-
Notifications
You must be signed in to change notification settings - Fork 13
/
Copy pathtest80_mlj_interface.jl
250 lines (187 loc) · 8.08 KB
/
test80_mlj_interface.jl
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
module TestMLJInterface
using ParallelKMeans
using ParallelKMeans: KMeans
using StableRNGs
using Random
using Test
using Suppressor
using MLJBase
@testset "Test struct construction" begin
model = KMeans()
@test model.algo === Hamerly()
@test model.init == nothing
@test model.k == 3
@test model.k_init == "k-means++"
@test model.max_iters == 300
@test model.copy == true
@test model.threads == Threads.nthreads()
@test model.tol == 1.0e-6
@test model.rng === Random.GLOBAL_RNG
@test isnothing(model.weights)
end
@testset "Test bad struct warings" begin
@test_logs (:warn, "Unsupported KMeans variant. Defaulting to Hamerly algorithm.") ParallelKMeans.KMeans(algo=:Fake)
@test_logs (:warn, "Only \"k-means++\" or \"random\" seeding algorithms are supported. Defaulting to k-means++ seeding.") ParallelKMeans.KMeans(k_init="abc")
@test_logs (:warn, "Number of clusters must be greater than 0. Defaulting to 3 clusters.") ParallelKMeans.KMeans(k=0)
@test_logs (:warn, "Tolerance level must be less than 1. Defaulting to tol of 1e-6.") ParallelKMeans.KMeans(tol=2)
@test_logs (:warn, "Number of permitted iterations must be greater than 0. Defaulting to 300 iterations.") ParallelKMeans.KMeans(max_iters=0)
@test_logs (:warn, "Number of threads must be at least 1. Defaulting to all threads available.") ParallelKMeans.KMeans(threads=0)
end
@testset "Test model fitting verbosity" begin
rng = StableRNG(2020)
X = table([1 2; 1 4; 1 0; 10 2; 10 4; 10 0])
model = KMeans(k=2, max_iters=1, rng = rng)
results = @capture_out fit(model, 1, X)
@test results == "Iteration 1: Jclust = 28.0\n"
end
@testset "Test Lloyd model fitting" begin
X = table([1 2; 1 4; 1 0; 10 2; 10 4; 10 0])
X_test = table([10 1])
model = KMeans(algo = :Lloyd, k=2, rng = StableRNG(2020))
results, cache, report = fit(model, 0, X)
@test cache == nothing
@test results.converged
@test report.totalcost == 16
params = fitted_params(model, results)
@test params.cluster_centers == [1.0 10.0; 2.0 2.0]
# Use trained model to cluster new data X_test
preds = transform(model, results, X_test)
@test preds[:x1][1] == 82.0
@test preds[:x2][1] == 1.0
# Make predictions on new data X_test with fitted params
yhat = predict(model, results, X_test)
@test yhat[1] == 2
model = KMeans(algo = Lloyd(), k=2, rng = StableRNG(2020))
results, cache, report = fit(model, 0, X)
@test cache == nothing
@test results.converged
@test report.totalcost == 16
end
@testset "Test Hamerly model fitting" begin
X = table([1 2; 1 4; 1 0; 10 2; 10 4; 10 0])
X_test = table([10 1])
model = KMeans(algo = :Hamerly, k = 2, rng = StableRNG(2020))
results, cache, report = fit(model, 0, X)
@test cache == nothing
@test results.converged
@test report.totalcost == 16
params = fitted_params(model, results)
@test params.cluster_centers == [1.0 10.0; 2.0 2.0]
# Use trained model to cluster new data X_test
preds = transform(model, results, X_test)
@test preds[:x1][1] == 82.0
@test preds[:x2][1] == 1.0
# Make predictions on new data X_test with fitted params
yhat = predict(model, results, X_test)
@test yhat[1] == 2
model = KMeans(algo = Hamerly(), k = 2, rng = StableRNG(2020))
results, cache, report = fit(model, 0, X)
@test cache == nothing
@test results.converged
@test report.totalcost == 16
end
@testset "Test Elkan model fitting" begin
X = table([1 2; 1 4; 1 0; 10 2; 10 4; 10 0])
X_test = table([10 1])
model = KMeans(algo = :Elkan, k = 2, rng = StableRNG(2020))
results, cache, report = fit(model, 0, X)
@test cache == nothing
@test results.converged
@test report.totalcost == 16
