Solves # 71 and push to v0.11.4

Project.toml

@@ -1,7 +1,7 @@
 name = "BetaML"
 uuid = "024491cd-cc6b-443e-8034-08ea7eb7db2b"
 authors = ["Antonello Lobianco <[email protected]>"]
-version = "0.11.3"
+version = "0.11.4"
 
 [deps]
 AbstractTrees = "1520ce14-60c1-5f80-bbc7-55ef81b5835c"

src/Clustering/Clustering_hard.jl

@@ -250,7 +250,7 @@ $(TYPEDFIELDS)
 Base.@kwdef mutable struct KMeansC_hp <: BetaMLHyperParametersSet
     "Number of classes to discriminate the data [def: 3]"
     n_classes::Int64                  = 3
-    "Function to employ as distance. Default to the Euclidean distance. Can be one of the predefined distances (`l1_distance`, `l2_distance`, `l2squared_distance`),  `cosine_distance`), any user defined function accepting two vectors and returning a scalar or an anonymous function with the same characteristics. Attention that the `KMeansClusterer` algorithm is not guaranteed to converge with other distances than the Euclidean one."
+    "Function to employ as distance. Default to the Euclidean distance. Can be one of the predefined distances (`l1_distance`, `l2_distance`, `l2squared_distance`,  `cosine_distance`), any user defined function accepting two vectors and returning a scalar or an anonymous function with the same characteristics. Attention that the `KMeansClusterer` algorithm is not guaranteed to converge with other distances than the Euclidean one."
     dist::Function                    = (x,y) -> norm(x-y)
     """
     The computation method of the vector of the initial representatives.
@@ -276,7 +276,7 @@ $(TYPEDFIELDS)
 Base.@kwdef mutable struct KMedoidsC_hp <: BetaMLHyperParametersSet
     "Number of classes to discriminate the data [def: 3]"
     n_classes::Int64                  = 3
-    "Function to employ as distance. Default to the Euclidean distance. Can be one of the predefined distances (`l1_distance`, `l2_distance`, `l2squared_distance`),  `cosine_distance`), any user defined function accepting two vectors and returning a scalar or an anonymous function with the same characteristics. Attention that the `KMeansClusterer` algorithm is not guaranteed to converge with other distances than the Euclidean one."
+    "Function to employ as distance. Default to the Euclidean distance. Can be one of the predefined distances (`l1_distance`, `l2_distance`, `l2squared_distance`,  `cosine_distance`), any user defined function accepting two vectors and returning a scalar or an anonymous function with the same characteristics. Attention that the `KMeansClusterer` algorithm is not guaranteed to converge with other distances than the Euclidean one."
     dist::Function                    = (x,y) -> norm(x-y)
     """
     The computation method of the vector of the initial representatives.

src/Utils/Measures.jl

@@ -6,14 +6,15 @@
 # ------------------------------------------------------------------------------
 # Some common distance measures
 
+# https://weaviate.io/blog/distance-metrics-in-vector-search
 """L1 norm distance (aka _Manhattan Distance_)"""
 l1_distance(x,y)     = sum(abs.(x-y))
 """Euclidean (L2) distance"""
 l2_distance(x,y)     = norm(x-y)
 """Squared Euclidean (L2) distance"""
 l2squared_distance(x,y)    = norm(x-y)^2
 """Cosine distance"""
-cosine_distance(x,y) = dot(x,y)/(norm(x)*norm(y))
+cosine_distance(x,y) = 1-dot(x,y)/(norm(x)*norm(y))
 """
 $(TYPEDSIGNATURES)
 

test/Utils_tests.jl

@@ -723,6 +723,12 @@ size(w2) == (4,)
 eltype(w2) == Float64
 
 
+# ==================================
+# New test
+println("** Testing cosine distance....")
+x = [0,1]; y = [1,0]
+@test cosine_distance(x,y) == 1
+
 # MLJ Tests
 # ==================================
 # NEW TEST