Changeset 14251 for branches/symbreg-factors-2650/HeuristicLab.Algorithms.DataAnalysis/3.4/NonlinearRegression

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.Algorithms.DataAnalysis/3.4/NonlinearRegression/NonlinearRegression.cs (modified) (2 diffs)

branches/symbreg-factors-2650/HeuristicLab.Algorithms.DataAnalysis/3.4/NonlinearRegression/NonlinearRegression.cs

@@ -27 +27 @@
 using HeuristicLab.Data;
 using HeuristicLab.Parameters;
-using HeuristicLab.Encodings.SymbolicExpressionTreeEncoding;
 using HeuristicLab.Optimization;
 using HeuristicLab.Persistence.Default.CompositeSerializers.Storable;
@@ -93 +92 @@
       var parser = new InfixExpressionParser();
       var tree = parser.Parse(modelStructure);
-      var simplifier = new SymbolicDataAnalysisExpressionTreeSimplifier();
-      
+      // parser handles double and string variables equally by creating a VariableTreeNode
+      // post-process to replace VariableTreeNodes by FactorVariableTreeNodes for all string variables
+      var factorSymbol = new FactorVariable();
+      factorSymbol.VariableNames =
+        problemData.AllowedInputVariables.Where(name => problemData.Dataset.VariableHasType<string>(name));
+      factorSymbol.AllVariableNames = factorSymbol.VariableNames;
+      factorSymbol.VariableValues =
+        factorSymbol.VariableNames.Select(name => new KeyValuePair<string, List<string>>(name, problemData.Dataset.GetReadOnlyStringValues(name).Distinct().ToList()));
+
+      foreach (var parent in tree.IterateNodesPrefix().ToArray()) {
+        for (int i = 0; i < parent.SubtreeCount; i++) {
+          var child = parent.GetSubtree(i) as VariableTreeNode;
+          if (child != null && factorSymbol.VariableNames.Contains(child.VariableName)) {
+            parent.RemoveSubtree(i);
+            var factorTreeNode = (FactorVariableTreeNode)factorSymbol.CreateTreeNode();
+            factorTreeNode.VariableName = child.VariableName;
+            factorTreeNode.Weights =
+              factorTreeNode.Symbol.GetVariableValues(factorTreeNode.VariableName).Select(_ => 1.0).ToArray(); // weight = 1.0 for each value
+            parent.InsertSubtree(i, factorTreeNode);
+          }
+        }
+      }
+
       if (!SymbolicRegressionConstantOptimizationEvaluator.CanOptimizeConstants(tree)) throw new ArgumentException("The optimizer does not support the specified model structure.");
 
       var interpreter = new SymbolicDataAnalysisExpressionTreeLinearInterpreter();
-      SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, tree, problemData, problemData.TrainingIndices, 
+      SymbolicRegressionConstantOptimizationEvaluator.OptimizeConstants(interpreter, tree, problemData, problemData.TrainingIndices,
         applyLinearScaling: false, maxIterations: maxIterations,
         updateVariableWeights: false, updateConstantsInTree: true);