Changeset 6002 for trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear

Timestamp:

04/11/11 18:41:03 (14 years ago)

Author:

gkronber

Message:

#790 Fixed minor issues in LDA, LR, SVC and SVR to make sure everything works correctly in presence of NaN and infinity values.

Location:

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear

Files:

• AlglibUtil.cs (modified) (2 diffs)
• LinearDiscriminantAnalysis.cs (modified) (1 diff)
• LinearRegression.cs (modified) (1 diff)

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/AlglibUtil.cs

@@ -27 +27 @@
   public static class AlglibUtil {
     public static double[,] PrepareInputMatrix(Dataset dataset, IEnumerable<string> variables, IEnumerable<int> rows) {
-      List<int> allowedRows = CalculateAllowedRows(dataset, variables, rows).ToList();
+      List<string> variablesList = variables.ToList();
+      List<int> rowsList = rows.ToList();
 
-      double[,] matrix = new double[allowedRows.Count, variables.Count()];
-      for (int row = 0; row < allowedRows.Count; row++) {
+      double[,] matrix = new double[rowsList.Count, variablesList.Count];
+      for (int row = 0; row < rowsList.Count; row++) {
         int col = 0;
         foreach (string column in variables) {
-          matrix[row, col] = dataset[column, row];
+          matrix[row, col] = dataset[column, rowsList[row]];
           col++;
         }
@@ -39 +40 @@
       return matrix;
     }
-
-    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;
-    }
   }
 }

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearDiscriminantAnalysis.cs

@@ -73 +73 @@
       int nClasses = problemData.ClassNames.Count();
       double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables.Concat(new string[] { targetVariable }), rows);
+      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.");
 
       // change class values into class index

trunk/sources/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearRegression.cs

@@ -76 +76 @@
       IEnumerable<int> rows = Enumerable.Range(samplesStart, samplesEnd - samplesStart);
       double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables.Concat(new string[] { targetVariable }), rows);
+      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.");
 
       alglib.linearmodel lm = new alglib.linearmodel();