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_fit_predict_on_pipeline():
# test that the fit_predict method is implemented on a pipeline
# test that the fit_predict on pipeline yields same results as applying
# transform and clustering steps separately
iris = load_iris()
scaler = StandardScaler()
km = KMeans(random_state=0)
# As pipeline doesn't clone estimators on construction,
# it must have its own estimators
scaler_for_pipeline = StandardScaler()
km_for_pipeline = KMeans(random_state=0)
# first compute the transform and clustering step separately
scaled = scaler.fit_transform(iris.data)
separate_pred = km.fit_predict(scaled)
# use a pipeline to do the transform and clustering in one step
pipe = Pipeline([
('scaler', scaler_for_pipeline),
('Kmeans', km_for_pipeline)
])
pipeline_pred = pipe.fit_predict(iris.data)
assert_array_almost_equal(pipeline_pred, separate_pred)
# Create a subplot with 1 row and 2 columns
fig, (ax1, ax2) = plt.subplots(1, 2)
fig.set_size_inches(18, 7)
# The 1st subplot is the silhouette plot
# The silhouette coefficient can range from -1, 1 but in this example all
# lie within [-0.1, 1]
ax1.set_xlim([-0.1, 1])
# The (n_clusters+1)*10 is for inserting blank space between silhouette
# plots of individual clusters, to demarcate them clearly.
ax1.set_ylim([0, len(X) + (n_clusters + 1) * 10])
# Initialize the clusterer with n_clusters value and a random generator
# seed of 10 for reproducibility.
clusterer = KMeans(n_clusters=n_clusters, random_state=10)
cluster_labels = clusterer.fit_predict(X)
# The silhouette_score gives the average value for all the samples.
# This gives a perspective into the density and separation of the formed
# clusters
silhouette_avg = silhouette_score(X, cluster_labels)
print("For n_clusters =", n_clusters, "The average silhouette_score is :",
silhouette_avg)
# Compute the silhouette scores for each sample
sample_silhouette_values = silhouette_samples(X, cluster_labels)
y_lower = 10
for i in range(n_clusters):
# Aggregate the silhouette scores for samples belonging to
# cluster i, and sort them