def test_minibatch_sensible_reassign_fit():
# check if identical initial clusters are reassigned
# also a regression test for when there are more desired reassignments than
# samples.
zeroed_X, true_labels = make_blobs(n_samples=100,
centers=5,
cluster_std=1.,
random_state=42)
zeroed_X[::2, :] = 0
mb_k_means = MiniBatchKMeans(n_clusters=20,
batch_size=10,
random_state=42,
init="random")
mb_k_means.fit(zeroed_X)
# there should not be too many exact zero cluster centers
assert mb_k_means.cluster_centers_.any(axis=1).sum() > 10
# do the same with batch-size > X.shape[0] (regression test)
mb_k_means = MiniBatchKMeans(n_clusters=20,
batch_size=201,
random_state=42,
init="random")
mb_k_means.fit(zeroed_X)
# there should not be too many exact zero cluster centers
assert mb_k_means.cluster_centers_.any(axis=1).sum() > 10
def test_spectral_embedding_amg_solver_failure(seed=36):
# Test spectral embedding with amg solver failure, see issue #13393
pytest.importorskip('pyamg')
# The generated graph below is NOT fully connected if n_neighbors=3
n_samples = 200
n_clusters = 3
n_features = 3
centers = np.eye(n_clusters, n_features)
S, true_labels = make_blobs(n_samples=n_samples,
centers=centers,
cluster_std=1.,
random_state=42)
se_amg0 = SpectralEmbedding(n_components=3,
affinity="nearest_neighbors",
eigen_solver="amg",
n_neighbors=3,
random_state=np.random.RandomState(seed))
embed_amg0 = se_amg0.fit_transform(S)
for i in range(10):
se_amg0.set_params(random_state=np.random.RandomState(seed + 1))
embed_amg1 = se_amg0.fit_transform(S)
assert _check_with_col_sign_flipping(embed_amg0, embed_amg1, 0.05)
def test_bin_seeds():
# Test the bin seeding technique which can be used in the mean shift
# algorithm
# Data is just 6 points in the plane
X = np.array([[1., 1.], [1.4, 1.4], [1.8, 1.2],
[2., 1.], [2.1, 1.1], [0., 0.]])
# With a bin coarseness of 1.0 and min_bin_freq of 1, 3 bins should be
# found
ground_truth = {(1., 1.), (2., 1.), (0., 0.)}
test_bins = get_bin_seeds(X, 1, 1)
test_result = set(tuple(p) for p in test_bins)
assert len(ground_truth.symmetric_difference(test_result)) == 0
# With a bin coarseness of 1.0 and min_bin_freq of 2, 2 bins should be
# found
ground_truth = {(1., 1.), (2., 1.)}
test_bins = get_bin_seeds(X, 1, 2)
test_result = set(tuple(p) for p in test_bins)
assert len(ground_truth.symmetric_difference(test_result)) == 0
# With a bin size of 0.01 and min_bin_freq of 1, 6 bins should be found
# we bail and use the whole data here.
with warnings.catch_warnings(record=True):
test_bins = get_bin_seeds(X, 0.01, 1)
assert_array_almost_equal(test_bins, X)
# tight clusters around [0, 0] and [1, 1], only get two bins
X, _ = make_blobs(n_samples=100, n_features=2, centers=[[0, 0], [1, 1]],
cluster_std=0.1, random_state=0)
test_bins = get_bin_seeds(X, 1)
assert_array_equal(test_bins, [[0, 0], [1, 1]])
def test_k_means_fit_predict(algo, dtype, constructor, seed, max_iter, tol):
# check that fit.predict gives same result as fit_predict
# There's a very small chance of failure with elkan on unstructured dataset
# because predict method uses fast euclidean distances computation which
# may cause small numerical instabilities.
# NB: This test is largely redundant with respect to test_predict and
# test_predict_equal_labels. This test has the added effect of
# testing idempotence of the fittng procesdure which appears to
# be where it fails on some MacOS setups.
if sys.platform == "darwin":
pytest.xfail(
"Known failures on MacOS, See "
"https://github.com/scikit-learn/scikit-learn/issues/12644")
if not (algo == 'elkan' and constructor is sp.csr_matrix):
rng = np.random.RandomState(seed)
X = make_blobs(n_samples=1000,
n_features=10,
centers=10,
random_state=rng)[0].astype(dtype, copy=False)
X = constructor(X)
kmeans = KMeans(algorithm=algo,
n_clusters=10,
random_state=seed,
tol=tol,
max_iter=max_iter,
n_jobs=1)
labels_1 = kmeans.fit(X).predict(X)
labels_2 = kmeans.fit_predict(X)
assert_array_equal(labels_1, labels_2)
def test_bad_reachability():
msg = "All reachability values are inf. Set a larger max_eps."
centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(n_samples=750, centers=centers,
cluster_std=0.4, random_state=0)
with pytest.warns(UserWarning, match=msg):
clust = OPTICS(max_eps=5.0 * 0.003, min_samples=10, eps=0.015)
clust.fit(X)
def test_minibatch_sensible_reassign_partial_fit():
zeroed_X, true_labels = make_blobs(n_samples=n_samples,
centers=5,
cluster_std=1.,
random_state=42)
zeroed_X[::2, :] = 0
mb_k_means = MiniBatchKMeans(n_clusters=20, random_state=42, init="random")
for i in range(100):
mb_k_means.partial_fit(zeroed_X)
# there should not be too many exact zero cluster centers
assert mb_k_means.cluster_centers_.any(axis=1).sum() > 10
def test_close_extract():
# Test extract where extraction eps is close to scaled max_eps
centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(n_samples=750, centers=centers,
cluster_std=0.4, random_state=0)
# Compute OPTICS
clust = OPTICS(max_eps=1.0, cluster_method='dbscan',
eps=0.3, min_samples=10).fit(X)
# Cluster ordering starts at 0; max cluster label = 2 is 3 clusters
assert max(clust.labels_) == 2
def test_bad_extract():
# Test an extraction of eps too close to original eps
msg = "Specify an epsilon smaller than 0.15. Got 0.3."
centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(n_samples=750, centers=centers,
cluster_std=0.4, random_state=0)
# Compute OPTICS
clust = OPTICS(max_eps=5.0 * 0.03,
cluster_method='dbscan',
eps=0.3, min_samples=10)
assert_raise_message(ValueError, msg, clust.fit, X)
def test_parallel():
centers = np.array([[1, 1], [-1, -1], [1, -1]]) + 10
X, _ = make_blobs(n_samples=50, n_features=2, centers=centers,
cluster_std=0.4, shuffle=True, random_state=11)
ms1 = MeanShift(n_jobs=2)
ms1.fit(X)
ms2 = MeanShift()
ms2.fit(X)
assert_array_almost_equal(ms1.cluster_centers_, ms2.cluster_centers_)
assert_array_equal(ms1.labels_, ms2.labels_)
def test_elkan_results(distribution):
# check that results are identical between lloyd and elkan algorithms
rnd = np.random.RandomState(0)
if distribution == 'normal':
X = rnd.normal(size=(50, 10))
else:
X, _ = make_blobs(random_state=rnd)
km_full = KMeans(algorithm='full', n_clusters=5, random_state=0, n_init=1)
km_elkan = KMeans(algorithm='elkan',
n_clusters=5,
random_state=0,
n_init=1)
km_full.fit(X)
km_elkan.fit(X)
assert_array_almost_equal(km_elkan.cluster_centers_,
km_full.cluster_centers_)
assert_array_equal(km_elkan.labels_, km_full.labels_)
def test_dbscan_optics_parity(eps, min_samples):
# Test that OPTICS clustering labels are <= 5% difference of DBSCAN
centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(n_samples=750, centers=centers,
cluster_std=0.4, random_state=0)
# calculate optics with dbscan extract at 0.3 epsilon
op = OPTICS(min_samples=min_samples, cluster_method='dbscan',
eps=eps).fit(X)
# calculate dbscan labels
db = DBSCAN(eps=eps, min_samples=min_samples).fit(X)
contingency = contingency_matrix(db.labels_, op.labels_)
agree = min(np.sum(np.max(contingency, axis=0)),
np.sum(np.max(contingency, axis=1)))
disagree = X.shape[0] - agree
percent_mismatch = np.round((disagree - 1) / X.shape[0], 2)
# verify label mismatch is <= 5% labels
assert percent_mismatch <= 0.05
from scipy import sparse
from mrex.utils.testing import assert_array_equal
from mrex.utils.testing import assert_array_almost_equal
from mrex.utils.testing import assert_raise_message
from mrex.cluster import MeanShift
from mrex.cluster import mean_shift
from mrex.cluster import estimate_bandwidth
from mrex.cluster import get_bin_seeds
from mrex.datasets.samples_generator import make_blobs
n_clusters = 3
centers = np.array([[1, 1], [-1, -1], [1, -1]]) + 10
X, _ = make_blobs(n_samples=300, n_features=2, centers=centers,
cluster_std=0.4, shuffle=True, random_state=11)
def test_estimate_bandwidth():
# Test estimate_bandwidth
bandwidth = estimate_bandwidth(X, n_samples=200)
assert 0.9 <= bandwidth <= 1.5
def test_estimate_bandwidth_1sample():
