Changeset 14251 for branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression.Views

Timestamp:

08/10/16 20:10:25 (8 years ago)

Author:

gkronber

Message:

#2650:

• extended non-linear regression to work with factors
• fixed bugs in constants optimizer and tree interpreter
• improved simplification of factor variables
• added support for factors to ERC view
• added support for factors to solution comparison view
• activated view for all factors

File:

• branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression.Views/3.4/SymbolicRegressionSolutionErrorCharacteristicsCurveView.cs (modified) (2 diffs)

branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression.Views/3.4/SymbolicRegressionSolutionErrorCharacteristicsCurveView.cs

@@ -21 +21 @@
 
 using System;
+using System.Collections;
 using System.Collections.Generic;
 using System.Diagnostics.Contracts;
@@ -47 +48 @@
       if (!problemData.TrainingIndices.Any()) return null; // don't create an LR model if the problem does not have a training set (e.g. loaded into an existing model)
 
-      var usedDoubleVariables =
-        Content.Model.SymbolicExpressionTree.IterateNodesPostfix()
-        .OfType<VariableTreeNode>()
-        .Select(node => node.VariableName)
-      .Concat(
-        Content.Model.SymbolicExpressionTree.IterateNodesPostfix()
-        .OfType<VariableConditionTreeNode>()
-        .Select(node => node.VariableName)
-        )
+      var usedVariables = Content.Model.SymbolicExpressionTree.IterateNodesPostfix()
+        .OfType<IVariableTreeNode>()
+        .Select(node => node.VariableName).ToArray();
+
+      var usedDoubleVariables = usedVariables
+        .Where(name => problemData.Dataset.VariableHasType<double>(name))
       .Distinct();
 
-      var usedFactorVariables =
-        Content.Model.SymbolicExpressionTree.IterateNodesPostfix()
-        .OfType<BinaryFactorVariableTreeNode>()
-        .Select(node => Tuple.Create(node.VariableName, node.VariableValue))
+      var usedFactorVariables = usedVariables
+        .Where(name => problemData.Dataset.VariableHasType<string>(name))
         .Distinct();
+
+      // gkronber: for binary factors we actually produce a binary variable in the new dataset
+      // but only if the variable is not used as a full factor anyway (LR creates binary columns anyway)
+      var usedBinaryFactors =
+        Content.Model.SymbolicExpressionTree.IterateNodesPostfix().OfType<BinaryFactorVariableTreeNode>()
+        .Where(node => !usedFactorVariables.Contains(node.VariableName))
+        .Select(node => Tuple.Create(node.VariableValue, node.VariableValue));
 
       // create a new problem and dataset
       var variableNames =
         usedDoubleVariables
-        .Concat(usedFactorVariables.Select(t => t.Item1 + "=" + t.Item2))
+        .Concat(usedFactorVariables)
+        .Concat(usedBinaryFactors.Select(t => t.Item1 + "=" + t.Item2))
         .Concat(new string[] { problemData.TargetVariable })
         .ToArray();
       var variableValues =
-        usedDoubleVariables.Select(name => problemData.Dataset.GetDoubleValues(name).ToList())
+        usedDoubleVariables.Select(name => (IList)problemData.Dataset.GetDoubleValues(name).ToList())
+        .Concat(usedFactorVariables.Select(name => problemData.Dataset.GetStringValues(name).ToList()))
         .Concat(
-        // create binary variable
-          usedFactorVariables.Select(t => problemData.Dataset.GetReadOnlyStringValues(t.Item1).Select(val => val == t.Item2 ? 1.0 : 0.0).ToList())
+          // create binary variable
+          usedBinaryFactors.Select(t => problemData.Dataset.GetReadOnlyStringValues(t.Item1).Select(val => val == t.Item2 ? 1.0 : 0.0).ToList())
         )
         .Concat(new[] { problemData.Dataset.GetDoubleValues(problemData.TargetVariable).ToList() });