def test_predict():
"""Test predict."""
clusterer = BlockClustering(blocking="precomputed",
base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer.fit(X, blocks=(y <= 1))
pred = clusterer.predict(X, blocks=(y <= 1))
assert_array_equal([25, 25, 25, 25], np.bincount(clusterer.labels_))
pred = clusterer.predict(X, blocks=10 * np.ones(len(X)))
assert_array_equal(-np.ones(len(X)), pred)
def test_predict():
"""Test predict."""
clusterer = BlockClustering(blocking="precomputed",
base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer.fit(X, blocks=(y <= 1))
pred = clusterer.predict(X, blocks=(y <= 1))
assert_array_equal([25, 25, 25, 25], np.bincount(clusterer.labels_))
pred = clusterer.predict(X, blocks=10 * np.ones(len(X)))
assert_array_equal(-np.ones(len(X)), pred)
def test_validation():
"""Test the validation of hyper-parameters and input data."""
with pytest.raises(ValueError):
clusterer = BlockClustering(
blocking="foobar", base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer.fit(X)
with pytest.raises(ValueError):
clusterer = BlockClustering(
blocking="precomputed",
base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer.fit(X)
with pytest.raises(ValueError):
clusterer = BlockClustering(
blocking="precomputed",
base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer.fit(X, blocks=(y <= 1))
clusterer.predict(X)
def test_validation():
"""Test the validation of hyper-parameters and input data."""
with pytest.raises(ValueError):
clusterer = BlockClustering(
blocking="foobar",
base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer.fit(X)
with pytest.raises(ValueError):
clusterer = BlockClustering(
blocking="precomputed",
base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer.fit(X)
with pytest.raises(ValueError):
clusterer = BlockClustering(
blocking="precomputed",
base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer.fit(X, blocks=(y <= 1))
clusterer.predict(X)
def test_partial_fit():
"""Test partial_fit."""
blocks = (y <= 1)
clusterer1 = BlockClustering(blocking="precomputed",
base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer1.partial_fit(X[y <= 1], blocks=blocks[y <= 1])
assert_equal(len(clusterer1.clusterers_), 1)
clusterer1.partial_fit(X[y > 1], blocks=blocks[y > 1])
assert_equal(len(clusterer1.clusterers_), 2)
clusterer2 = BlockClustering(blocking="precomputed",
base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer2.fit(X, blocks=blocks)
c1 = clusterer1.predict(X, blocks=blocks)
c2 = clusterer2.labels_
assert_equal(paired_f_score(c1, c2), 1.0)
def test_partial_fit():
"""Test partial_fit."""
blocks = (y <= 1)
clusterer1 = BlockClustering(blocking="precomputed",
base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer1.partial_fit(X[y <= 1], blocks=blocks[y <= 1])
assert_equal(len(clusterer1.clusterers_), 1)
clusterer1.partial_fit(X[y > 1], blocks=blocks[y > 1])
assert_equal(len(clusterer1.clusterers_), 2)
clusterer2 = BlockClustering(blocking="precomputed",
base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer2.fit(X, blocks=blocks)
c1 = clusterer1.predict(X, blocks=blocks)
c2 = clusterer2.labels_
assert_equal(paired_f_score(c1, c2), 1.0)
def test_single_signature(n_jobs):
"""Test clustering of a single signature."""
import numbers
clusterer = BlockClustering(base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer.fit(np.array([X[0]]))
assert isinstance(clusterer.predict(X[0])[0], numbers.Integral)
def test_single_signature(n_jobs):
"""Test clustering of a single signature."""
import numbers
clusterer = BlockClustering(base_estimator=MiniBatchKMeans(n_clusters=2))
clusterer.fit(np.array([X[0]]))
assert isinstance(clusterer.predict(X[0])[0], numbers.Integral)
