Changeset 14767 for branches/TSNE/HeuristicLab.Algorithms.DataAnalysis/3.4/TSNE/Distances

Timestamp:

03/19/17 18:47:00 (7 years ago)

Author:

gkronber

Message:

#2700: made some changes while reviewing the code

Location:

branches/TSNE/HeuristicLab.Algorithms.DataAnalysis/3.4/TSNE/Distances

Files:

• DataPointDistance.cs (modified) (1 diff)
• DistanceBase.cs (modified) (1 diff)
• EuclidianDistance.cs (modified) (2 diffs)
• FuctionalDistance.cs (deleted)
• InnerProductDistance.cs (modified) (2 diffs)

branches/TSNE/HeuristicLab.Algorithms.DataAnalysis/3.4/TSNE/Distances/DataPointDistance.cs

@@ -49 +49 @@
       return dist.Get(a.X, b.X);
     }
-
-    public override double Get(IDataPoint<T> a, IDataPoint<T> b, double threshold) {
-      return dist.Get(a.X, b.X, threshold);
-    }
   }
 }

branches/TSNE/HeuristicLab.Algorithms.DataAnalysis/3.4/TSNE/Distances/DistanceBase.cs

@@ -37 +37 @@
 
     public abstract double Get(T a, T b);
-    public abstract double Get(T a, T b, double threshold);
 
     public IComparer<T> GetDistanceComparer(T item) {

branches/TSNE/HeuristicLab.Algorithms.DataAnalysis/3.4/TSNE/Distances/EuclidianDistance.cs

@@ -45 +45 @@
       return Math.Sqrt(point1.Zip(point2, (a1, b1) => (a1 - b1) * (a1 - b1)).Sum());
     }
-    public static double GetDistance(IEnumerable<double> a, IEnumerable<double> b, double threshold) {
-      double sum = 0;
-      var it1 = a.GetEnumerator();
-      var it2 = b.GetEnumerator();
-      while (sum > threshold * threshold && it1.MoveNext() && it2.MoveNext()) {
-        var d = it1.Current - it2.Current;
-        sum += d * d;
-      }
-      it1.Dispose();
-      it2.Dispose();
-      return sum;
-    }
     #endregion
 
@@ -62 +50 @@
       return GetDistance(a.ToArray(), b.ToArray());
     }
-    public override double Get(IEnumerable<double> a, IEnumerable<double> b, double threshold) {
-      return GetDistance(a, b, threshold);
-    }
   }
 }

branches/TSNE/HeuristicLab.Algorithms.DataAnalysis/3.4/TSNE/Distances/InnerProductDistance.cs

@@ -30 +30 @@
 
   /// <summary>
-  /// this is not a proper distance 
+  /// The angluar distance as defined as a normalized distance measure dependent on the angle between two vectors.
+  /// It is designed for vectors with all positive coordinates.
   /// </summary>
   [StorableClass]
-  [Item("InnerProductDistance", "The Angluar Distance as defined as a normalized distance measure dependent on the angle between two vectors.\nIt is designed for vectors with all positive coordinates")]
-  public class InnerProductDistance : DistanceBase<IReadOnlyList<double>> {
+  [Item("InnerProductDistance", "The angluar distance as defined as a normalized distance measure dependent on the angle between two vectors.\nIt is designed for vectors with all positive coordinates")]
+  public class InnerProductDistance : DistanceBase<IEnumerable<double>> {
 
     #region HLConstructors
@@ -48 +49 @@
 
     #region statics
-    public static double GetDistance(IReadOnlyList<double> point1, IReadOnlyList<double> point2) {
-      if (point1.Count != point2.Count) throw new ArgumentException("Inner Product distance not defined on vectors of different length");
-      return point1.Zip(point2, (x, y) => x * y).Sum();
-    }
-    public static double GetDistance(IEnumerable<double> a, IEnumerable<double> b, double threshold) {
-      return GetDistance(a.ToArray(), b.ToArray());     //no shortcut evaluation for Inner Product (summands may be negative => no way of telling if threshold is reached or not)
+    public static double GetDistance(IEnumerable<double> point1, IEnumerable<double> point2) {
+      var xs = point1.GetEnumerator();
+      var ys = point2.GetEnumerator();
+      var sum = 0.0;
+      while(xs.MoveNext() & ys.MoveNext()) {
+        if(xs.Current < 0 || ys.Current < 0) throw new ArgumentException("Inner product distance is only defined for vectors with non-negative elements");
+        sum += xs.Current * ys.Current;
+      }
+      if(xs.MoveNext() || ys.MoveNext()) throw new ArgumentException("Enumerables contain a different number of elements");
+      return sum;
     }
     #endregion
-    public override double Get(IReadOnlyList<double> a, IReadOnlyList<double> b) {
+    public override double Get(IEnumerable<double> a, IEnumerable<double> b) {
       return GetDistance(a, b);
-    }
-    public override double Get(IReadOnlyList<double> a, IReadOnlyList<double> b, double threshold) {
-      return GetDistance(a, b, threshold);
     }
   }