From 2595c8ce09ece14da6b5bc406496e5c9cebb65c4 Mon Sep 17 00:00:00 2001
From: unknown <ogoun.er@yandex.ru>
Date: Fri, 10 Dec 2021 06:12:32 +0300
Subject: [PATCH] HNSW. New distance metrics

L1, L2, Minkowski, Chebyshev
---
 TestHNSW/HNSWDemo/Program.cs           |  6 +-
 ZeroLevel.HNSW/Utils/EuclidDistance.cs | 83 ++++++++++++++++++++++++++
 2 files changed, 88 insertions(+), 1 deletion(-)
 create mode 100644 ZeroLevel.HNSW/Utils/EuclidDistance.cs

diff --git a/TestHNSW/HNSWDemo/Program.cs b/TestHNSW/HNSWDemo/Program.cs
index 1f40801..009a04b 100644
--- a/TestHNSW/HNSWDemo/Program.cs
+++ b/TestHNSW/HNSWDemo/Program.cs
@@ -380,7 +380,11 @@ namespace HNSWDemo
             int K = 200;
             var vectors = RandomVectors(dimensionality, testCount);
 
-            var context = new SearchContext().SetActiveNodes(map.ConvertFeaturesToIds(samples.Where(p => p.Item2.Age > 20 && p.Item2.Age < 50 && p.Item2.Gender == Gender.Feemale).Select(p => p.Item2.Number)));
+            var context = new SearchContext()
+                .SetActiveNodes(map
+                    .ConvertFeaturesToIds(samples
+                        .Where(p => p.Item2.Age > 20 && p.Item2.Age < 50 && p.Item2.Gender == Gender.Feemale)
+                        .Select(p => p.Item2.Number)));
 
             var hits = 0;
             var miss = 0;
diff --git a/ZeroLevel.HNSW/Utils/EuclidDistance.cs b/ZeroLevel.HNSW/Utils/EuclidDistance.cs
new file mode 100644
index 0000000..1fa0211
--- /dev/null
+++ b/ZeroLevel.HNSW/Utils/EuclidDistance.cs
@@ -0,0 +1,83 @@
+using System;
+
+namespace ZeroLevel.HNSW.Utils
+{
+    public static class Metrics
+    {
+        /// <summary>
+        /// The taxicab metric is also known as rectilinear distance, 
+        /// L1 distance or L1 norm, city block distance, Manhattan distance, 
+        /// or Manhattan length, with the corresponding variations in the name of the geometry. 
+        /// It represents the distance between points in a city road grid. 
+        /// It examines the absolute differences between the coordinates of a pair of objects.
+        /// </summary>
+        public static float L1Manhattan(float[] v1, float[] v2)
+        {
+            float res = 0;
+            for (int i = 0; i < v1.Length; i++)
+            {
+                float t = v1[i] - v2[i];
+                res += t * t;
+            }
+            return (res);
+        }
+
+        /// <summary>
+        /// Euclidean distance is the most common use of distance. 
+        /// Euclidean distance, or simply 'distance', 
+        /// examines the root of square differences between the coordinates of a pair of objects. 
+        /// This is most generally known as the Pythagorean theorem.
+        /// </summary>
+        public static float L2Euclidean(float[] v1, float[] v2)
+        {
+            float res = 0;
+            for (int i = 0; i < v1.Length; i++)
+            {
+                float t = v1[i] - v2[i];
+                res += t * t;
+            }
+            return (float)Math.Sqrt(res);
+        }
+
+        /// <summary>
+        /// The general metric for distance is the Minkowski distance. 
+        /// When lambda is equal to 1, it becomes the city block distance (L1), 
+        /// and when lambda is equal to 2, it becomes the Euclidean distance (L2). 
+        /// The special case is when lambda is equal to infinity (taking a limit), 
+        /// where it is considered as the Chebyshev distance.
+        /// </summary>
+        public static float MinkowskiDistance(float[] v1, float[] v2, int order)
+        {
+            int count = v1.Length;
+            double sum = 0.0;
+            for (int i = 0; i < count; i++)
+            {
+                sum = sum + Math.Pow(Math.Abs(v1[i] - v2[i]), order);
+            }
+            return (float)Math.Pow(sum, (1 / order));
+        }
+
+        /// <summary>
+        /// Chebyshev distance is also called the Maximum value distance, 
+        /// defined on a vector space where the distance between two vectors is 
+        /// the greatest of their differences along any coordinate dimension. 
+        /// In other words, it examines the absolute magnitude of the differences 
+        /// between the coordinates of a pair of objects.
+        /// </summary>
+        public static double ChebyshevDistance(float[] v1, float[] v2)
+        {
+            int count = v1.Length;
+            float max = float.MinValue;
+            float c;
+            for (int i = 0; i < count; i++)
+            {
+                c = Math.Abs(v1[i] - v2[i]);
+                if (c > max)
+                {
+                    max = c;
+                }
+            }
+            return max;
+        }
+    }
+}