def test_project_and_cluster():
model = SpectralBiclustering(random_state=0)
data = np.array([[1, 1, 1], [1, 1, 1], [3, 6, 3], [3, 6, 3]])
vectors = np.array([[1, 0], [0, 1], [0, 0]])
for mat in (data, csr_matrix(data)):
labels = model._project_and_cluster(data, vectors, n_clusters=2)
assert_almost_equal(v_measure_score(labels, [0, 0, 1, 1]), 1.0)
def bench_k_means(estimator, name, data):
t0 = time()
estimator.fit(data)
print('%-9s\t%.2fs\t%i\t%.3f\t%.3f\t%.3f\t%.3f\t%.3f\t%.3f' %
(name, (time() - t0), estimator.inertia_,
metrics.homogeneity_score(labels, estimator.labels_),
metrics.completeness_score(labels, estimator.labels_),
metrics.v_measure_score(labels, estimator.labels_),
metrics.adjusted_rand_score(labels, estimator.labels_),
metrics.adjusted_mutual_info_score(labels, estimator.labels_),
metrics.silhouette_score(data,
estimator.labels_,
metric='euclidean',
sample_size=sample_size)))
def test_birch_predict():
# Test the predict method predicts the nearest centroid.
rng = np.random.RandomState(0)
X = generate_clustered_data(n_clusters=3,
n_features=3,
n_samples_per_cluster=10)
# n_samples * n_samples_per_cluster
shuffle_indices = np.arange(30)
rng.shuffle(shuffle_indices)
X_shuffle = X[shuffle_indices, :]
brc = Birch(n_clusters=4, threshold=1.)
brc.fit(X_shuffle)
centroids = brc.subcluster_centers_
assert_array_equal(brc.labels_, brc.predict(X_shuffle))
nearest_centroid = pairwise_distances_argmin(X_shuffle, centroids)
assert_almost_equal(v_measure_score(nearest_centroid, brc.labels_), 1.0)
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" %
metrics.adjusted_rand_score(labels_true, labels))
print("Adjusted Mutual Information: %0.3f" %
metrics.adjusted_mutual_info_score(labels_true, labels))
print("Silhouette Coefficient: %0.3f" %
metrics.silhouette_score(X, labels, metric='sqeuclidean'))
# #############################################################################
# Plot result
import matplotlib.pyplot as plt
from itertools import cycle
plt.close('all')
plt.figure(1)
plt.clf()
else:
km = KMeans(n_clusters=true_k,
init='k-means++',
max_iter=100,
n_init=1,
verbose=opts.verbose)
print("Clustering sparse data with %s" % km)
t0 = time()
km.fit(X)
print("done in %0.3fs" % (time() - t0))
print()
print("Homogeneity: %0.3f" % metrics.homogeneity_score(labels, km.labels_))
print("Completeness: %0.3f" % metrics.completeness_score(labels, km.labels_))
print("V-measure: %0.3f" % metrics.v_measure_score(labels, km.labels_))
print("Adjusted Rand-Index: %.3f" %
metrics.adjusted_rand_score(labels, km.labels_))
print("Silhouette Coefficient: %0.3f" %
metrics.silhouette_score(X, km.labels_, sample_size=1000))
print()
if not opts.use_hashing:
print("Top terms per cluster:")
if opts.n_components:
original_space_centroids = svd.inverse_transform(km.cluster_centers_)
order_centroids = original_space_centroids.argsort()[:, ::-1]
else:
order_centroids = km.cluster_centers_.argsort()[:, ::-1]