def route_clustering(self, params: dict) -> list:
clf = DBSCAN(**params, n_jobs=-1)
# clf = hdbscan.HDBSCAN(
# algorithm='best', alpha=1.0, approx_min_span_tree=True,
# gen_min_span_tree=False, leaf_size=40, memory=Memory(cachedir=None),
# metric=params['metric'], min_cluster_size=params['eps'],
# min_samples=params['min_samples'],
# p=None)
return clf.fit_predict(self.dissimilarity_matrix)
def test_weighted_dbscan():
# ensure sample_weight is validated
assert_raises(ValueError, dbscan, [[0], [1]], sample_weight=[2])
assert_raises(ValueError, dbscan, [[0], [1]], sample_weight=[2, 3, 4])
# ensure sample_weight has an effect
assert_array_equal([], dbscan([[0], [1]], sample_weight=None, min_samples=6)[0])
assert_array_equal([], dbscan([[0], [1]], sample_weight=[5, 5], min_samples=6)[0])
assert_array_equal([0], dbscan([[0], [1]], sample_weight=[6, 5], min_samples=6)[0])
assert_array_equal([0, 1], dbscan([[0], [1]], sample_weight=[6, 6], min_samples=6)[0])
# points within eps of each other:
assert_array_equal([0, 1], dbscan([[0], [1]], eps=1.5, sample_weight=[5, 1], min_samples=6)[0])
# and effect of non-positive and non-integer sample_weight:
assert_array_equal([], dbscan([[0], [1]], sample_weight=[5, 0], eps=1.5, min_samples=6)[0])
assert_array_equal([0, 1], dbscan([[0], [1]], sample_weight=[5.9, 0.1], eps=1.5, min_samples=6)[0])
assert_array_equal([0, 1], dbscan([[0], [1]], sample_weight=[6, 0], eps=1.5, min_samples=6)[0])
assert_array_equal([], dbscan([[0], [1]], sample_weight=[6, -1], eps=1.5, min_samples=6)[0])
# for non-negative sample_weight, cores should be identical to repetition
rng = np.random.RandomState(42)
sample_weight = rng.randint(0, 5, X.shape[0])
core1, label1 = dbscan(X, sample_weight=sample_weight)
assert_equal(len(label1), len(X))
X_repeated = np.repeat(X, sample_weight, axis=0)
core_repeated, label_repeated = dbscan(X_repeated)
core_repeated_mask = np.zeros(X_repeated.shape[0], dtype=bool)
core_repeated_mask[core_repeated] = True
core_mask = np.zeros(X.shape[0], dtype=bool)
core_mask[core1] = True
assert_array_equal(np.repeat(core_mask, sample_weight), core_repeated_mask)
# sample_weight should work with precomputed distance matrix
D = pairwise_distances(X)
core3, label3 = dbscan(D, sample_weight=sample_weight, metric="precomputed")
assert_array_equal(core1, core3)
assert_array_equal(label1, label3)
# sample_weight should work with estimator
est = DBSCAN().fit(X, sample_weight=sample_weight)
core4 = est.core_sample_indices_
label4 = est.labels_
assert_array_equal(core1, core4)
assert_array_equal(label1, label4)
est = DBSCAN()
label5 = est.fit_predict(X, sample_weight=sample_weight)
core5 = est.core_sample_indices_
assert_array_equal(core1, core5)
assert_array_equal(label1, label5)
assert_array_equal(label1, est.labels_)
def test_weighted_dbscan():
# ensure sample_weight is validated
assert_raises(ValueError, dbscan, [[0], [1]], sample_weight=[2])
assert_raises(ValueError, dbscan, [[0], [1]], sample_weight=[2, 3, 4])
# ensure sample_weight has an effect
assert_array_equal([], dbscan([[0], [1]], sample_weight=None,
min_samples=6)[0])
assert_array_equal([], dbscan([[0], [1]], sample_weight=[5, 5],
min_samples=6)[0])
assert_array_equal([0], dbscan([[0], [1]], sample_weight=[6, 5],
min_samples=6)[0])
assert_array_equal([0, 1], dbscan([[0], [1]], sample_weight=[6, 6],
min_samples=6)[0])
# points within eps of each other:
assert_array_equal([0, 1], dbscan([[0], [1]], eps=1.5,
sample_weight=[5, 1], min_samples=6)[0])
# and effect of non-positive and non-integer sample_weight:
assert_array_equal([], dbscan([[0], [1]], sample_weight=[5, 0],
eps=1.5, min_samples=6)[0])
assert_array_equal([0, 1], dbscan([[0], [1]], sample_weight=[5.9, 0.1],
eps=1.5, min_samples=6)[0])
assert_array_equal([0, 1], dbscan([[0], [1]], sample_weight=[6, 0],
eps=1.5, min_samples=6)[0])
assert_array_equal([], dbscan([[0], [1]], sample_weight=[6, -1],
eps=1.5, min_samples=6)[0])
# for non-negative sample_weight, cores should be identical to repetition
rng = np.random.RandomState(42)
sample_weight = rng.randint(0, 5, X.shape[0])
core1, label1 = dbscan(X, sample_weight=sample_weight)
assert_equal(len(label1), len(X))
X_repeated = np.repeat(X, sample_weight, axis=0)
core_repeated, label_repeated = dbscan(X_repeated)
core_repeated_mask = np.zeros(X_repeated.shape[0], dtype=bool)
core_repeated_mask[core_repeated] = True
core_mask = np.zeros(X.shape[0], dtype=bool)
core_mask[core1] = True
assert_array_equal(np.repeat(core_mask, sample_weight), core_repeated_mask)
# sample_weight should work with precomputed distance matrix
D = pairwise_distances(X)
core3, label3 = dbscan(D, sample_weight=sample_weight,
metric='precomputed')
assert_array_equal(core1, core3)
assert_array_equal(label1, label3)
# sample_weight should work with estimator
est = DBSCAN().fit(X, sample_weight=sample_weight)
core4 = est.core_sample_indices_
label4 = est.labels_
assert_array_equal(core1, core4)
assert_array_equal(label1, label4)
est = DBSCAN()
label5 = est.fit_predict(X, sample_weight=sample_weight)
core5 = est.core_sample_indices_
assert_array_equal(core1, core5)
assert_array_equal(label1, label5)
assert_array_equal(label1, est.labels_)