def test_sparse(self):
""" Tests that DBSCAN produces the same results with sparse and
dense data.
"""
n_samples = 1500
x, y = make_blobs(n_samples=n_samples, random_state=170)
dbscan = DBSCAN(n_regions=1, eps=.15)
transformation = [[0.6, -0.6], [-0.4, 0.8]]
x = np.dot(x, transformation)
x = StandardScaler().fit_transform(x)
dense = ds.array(x, block_size=(300, 2))
sparse = ds.array(csr_matrix(x), block_size=(300, 2))
y_dense = dbscan.fit_predict(dense).collect()
y_sparse = dbscan.fit_predict(sparse).collect()
self.assertTrue(np.array_equal(y_dense, y_sparse))
def test_random_clusters_2(self):
""" Tests DBSCAN on random data with multiple clusters. """
# 2 dimensions
np.random.seed(2)
x = np.random.uniform(0, 10, size=(1000, 2))
ds_x = ds.array(x, block_size=(300, 2))
dbscan = DBSCAN(n_regions=10, max_samples=10, eps=0.5, min_samples=10)
y = dbscan.fit_predict(ds_x).collect()
self.assertEqual(dbscan.n_clusters, 27)
self.assertEqual(np.count_nonzero(y == -1), 206)
def test_random_clusters_3(self):
""" Tests DBSCAN on random data with multiple clusters. """
# 3 dimensions
np.random.seed(3)
x = np.random.uniform(0, 10, size=(1000, 3))
ds_x = ds.array(x, block_size=(300, 3))
dbscan = DBSCAN(n_regions=10,
dimensions=[0, 1],
eps=0.9,
min_samples=4)
y = dbscan.fit_predict(ds_x).collect()
self.assertEqual(dbscan.n_clusters, 50)
self.assertEqual(np.count_nonzero(y == -1), 266)
def test_n_clusters_aniso_dimensions(self):
""" Tests that DBSCAN finds the correct number of clusters when
dimensions is not None.
"""
n_samples = 1500
x, y = make_blobs(n_samples=n_samples, random_state=170)
dbscan = DBSCAN(n_regions=5, dimensions=[1], eps=.15)
transformation = [[0.6, -0.6], [-0.4, 0.8]]
x = np.dot(x, transformation)
x = StandardScaler().fit_transform(x)
ds_x = ds.array(x, block_size=(300, 2))
y_pred = dbscan.fit_predict(ds_x).collect()
true_sizes = {19, 496, 491, 488, 6}
cluster_sizes = {
y_pred[y_pred == -1].size, y_pred[y_pred == 0].size,
y_pred[y_pred == 1].size, y_pred[y_pred == 2].size,
y_pred[y_pred == 3].size
}
self.assertEqual(dbscan.n_clusters, 4)
self.assertEqual(true_sizes, cluster_sizes)