Changeset 15131 for stable/HeuristicLab.Algorithms.DataAnalysis/3.4/Linear/AlglibUtil.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/AlglibUtil.cs (modified) (4 diffs)

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

@@ -20 +20 @@
 #endregion
 
+using System;
 using System.Collections.Generic;
 using System.Linq;
@@ -27 +28 @@
   public static class AlglibUtil {
     public static double[,] PrepareInputMatrix(IDataset dataset, IEnumerable<string> variables, IEnumerable<int> rows) {
-      List<string> variablesList = variables.ToList();
+      // check input variables. Only double variables are allowed.
+      var invalidInputs =
+        variables.Where(name => !dataset.VariableHasType<double>(name));
+      if (invalidInputs.Any())
+        throw new NotSupportedException("Unsupported inputs: " + string.Join(", ", invalidInputs));
+
       List<int> rowsList = rows.ToList();
-
-      double[,] matrix = new double[rowsList.Count, variablesList.Count];
+      double[,] matrix = new double[rowsList.Count, variables.Count()];
 
       int col = 0;
@@ -45 +50 @@
       return matrix;
     }
+
     public static double[,] PrepareAndScaleInputMatrix(IDataset dataset, IEnumerable<string> variables, IEnumerable<int> rows, Scaling scaling) {
+      // check input variables. Only double variables are allowed.
+      var invalidInputs =
+        variables.Where(name => !dataset.VariableHasType<double>(name));
+      if (invalidInputs.Any())
+        throw new NotSupportedException("Unsupported inputs: " + string.Join(", ", invalidInputs));
+
       List<string> variablesList = variables.ToList();
       List<int> rowsList = rows.ToList();
@@ -64 +76 @@
       return matrix;
     }
+
+    /// <summary>
+    /// Prepares a binary data matrix from a number of factors and specified factor values
+    /// </summary>
+    /// <param name="dataset">A dataset that contains the variable values</param>
+    /// <param name="factorVariables">An enumerable of categorical variables (factors). For each variable an enumerable of values must be specified.</param>
+    /// <param name="rows">An enumerable of row indices for the dataset</param>
+    /// <returns></returns>
+    /// <remarks>Factor variables (categorical variables) are split up into multiple binary variables one for each specified value.</remarks>
+    public static double[,] PrepareInputMatrix(
+      IDataset dataset,
+      IEnumerable<KeyValuePair<string, IEnumerable<string>>> factorVariables,
+      IEnumerable<int> rows) {
+      // check input variables. Only string variables are allowed.
+      var invalidInputs =
+        factorVariables.Select(kvp => kvp.Key).Where(name => !dataset.VariableHasType<string>(name));
+      if (invalidInputs.Any())
+        throw new NotSupportedException("Unsupported inputs: " + string.Join(", ", invalidInputs));
+
+      int numBinaryColumns = factorVariables.Sum(kvp => kvp.Value.Count());
+
+      List<int> rowsList = rows.ToList();
+      double[,] matrix = new double[rowsList.Count, numBinaryColumns];
+
+      int col = 0;
+      foreach (var kvp in factorVariables) {
+        var varName = kvp.Key;
+        var cats = kvp.Value;
+        if (!cats.Any()) continue;
+        foreach (var cat in cats) {
+          var values = dataset.GetStringValues(varName, rows);
+          int row = 0;
+          foreach (var value in values) {
+            matrix[row, col] = value == cat ? 1 : 0;
+            row++;
+          }
+          col++;
+        }
+      }
+      return matrix;
+    }
+
+    public static IEnumerable<KeyValuePair<string, IEnumerable<string>>> GetFactorVariableValues(IDataset ds, IEnumerable<string> factorVariables, IEnumerable<int> rows) {
+      return from factor in factorVariables
+             let distinctValues = ds.GetStringValues(factor, rows).Distinct().ToArray()
+             // 1 distinct value => skip (constant)
+             // 2 distinct values => only take one of the two values
+             // >=3 distinct values => create a binary value for each value
+             let reducedValues = distinctValues.Length <= 2
+               ? distinctValues.Take(distinctValues.Length - 1)
+               : distinctValues
+             select new KeyValuePair<string, IEnumerable<string>>(factor, reducedValues);
+    }
   }
 }