Changeset 14237 for branches/symbreg-factors-2650/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearRegression.cs

Timestamp:

08/05/16 14:25:28 (8 years ago)

Author:

gkronber

Message:

#2650: work in progress..

File:

• branches/symbreg-factors-2650/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearRegression.cs (modified) (2 diffs)

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

@@ -73 +73 @@
       IEnumerable<string> allowedInputVariables = problemData.AllowedInputVariables;
       IEnumerable<int> rows = problemData.TrainingIndices;
-      double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables.Concat(new string[] { targetVariable }), rows);
+      var doubleVariables = allowedInputVariables.Where(dataset.VariableHasType<double>);
+      var factorVariableNames = allowedInputVariables.Where(dataset.VariableHasType<string>);
+      var factorVariables = from factor in factorVariableNames
+                            let distinctValues = dataset.GetStringValues(factor, rows).Distinct().ToArray()
+                            // 1 distinct value => skip (constant)
+                            // 2 distinct values => only take one of the two values
+                            // >=3 distinct values => create a binary value for each value
+                            let reducedValues = distinctValues.Length <= 2
+                              ? distinctValues.Take(distinctValues.Length - 1)
+                              : distinctValues
+                            select new KeyValuePair<string, IEnumerable<string>>(factor, reducedValues);
+      double[,] binaryMatrix = AlglibUtil.PrepareInputMatrix(dataset, factorVariables, rows);
+      double[,] doubleVarMatrix = AlglibUtil.PrepareInputMatrix(dataset, doubleVariables.Concat(new string[] { targetVariable }), rows);
+      var inputMatrix = binaryMatrix.VertCat(doubleVarMatrix);
+
       if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
         throw new NotSupportedException("Linear regression does not support NaN or infinity values in the input dataset.");
@@ -98 +112 @@
 
       int col = 0;
-      foreach (string column in allowedInputVariables) {
+      foreach (var kvp in factorVariables) {
+        var varName = kvp.Key;
+        foreach (var cat in kvp.Value) {
+          FactorVariableTreeNode vNode =
+            (FactorVariableTreeNode)new HeuristicLab.Problems.DataAnalysis.Symbolic.FactorVariable().CreateTreeNode();
+          vNode.VariableName = varName;
+          vNode.VariableValue = cat;
+          vNode.Weight = coefficients[col];
+          addition.AddSubtree(vNode);
+          col++;
+        }
+      }
+      foreach (string column in doubleVariables) {
         VariableTreeNode vNode = (VariableTreeNode)new HeuristicLab.Problems.DataAnalysis.Symbolic.Variable().CreateTreeNode();
         vNode.VariableName = column;