def test_spectral_embedding_two_components(seed=36):
"""Test spectral embedding with two components"""
random_state = np.random.RandomState(seed)
n_sample = 100
affinity = np.zeros(shape=[n_sample * 2,
n_sample * 2])
# first component
affinity[0:n_sample,
0:n_sample] = np.abs(random_state.randn(n_sample, n_sample)) + 2
# second component
affinity[n_sample::,
n_sample::] = np.abs(random_state.randn(n_sample, n_sample)) + 2
# connection
affinity[0, n_sample + 1] = 1
affinity[n_sample + 1, 0] = 1
affinity.flat[::2 * n_sample + 1] = 0
affinity = 0.5 * (affinity + affinity.T)
true_label = np.zeros(shape=2 * n_sample)
true_label[0:n_sample] = 1
se_precomp = SpectralEmbedding(n_components=1, affinity="precomputed",
random_state=np.random.RandomState(seed))
embedded_coordinate = se_precomp.fit_transform(affinity)
# Some numpy versions are touchy with types
embedded_coordinate = \
se_precomp.fit_transform(affinity.astype(np.float32))
# thresholding on the first components using 0.
label_ = np.array(embedded_coordinate.ravel() < 0, dtype="float")
assert_equal(normalized_mutual_info_score(true_label, label_), 1.0)
def test_spectral_embedding_amg_solver(seed=36):
# Test spectral embedding with amg solver
try:
from pyamg import smoothed_aggregation_solver # noqa
except ImportError:
raise SkipTest("pyamg not available.")
se_amg = SpectralEmbedding(n_components=2, affinity="nearest_neighbors",
eigen_solver="amg", n_neighbors=5,
random_state=np.random.RandomState(seed))
se_arpack = SpectralEmbedding(n_components=2, affinity="nearest_neighbors",
eigen_solver="arpack", n_neighbors=5,
random_state=np.random.RandomState(seed))
embed_amg = se_amg.fit_transform(S)
embed_arpack = se_arpack.fit_transform(S)
assert _check_with_col_sign_flipping(embed_amg, embed_arpack, 0.1e-4)
# same with special case in which amg is not actually used
# regression test for #10715
# affinity between nodes
row = [0, 0, 1, 2, 3, 3, 4]
col = [1, 2, 2, 3, 4, 5, 5]
val = [100, 100, 100, 1, 100, 100, 100]
affinity = sparse.coo_matrix((val + val, (row + col, col + row)),
shape=(6, 6)).toarray()
se_amg.affinity = "precomputed"
se_arpack.affinity = "precomputed"
embed_amg = se_amg.fit_transform(affinity)
embed_arpack = se_arpack.fit_transform(affinity)
assert _check_with_col_sign_flipping(embed_amg, embed_arpack, 0.1e-4)
def test_spectral_embedding_unknown_affinity(seed=36):
# Test that SpectralClustering fails with an unknown affinity type
se = SpectralEmbedding(n_components=1,
affinity="<unknown>",
random_state=np.random.RandomState(seed))
with pytest.raises(ValueError):
se.fit(S)
def test_spectral_embedding_unknown_eigensolver(seed=36):
# Test that SpectralClustering fails with an unknown eigensolver
se = SpectralEmbedding(n_components=1, affinity="precomputed",
random_state=np.random.RandomState(seed),
eigen_solver="<unknown>")
with pytest.raises(ValueError):
se.fit(S)
def test_spectral_embedding_two_components(seed=36):
"""Test spectral embedding with two components"""
random_state = np.random.RandomState(seed)
n_sample = 100
affinity = np.zeros(shape=[n_sample * 2, n_sample * 2])
# first component
affinity[0:n_sample,
0:n_sample] = np.abs(random_state.randn(n_sample, n_sample)) + 2
# second component
affinity[n_sample::,
n_sample::] = np.abs(random_state.randn(n_sample, n_sample)) + 2
# connection
affinity[0, n_sample + 1] = 1
affinity[n_sample + 1, 0] = 1
affinity.flat[::2 * n_sample + 1] = 0
affinity = 0.5 * (affinity + affinity.T)
true_label = np.zeros(shape=2 * n_sample)
true_label[0:n_sample] = 1
se_precomp = SpectralEmbedding(n_components=1,
affinity="precomputed",
random_state=np.random.RandomState(seed))
embedded_coordinate = se_precomp.fit_transform(affinity)
# Some numpy versions are touchy with types
embedded_coordinate = \
se_precomp.fit_transform(affinity.astype(np.float32))
