Changeset 6011 for branches/histogram/HeuristicLab.Algorithms.DataAnalysis/3.4

Timestamp:

04/15/11 14:54:43 (14 years ago)

Author:

abeham

Message:

#1465

• updated branch with changes from trunk
• fixed some bugs
• introduced secondary x-axis option

Location:

branches/histogram

Files:

• . (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/AlglibUtil.cs (modified) (2 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearDiscriminantAnalysis.cs (modified) (1 diff)
• HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/LinearRegression.cs (modified) (1 diff)
• HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorMachineUtil.cs (modified) (1 diff)
• HeuristicLab.Algorithms.DataAnalysis/3.4/kMeans/KMeansClustering.cs (modified) (1 diff)

branches/histogram/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;
-    }
   }
 }

branches/histogram/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

branches/histogram/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();

branches/histogram/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorMachineUtil.cs

@@ -41 +41 @@
       int maxNodeIndex = 0;
       int svmProblemRowIndex = 0;
+      List<string> inputVariablesList = inputVariables.ToList();
       foreach (int row in rowIndices) {
         tempRow = new List<SVM.Node>();
-        foreach (var inputVariable in inputVariables) {
-          int col = dataset.GetVariableIndex(inputVariable);
-          double value = dataset[row, col];
+        int colIndex = 1; // make sure the smallest node index for SVM = 1
+        foreach (var inputVariable in inputVariablesList) {
+          double value = dataset[row, dataset.GetVariableIndex(inputVariable)];
+          // SVM also works with missing values
+          // => don't add NaN values in the dataset to the sparse SVM matrix representation
           if (!double.IsNaN(value)) {
-            int nodeIndex = col + 1; // make sure the smallest nodeIndex is 1 (libSVM convention)
-            tempRow.Add(new SVM.Node(nodeIndex, value));
-            if (nodeIndex > maxNodeIndex) maxNodeIndex = nodeIndex;
+            tempRow.Add(new SVM.Node(colIndex, value)); // nodes must be sorted in ascending ordered by column index
+            if (colIndex > maxNodeIndex) maxNodeIndex = colIndex;
           }
+          colIndex++;
         }
-        nodes[svmProblemRowIndex++] = tempRow.OrderBy(x => x.Index).ToArray(); // make sure the values are sorted by node index
+        nodes[svmProblemRowIndex++] = tempRow.ToArray();
       }
 

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

@@ -92 +92 @@
       int[] xyc;
       double[,] inputMatrix = AlglibUtil.PrepareInputMatrix(dataset, allowedInputVariables, rows);
+      if (inputMatrix.Cast<double>().Any(x => double.IsNaN(x) || double.IsInfinity(x)))
+        throw new NotSupportedException("k-Means clustering does not support NaN or infinity values in the input dataset.");
+
       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");