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
|
"""
Tests for DBSCAN clustering algorithm
"""
import pickle
import numpy as np
from numpy.testing import assert_equal
from scipy.spatial import distance
from sklearn.cluster.dbscan_ import DBSCAN, dbscan
from .common import generate_clustered_data
n_clusters = 3
X = generate_clustered_data(n_clusters=n_clusters)
def test_dbscan_similarity():
"""Tests the DBSCAN algorithm with a similarity array."""
# Parameters chosen specifically for this task.
eps = 0.15
min_samples = 10
# Compute similarities
D = distance.squareform(distance.pdist(X))
D /= np.max(D)
# Compute DBSCAN
core_samples, labels = dbscan(D, metric="precomputed",
eps=eps, min_samples=min_samples)
# number of clusters, ignoring noise if present
n_clusters_1 = len(set(labels)) - (1 if -1 in labels else 0)
assert_equal(n_clusters_1, n_clusters)
db = DBSCAN(metric="precomputed", eps=eps, min_samples=min_samples)
labels = db.fit(D).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
assert_equal(n_clusters_2, n_clusters)
def test_dbscan_feature():
"""Tests the DBSCAN algorithm with a feature vector array."""
# Parameters chosen specifically for this task.
# Different eps to other test, because distance is not normalised.
eps = 0.8
min_samples = 10
metric = 'euclidean'
# Compute DBSCAN
# parameters chosen for task
core_samples, labels = dbscan(X, metric=metric,
eps=eps, min_samples=min_samples)
# number of clusters, ignoring noise if present
n_clusters_1 = len(set(labels)) - int(-1 in labels)
assert_equal(n_clusters_1, n_clusters)
db = DBSCAN(metric=metric, eps=eps, min_samples=min_samples)
labels = db.fit(X).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
assert_equal(n_clusters_2, n_clusters)
def test_dbscan_callable():
"""Tests the DBSCAN algorithm with a callable metric."""
# Parameters chosen specifically for this task.
# Different eps to other test, because distance is not normalised.
eps = 0.8
min_samples = 10
# metric is the function reference, not the string key.
metric = distance.euclidean
# Compute DBSCAN
# parameters chosen for task
core_samples, labels = dbscan(X, metric=metric,
eps=eps, min_samples=min_samples)
# number of clusters, ignoring noise if present
n_clusters_1 = len(set(labels)) - int(-1 in labels)
assert_equal(n_clusters_1, n_clusters)
db = DBSCAN(metric=metric, eps=eps, min_samples=min_samples)
labels = db.fit(X).labels_
n_clusters_2 = len(set(labels)) - int(-1 in labels)
assert_equal(n_clusters_2, n_clusters)
def test_pickle():
obj = DBSCAN()
s = pickle.dumps(obj)
assert_equal(type(pickle.loads(s)), obj.__class__)
|
