Changeset 17164 for stable/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour

Timestamp:

07/23/19 20:56:15 (5 years ago)

Author:

gkronber

Message:

#2942: merged r16491 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/NearestNeighbour/NearestNeighbourClassification.cs (modified) (6 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourModel.cs (modified) (9 diffs)
• HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourRegression.cs (modified) (6 diffs)

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourClassification.cs

@@ -1 @@
-#region License Information
+#region License Information
 /* HeuristicLab
  * Copyright (C) 2002-2019 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)"));
@@ -83 +91 @@
       if (!Parameters.ContainsKey(WeightsParameterName)) {
         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)"));
+      }
+      if (!Parameters.ContainsKey(SelfMatchParameterName)) {
+        Parameters.Add(new FixedValueParameter<BoolValue>(SelfMatchParameterName, "Should we use equal points for classification?", new BoolValue(false)));
       }
       #endregion
@@ -95 +106 @@
       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,

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourModel.cs

@@ -1 @@
-#region License Information
+#region License Information
 /* HeuristicLab
  * Copyright (C) 2002-2019 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
@@ -37 +37 @@
 
     private readonly object kdTreeLockObject = new object();
+
     private alglib.nearestneighbor.kdtree kdTree;
     public alglib.nearestneighbor.kdtree KDTree {
@@ -49 +50 @@
     }
 
-
     public override IEnumerable<string> VariablesUsedForPrediction {
       get { return allowedInputVariables; }
@@ -60 +60 @@
     [Storable]
     private int k;
+    [Storable(DefaultValue = false)]
+    private bool selfMatch;
     [Storable(DefaultValue = null)]
     private double[] weights; // not set for old versions loaded from disk
@@ -95 +97 @@
       kdTree.x = (double[])original.kdTree.x.Clone();
       kdTree.xy = (double[,])original.kdTree.xy.Clone();
-
+      selfMatch = original.selfMatch;
       k = original.k;
       isCompatibilityLoaded = original.IsCompatibilityLoaded;
@@ -108 +110 @@
         this.classValues = (double[])original.classValues.Clone();
     }
-    public NearestNeighbourModel(IDataset dataset, IEnumerable<int> rows, int k, string targetVariable, IEnumerable<string> allowedInputVariables, IEnumerable<double> weights = null, double[] classValues = null)
+    public NearestNeighbourModel(IDataset dataset, IEnumerable<int> rows, int k, bool selfMatch, string targetVariable, IEnumerable<string> allowedInputVariables, IEnumerable<double> weights = null, double[] classValues = null)
       : base(targetVariable) {
       Name = ItemName;
       Description = ItemDescription;
+      this.selfMatch = selfMatch;
       this.k = k;
       this.allowedInputVariables = allowedInputVariables.ToArray();
@@ -130 +133 @@
             .Select(name => {
               var pop = dataset.GetDoubleValues(name, rows).StandardDeviationPop();
-              return  pop.IsAlmost(0) ? 1.0 : 1.0/pop;
+              return pop.IsAlmost(0) ? 1.0 : 1.0 / pop;
             })
             .Concat(new double[] { 1.0 }) // no scaling for target variable
@@ -199 +202 @@
         int numNeighbours;
         lock (kdTreeLockObject) { // gkronber: the following calls change the kdTree data structure
-          numNeighbours = alglib.nearestneighbor.kdtreequeryknn(kdTree, x, k, false);
+          numNeighbours = alglib.nearestneighbor.kdtreequeryknn(kdTree, x, k, selfMatch);
           alglib.nearestneighbor.kdtreequeryresultsdistances(kdTree, ref dists);
           alglib.nearestneighbor.kdtreequeryresultsxy(kdTree, ref neighbours);
         }
-
+        if (selfMatch) {
+          // weights for neighbours are 1/d.
+          // override distances (=0) of exact matches using 1% of the distance of the next closest non-self-match neighbour -> selfmatches weight 100x more than the next closest neighbor.
+          // if all k neighbours are selfmatches then they all have weight 0.01.
+          double minDist = dists[0] + 1;
+          for (int i = 0; i < numNeighbours; i++) {
+            if ((minDist > dists[i]) && (dists[i] != 0)) {
+              minDist = dists[i];
+            }
+          }
+          minDist /= 100.0;
+          for (int i = 0; i < numNeighbours; i++) {
+            if (dists[i] == 0) {
+              dists[i] = minDist;
+            }
+          }
+        }
         double distanceWeightedValue = 0.0;
         double distsSum = 0.0;
@@ -236 +255 @@
         lock (kdTreeLockObject) {
           // gkronber: the following calls change the kdTree data structure
-          numNeighbours = alglib.nearestneighbor.kdtreequeryknn(kdTree, x, k, false);
+          numNeighbours = alglib.nearestneighbor.kdtreequeryknn(kdTree, x, k, selfMatch);
           alglib.nearestneighbor.kdtreequeryresultsdistances(kdTree, ref dists);
           alglib.nearestneighbor.kdtreequeryresultsxy(kdTree, ref neighbours);

