Changeset 14266 for branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression

Timestamp:

08/29/16 10:29:10 (8 years ago)

Author:

gkronber

Message:

#2650: improved handling of factors in ConstantOptimizationEvaluator (create binary indicators only once)

File:

• branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SingleObjective/Evaluators/SymbolicRegressionConstantOptimizationEvaluator.cs (modified) (4 diffs)

branches/symbreg-factors-2650/HeuristicLab.Problems.DataAnalysis.Symbolic.Regression/3.4/SingleObjective/Evaluators/SymbolicRegressionConstantOptimizationEvaluator.cs

@@ -22 +22 @@
 using System;
 using System.Collections.Generic;
+using System.Diagnostics.Contracts;
 using System.Linq;
 using AutoDiff;
@@ -322 +323 @@
         var factorVarNode = node as BinaryFactorVariableTreeNode;
         // factor variable values are only 0 or 1 and set in x accordingly
-        var par = new AutoDiff.Variable();
-        parameters.Add(par);
-        variableNames.Add(varNode.VariableName);
-        categoricalVariableValues.Add(factorVarNode != null ? factorVarNode.VariableValue : string.Empty);
+        var varValue = factorVarNode != null ? factorVarNode.VariableValue : string.Empty;
+        var par = FindOrCreateParameter(varNode.VariableName, varValue, parameters, variableNames, categoricalVariableValues);
 
         if (updateVariableWeights) {
@@ -340 +339 @@
         var products = new List<Term>();
         foreach (var variableValue in factorVarNode.Symbol.GetVariableValues(factorVarNode.VariableName)) {
-          var par = new AutoDiff.Variable();
-          parameters.Add(par);
-          variableNames.Add(factorVarNode.VariableName);
-          categoricalVariableValues.Add(variableValue);
+          var par = FindOrCreateParameter(factorVarNode.VariableName, variableValue, parameters, variableNames, categoricalVariableValues);
 
           var wVar = new AutoDiff.Variable();
@@ -516 +512 @@
       term = null;
       return false;
+    }
+
+    // for each factor variable value we need a parameter which represents a binary indicator for that variable & value combination
+    // each binary indicator is only necessary once. So we only create a parameter if this combination is not yet available
+    private static Term FindOrCreateParameter(string varName, string varValue,
+      List<AutoDiff.Variable> parameters, List<string> variableNames, List<string> variableValues) {
+      Contract.Assert(variableNames.Count == variableValues.Count);
+      int idx = -1;
+      for (int i = 0; i < variableNames.Count; i++) {
+        if (variableNames[i] == varName && variableValues[i] == varValue) {
+          idx = i;
+          break;
+        }
+      }
+
+      AutoDiff.Variable par = null;
+      if (idx == -1) {
+        // not found -> create new parameter and entries in names and values lists
+        par = new AutoDiff.Variable();
+        parameters.Add(par);
+        variableNames.Add(varName);
+        variableValues.Add(varValue);
+      } else {
+        par = parameters[idx];
+      }
+      return par;
     }