added more tests for coverage

Author: PyDataBlog

src/mlj_interface.jl

@@ -27,7 +27,7 @@ const ParallelKMeans_Desc = "Parallel & lightning fast implementation of all var
 # availalbe variants for reference
 const MLJDICT = Dict(:Lloyd => Lloyd(),
                      :Hamerly => Hamerly(),
-                    :LightElkan => LightElkan())  
+                     :LightElkan => LightElkan())
 
 # TODO 3: implementation of fit, predict, and fitted_params of the model
 ####
@@ -49,7 +49,7 @@ function MLJModelInterface.fit(m::KMeans, X)
         # tranposes input table as a column major matrix after making a copy of the data
         DMatrix = MLJModelInterface.matrix(X; transpose=true)
     end
-    
+
     # lookup available algorithms
     algo = MLJDICT[m.algo]  # select algo
 
@@ -60,7 +60,7 @@ function MLJModelInterface.fit(m::KMeans, X)
                                       max_iters=m.max_iters, tol=m.tol, init=m.init,
                                       verbose=verbose)
     cache = nothing
-    report = (cluster_centers=fitresult.centers, iterations=fitresult.iterations, 
+    report = (cluster_centers=fitresult.centers, iterations=fitresult.iterations,
               converged=fitresult.converged, totalcost=fitresult.totalcost,
               labels=fitresult.assignments)
 
@@ -122,10 +122,8 @@ metadata_pkg.(KMeans,
 
 # Metadata for ParaKMeans model interface
 metadata_model(KMeans,
-    input   = MLJModelInterface.Table(MLJModelInterface.Continuous),  # what input data is supported?
-    output  = MLJModelInterface.Table(MLJModelInterface.Count),  # for an unsupervised, what output?
-    weights = false,                                             
+    input   = MLJModelInterface.Table(MLJModelInterface.Continuous),
+    output  = MLJModelInterface.Table(MLJModelInterface.Count),
+    weights = false,
     descr   = ParallelKMeans_Desc,
-	path	= "ParallelKMeans.src.mlj_interface.KMeans"
-	#path    = "YourPackage.SubModuleContainingModelStructDefinition.YourModel1"
-    )
+	path	= "ParallelKMeans.src.mlj_interface.KMeans")

test/test06_verbose.jl

@@ -13,7 +13,6 @@ using Suppressor
     # Capture output and compare
     r = @capture_out kmeans(Lloyd(), X, 3; n_threads=1, max_iters=1, verbose=true)
     @test r == "Iteration 1: Jclust = 46.534795844478815\n"
-    
 end
 
 end # module

test/test07_mlj_interface.jl

@@ -23,7 +23,18 @@ using MLJBase
 end
 
 
-@testset "Test model fitting" begin
+@testset "Test model fitting verbosity" begin
+    Random.seed!(2020)
+    X = table([1 2; 1 4; 1 0; 10 2; 10 4; 10 0])
+    model = ParallelKMeans.KMeans(k=2, max_iters=1, verbosity=1)
+    results = @capture_out fit(model, X)
+
+    @test results == "Iteration 1: Jclust = 28.0\n"
+end
+
+
+@testset "Test Lloyd model fitting" begin
+    Random.seed!(2020)
     X = table([1 2; 1 4; 1 0; 10 2; 10 4; 10 0])
     model = ParallelKMeans.KMeans(k=2)
     results = fit(model, X)
@@ -34,23 +45,47 @@ end
 end
 
 
-@testset "Test fitted params" begin
+@testset "Test Hamerly model fitting" begin
+    Random.seed!(2020)
+    X = table([1 2; 1 4; 1 0; 10 2; 10 4; 10 0])
+    model = ParallelKMeans.KMeans(algo=:Hamerly, k=2)
+    results = fit(model, X)
+
+    @test results[2]             == nothing
+    @test results[end].converged == true
+    @test results[end].totalcost == 16
+end
+
+
+@testset "Test Lloyd fitted params" begin
+    Random.seed!(2020)
     X = table([1 2; 1 4; 1 0; 10 2; 10 4; 10 0])
     model = ParallelKMeans.KMeans(k=2)
     results = fit(model, X)
 
     params = fitted_params(model, results)
     @test params.converged == true
     @test params.totalcost == 16
-    
 end
 
 
-@testset "Test transform" begin
+@testset "Test Hamerly fitted params" begin
+    Random.seed!(2020)
+    X = table([1 2; 1 4; 1 0; 10 2; 10 4; 10 0])
+    model = ParallelKMeans.KMeans(algo=:Hamerly, k=2)
+    results = fit(model, X)
+
+    params = fitted_params(model, results)
+    @test params.converged == true
+    @test params.totalcost == 16
+end
+
+
+@testset "Test Lloyd transform" begin
     Random.seed!(2020)
     X = table([1 2; 1 4; 1 0; 10 2; 10 4; 10 0])
     X_test = table([10 1])
-    
+
     # Train model using training data X
     model = ParallelKMeans.KMeans(k=2)
     results = fit(model, X)
@@ -61,4 +96,18 @@ end
 end
 
 
+@testset "Test Hamerly transform" begin
+    Random.seed!(2020)
+    X = table([1 2; 1 4; 1 0; 10 2; 10 4; 10 0])
+    X_test = table([10 1])
+
+    # Train model using training data X
+    model = ParallelKMeans.KMeans(algo=:Hamerly, k=2)
+    results = fit(model, X)
+
+    # Use trained model to cluster new data X_test
+    preds = transform(model, results, X_test)
+    @test preds[:x1][1] == 2
+end
+
 end # end module