stable/HeuristicLab.Algorithms.DataAnalysis/3.4/NearestNeighbour/NearestNeighbourRegression.cs

@@ -41 +41 @@
     private const string NearestNeighbourRegressionModelResultName = "Nearest neighbour regression solution";
     private const string WeightsParameterName = "Weights";
+    private const string SelfMatchParameterName = "SelfMatch";
 
     #region parameter properties
@@ -46 +47 @@
       get { return (IFixedValueParameter<IntValue>)Parameters[KParameterName]; }
     }
-
+    public IFixedValueParameter<BoolValue> SelfMatchParameter {
+      get { return (IFixedValueParameter<BoolValue>)Parameters[SelfMatchParameterName]; }
+    }
     public IValueParameter<DoubleArray> WeightsParameter {
       get { return (IValueParameter<DoubleArray>)Parameters[WeightsParameterName]; }
@@ -59 +62 @@
       }
     }
-
+    public bool SelfMatch {
+      get { return SelfMatchParameter.Value.Value; }
+      set { SelfMatchParameter.Value.Value = value; }
+    }
     public DoubleArray Weights {
       get { return WeightsParameter.Value; }
@@ -75 +81 @@
       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)"));
+      Parameters.Add(new FixedValueParameter<BoolValue>(SelfMatchParameterName, "Should we use equal points for classification?", new BoolValue(false)));
       Problem = new RegressionProblem();
     }
@@ -84 +91 @@
       if (!Parameters.ContainsKey(WeightsParameterName)) {
         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)"));
+      }
+      if (!Parameters.ContainsKey(SelfMatchParameterName)) {
+        Parameters.Add(new FixedValueParameter<BoolValue>(SelfMatchParameterName, "Should we use equal points for classification?", new BoolValue(false)));
       }
       #endregion
@@ -96 +106 @@
       double[] weights = null;
       if (Weights != null) weights = Weights.CloneAsArray();
-      var solution = CreateNearestNeighbourRegressionSolution(Problem.ProblemData, K, weights);
+      var solution = CreateNearestNeighbourRegressionSolution(Problem.ProblemData, K, SelfMatch, weights);
       Results.Add(new Result(NearestNeighbourRegressionModelResultName, "The nearest neighbour regression solution.", solution));
     }
 
-    public static IRegressionSolution CreateNearestNeighbourRegressionSolution(IRegressionProblemData problemData, int k, double[] weights = null) {
+    public static IRegressionSolution CreateNearestNeighbourRegressionSolution(IRegressionProblemData problemData, int k, bool selfMatch = false, double[] weights = null) {
       var clonedProblemData = (IRegressionProblemData)problemData.Clone();
-      return new NearestNeighbourRegressionSolution(Train(problemData, k, weights), clonedProblemData);
+      return new NearestNeighbourRegressionSolution(Train(problemData, k, selfMatch, weights), clonedProblemData);
     }
 
-    public static INearestNeighbourModel Train(IRegressionProblemData problemData, int k, double[] weights = null) {
+    public static INearestNeighbourModel Train(IRegressionProblemData problemData, int k, bool selfMatch = false, double[] weights = null) {
       return new NearestNeighbourModel(problemData.Dataset,
         problemData.TrainingIndices,
         k,
+        selfMatch,
         problemData.TargetVariable,
         problemData.AllowedInputVariables,