# thresholding on the first components using 0.
label_ = np.array(embedded_coordinate.ravel() < 0, dtype="float")
assert_equal(normalized_mutual_info_score(true_label, label_), 1.0)
def test_spectral_embedding_precomputed_affinity(seed=36):
# Test spectral embedding with precomputed kernel
gamma = 1.0
se_precomp = SpectralEmbedding(n_components=2, affinity="precomputed", random_state=np.random.RandomState(seed))
se_rbf = SpectralEmbedding(n_components=2, affinity="rbf", gamma=gamma, random_state=np.random.RandomState(seed))
embed_precomp = se_precomp.fit_transform(rbf_kernel(S, gamma=gamma))
embed_rbf = se_rbf.fit_transform(S)
assert_array_almost_equal(se_precomp.affinity_matrix_, se_rbf.affinity_matrix_)
assert_true(_check_with_col_sign_flipping(embed_precomp, embed_rbf, 0.05))
def specEmbedding():
clf = SpectralEmbedding(3)
X = clf.fit_transform(dataSets[2].getDataForTraining([0], 2)[0][:])
c = range(0, len(X))
plt.figure()
plt.plot(X[:, 0], X[:, 1])
plt.scatter(X[:, 0], X[:, 1], c=c, cmap='gray')
fig = plt.figure()
ax = fig.add_subplot(111, projection='3d')
ax.plot(X[:, 0], X[:, 1], X[:, 2])
ax.scatter(X[:, 0], X[:, 1], X[:, 2], c=c, marker='o')
def test_pipeline_spectral_clustering(seed=36):
# Test using pipeline to do spectral clustering
random_state = np.random.RandomState(seed)
se_rbf = SpectralEmbedding(n_components=n_clusters,
affinity="rbf",
random_state=random_state)
se_knn = SpectralEmbedding(n_components=n_clusters,
affinity="nearest_neighbors",
n_neighbors=5,
random_state=random_state)
for se in [se_rbf, se_knn]:
km = KMeans(n_clusters=n_clusters, random_state=random_state)
km.fit(se.fit_transform(S))
assert_array_almost_equal(
normalized_mutual_info_score(km.labels_, true_labels), 1.0, 2)
def test_spectral_embedding_amg_solver(seed=36):
"""Test spectral embedding with amg solver"""
try:
from pyamg import smoothed_aggregation_solver
except ImportError:
raise SkipTest("pyamg not available.")
se_amg = SpectralEmbedding(n_components=2, affinity="nearest_neighbors",
eigen_solver="amg", n_neighbors=5,
random_state=np.random.RandomState(seed))
se_arpack = SpectralEmbedding(n_components=2, affinity="nearest_neighbors",
eigen_solver="arpack", n_neighbors=5,
random_state=np.random.RandomState(seed))
embed_amg = se_amg.fit_transform(S)
embed_arpack = se_arpack.fit_transform(S)
assert_true(_check_with_col_sign_flipping(embed_amg, embed_arpack, 0.05))
def test_spectral_embedding_callable_affinity(seed=36):
# Test spectral embedding with callable affinity
gamma = 0.9
kern = rbf_kernel(S, gamma=gamma)
se_callable = SpectralEmbedding(
n_components=2,
affinity=(lambda x: rbf_kernel(x, gamma=gamma)),
gamma=gamma,
random_state=np.random.RandomState(seed),
)
se_rbf = SpectralEmbedding(n_components=2, affinity="rbf", gamma=gamma, random_state=np.random.RandomState(seed))
embed_rbf = se_rbf.fit_transform(S)
embed_callable = se_callable.fit_transform(S)
assert_array_almost_equal(se_callable.affinity_matrix_, se_rbf.affinity_matrix_)
assert_array_almost_equal(kern, se_rbf.affinity_matrix_)
assert_true(_check_with_col_sign_flipping(embed_rbf, embed_callable, 0.05))
def test_spectral_embedding_two_components(seed=36):
"""Test spectral embedding with two components"""
random_state = np.random.RandomState(seed)
n_sample = 100
affinity = np.zeros(shape=[n_sample * 2, n_sample * 2])
# first component
affinity[0:n_sample,
0:n_sample] = np.abs(random_state.randn(n_sample, n_sample)) + 2
# second component
affinity[n_sample::,
n_sample::] = np.abs(random_state.randn(n_sample, n_sample)) + 2
# connection
affinity[0, n_sample + 1] = 1
affinity[n_sample + 1, 0] = 1
affinity.flat[::2 * n_sample + 1] = 0
affinity = 0.5 * (affinity + affinity.T)
true_label = np.zeros(shape=2 * n_sample)
true_label[0:n_sample] = 1
se_precomp = SpectralEmbedding(n_components=1,
affinity="precomputed",
random_state=np.random.RandomState(seed))
embedded_coordinate = se_precomp.fit_transform(affinity)
# Some numpy versions are touchy with types
embedded_coordinate = \
se_precomp.fit_transform(affinity.astype(np.float32))