params = fitted_params(model, results)
@test params.cluster_centers == [1.0 10.0; 2.0 2.0]
# Use trained model to cluster new data X_test
preds = transform(model, results, X_test)
@test preds[:x1][1] == 82.0
@test preds[:x2][1] == 1.0
# Make predictions on new data X_test with fitted params
yhat = predict(model, results, X_test)
@test yhat[1] == 2
model = KMeans(algo = Elkan(), k = 2, rng = StableRNG(2020))
results, cache, report = fit(model, 0, X)
@test cache == nothing
@test results.converged
@test report.totalcost == 16
end
@testset "Test Yinyang model fitting" begin
X = table([1 2; 1 4; 1 0; 10 2; 10 4; 10 0])
X_test = table([10 1])
model = KMeans(algo = Yinyang(), k = 2, rng = StableRNG(2020))
results, cache, report = fit(model, 0, X)
@test cache == nothing
@test results.converged
@test report.totalcost == 16
params = fitted_params(model, results)
@test params.cluster_centers == [1.0 10.0; 2.0 2.0]
# Use trained model to cluster new data X_test
preds = transform(model, results, X_test)
@test preds[:x1][1] == 82.0
@test preds[:x2][1] == 1.0
# Make predictions on new data X_test with fitted params
yhat = predict(model, results, X_test)
@test yhat[1] == 2
end
@testset "Test Coreset model fitting" begin
X = table([1 2; 1 4; 1 0; 10 2; 10 4; 10 0])
X_test = table([10 1])
model = KMeans(algo = Coreset(), k = 2, rng = StableRNG(2020))
results, cache, report = fit(model, 0, X)
@test cache == nothing
@test results.converged
@test report.totalcost ≈ 16.009382850308658
params = fitted_params(model, results)
@test all(params.cluster_centers .≈ [1.0 10.000000000000004; 1.981857897094857 1.9470993301391037])
# Use trained model to cluster new data X_test
preds = transform(model, results, X_test)
@test preds[:x1][1] ≈ 81.96404493008754
@test preds[:x2][1] ≈ 0.8969971411499387
# Make predictions on new data X_test with fitted params
yhat = predict(model, results, X_test)
@test yhat[1] == 2
end
@testset "Test MiniBatch model fitting" begin
rng = StableRNG(2020)
X = table(rand(rng, 3, 100)')
X_test = table([0.25 0.17 0.29; 0.52 0.71 0.75]) # similar to first 2 examples
model = KMeans(algo = MiniBatch(50), k=2, rng=rng, max_iters=2_000)
results, cache, report = fit(model, 0, X)
@test cache == nothing
@test results.converged
@test report.totalcost ≈ 18.03007733451847
params = fitted_params(model, results)
@test all(params.cluster_centers .≈ [0.39739206832613827 0.4818900563319951;
0.7695625526281311 0.30986081763964723;
0.6175496080776439 0.3911138270823586])
# Use trained model to cluster new data X_test
preds = transform(model, results, X_test)
@test preds[:x1][1] ≈ 0.48848842207123555
@test preds[:x2][1] ≈ 0.08355805256372761
# Make predictions on new data X_test with fitted params
yhat = predict(model, results, X_test)
@test yhat == report.assignments[1:2]
end
@testset "Testing weights support" begin
rng = StableRNG(2020)
X = table(rand(rng, 3, 100)')
weights = rand(rng, 100)
model = KMeans(algo = :Lloyd, k = 10, weights = weights, rng = rng)
results, cache, report = fit(model, 0, X)
@test report.totalcost ≈ 2.398132337904731
@test report.iterations == 6
@test results.converged
end
@testset "Testing non convergence warning" begin
X = table([1 2; 1 4; 1 0; 10 2; 10 4; 10 0])
X_test = table([10 1])
model = KMeans(k = 2, max_iters = 1, rng = StableRNG(2020))
results, cache, report = fit(model, 0, X)
@test_logs (:warn, "Failed to converge. Using last assignments to make transformations.") transform(model, results, X_test)
end
@testset "Testing non convergence warning during model fitting" begin
Random.seed!(2020)
X = table([1 2; 1 4; 1 0; 10 2; 10 4; 10 0])
X_test = table([10 1])
model = KMeans(k=2, max_iters=1)
@test_logs (:warn, "Specified model failed to converge.") fit(model, 1, X);
end
end # module