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

Timestamp:

12/19/18 14:56:54 (6 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/NearestNeighbourModel.cs (modified) (8 diffs)

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

@@ -1 @@
-#region License Information
+#region License Information
 /* HeuristicLab
  * Copyright (C) 2002-2018 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
@@ -37 +37 @@
 
     private readonly object kdTreeLockObject = new object();
+
     private alglib.nearestneighbor.kdtree kdTree;
     public alglib.nearestneighbor.kdtree KDTree {
@@ -60 +61 @@
     [Storable]
     private int k;
+    [Storable]
+    private bool selfMatch;
     [Storable(DefaultValue = null)]
     private double[] weights; // not set for old versions loaded from disk
@@ -97 +100 @@
       kdTree.x = (double[])original.kdTree.x.Clone();
       kdTree.xy = (double[,])original.kdTree.xy.Clone();
-
+      selfMatch = original.selfMatch;
       k = original.k;
       isCompatibilityLoaded = original.IsCompatibilityLoaded;
@@ -110 +113 @@
         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();
@@ -132 +136 @@
             .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
@@ -201 +205 @@
         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) {
+          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;
@@ -238 +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);