Changeset 14240 for branches/symbreg-factors-2650/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearRegression.cs

Timestamp:

08/05/16 18:44:51 (8 years ago)

Author:

gkronber

Message:

#2650: added support for categorical variables to LDA and MNL (TODO: OneR )

File:

• branches/symbreg-factors-2650/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearRegression.cs (modified) (1 diff)

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

@@ -75 +75 @@
       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);
+      var factorVariables = AlglibUtil.GetFactorVariableValues(dataset, factorVariableNames, rows);
       double[,] binaryMatrix = AlglibUtil.PrepareInputMatrix(dataset, factorVariables, rows);
       double[,] doubleVarMatrix = AlglibUtil.PrepareInputMatrix(dataset, doubleVariables.Concat(new string[] { targetVariable }), rows);