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
|
import numpy as np
from umap import UMAP
# ===================================================
# Spatial Data Test cases
# ===================================================
# Use force_approximation_algorithm in order to test
# the region of the code that is called for n>4096
# ---------------------------------------------------
def test_repeated_points_large_sparse_spatial(sparse_spatial_data_repeats):
model = UMAP(
n_neighbors=3,
unique=True,
force_approximation_algorithm=True,
n_epochs=20,
verbose=True,
).fit(sparse_spatial_data_repeats)
assert np.unique(model.embedding_[0:2], axis=0).shape[0] == 1
def test_repeated_points_small_sparse_spatial(sparse_spatial_data_repeats):
model = UMAP(n_neighbors=3, unique=True, n_epochs=20).fit(
sparse_spatial_data_repeats
)
assert np.unique(model.embedding_[0:2], axis=0).shape[0] == 1
# Use force_approximation_algorithm in order to test the region
# of the code that is called for n>4096
def test_repeated_points_large_dense_spatial(spatial_repeats):
model = UMAP(
n_neighbors=3, unique=True, force_approximation_algorithm=True, n_epochs=50
).fit(spatial_repeats)
assert np.unique(model.embedding_[0:2], axis=0).shape[0] == 1
def test_repeated_points_small_dense_spatial(spatial_repeats):
model = UMAP(n_neighbors=3, unique=True, n_epochs=20).fit(spatial_repeats)
assert np.unique(model.embedding_[0:2], axis=0).shape[0] == 1
# ===================================================
# Binary Data Test cases
# ===================================================
# Use force_approximation_algorithm in order to test
# the region of the code that is called for n>4096
# ---------------------------------------------------
def test_repeated_points_large_sparse_binary(sparse_binary_data_repeats):
model = UMAP(
n_neighbors=3, unique=True, force_approximation_algorithm=True, n_epochs=50
).fit(sparse_binary_data_repeats)
assert np.unique(model.embedding_[0:2], axis=0).shape[0] == 1
def test_repeated_points_small_sparse_binary(sparse_binary_data_repeats):
model = UMAP(n_neighbors=3, unique=True, n_epochs=20).fit(
sparse_binary_data_repeats
)
assert np.unique(model.embedding_[0:2], axis=0).shape[0] == 1
# Use force_approximation_algorithm in order to test
# the region of the code that is called for n>4096
def test_repeated_points_large_dense_binary(binary_repeats):
model = UMAP(
n_neighbors=3, unique=True, force_approximation_algorithm=True, n_epochs=20
).fit(binary_repeats)
assert np.unique(model.embedding_[0:2], axis=0).shape[0] == 1
def test_repeated_points_small_dense_binary(binary_repeats):
model = UMAP(n_neighbors=3, unique=True, n_epochs=20).fit(binary_repeats)
assert np.unique(binary_repeats[0:2], axis=0).shape[0] == 1
assert np.unique(model.embedding_[0:2], axis=0).shape[0] == 1
# ===================================================
# Repeated Data Test cases
# ===================================================
# ----------------------------------------------------
# This should test whether the n_neighbours are being
# reduced properly when your n_neighbours is larger
# than the unique data set size
# ----------------------------------------------------
def test_repeated_points_large_n(repetition_dense):
model = UMAP(n_neighbors=5, unique=True, n_epochs=20).fit(repetition_dense)
assert model._n_neighbors == 3
|
