Changeset 13083 for branches/ClassificationModelComparison/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblemData.cs

Timestamp:

10/29/15 18:33:51 (8 years ago)

Author:

gkronber

Message:

#1998: merged changesets r10551:13081 (only on HeuristicLab.Problems.DataAnalysis) from trunk to branch

Location:

branches/ClassificationModelComparison/HeuristicLab.Problems.DataAnalysis

Files:

• . (modified) (1 prop)
• 3.4/Implementation/Classification/ClassificationProblemData.cs (modified) (13 diffs)

branches/ClassificationModelComparison/HeuristicLab.Problems.DataAnalysis/3.4/Implementation/Classification/ClassificationProblemData.cs

@@ -1 +1 @@
 #region License Information
 /* HeuristicLab
- * Copyright (C) 2002-2013 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
+ * Copyright (C) 2002-2015 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
  *
  * This file is part of HeuristicLab.
@@ -36 +36 @@
     protected const string ClassNamesParameterName = "ClassNames";
     protected const string ClassificationPenaltiesParameterName = "ClassificationPenalties";
+    protected const string PositiveClassParameterName = "PositiveClass";
     protected const int MaximumNumberOfClasses = 100;
     protected const int InspectedRowsToDetermineTargets = 2000;
@@ -213 +214 @@
       get { return (IFixedValueParameter<StringMatrix>)Parameters[ClassNamesParameterName]; }
     }
+    public IConstrainedValueParameter<StringValue> PositiveClassParameter {
+      get { return (IConstrainedValueParameter<StringValue>)Parameters[PositiveClassParameterName]; }
+    }
     public IFixedValueParameter<DoubleMatrix> ClassificationPenaltiesParameter {
       get { return (IFixedValueParameter<DoubleMatrix>)Parameters[ClassificationPenaltiesParameterName]; }
@@ -262 +266 @@
       get { return ClassNamesCache; }
     }
+
+    public string PositiveClass {
+      get { return PositiveClassParameter.Value.Value; }
+      set {
+        var matchingValue = PositiveClassParameter.ValidValues.SingleOrDefault(x => x.Value == value);
+        if (matchingValue == null) throw new ArgumentException(string.Format("{0} cannot be set as positive class.", value));
+        PositiveClassParameter.Value = matchingValue;
+      }
+    }
     #endregion
 
@@ -270 +283 @@
     private void AfterDeserialization() {
       RegisterParameterEvents();
+      // BackwardsCompatibility3.4
+      #region Backwards compatible code, remove with 3.5
+      if (!Parameters.ContainsKey(PositiveClassParameterName)) {
+        var validValues = new ItemSet<StringValue>(ClassNames.Select(s => new StringValue(s).AsReadOnly()));
+        Parameters.Add(new ConstrainedValueParameter<StringValue>(PositiveClassParameterName,
+          "The positive class which is used for quality measure calculation (e.g., specifity, sensitivity,...)", validValues, validValues.First()));
+      }
+      #endregion
+
     }
 
@@ -290 +312 @@
       TestPartition.End = classificationProblemData.TestPartition.End;
 
+      PositiveClass = classificationProblemData.PositiveClass;
+
       for (int i = 0; i < classificationProblemData.ClassNames.Count(); i++)
         ClassNamesParameter.Value[i, 0] = classificationProblemData.ClassNames.ElementAt(i);
@@ -300 +324 @@
     }
 
-    public ClassificationProblemData(Dataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable)
-      : base(dataset, allowedInputVariables) {
+    public ClassificationProblemData(IDataset dataset, IEnumerable<string> allowedInputVariables, string targetVariable, IEnumerable<ITransformation> transformations = null)
+      : base(dataset, allowedInputVariables, transformations ?? Enumerable.Empty<ITransformation>()) {
       var validTargetVariableValues = CheckVariablesForPossibleTargetVariables(dataset).Select(x => new StringValue(x).AsReadOnly()).ToList();
       var target = validTargetVariableValues.Where(x => x.Value == targetVariable).DefaultIfEmpty(validTargetVariableValues.First()).First();
@@ -307 +331 @@
       Parameters.Add(new ConstrainedValueParameter<StringValue>(TargetVariableParameterName, new ItemSet<StringValue>(validTargetVariableValues), target));
       Parameters.Add(new FixedValueParameter<StringMatrix>(ClassNamesParameterName, ""));
+      Parameters.Add(new ConstrainedValueParameter<StringValue>(PositiveClassParameterName, "The positive class which is used for quality measure calculation (e.g., specifity, sensitivity,...)"));
       Parameters.Add(new FixedValueParameter<DoubleMatrix>(ClassificationPenaltiesParameterName, ""));
 
@@ -313 +338 @@
     }
 
-    public static IEnumerable<string> CheckVariablesForPossibleTargetVariables(Dataset dataset) {
+    public static IEnumerable<string> CheckVariablesForPossibleTargetVariables(IDataset dataset) {
       int maxSamples = Math.Min(InspectedRowsToDetermineTargets, dataset.Rows);
       var validTargetVariables = (from v in dataset.DoubleVariables
@@ -339 +364 @@
       ClassNamesParameter.Value.ColumnNames = new List<string>() { "ClassNames" };
       ClassNamesParameter.Value.RowNames = ClassValues.Select(s => "ClassValue: " + s);
+
+      PositiveClassParameter.ValidValues.Clear();
+      foreach (var className in ClassNames) {
+        PositiveClassParameter.ValidValues.Add(new StringValue(className).AsReadOnly());
+      }
 
       ((IStringConvertibleMatrix)ClassificationPenaltiesParameter.Value).Rows = Classes;
@@ -411 +441 @@
     }
     private void Parameter_ValueChanged(object sender, EventArgs e) {
+      var oldPositiveClass = PositiveClass;
+      var oldClassNames = classNamesCache;
+      var index = oldClassNames.IndexOf(oldPositiveClass);
+
       classNamesCache = null;
       ClassificationPenaltiesParameter.Value.RowNames = ClassNames.Select(name => "Actual " + name);
       ClassificationPenaltiesParameter.Value.ColumnNames = ClassNames.Select(name => "Estimated " + name);
+
+      PositiveClassParameter.ValidValues.Clear();
+      foreach (var className in ClassNames) {
+        PositiveClassParameter.ValidValues.Add(new StringValue(className).AsReadOnly());
+      }
+      PositiveClassParameter.Value = PositiveClassParameter.ValidValues.ElementAt(index);
+
       OnChanged();
     }
@@ -435 +476 @@
       if (!newClassValues.SequenceEqual(ClassValues)) {
         errorMessage = errorMessage + string.Format("The class values differ in the provided classification problem data.");
-        return false;
+        returnValue = false;
+      }
+
+      var newPositivieClassName = classificationProblemData.PositiveClass;
+      if (newPositivieClassName != PositiveClass) {
+        errorMessage = errorMessage + string.Format("The positive class differs in the provided classification problem data.");
+        returnValue = false;
       }
 
@@ -452 +499 @@
         ClassNamesParameter.Value[i, 0] = classificationProblemData.ClassNames.ElementAt(i);
 
+      PositiveClass = classificationProblemData.PositiveClass;
+
       for (int i = 0; i < Classes; i++) {
         for (int j = 0; j < Classes; j++) {