def test_v_measure_and_mutual_information(seed=36):
# Check relation between v_measure, entropy and mutual information
for i in np.logspace(1, 4, 4).astype(np.int):
random_state = np.random.RandomState(seed)
labels_a, labels_b = (random_state.randint(0, 10, i),
random_state.randint(0, 10, i))
assert_almost_equal(v_measure_score(labels_a, labels_b),
2.0 * mutual_info_score(labels_a, labels_b) /
(entropy(labels_a) + entropy(labels_b)), 0)
avg = 'arithmetic'
assert_almost_equal(v_measure_score(labels_a, labels_b),
normalized_mutual_info_score(labels_a, labels_b,
average_method=avg)
)
def test_int_input():
X_list = [[0, 0], [10, 10], [12, 9], [-1, 1], [2, 0], [8, 10]]
for dtype in [np.int32, np.int64]:
X_int = np.array(X_list, dtype=dtype)
X_int_csr = sp.csr_matrix(X_int)
init_int = X_int[:2]
fitted_models = [
KMeans(n_clusters=2).fit(X_int),
KMeans(n_clusters=2, init=init_int, n_init=1).fit(X_int),
# mini batch kmeans is very unstable on such a small dataset hence
# we use many inits
MiniBatchKMeans(n_clusters=2, n_init=10, batch_size=2).fit(X_int),
MiniBatchKMeans(n_clusters=2, n_init=10,
batch_size=2).fit(X_int_csr),
MiniBatchKMeans(n_clusters=2,
batch_size=2,
init=init_int,
n_init=1).fit(X_int),
MiniBatchKMeans(n_clusters=2,
batch_size=2,
init=init_int,
n_init=1).fit(X_int_csr),
]
for km in fitted_models:
assert km.cluster_centers_.dtype == np.float64
expected_labels = [0, 1, 1, 0, 0, 1]
scores = np.array([
v_measure_score(expected_labels, km.labels_)
for km in fitted_models
])
assert_array_almost_equal(scores, np.ones(scores.shape[0]))
def test_mini_batch_k_means_random_init_partial_fit():
km = MiniBatchKMeans(n_clusters=n_clusters, init="random", random_state=42)
# use the partial_fit API for online learning
for X_minibatch in np.array_split(X, 10):
km.partial_fit(X_minibatch)
# compute the labeling on the complete dataset
labels = km.predict(X)
assert v_measure_score(true_labels, labels) == 1.0
def test_scaled_weights():
# scaling all sample weights by a common factor
# shouldn't change the result
sample_weight = np.ones(n_samples)
for estimator in [
KMeans(n_clusters=n_clusters, random_state=42),
MiniBatchKMeans(n_clusters=n_clusters, random_state=42)
]:
est_1 = clone(estimator).fit(X)
est_2 = clone(estimator).fit(X, sample_weight=0.5 * sample_weight)
assert_almost_equal(v_measure_score(est_1.labels_, est_2.labels_), 1.0)
assert_almost_equal(_sort_centers(est_1.cluster_centers_),
_sort_centers(est_2.cluster_centers_))
def test_unit_weights_vs_no_weights():
# not passing any sample weights should be equivalent
# to all weights equal to one
sample_weight = np.ones(n_samples)
for estimator in [
KMeans(n_clusters=n_clusters, random_state=42),
MiniBatchKMeans(n_clusters=n_clusters, random_state=42)
]:
est_1 = clone(estimator).fit(X)
est_2 = clone(estimator).fit(X, sample_weight=sample_weight)
assert_almost_equal(v_measure_score(est_1.labels_, est_2.labels_), 1.0)
assert_almost_equal(_sort_centers(est_1.cluster_centers_),
_sort_centers(est_2.cluster_centers_))
def test_exactly_zero_info_score():
# Check numerical stability when information is exactly zero
for i in np.logspace(1, 4, 4).astype(np.int):
labels_a, labels_b = (np.ones(i, dtype=np.int),
np.arange(i, dtype=np.int))
assert normalized_mutual_info_score(labels_a, labels_b) == 0.0
assert v_measure_score(labels_a, labels_b) == 0.0
assert adjusted_mutual_info_score(labels_a, labels_b) == 0.0
assert normalized_mutual_info_score(labels_a, labels_b) == 0.0
for method in ["min", "geometric", "arithmetic", "max"]:
assert adjusted_mutual_info_score(labels_a, labels_b,
method) == 0.0
assert normalized_mutual_info_score(labels_a, labels_b,
method) == 0.0
def _check_fitted_model(km):
# check that the number of clusters centers and distinct labels match
# the expectation
centers = km.cluster_centers_
assert centers.shape == (n_clusters, n_features)
labels = km.labels_
assert np.unique(labels).shape[0] == n_clusters
# check that the labels assignment are perfect (up to a permutation)
assert v_measure_score(true_labels, labels) == 1.0
assert km.inertia_ > 0.0
# check error on dataset being too small
assert_raise_message(
ValueError, "n_samples=1 should be >= n_clusters=%d" % km.n_clusters,
km.fit, [[0., 1.]])