# Test estimate_bandwidth when n_samples=1 and quantile<1, so that
# n_neighbors is set to 1.
bandwidth = estimate_bandwidth(X, n_samples=1, quantile=0.3)
assert bandwidth == pytest.approx(0., abs=1e-5)
from mrex.cluster.k_means_ import _labels_inertia
from mrex.cluster.k_means_ import _mini_batch_step
from mrex.datasets.samples_generator import make_blobs
from io import StringIO
from mrex.metrics.cluster import homogeneity_score
# non centered, sparse centers to check the
centers = np.array([
[0.0, 5.0, 0.0, 0.0, 0.0],
[1.0, 1.0, 4.0, 0.0, 0.0],
[1.0, 0.0, 0.0, 5.0, 1.0],
])
n_samples = 100
n_clusters, n_features = centers.shape
X, true_labels = make_blobs(n_samples=n_samples,
centers=centers,
cluster_std=1.,
random_state=42)
X_csr = sp.csr_matrix(X)
@pytest.mark.parametrize("representation, algo", [('dense', 'full'),
('dense', 'elkan'),
('sparse', 'full')])
@pytest.mark.parametrize("dtype", [np.float32, np.float64])
def test_kmeans_results(representation, algo, dtype):
# cheks that kmeans works as intended
array_constr = {'dense': np.array, 'sparse': sp.csr_matrix}[representation]
X = array_constr([[0, 0], [0.5, 0], [0.5, 1], [1, 1]], dtype=dtype)
sample_weight = [3, 1, 1, 3] # will be rescaled to [1.5, 0.5, 0.5, 1.5]
init_centers = np.array([[0, 0], [1, 1]], dtype=dtype)
Dorin Comaniciu and Peter Meer, "Mean Shift: A robust approach toward feature space analysis". IEEE Transactions on Pattern Analysis and Machine Intelligence. 2002. pp. 603-619. """ print(__doc__) import numpy as np from mrex.cluster import MeanShift, estimate_bandwidth from mrex.datasets.samples_generator import make_blobs # ############################################################################# # Generate sample data centers = [[1, 1], [-1, -1], [1, -1]] X, _ = make_blobs(n_samples=10000, centers=centers, cluster_std=0.6) # ############################################################################# # Compute clustering with MeanShift # The following bandwidth can be automatically detected using bandwidth = estimate_bandwidth(X, quantile=0.2, n_samples=500) ms = MeanShift(bandwidth=bandwidth, bin_seeding=True) ms.fit(X) labels = ms.labels_ cluster_centers = ms.cluster_centers_ labels_unique = np.unique(labels) n_clusters_ = len(labels_unique)
import numpy as np
import matplotlib.pyplot as plt
from mrex.cluster import MiniBatchKMeans, KMeans
from mrex.metrics.pairwise import pairwise_distances_argmin
from mrex.datasets.samples_generator import make_blobs
# #############################################################################
# Generate sample data
np.random.seed(0)
batch_size = 45
centers = [[1, 1], [-1, -1], [1, -1]]
n_clusters = len(centers)
X, labels_true = make_blobs(n_samples=3000, centers=centers, cluster_std=0.7)
# #############################################################################
# Compute clustering with Means
k_means = KMeans(init='k-means++', n_clusters=3, n_init=10)
t0 = time.time()
k_means.fit(X)
t_batch = time.time() - t0
# #############################################################################
# Compute clustering with MiniBatchKMeans
mbk = MiniBatchKMeans(init='k-means++',
n_clusters=3,
batch_size=batch_size,
import matplotlib.pyplot as plt
import matplotlib.colors as colors
from mrex.cluster import Birch, MiniBatchKMeans
from mrex.datasets.samples_generator import make_blobs
# Generate centers for the blobs so that it forms a 10 X 10 grid.
xx = np.linspace(-22, 22, 10)
yy = np.linspace(-22, 22, 10)
xx, yy = np.meshgrid(xx, yy)
n_centres = np.hstack((np.ravel(xx)[:, np.newaxis],
np.ravel(yy)[:, np.newaxis]))
# Generate blobs to do a comparison between MiniBatchKMeans and Birch.
X, y = make_blobs(n_samples=100000, centers=n_centres, random_state=0)
# Use all colors that matplotlib provides by default.
colors_ = cycle(colors.cnames.keys())
fig = plt.figure(figsize=(12, 4))
fig.subplots_adjust(left=0.04, right=0.98, bottom=0.1, top=0.9)
# Compute clustering with Birch with and without the final clustering step
# and plot.
birch_models = [Birch(threshold=1.7, n_clusters=None),
Birch(threshold=1.7, n_clusters=100)]
final_step = ['without global clustering', 'with global clustering']
for ind, (birch_model, info) in enumerate(zip(birch_models, final_step)):
t = time()
Reference:
Brendan J. Frey and Delbert Dueck, "Clustering by Passing Messages
Between Data Points", Science Feb. 2007
"""
print(__doc__)
from mrex.cluster import AffinityPropagation
from mrex import metrics
from mrex.datasets.samples_generator import make_blobs
# #############################################################################
# Generate sample data
centers = [[1, 1], [-1, -1], [1, -1]]
X, labels_true = make_blobs(n_samples=300,
centers=centers,
cluster_std=0.5,
random_state=0)
# #############################################################################
# Compute Affinity Propagation
af = AffinityPropagation(preference=-50).fit(X)
cluster_centers_indices = af.cluster_centers_indices_
labels = af.labels_
n_clusters_ = len(cluster_centers_indices)
print('Estimated number of clusters: %d' % n_clusters_)
print("Homogeneity: %0.3f" % metrics.homogeneity_score(labels_true, labels))
print("Completeness: %0.3f" % metrics.completeness_score(labels_true, labels))
print("V-measure: %0.3f" % metrics.v_measure_score(labels_true, labels))
print("Adjusted Rand Index: %0.3f" %