Improved tests & fixes

Author: PyDataBlog

README.md

@@ -2,8 +2,8 @@
 
 [![Stable](https://img.shields.io/badge/docs-stable-blue.svg)](https://PyDataBlog.github.io/ParallelKMeans.jl/stable)
 [![Dev](https://img.shields.io/badge/docs-dev-blue.svg)](https://PyDataBlog.github.io/ParallelKMeans.jl/dev)
-[![Build Status](https://www.travis-ci.org/PyDataBlog/ParallelKMeans.jl.svg?branch=master)](https://www.travis-ci.org/PyDataBlog/ParallelKMeans.jl)
-[![Coverage Status](https://coveralls.io/repos/github/PyDataBlog/ParallelKMeans.jl/badge.svg?branch=master)](https://coveralls.io/github/PyDataBlog/ParallelKMeans.jl?branch=master)
+[![Build Status](https://github.com/PyDataBlog/ParallelKMeans.jl/actions/workflows/CI.yml/badge.svg)](https://github.com/PyDataBlog/ParallelKMeans.jl/actions/workflows/CI.yml/badge.svg)
+[![codecov](https://codecov.io/gh/PyDataBlog/ParallelKMeans.jl/branch/master/graph/badge.svg?token=799USS6BPH)](https://codecov.io/gh/PyDataBlog/ParallelKMeans.jl)
 [![FOSSA Status](https://app.fossa.com/api/projects/git%2Bgithub.com%2FPyDataBlog%2FParallelKMeans.jl.svg?type=shield)](https://app.fossa.com/projects/git%2Bgithub.com%2FPyDataBlog%2FParallelKMeans.jl?ref=badge_shield)
 [![Binder](https://mybinder.org/badge_logo.svg)](https://mybinder.org/v2/gh/PyDataBlog/ParallelKMeans.jl/master)
 _________________________________________________________________________________________________________
@@ -22,10 +22,13 @@ ________________________________________________________________________________
 
 ## Table Of Content
 
-1. [Documentation](#Documentation)
-2. [Installation](#Installation)
-3. [Features](#Features)
-4. [License](#License)
+- [ParallelKMeans](#parallelkmeans)
+  - [Table Of Content](#table-of-content)
+    - [Documentation](#documentation)
+    - [Installation](#installation)
+    - [Features](#features)
+    - [Benchmarks](#benchmarks)
+    - [License](#license)
 
 _________________________________________________________________________________________________________
 

src/mini_batch.jl

@@ -34,7 +34,7 @@ function kmeans!(alg::MiniBatch, containers, X, k,
 
     # Initialize nearest centers for both batch and whole dataset labels
     converged = false
-    niters = 0
+    niters = 1
     counter = 0
     J_previous = zero(T)
     J = zero(T)
@@ -99,19 +99,25 @@ function kmeans!(alg::MiniBatch, containers, X, k,
                 # Compute totalcost for the complete dataset
                 @parallelize 1 ncol sum_of_squares(containers, X, containers.labels, centroids, weights, metric)
                 totalcost = sum(containers.sum_of_squares)
+                
+                # Print convergence message to user
+                if verbose
+                    println("Successfully terminated with convergence.")
+                end
+
                 break
             end
         else
             counter = 0
         end
 
         # Warn users if model doesn't converge at max iterations
-        if (niters > max_iters) & (!converged)
+        if (niters >= max_iters) & (!converged)
 
             if verbose
                 println("Clustering model failed to converge. Labelling data with latest centroids.")
             end
-            containers.labels = reassign_labels(X, metric, containers.labels, centroids)
+            containers.labels .= reassign_labels(X, metric, containers.labels, centroids)
 
             # Compute totalcost for unconverged model
             @parallelize 1 ncol sum_of_squares(containers, X, containers.labels, centroids, weights, metric)

test/test70_verbose.jl

@@ -48,8 +48,16 @@ end
 
     # Capture output and compare
     r = @capture_out kmeans(Coreset(), X, 3; n_threads=1, max_iters=1, verbose=true, rng = rng)
-    # This test is broken on 1.5 dev, see https://github.com/rfourquet/StableRNGs.jl/issues/3
-    # @test startswith(r, "Iteration 1: Jclust = 32.8028409136")
+    @test startswith(r, "Iteration 1: Jclust = 32.8028409136")
+end
+
+@testset "MiniBatch: Testing verbosity of implementation" begin
+    rng = StableRNG(2020)
+    X = rand(rng, 3, 100)
+
+    # Capture output and compare
+    r = @capture_out kmeans(MiniBatch(10), X, 2; n_threads=1, max_iters=1, verbose=true, rng = rng)
+    @test startswith(r, "Iteration 1: Jclust = 18.298067523612104")
 end
 
 end # module

test/test90_minibatch.jl

@@ -5,6 +5,7 @@ using Test
 using StableRNGs
 using StatsBase
 using Distances
+using Suppressor
 
 
 @testset "MiniBatch default batch size" begin
@@ -15,14 +16,27 @@ end
 @testset "MiniBatch convergence" begin
     rng = StableRNG(2020)
     X = rand(rng, 3, 100)
+    rng_orig = deepcopy(rng)
 
+    # use lloyd as baseline
     baseline = [kmeans(Lloyd(), X, 2; max_iters=100_000).totalcost for i in 1:200] |> mean |> round
-
+    # mini batch results
     res = [kmeans(MiniBatch(10), X, 2; max_iters=100_000).totalcost for i in 1:200] |> mean |> round
+    # test for verbosity with convergence
+    r = @capture_out kmeans(MiniBatch(50), X, 2; max_iters=2_000, verbose=true, rng=rng_orig)
 
     @test baseline == res
+    @test endswith(r, "Successfully terminated with convergence.\n")
 end
 
+@testset "MiniBatch non-convergence warning" begin
+    rng = StableRNG(2020)
+    X = rand(rng, 3, 100)
+
+    # Capture output and compare
+    r = @capture_out kmeans(MiniBatch(10), X, 2; n_threads=1, max_iters=10, verbose=true, rng = rng)
+    @test endswith(r, "Clustering model failed to converge. Labelling data with latest centroids.\n")
+end
 
 @testset "MiniBatch metric support" begin
     rng = StableRNG(2020)