Changeset 5658 for branches/DataAnalysis Refactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/kMeans

Timestamp:

03/10/11 12:38:43 (14 years ago)

Author:

gkronber

Message:

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

Location:

branches/DataAnalysis Refactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/kMeans

Files:

• KMeansClustering.cs (modified) (1 diff)
• KMeansClusteringModel.cs (modified) (1 diff)
• KMeansClusteringUtil.cs (modified) (1 diff)

branches/DataAnalysis Refactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/kMeans/KMeansClustering.cs

@@ -94 +94 @@
       double[,] centers;
       int[] xyc;
-      double[,] inputMatrix = KMeansClusteringUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
+      double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
       alglib.kmeansgenerate(inputMatrix, inputMatrix.GetLength(0), inputMatrix.GetLength(1), k, restarts + 1, out info, out centers, out xyc);
       if (info != 1) throw new ArgumentException("Error in calculation of k-Means clustering solution");

branches/DataAnalysis Refactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/kMeans/KMeansClusteringModel.cs

@@ -64 +64 @@
     public KMeansClusteringModel(double[,] centers, IEnumerable<string> allowedInputVariables)
       : base() {
+      this.name = ItemName;
+      this.description = ItemDescription;
       // disect center matrix into list of double[]
       // centers are given as double matrix where number of rows = dimensions and number of columns = clusters

branches/DataAnalysis Refactoring/HeuristicLab.Algorithms.DataAnalysis/3.4/kMeans/KMeansClusteringUtil.cs

@@ -27 +27 @@
 namespace HeuristicLab.Algorithms.DataAnalysis {
   public static class KMeansClusteringUtil {
-    public static double[,] PrepareInputMatrix(Dataset dataset, IEnumerable<string> allowedInputVariables, IEnumerable<int> rows) {
-      List<int> allowedRows = CalculateAllowedRows(dataset, allowedInputVariables, rows).ToList();
-
-      double[,] matrix = new double[allowedRows.Count, allowedInputVariables.Count()];
-      for (int row = 0; row < allowedRows.Count; row++) {
-        int col = 0;
-        foreach (string column in allowedInputVariables) {
-          matrix[row, col] = dataset[column, row];
-          col++;
-        }
-      }
-      return matrix;
-    }
-
-    private static IEnumerable<int> CalculateAllowedRows(Dataset dataset, IEnumerable<string> allowedInputVariables, IEnumerable<int> rows) {
-      // return only rows that contain no infinity or NaN values
-      return from row in rows
-             where (from inputVariable in allowedInputVariables
-                    let x = dataset[inputVariable, row]
-                    where double.IsInfinity(x) || double.IsNaN(x)
-                    select 1)
-                    .Any() == false
-             select row;
-    }
-
     public static IEnumerable<int> FindClosestCenters(IEnumerable<double[]> centers, Dataset dataset, IEnumerable<string> allowedInputVariables, IEnumerable<int> rows) {
       int nRows = rows.Count();