def test_k_means_function():
# test calling the k_means function directly
# catch output
old_stdout = sys.stdout
sys.stdout = StringIO()
try:
cluster_centers, labels, inertia = k_means(X,
n_clusters=n_clusters,
sample_weight=None,
verbose=True)
finally:
sys.stdout = old_stdout
centers = cluster_centers
assert centers.shape == (n_clusters, n_features)
labels = labels
assert np.unique(labels).shape[0] == n_clusters
# check that the labels assignment are perfect (up to a permutation)
assert v_measure_score(true_labels, labels) == 1.0
assert inertia > 0.0
# check warning when centers are passed
assert_warns(RuntimeWarning,
k_means,
X,
n_clusters=n_clusters,
sample_weight=None,
init=centers)
# to many clusters desired
with pytest.raises(ValueError):
k_means(X, n_clusters=X.shape[0] + 1, sample_weight=None)
# kmeans for algorithm='elkan' raises TypeError on sparse matrix
assert_raise_message(TypeError, "algorithm='elkan' not supported for "
"sparse input X",
k_means,
X=X_csr,
n_clusters=2,
sample_weight=None,
algorithm="elkan")
def test_weighted_vs_repeated():
# a sample weight of N should yield the same result as an N-fold
# repetition of the sample
rng = np.random.RandomState(0)
sample_weight = rng.randint(1, 5, size=n_samples)
X_repeat = np.repeat(X, sample_weight, axis=0)
estimators = [
KMeans(init="k-means++", n_clusters=n_clusters, random_state=42),
KMeans(init="random", n_clusters=n_clusters, random_state=42),
KMeans(init=centers.copy(), n_clusters=n_clusters, random_state=42),
MiniBatchKMeans(n_clusters=n_clusters, batch_size=10, random_state=42)
]
for estimator in estimators:
est_weighted = clone(estimator).fit(X, sample_weight=sample_weight)
est_repeated = clone(estimator).fit(X_repeat)
repeated_labels = np.repeat(est_weighted.labels_, sample_weight)
assert_almost_equal(
v_measure_score(est_repeated.labels_, repeated_labels), 1.0)
if not isinstance(estimator, MiniBatchKMeans):
assert_almost_equal(_sort_centers(est_weighted.cluster_centers_),
_sort_centers(est_repeated.cluster_centers_))
def test_beta_parameter():
# test for when beta passed to
# homogeneity_completeness_v_measure
# and v_measure_score
beta_test = 0.2
h_test = 0.67
c_test = 0.42
v_test = ((1 + beta_test) * h_test * c_test
/ (beta_test * h_test + c_test))
h, c, v = homogeneity_completeness_v_measure(
[0, 0, 0, 1, 1, 1],
[0, 1, 0, 1, 2, 2],
beta=beta_test)
assert_almost_equal(h, h_test, 2)
assert_almost_equal(c, c_test, 2)
assert_almost_equal(v, v_test, 2)
v = v_measure_score(
[0, 0, 0, 1, 1, 1],
[0, 1, 0, 1, 2, 2],
beta=beta_test)
assert_almost_equal(v, v_test, 2)
cocluster = SpectralCoclustering(n_clusters=len(categories),
svd_method='arpack',
random_state=0)
kmeans = MiniBatchKMeans(n_clusters=len(categories),
batch_size=20000,
random_state=0)
print("Vectorizing...")
X = vectorizer.fit_transform(newsgroups.data)
print("Coclustering...")
start_time = time()
cocluster.fit(X)
y_cocluster = cocluster.row_labels_
print("Done in {:.2f}s. V-measure: {:.4f}".format(
time() - start_time, v_measure_score(y_cocluster, y_true)))
print("MiniBatchKMeans...")
start_time = time()
y_kmeans = kmeans.fit_predict(X)
print("Done in {:.2f}s. V-measure: {:.4f}".format(
time() - start_time, v_measure_score(y_kmeans, y_true)))
feature_names = vectorizer.get_feature_names()
document_names = list(newsgroups.target_names[i] for i in newsgroups.target)
def bicluster_ncut(i):
rows, cols = cocluster.get_indices(i)
if not (np.any(rows) and np.any(cols)):
import sys
