Moved metric internally as a positional arg

Author: PyDataBlog

src/elkan.jl

@@ -19,7 +19,7 @@ kmeans(Elkan(), X, 3) # 3 clusters, Elkan algorithm
 struct Elkan <: AbstractKMeansAlg end
 
 
-function kmeans!(alg::Elkan, containers, X, k, weights;
+function kmeans!(alg::Elkan, containers, X, k, weights=nothing, metric=Euclidean();
                 n_threads = Threads.nthreads(),
                 k_init = "k-means++", max_iters = 300,
                 tol = eltype(X)(1e-6), verbose = false,

src/hamerly.jl

@@ -18,7 +18,7 @@ kmeans(Hamerly(), X, 3) # 3 clusters, Hamerly algorithm
 struct Hamerly <: AbstractKMeansAlg end
 
 
-function kmeans!(alg::Hamerly, containers, X, k, weights;
+function kmeans!(alg::Hamerly, containers, X, k, weights=nothing, metric=Euclidean();
                 n_threads = Threads.nthreads(),
                 k_init = "k-means++", max_iters = 300,
                 tol = eltype(X)(1e-6), verbose = false,

src/kmeans.jl

@@ -168,19 +168,36 @@ alternatively one can use `rand` to choose random points for init.
 
 A `KmeansResult` structure representing labels, centroids, and sum_squares is returned.
 """
+<<<<<<< HEAD
 function kmeans(alg::AbstractKMeansAlg, design_matrix, k;
                 weights = nothing,
                 n_threads = Threads.nthreads(),
                 k_init = "k-means++", max_iters = 300,
                 tol = eltype(design_matrix)(1e-6), verbose = false,
                 init = nothing, rng = Random.GLOBAL_RNG, metric = Euclidean())
 
+=======
+function kmeans(alg::AbstractKMeansAlg, design_matrix, k, weights = nothing;
+                n_threads = Threads.nthreads(), k_init = "k-means++", max_iters = 300,
+                tol = eltype(design_matrix)(1e-6), verbose = false, init = nothing, metric=Euclidean())
+
+    # Get dimensions of the input data
+>>>>>>> Moved metric internally as a positional arg
     nrow, ncol = size(design_matrix)
+
+    # Create containers based on the dimensions and specifications
     containers = create_containers(alg, design_matrix, k, nrow, ncol, n_threads)
 
+<<<<<<< HEAD
     return kmeans!(alg, containers, design_matrix, k, weights, n_threads = n_threads,
                     k_init = k_init, max_iters = max_iters, tol = tol,
                     verbose = verbose, init = init, rng = rng, metric = metric)
+=======
+    # Dispatch based on the specified algorithm
+    return kmeans!(alg, containers, design_matrix, k, weights, metric;
+                   n_threads = n_threads, k_init = k_init, max_iters = max_iters,
+                   tol = tol, verbose = verbose, init = init)
+>>>>>>> Moved metric internally as a positional arg
 
 end
 

src/lloyd.jl

@@ -14,12 +14,13 @@ found in `kmeans`.
 Argument `containers` represent algorithm specific containers, such as labels, intermidiate
 centroids and so on, which are used during calculations.
 """
-function kmeans!(alg::Lloyd, containers, X, k, weights;
+function kmeans!(alg::Lloyd, containers, X, k, weights=nothing, metric=Euclidean();
                 n_threads = Threads.nthreads(),
                 k_init = "k-means++", max_iters = 300,
                 tol = eltype(design_matrix)(1e-6), verbose = false,
                 init = nothing, rng = Random.GLOBAL_RNG, metric=Euclidean())
 
+    # Get dimensions of the input data
     nrow, ncol = size(X)
     centroids = isnothing(init) ? smart_init(X, k, n_threads, weights, rng, init=k_init).centroids : deepcopy(init)
 
@@ -48,6 +49,7 @@ function kmeans!(alg::Lloyd, containers, X, k, weights;
         J_previous = J
         niters += 1  # TODO: Investigate the potential bug in number of iterations
     end
+
     @parallelize n_threads ncol sum_of_squares(containers, X, containers.labels, centroids, weights, metric)
     totalcost = sum(containers.sum_of_squares)