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
|
from umap import UMAP
from scipy import sparse
import numpy as np
from sklearn.cluster import KMeans
from sklearn.metrics import adjusted_rand_score
from sklearn.neighbors import KDTree
from scipy.spatial.distance import cdist, pdist, squareform
try:
# works for sklearn>=0.22
from sklearn.manifold import trustworthiness
except ImportError:
# this is to comply with requirements (scikit-learn>=0.20)
# More recent versions of sklearn have exposed trustworthiness
# in top level module API
# see: https://github.com/scikit-learn/scikit-learn/pull/15337
from sklearn.manifold.t_sne import trustworthiness
# ===================================================
# UMAP Test cases on IRIS Dataset
# ===================================================
# UMAP Trustworthiness on iris
# ----------------------------
def test_umap_trustworthiness_on_iris(iris, iris_model):
embedding = iris_model.embedding_
trust = trustworthiness(iris.data, embedding, n_neighbors=10)
assert (
trust >= 0.97
), "Insufficiently trustworthy embedding for" "iris dataset: {}".format(trust)
def test_initialized_umap_trustworthiness_on_iris(iris):
data = iris.data
embedding = UMAP(
n_neighbors=10,
min_dist=0.01,
init=data[:, 2:],
n_epochs=200,
random_state=42,
).fit_transform(data)
trust = trustworthiness(iris.data, embedding, n_neighbors=10)
assert (
trust >= 0.97
), "Insufficiently trustworthy embedding for" "iris dataset: {}".format(trust)
def test_umap_trustworthiness_on_sphere_iris(
iris,
):
data = iris.data
embedding = UMAP(
n_neighbors=10,
min_dist=0.01,
n_epochs=200,
random_state=42,
output_metric="haversine",
).fit_transform(data)
# Since trustworthiness doesn't support haversine, project onto
# a 3D embedding of the sphere and use cosine distance
r = 3
projected_embedding = np.vstack(
[
r * np.sin(embedding[:, 0]) * np.cos(embedding[:, 1]),
r * np.sin(embedding[:, 0]) * np.sin(embedding[:, 1]),
r * np.cos(embedding[:, 0]),
]
).T
trust = trustworthiness(
iris.data, projected_embedding, n_neighbors=10, metric="cosine"
)
assert (
trust >= 0.65
), "Insufficiently trustworthy spherical embedding for iris dataset: {}".format(
trust
)
# UMAP Transform on iris
# ----------------------
def test_umap_transform_on_iris(iris, iris_subset_model, iris_selection):
fitter = iris_subset_model
new_data = iris.data[~iris_selection]
embedding = fitter.transform(new_data)
trust = trustworthiness(new_data, embedding, n_neighbors=10)
assert (
trust >= 0.85
), "Insufficiently trustworthy transform for" "iris dataset: {}".format(trust)
def test_umap_transform_on_iris_w_pynndescent(iris, iris_selection):
data = iris.data[iris_selection]
fitter = UMAP(
n_neighbors=10,
min_dist=0.01,
n_epochs=100,
random_state=42,
force_approximation_algorithm=True,
).fit(data)
new_data = iris.data[~iris_selection]
embedding = fitter.transform(new_data)
trust = trustworthiness(new_data, embedding, n_neighbors=10)
assert (
trust >= 0.85
), "Insufficiently trustworthy transform for" "iris dataset: {}".format(trust)
def test_umap_transform_on_iris_modified_dtype(iris, iris_subset_model, iris_selection):
fitter = iris_subset_model
fitter.embedding_ = fitter.embedding_.astype(np.float64)
new_data = iris.data[~iris_selection]
embedding = fitter.transform(new_data)
trust = trustworthiness(new_data, embedding, n_neighbors=10)
assert (
trust >= 0.8
), "Insufficiently trustworthy transform for iris dataset: {}".format(trust)
def test_umap_sparse_transform_on_iris(iris, iris_selection):
data = sparse.csr_matrix(iris.data[iris_selection])
assert sparse.issparse(data)
fitter = UMAP(
n_neighbors=10,
min_dist=0.01,
random_state=42,
n_epochs=100,
# force_approximation_algorithm=True,
).fit(data)
new_data = sparse.csr_matrix(iris.data[~iris_selection])
assert sparse.issparse(new_data)
embedding = fitter.transform(new_data)
trust = trustworthiness(new_data, embedding, n_neighbors=10)
assert (
trust >= 0.80
), "Insufficiently trustworthy transform for" "iris dataset: {}".format(trust)
# UMAP precomputed metric transform on iris
# ----------------------
def test_precomputed_transform_on_iris(iris, iris_selection):
data = iris.data[iris_selection]
distance_matrix = squareform(pdist(data))
fitter = UMAP(
n_neighbors=10,
min_dist=0.01,
random_state=42,
n_epochs=100,
metric="precomputed",
).fit(distance_matrix)
new_data = iris.data[~iris_selection]
new_distance_matrix = cdist(new_data, data)
embedding = fitter.transform(new_distance_matrix)
trust = trustworthiness(new_data, embedding, n_neighbors=10)
assert (
trust >= 0.85
), "Insufficiently trustworthy transform for" "iris dataset: {}".format(trust)
# UMAP precomputed metric transform on iris with sparse distances
# ----------------------
def test_precomputed_sparse_transform_on_iris(iris, iris_selection):
data = iris.data[iris_selection]
distance_matrix = sparse.csr_matrix(squareform(pdist(data)))
fitter = UMAP(
n_neighbors=10,
min_dist=0.01,
random_state=42,
n_epochs=100,
metric="precomputed",
).fit(distance_matrix)
new_data = iris.data[~iris_selection]
new_distance_matrix = sparse.csr_matrix(cdist(new_data, data))
embedding = fitter.transform(new_distance_matrix)
trust = trustworthiness(new_data, embedding, n_neighbors=10)
assert (
trust >= 0.85
), "Insufficiently trustworthy transform for" "iris dataset: {}".format(trust)
# UMAP Clusterability on Iris
# ---------------------------
def test_umap_clusterability_on_supervised_iris(supervised_iris_model, iris):
embedding = supervised_iris_model.embedding_
clusters = KMeans(3).fit_predict(embedding)
assert adjusted_rand_score(clusters, iris.target) >= 0.95
# UMAP Inverse transform on Iris
# ------------------------------
def test_umap_inverse_transform_on_iris(iris, iris_model):
highd_tree = KDTree(iris.data)
fitter = iris_model
lowd_tree = KDTree(fitter.embedding_)
for i in range(1, 150, 20):
query_point = fitter.embedding_[i]
near_points = lowd_tree.query([query_point], k=5, return_distance=False)
centroid = np.mean(np.squeeze(fitter.embedding_[near_points]), axis=0)
highd_centroid = fitter.inverse_transform([centroid])
highd_near_points = highd_tree.query(
highd_centroid, k=10, return_distance=False
)
assert np.intersect1d(near_points, highd_near_points[0]).shape[0] >= 3
|
