dataset.ReplaceVariable(variable, replacementValues.ToList());
+      //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();
+      dataset.ReplaceVariable(variable, originalValues);
+
+      return estimates;
+    }
   }
 }

branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis/3.4/ModifiableDataset.cs

@@ -77 +77 @@
     public void ReplaceVariable(string variableName, IList values) {
       if (!variableValues.ContainsKey(variableName))
-        throw new ArgumentException(string.Format("Variable {0} is not present in the dataset."), variableName);
+        throw new ArgumentException(string.Format("Variable {0} is not present in the dataset.", variableName));
       if (values.Count != variableValues[variableName].Count)
         throw new ArgumentException("The number of values must coincide with the number of dataset rows.");