Changeset 8566 for trunk/sources/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Regression

Timestamp:

09/04/12 11:32:31 (12 years ago)

Author:

gkronber

Message:

#1927 implemented check to deactivate input variables that are constant in the training partition in the CSV problem instance providers for regression, classification and clustering.

File:

• trunk/sources/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Regression/CSV/RegressionCSVInstanceProvider.cs (modified) (2 diffs)

trunk/sources/HeuristicLab.Problems.Instances.DataAnalysis/3.3/Regression/CSV/RegressionCSVInstanceProvider.cs

@@ -26 +26 @@
 using System.Linq;
 using System.Text;
+using HeuristicLab.Common;
 using HeuristicLab.Problems.DataAnalysis;
 
@@ -60 +61 @@
 
       Dataset dataset = new Dataset(csvFileParser.VariableNames, csvFileParser.Values);
-      string targetVar = csvFileParser.VariableNames.Where(x => dataset.DoubleVariables.Contains(x)).Last();
+      string targetVar = dataset.DoubleVariables.Last();
 
-      IEnumerable<string> allowedInputVars = dataset.DoubleVariables.Where(x => !x.Equals(targetVar));
+      // turn of input variables that are constant in the training partition
+      var allowedInputVars = new List<string>();
+      var trainingIndizes = Enumerable.Range(0, (csvFileParser.Rows * 2) / 3);
+      foreach (var variableName in dataset.DoubleVariables) {
+        if (dataset.GetDoubleValues(variableName, trainingIndizes).Range() > 0 &&
+          variableName != targetVar)
+          allowedInputVars.Add(variableName);
+      }
 
-      IRegressionProblemData regData = new RegressionProblemData(dataset, allowedInputVars, targetVar);
+      IRegressionProblemData regressionData = new RegressionProblemData(dataset, allowedInputVars, targetVar);
 
-      int trainingPartEnd = csvFileParser.Rows * 2 / 3;
-      regData.TrainingPartition.Start = 0;
-      regData.TrainingPartition.End = trainingPartEnd;
-      regData.TestPartition.Start = trainingPartEnd;
-      regData.TestPartition.End = csvFileParser.Rows;
+      var trainingPartEnd = trainingIndizes.Last();
+      regressionData.TrainingPartition.Start = trainingIndizes.First();
+      regressionData.TrainingPartition.End = trainingPartEnd;
+      regressionData.TestPartition.Start = trainingPartEnd;
+      regressionData.TestPartition.End = csvFileParser.Rows;
 
-      int pos = path.LastIndexOf('\\');
-      if (pos < 0)
-        regData.Name = path;
-      else {
-        pos++;
-        regData.Name = path.Substring(pos, path.Length - pos);
-      }
-      return regData;
+      regressionData.Name = Path.GetFileName(path);
+
+      return regressionData;
     }