Changeset 16160 for stable/HeuristicLab.Algorithms.DataAnalysis

Timestamp:

09/20/18 14:43:40 (6 years ago)

Author:

gkronber

Message:

#2905: merged r15854 from trunk to stable

Location:

stable

Files:

• . (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4 (modified) (1 prop)
• HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorMachineModel.cs (modified) (1 diff)
• HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorMachineUtil.cs (modified) (2 diffs)

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorMachineModel.cs

@@ -155 +155 @@
     private IEnumerable<double> GetEstimatedValuesHelper(IDataset dataset, IEnumerable<int> rows) {
       // calculate predictions for the currently requested rows
-      svm_problem problem = SupportVectorMachineUtil.CreateSvmProblem(dataset, TargetVariable, allowedInputVariables, rows);
+      svm_problem problem = SupportVectorMachineUtil.CreateSvmProblem(dataset, allowedInputVariables, rows);
       svm_problem scaledProblem = rangeTransform.Scale(problem);
 

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/SupportVectorMachine/SupportVectorMachineUtil.cs

@@ -35 +35 @@
   public class SupportVectorMachineUtil {
     /// <summary>
-    /// Transforms <paramref name="problemData"/> into a data structure as needed by libSVM.
-    /// </summary>
-    /// <param name="problemData">The problem data to transform</param>
+    /// Transforms <paramref name="dataset"/> into a data structure as needed by libSVM.
+    /// </summary>
+    /// <param name="dataset">The source dataset</param>
+    /// <param name="targetVariable">The target variable</param>
+    /// <param name="inputVariables">The selected input variables to include in the svm_problem.</param>
     /// <param name="rowIndices">The rows of the dataset that should be contained in the resulting SVM-problem</param>
     /// <returns>A problem data type that can be used to train a support vector machine.</returns>
     public static svm_problem CreateSvmProblem(IDataset dataset, string targetVariable, IEnumerable<string> inputVariables, IEnumerable<int> rowIndices) {
-      double[] targetVector = dataset.GetDoubleValues(targetVariable, rowIndices).ToArray();
-      svm_node[][] nodes = new svm_node[targetVector.Length][];
+      double[] targetVector ;
+      var nRows = rowIndices.Count();
+      if (string.IsNullOrEmpty(targetVariable)) {
+        // if the target variable is not set (e.g. for prediction of a trained model) we just use a zero vector
+        targetVector = new double[nRows];
+      } else {
+        targetVector = dataset.GetDoubleValues(targetVariable, rowIndices).ToArray();
+      }
+      svm_node[][] nodes = new svm_node[nRows][];
       int maxNodeIndex = 0;
       int svmProblemRowIndex = 0;
@@ -66 +75 @@
 
     /// <summary>
+    /// Transforms <paramref name="dataset"/> into a data structure as needed by libSVM for prediction.
+    /// </summary>
+    /// <param name="dataset">The problem data to transform</param>
+    /// <param name="inputVariables">The selected input variables to include in the svm_problem.</param>
+    /// <param name="rowIndices">The rows of the dataset that should be contained in the resulting SVM-problem</param>
+    /// <returns>A problem data type that can be used for prediction with a trained support vector machine.</returns>
+    public static svm_problem CreateSvmProblem(IDataset dataset, IEnumerable<string> inputVariables, IEnumerable<int> rowIndices) {
+      // for prediction we don't need a target variable
+      return CreateSvmProblem(dataset, string.Empty, inputVariables, rowIndices);
+    }
+
+    /// <summary>
     /// Instantiate and return a svm_parameter object with default values.
     /// </summary>