Minor cleanup for v0.1.7

Author: PyDataBlog

Project.toml

@@ -15,6 +15,7 @@ Distances = "0.8.2"
 MLJModelInterface = "0.2.1"
 StatsBase = "0.32, 0.33"
 julia = "1.3"
+UnsafeArrays = "1"
 
 [extras]
 MLJBase = "a7f614a8-145f-11e9-1d2a-a57a1082229d"

README.md

@@ -11,7 +11,7 @@ ________________________________________________________________________________
 _________________________________________________________________________________________________________
 
 <div align="center">
-    <b>Classic & Contemporary Variants Of K-Means In Sonic Mode<b>
+    <b>Classic & Contemporary Variants Of K-Means In Sonic Mode</b>
 </div>
 
 <p align="center">

benchmark/bench01_distance.jl

@@ -9,13 +9,13 @@ suite = BenchmarkGroup()
 Random.seed!(2020)
 X = rand(3, 100_000)
 centroids = rand(3, 2)
-d = Vector{Float64}(undef, 100_000)
-suite["100kx3"] = @benchmarkable ParallelKMeans.chunk_colwise($d, $X, $centroids, 1, nothing, Euclidean(), 1:100_000, 1)
+d = fill(-Inf, 100_000)
+suite["100kx3"] = @benchmarkable ParallelKMeans.chunk_colwise(d1, $X, $centroids, 1, nothing, Euclidean(), 1:100_000, 1) setup=(d1 = copy(d))
 
 X = rand(10, 100_000)
 centroids = rand(10, 2)
-d = Vector{Float64}(undef, 100_000)
-suite["100kx10"] = @benchmarkable ParallelKMeans.chunk_colwise($d, $X, $centroids, 1, nothing, Euclidean(), 1:100_000, 1)
+d = fill(-Inf, 100_000)
+suite["100kx10"] = @benchmarkable ParallelKMeans.chunk_colwise(d1, $X, $centroids, 1, nothing, Euclidean(), 1:100_000, 1) setup=(d1 = copy(d))
 
 end # module
 

docs/src/index.md

@@ -80,7 +80,6 @@ pkg> free ParallelKMeans
 - [X] Support of MLJ Random generation hyperparameter.
 - [ ] Support for other distance metrics supported by [Distances.jl](https://github.com/JuliaStats/Distances.jl#supported-distances).
 - [ ] Implementation of [Geometric methods to accelerate k-means algorithm](http://cs.baylor.edu/~hamerly/papers/sdm2016_rysavy_hamerly.pdf).
-- [ ] Support of MLJ Random generation hyperparameter.
 - [ ] Native support for tabular data inputs outside of MLJModels' interface.
 - [ ] Refactoring and finalization of API design.
 - [ ] GPU support.

src/hamerly.jl

@@ -149,8 +149,7 @@ function update_containers(::Hamerly, containers, centroids, n_threads, metric)
     s .= T(Inf)
     @inbounds for i in axes(centroids, 2)
         for j in i+1:size(centroids, 2)
-            d = distance(metric, centroids, centroids, i, j)
-            d = T(centers_coefficient(metric)) * d
+            d = T(centers_coefficient(metric)) * distance(metric, centroids, centroids, i, j)
             s[i] = s[i] > d ? d : s[i]
             s[j] = s[j] > d ? d : s[j]
         end

src/kmeans.jl

@@ -205,4 +205,4 @@ end
 
 # Special center co-efficent dispatched on Euclidean or different metrics supported by Distances.jl
 centers_coefficient(::Euclidean) = 0.25
-centers_coefficient(::Distances.Metric) = 0.5
+centers_coefficient(::Metric) = 0.5

test/test04_elkan.jl

@@ -108,6 +108,7 @@ end
     res = kmeans(Elkan(), X, 2; tol = 1e-16, metric = Cityblock(), rng = rng)
     @test res.totalcost ≈ 60.893492629945044
     @test res.converged
+    @test res.iterations == 6
 end
 
 end # module

test/test05_hamerly.jl

@@ -4,7 +4,6 @@ using ParallelKMeans
 using ParallelKMeans: chunk_initialize, double_argmax
 using Test
 using StableRNGs
-using Random
 using Distances