# thresholding on the first components using 0.
label_ = np.array(embedded_coordinate.ravel() < 0, dtype="float")
assert_equal(normalized_mutual_info_score(true_label, label_), 1.0)
# test that we can still import spectral embedding
from sklearn.cluster import spectral_embedding as se_deprecated
warnings.simplefilter("always", DeprecationWarning)
with warnings.catch_warnings(record=True) as warning_list:
embedded_depr = se_deprecated(affinity,
n_components=1,
random_state=np.random.RandomState(seed))
assert_equal(len(warning_list), 1)
warnings.filters.pop(0)
assert_true(
_check_with_col_sign_flipping(embedded_coordinate, embedded_depr,
0.05))
def test_spectral_embedding_two_components(seed=36):
"""Test spectral embedding with two components"""
random_state = np.random.RandomState(seed)
n_sample = 100
affinity = np.zeros(shape=[n_sample * 2,
n_sample * 2])
# first component
affinity[0:n_sample,
0:n_sample] = np.abs(random_state.randn(n_sample, n_sample)) + 2
# second component
affinity[n_sample::,
n_sample::] = np.abs(random_state.randn(n_sample, n_sample)) + 2
# connection
affinity[0, n_sample + 1] = 1
affinity[n_sample + 1, 0] = 1
affinity.flat[::2 * n_sample + 1] = 0
affinity = 0.5 * (affinity + affinity.T)
true_label = np.zeros(shape=2 * n_sample)
true_label[0:n_sample] = 1
se_precomp = SpectralEmbedding(n_components=1, affinity="precomputed",
random_state=np.random.RandomState(seed))
embedded_coordinate = se_precomp.fit_transform(affinity)
# Some numpy versions are touchy with types
embedded_coordinate = \
se_precomp.fit_transform(affinity.astype(np.float32))
# thresholding on the first components using 0.
label_ = np.array(embedded_coordinate.ravel() < 0, dtype="float")
assert_equal(normalized_mutual_info_score(true_label, label_), 1.0)
# test that we can still import spectral embedding
from sklearn.cluster import spectral_embedding as se_deprecated
warnings.simplefilter("always", DeprecationWarning)
with warnings.catch_warnings(record=True) as warning_list:
embedded_depr = se_deprecated(affinity, n_components=1,
random_state=np.random.RandomState(seed))
assert_equal(len(warning_list), 1)
warnings.filters.pop(0)
assert_true(_check_with_col_sign_flipping(embedded_coordinate,
embedded_depr, 0.05))
def test_spectral_embedding_amg_solver_failure(seed=36):
# Test spectral embedding with amg solver failure, see issue #13393
pytest.importorskip('pyamg')
# The generated graph below is NOT fully connected if n_neighbors=3
n_samples = 200
n_clusters = 3
n_features = 3
centers = np.eye(n_clusters, n_features)
S, true_labels = make_blobs(n_samples=n_samples,
centers=centers,
cluster_std=1.,
random_state=42)
se_amg0 = SpectralEmbedding(n_components=3,
affinity="nearest_neighbors",
eigen_solver="amg",
n_neighbors=3,
random_state=np.random.RandomState(seed))
embed_amg0 = se_amg0.fit_transform(S)
for i in range(10):
se_amg0.set_params(random_state=np.random.RandomState(seed + 1))
embed_amg1 = se_amg0.fit_transform(S)
assert _check_with_col_sign_flipping(embed_amg0, embed_amg1, 0.05)
def test_precomputed_nearest_neighbors_filtering():
# Test precomputed graph filtering when containing too many neighbors
n_neighbors = 2
results = []
for additional_neighbors in [0, 10]:
nn = NearestNeighbors(n_neighbors=n_neighbors +
additional_neighbors).fit(S)
graph = nn.kneighbors_graph(S, mode='connectivity')
embedding = SpectralEmbedding(
random_state=0,
