Changeset 5658 for branches/DataAnalysis Refactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/AlglibUtil.cs

Timestamp:

03/10/11 12:38:43 (12 years ago)

Author:

gkronber

Message:

#1418 implemented wrapper for LDA (linear discriminant analysis) implemented in alglib.

File:

• branches/DataAnalysis Refactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/AlglibUtil.cs (moved) (moved from branches/DataAnalysis Refactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearRegressionUtil.cs) (1 diff)

branches/DataAnalysis Refactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/AlglibUtil.cs

@@ -25 +25 @@
 
 namespace HeuristicLab.Algorithms.DataAnalysis {
-  public static class LinearRegressionUtil {
-    public static double[,] PrepareInputMatrix(Dataset dataset, string targetVariable, IEnumerable<string> allowedInputVariables, int start, int end) {
-      List<int> allowedRows = CalculateAllowedRows(dataset, targetVariable, allowedInputVariables, start, end);
+  public static class AlglibUtil {
+    public static double[,] PrepareInputMatrix(Dataset dataset, IEnumerable<string> variables, IEnumerable<int> rows) {
+      List<int> allowedRows = CalculateAllowedRows(dataset, variables, rows).ToList();
 
-      double[,] matrix = new double[allowedRows.Count, allowedInputVariables.Count() + 1];
+      double[,] matrix = new double[allowedRows.Count, variables.Count()];
       for (int row = 0; row < allowedRows.Count; row++) {
         int col = 0;
-        foreach (string column in allowedInputVariables) {
+        foreach (string column in variables) {
           matrix[row, col] = dataset[column, row];
           col++;
         }
-        matrix[row, allowedInputVariables.Count()] = dataset[targetVariable, row];
       }
       return matrix;
     }
 
-    private static List<int> CalculateAllowedRows(Dataset dataset, string targetVariable, IEnumerable<string> allowedInputVariables, int start, int end) {
-      List<int> allowedRows = new List<int>();
-      bool add = false;
-
-      for (int row = start; row < end; row++) {
-        add = true;
-        foreach (string column in allowedInputVariables) {
-          double value = dataset[column, row];
-          if (double.IsInfinity(value) ||
-            double.IsNaN(value))
-            add = false;
-        }
-        if (double.IsNaN(dataset[targetVariable, row]))
-          add = false;
-        if (add)
-          allowedRows.Add(row);
-        add = true;
-      }
-      return allowedRows;
+    private static IEnumerable<int> CalculateAllowedRows(Dataset dataset, IEnumerable<string> variables, IEnumerable<int> rows) {
+      // return only rows that contain no infinity or NaN values
+      return from row in rows
+             where (from variable in variables
+                    let x = dataset[variable, row]
+                    where double.IsInfinity(x) || double.IsNaN(x)
+                    select 1)
+                    .Any() == false
+             select row;
     }
   }