Coreset & Yinyang exclusive euclidean support

Author: PyDataBlog

src/coreset.jl

@@ -35,7 +35,7 @@ Coreset(; m = 100, alg = Lloyd()) = Coreset(m, alg)
 Coreset(m::Int) = Coreset(m, Lloyd())
 Coreset(alg::AbstractKMeansAlg) = Coreset(100, alg)
 
-function kmeans!(alg::Coreset, containers, X, k, weights, metric=Euclidean();
+function kmeans!(alg::Coreset, containers, X, k, weights, metric::Euclidean = Euclidean();
                 n_threads = Threads.nthreads(),
                 k_init = "k-means++", max_iters = 300,
                 tol = eltype(design_matrix)(1e-6), verbose = false,

src/yinyang.jl

@@ -47,12 +47,17 @@ Yinyang(; group_size = 7, auto = true) = Yinyang(auto, group_size)
 阴阳(group_size::Int) = Yinyang(true, group_size)
 阴阳(; group_size = 7, auto = true) = Yinyang(auto, group_size)
 
-function kmeans!(alg::Yinyang, containers, X, k, weights, metric=Euclidean();
+metric_checker(metric::Euclidean) = Euclidean()
+metric_checker(metric::Metric) = throw(error("Euclidean() is the only supported distance metric."))
+
+
+function kmeans!(alg::Yinyang, containers, X, k, weights, metric::Euclidean = Euclidean();
                 n_threads = Threads.nthreads(),
                 k_init = "k-means++", max_iters = 300,
                 tol = 1e-6, verbose = false,
                 init = nothing, rng = Random.GLOBAL_RNG)
 
+    #metric = metric_checker(metric)
     nrow, ncol = size(X)
 
     centroids = init == nothing ? smart_init(X, k, n_threads, weights, rng, init=k_init).centroids : deepcopy(init)

test/test06_yinyang.jl

@@ -198,29 +198,11 @@ end
     @test !alg.auto
 end
 
-@testset "Yinyang metric support" begin
+@testset "Yinyang non-euclidean metric error" begin
     rng = StableRNG(2020)
     X = [1. 2. 4.;]
 
-    res = kmeans(Yinyang(), X, 2; tol = 1e-16, metric=Cityblock(), rng = rng)
-
-    @test res.assignments == [2, 2, 1]
-    @test res.centers == [4.0 1.5]
-    @test res.totalcost == 1.0
-    @test res.converged
-
-    rng = StableRNG(2020)
-    X = rand(3, 100)
-    rng_orig = deepcopy(rng)
-
-    baseline = kmeans(Lloyd(), X, 2, tol = 1e-16, metric=Cityblock(), rng = rng)
-
-    rng = deepcopy(rng_orig)
-    res = kmeans(Yinyang(), X, 2; tol = 1e-16, metric=Cityblock(), rng = rng)
-
-    @test res.totalcost ≈ baseline.totalcost
-    @test res.converged == baseline.converged
-    @test res.iterations == baseline.iterations
+    @test_throws MethodError res = kmeans(Yinyang(), X, 2; tol = 1e-16, metric=Cityblock(), rng = rng)
 end
 
 end # module

test/test07_coreset.jl

@@ -47,29 +47,11 @@ end
     @test alg.alg == Hamerly()
 end
 
-@testset "Coreset metric support" begin
+@testset "Coreset non-euclidean metric error" begin
     rng = StableRNG(2020)
     X = [1. 2. 4.;]
 
-    res = kmeans(Coreset(), X, 2; tol = 1e-16, metric=Cityblock(), rng = rng)
-
-    @test res.assignments == [2, 2, 1]
-    @test res.centers ≈ [4.0 1.4865168535972686]
-    @test res.totalcost == 1.0
-    @test res.converged
-
-
-    rng = StableRNG(2020)
-    X = rand(rng, 3, 100)
-    rng_orig = deepcopy(rng)
-
-    baseline = kmeans(Lloyd(), X, 10, tol = 1e-10, metric=Cityblock(), rng = rng, n_threads = 1)
-    rng = deepcopy(rng_orig)
-    res = kmeans(Coreset(), X, 10; tol = 1e-10, metric = Cityblock(), rng = rng, n_threads = 1)
-
-    @test res.converged == baseline.converged
-    @test res.iterations == baseline.iterations
-    @test floor(res.totalcost - baseline.totalcost) ≤ 1
+    @test_throws MethodError res = kmeans(Coreset(), X, 2; tol = 1e-16, metric=Cityblock(), rng = rng)
 
 end