Changeset 16408 for branches/2942_KNNRegressionClassification/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourClassification.cs

Timestamp:

12/19/18 14:56:54 (5 years ago)

Author:

msemenki

Message:

#2942: Add for KNN-Regression/Classification ability to utilize data points with zero distance to the query point. Alteration in the way weights are assigned to neighboring points (to except division-by-zero).

Location:

branches/2942_KNNRegressionClassification

Files:

• . (added)
• HeuristicLab.Algorithms.DataAnalysis (copied) (copied from trunk/HeuristicLab.Algorithms.DataAnalysis)
• HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourClassification.cs (modified) (5 diffs)

branches/2942_KNNRegressionClassification/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourClassification.cs

@@ -1 @@
-#region License Information
+#region License Information
 /* HeuristicLab
  * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
@@ -42 +42 @@
     private const string NearestNeighbourClassificationModelResultName = "Nearest neighbour classification solution";
     private const string WeightsParameterName = "Weights";
-
+    private const string SelfMatchParameterName = "SelfMatch";
 
     #region parameter properties
     public IFixedValueParameter<IntValue> KParameter {
       get { return (IFixedValueParameter<IntValue>)Parameters[KParameterName]; }
+    }
+    public IFixedValueParameter<BoolValue> SelfMatchParameter {
+      get { return (IFixedValueParameter<BoolValue>)Parameters[SelfMatchParameterName]; }
     }
     public IValueParameter<DoubleArray> WeightsParameter {
@@ -53 +56 @@
     #endregion
     #region properties
+    public bool SelfMatch {
+      get { return SelfMatchParameter.Value.Value; }
+      set { SelfMatchParameter.Value.Value = value; }
+    }
     public int K {
       get { return KParameter.Value.Value; }
@@ -73 +80 @@
     public NearestNeighbourClassification()
       : base() {
+      Parameters.Add(new FixedValueParameter<BoolValue>(SelfMatchParameterName, "Should we use equal points for classification?", new BoolValue(false)));
       Parameters.Add(new FixedValueParameter<IntValue>(KParameterName, "The number of nearest neighbours to consider for regression.", new IntValue(3)));
       Parameters.Add(new OptionalValueParameter<DoubleArray>(WeightsParameterName, "Optional: use weights to specify individual scaling values for all features. If not set the weights are calculated automatically (each feature is scaled to unit variance)"));
@@ -95 +103 @@
       double[] weights = null;
       if (Weights != null) weights = Weights.CloneAsArray();
-      var solution = CreateNearestNeighbourClassificationSolution(Problem.ProblemData, K, weights);
+      var solution = CreateNearestNeighbourClassificationSolution(Problem.ProblemData, K, SelfMatch, weights);
       Results.Add(new Result(NearestNeighbourClassificationModelResultName, "The nearest neighbour classification solution.", solution));
     }
 
-    public static IClassificationSolution CreateNearestNeighbourClassificationSolution(IClassificationProblemData problemData, int k, double[] weights = null) {
+    public static IClassificationSolution CreateNearestNeighbourClassificationSolution(IClassificationProblemData problemData, int k, bool selfMatch = false, double[] weights = null) {
       var problemDataClone = (IClassificationProblemData)problemData.Clone();
-      return new NearestNeighbourClassificationSolution(Train(problemDataClone, k, weights), problemDataClone);
+      return new NearestNeighbourClassificationSolution(Train(problemDataClone, k, selfMatch, weights), problemDataClone);
     }
 
-    public static INearestNeighbourModel Train(IClassificationProblemData problemData, int k, double[] weights = null) {
+    public static INearestNeighbourModel Train(IClassificationProblemData problemData, int k, bool selfMatch = false, double[] weights = null) {
       return new NearestNeighbourModel(problemData.Dataset,
         problemData.TrainingIndices,
         k,
+        selfMatch,
         problemData.TargetVariable,
         problemData.AllowedInputVariables,