def testKMeansFitPredict(self):
# check that fit.predict gives same result as fit_predict
algos = ['full', 'elkan']
seed_max_iter_tols = [
(0, 2, 1e-7), # strict non-convergence
(1, 2, 1e-1), # loose non-convergence
(3, 300, 1e-7), # strict convergence
(4, 300, 1e-1), # loose convergence
]
for algo in algos:
for seed, max_iter, tol in seed_max_iter_tols:
rng = np.random.RandomState(seed)
X = make_blobs(n_samples=1000,
n_features=10,
centers=10,
random_state=rng)[0]
kmeans = KMeans(algorithm=algo,
n_clusters=10,
random_state=seed,
tol=tol,
max_iter=max_iter,
init='k-means++')
labels_1 = kmeans.fit(X).predict(X)
labels_2 = kmeans.fit_predict(X)
# Due to randomness in the order in which chunks of data are processed when
# using more than one thread, the absolute values of the labels can be
# different between the 2 strategies but they should correspond to the same
# clustering.
self.assertAlmostEqual(v_measure_score(labels_1, labels_2), 1)
def test_k_means_fit_predict(setup, algo, seed, max_iter, tol):
# check that fit.predict gives same result as fit_predict
rng = np.random.RandomState(seed)
X = make_blobs(n_samples=1000, n_features=10, centers=10,
random_state=rng)[0]
kmeans = KMeans(algorithm=algo,
n_clusters=10,
random_state=seed,
tol=tol,
max_iter=max_iter,
init='k-means++')
labels_1 = kmeans.fit(X).predict(X)
labels_2 = kmeans.fit_predict(X)
# Due to randomness in the order in which chunks of data are processed when
# using more than one thread, the absolute values of the labels can be
# different between the 2 strategies but they should correspond to the same
# clustering.
assert pytest.approx(v_measure_score(labels_1, labels_2)) == 1
