Changeset 15131 for stable/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearDiscriminantAnalysis.cs

Timestamp:

07/06/17 10:19:37 (7 years ago)

Author:

gkronber

Message:

#2650: merged r14826 from trunk to stable. The only remaining conflict is DataTableControl and ScatterPlotControl which have been renamed within r14982 (-> tree conflict).

Location:

stable

Files:

• . (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearDiscriminantAnalysis.cs (modified) (4 diffs)

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearDiscriminantAnalysis.cs

@@ -37 +37 @@
   /// Linear discriminant analysis classification algorithm.
   /// </summary>
-  [Item("Linear Discriminant Analysis", "Linear discriminant analysis classification algorithm (wrapper for ALGLIB).")]
+  [Item("Linear Discriminant Analysis (LDA)", "Linear discriminant analysis classification algorithm (wrapper for ALGLIB).")]
   [Creatable(CreatableAttribute.Categories.DataAnalysisClassification, Priority = 100)]
   [StorableClass]
@@ -71 +71 @@
       IEnumerable<int> rows = problemData.TrainingIndices;
       int nClasses = problemData.ClassNames.Count();
-      double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables.Concat(new string[] { targetVariable }), rows);
+      var doubleVariableNames = allowedInputVariables.Where(dataset.VariableHasType<double>).ToArray();
+      var factorVariableNames = allowedInputVariables.Where(dataset.VariableHasType<string>).ToArray();
+      double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, doubleVariableNames.Concat(new string[] { targetVariable }), rows);
+
+      var factorVariables = AlglibUtil.GetFactorVariableValues(dataset, factorVariableNames, rows);
+      double[,] factorMatrix = AlglibUtil.PrepareInputMatrix(dataset, factorVariables, rows);
+
+      inputMatrix = factorMatrix.HorzCat(inputMatrix);
+
       if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
         throw new NotSupportedException("Linear discriminant analysis does not support NaN or infinity values in the input dataset.");
@@ -83 +91 @@
       int info;
       double[] w;
-      alglib.fisherlda(inputMatrix, inputMatrix.GetLength(0), allowedInputVariables.Count(), nClasses, out info, out w);
+      alglib.fisherlda(inputMatrix, inputMatrix.GetLength(0), inputMatrix.GetLength(1) - 1, nClasses, out info, out w);
       if (info < 1) throw new ArgumentException("Error in calculation of linear discriminant analysis solution");
 
@@ -93 +101 @@
 
       int col = 0;
-      foreach (string column in allowedInputVariables) {
+      foreach (var kvp in factorVariables) {
+        var varName = kvp.Key;
+        foreach (var cat in kvp.Value) {
+          BinaryFactorVariableTreeNode vNode =
+            (BinaryFactorVariableTreeNode)new HeuristicLab.Problems.DataAnalysis.Symbolic.BinaryFactorVariable().CreateTreeNode();
+          vNode.VariableName = varName;
+          vNode.VariableValue = cat;
+          vNode.Weight = w[col];
+          addition.AddSubtree(vNode);
+          col++;
+        }
+      }
+      foreach (string column in doubleVariableNames) {
         VariableTreeNode vNode = (VariableTreeNode)new HeuristicLab.Problems.DataAnalysis.Symbolic.Variable().CreateTreeNode();
         vNode.VariableName = column;