n_components=2,
affinity='precomputed_nearest_neighbors',
n_neighbors=n_neighbors).fit(graph).embedding_
results.append(embedding)
assert_array_equal(results[0], results[1])
def test_spectral_embedding_precomputed_affinity(seed=36):
# Test spectral embedding with precomputed kernel
gamma = 1.0
se_precomp = SpectralEmbedding(n_components=2, affinity="precomputed",
random_state=np.random.RandomState(seed))
se_rbf = SpectralEmbedding(n_components=2, affinity="rbf",
gamma=gamma,
random_state=np.random.RandomState(seed))
embed_precomp = se_precomp.fit_transform(rbf_kernel(S, gamma=gamma))
embed_rbf = se_rbf.fit_transform(S)
assert_array_almost_equal(
se_precomp.affinity_matrix_, se_rbf.affinity_matrix_)
assert _check_with_col_sign_flipping(embed_precomp, embed_rbf, 0.05)
def test_spectral_embedding_callable_affinity(seed=36):
"""Test spectral embedding with callable affinity"""
gamma = 0.9
kern = rbf_kernel(S, gamma=gamma)
se_callable = SpectralEmbedding(
n_components=2,
affinity=(lambda x: rbf_kernel(x, gamma=gamma)),
gamma=gamma,
random_state=np.random.RandomState(seed))
se_rbf = SpectralEmbedding(n_components=2,
affinity="rbf",
gamma=gamma,
random_state=np.random.RandomState(seed))
embed_rbf = se_rbf.fit_transform(S)
embed_callable = se_callable.fit_transform(S)
embed_rbf = se_rbf.fit_transform(S)
embed_callable = se_callable.fit_transform(S)
assert_array_almost_equal(se_callable.affinity_matrix_,
se_rbf.affinity_matrix_)
assert_array_almost_equal(kern, se_rbf.affinity_matrix_)
assert_true(_check_with_col_sign_flipping(embed_rbf, embed_callable, 0.05))
def test_spectral_embedding_amg_solver(seed=36):
# Test spectral embedding with amg solver
try:
from pyamg import smoothed_aggregation_solver # noqa
except ImportError:
raise SkipTest("pyamg not available.")
se_amg = SpectralEmbedding(n_components=2, affinity="nearest_neighbors",
eigen_solver="amg", n_neighbors=5,
random_state=np.random.RandomState(seed))
se_arpack = SpectralEmbedding(n_components=2, affinity="nearest_neighbors",
eigen_solver="arpack", n_neighbors=5,
random_state=np.random.RandomState(seed))
embed_amg = se_amg.fit_transform(S)
embed_arpack = se_arpack.fit_transform(S)
assert _check_with_col_sign_flipping(embed_amg, embed_arpack, 0.05)
'RandomizedPCA':RandomizedPCA(),
'Ridge':Ridge(),
'RidgeCV':RidgeCV(),
'RidgeClassifier':RidgeClassifier(),
'RidgeClassifierCV':RidgeClassifierCV(),
'RobustScaler':RobustScaler(),
'SGDClassifier':SGDClassifier(),
'SGDRegressor':SGDRegressor(),
'SVC':SVC(),
'SVR':SVR(),
'SelectFdr':SelectFdr(),
'SelectFpr':SelectFpr(),
'SelectFwe':SelectFwe(),
'SelectKBest':SelectKBest(),
'SelectPercentile':SelectPercentile(),
'ShrunkCovariance':ShrunkCovariance(),
'SkewedChi2Sampler':SkewedChi2Sampler(),
'SparsePCA':SparsePCA(),
'SparseRandomProjection':SparseRandomProjection(),
'SpectralBiclustering':SpectralBiclustering(),
'SpectralClustering':SpectralClustering(),
'SpectralCoclustering':SpectralCoclustering(),
'SpectralEmbedding':SpectralEmbedding(),
'StandardScaler':StandardScaler(),
'TSNE':TSNE(),
'TheilSenRegressor':TheilSenRegressor(),
'VBGMM':VBGMM(),
'VarianceThreshold':VarianceThreshold(),}
def test_spectral_embedding_unknown_affinity(seed=36):
"""Test that SpectralClustering fails with an unknown affinity type"""
se = SpectralEmbedding(n_components=1,
affinity="<unknown>",
random_state=np.random.RandomState(seed))
assert_raises(ValueError, se.fit, S)
