def test_perfect_checkerboard():
model = SpectralBiclustering(3, svd_method="arpack", random_state=0)
S, rows, cols = make_checkerboard((30, 30), 3, noise=0, random_state=0)
model.fit(S)
assert_equal(consensus_score(model.biclusters_, (rows, cols)), 1)
S, rows, cols = make_checkerboard((40, 30), 3, noise=0, random_state=0)
model.fit(S)
assert_equal(consensus_score(model.biclusters_, (rows, cols)), 1)
S, rows, cols = make_checkerboard((30, 40), 3, noise=0, random_state=0)
model.fit(S)
assert_equal(consensus_score(model.biclusters_, (rows, cols)), 1)
def test_spectral_biclustering():
"""Test Kluger methods on a checkerboard dataset."""
param_grid = {'method': ['scale', 'bistochastic', 'log'],
'svd_method': ['randomized', 'arpack'],
'n_svd_vecs': [None, 20],
'mini_batch': [False, True],
'init': ['k-means++'],
'n_init': [10],
'n_jobs': [1]}
random_state = 0
S, rows, cols = make_checkerboard((30, 30), 3, noise=0.5,
random_state=random_state)
for mat in (S, csr_matrix(S)):
for kwargs in ParameterGrid(param_grid):
model = SpectralBiclustering(n_clusters=3,
random_state=random_state,
**kwargs)
if issparse(mat) and kwargs['method'] == 'log':
# cannot take log of sparse matrix
assert_raises(ValueError, model.fit, mat)
continue
else:
model.fit(mat)
assert_equal(model.rows_.shape, (9, 30))
assert_equal(model.columns_.shape, (9, 30))
assert_array_equal(model.rows_.sum(axis=0),
np.repeat(3, 30))
assert_array_equal(model.columns_.sum(axis=0),
np.repeat(3, 30))
assert_equal(consensus_score(model.biclusters_,
(rows, cols)), 1)
def test_spectral_coclustering():
"""Test Dhillon's Spectral CoClustering on a simple problem."""
param_grid = {'svd_method': ['randomized', 'arpack'],
'n_svd_vecs': [None, 20],
'mini_batch': [False, True],
'init': ['k-means++'],
'n_init': [10],
'n_jobs': [1]}
random_state = 0
S, rows, cols = make_biclusters((30, 30), 3, noise=0.5,
random_state=random_state)
S -= S.min() # needs to be nonnegative before making it sparse
S = np.where(S < 1, 0, S) # threshold some values
for mat in (S, csr_matrix(S)):
for kwargs in ParameterGrid(param_grid):
model = SpectralCoclustering(n_clusters=3,
random_state=random_state,
**kwargs)
model.fit(mat)
assert_equal(model.rows_.shape, (3, 30))
assert_array_equal(model.rows_.sum(axis=0), np.ones(30))
assert_array_equal(model.columns_.sum(axis=0), np.ones(30))
assert_equal(consensus_score(model.biclusters_,
(rows, cols)), 1)
def test_spectral_biclustering():
"""Test Kluger methods on a checkerboard dataset."""
param_grid = {'method': ['scale', 'bistochastic', 'log'],
'svd_method': ['randomized', 'arpack'],
'n_svd_vecs': [None, 20],
'mini_batch': [False, True],
'init': ['k-means++'],
'n_init': [3],
'n_jobs': [1]}
random_state = 0
S, rows, cols = make_checkerboard((30, 30), 3, noise=0.5,
random_state=random_state)
for mat in (S, csr_matrix(S)):
for kwargs in ParameterGrid(param_grid):
model = SpectralBiclustering(n_clusters=3,
random_state=random_state,
**kwargs)
if issparse(mat) and kwargs['method'] == 'log':
# cannot take log of sparse matrix
assert_raises(ValueError, model.fit, mat)
continue
else:
model.fit(mat)
assert_equal(model.rows_.shape, (9, 30))
assert_equal(model.columns_.shape, (9, 30))
assert_array_equal(model.rows_.sum(axis=0),
np.repeat(3, 30))
assert_array_equal(model.columns_.sum(axis=0),
np.repeat(3, 30))
assert_equal(consensus_score(model.biclusters_,
(rows, cols)), 1)
def test_spectral_coclustering():
"""Test Dhillon's Spectral CoClustering on a simple problem."""
param_grid = {'svd_method': ['randomized', 'arpack'],
'n_svd_vecs': [None, 20],
'mini_batch': [False, True],
'init': ['k-means++'],
'n_init': [10],
'n_jobs': [1]}
random_state = 0
S, rows, cols = make_biclusters((30, 30), 3, noise=0.5,
random_state=random_state)
S -= S.min() # needs to be nonnegative before making it sparse
S = np.where(S < 1, 0, S) # threshold some values
for mat in (S, csr_matrix(S)):
for kwargs in ParameterGrid(param_grid):
model = SpectralCoclustering(n_clusters=3,
random_state=random_state,
**kwargs)
model.fit(mat)
assert_equal(model.rows_.shape, (3, 30))
assert_array_equal(model.rows_.sum(axis=0), np.ones(30))
assert_array_equal(model.columns_.sum(axis=0), np.ones(30))
assert_equal(consensus_score(model.biclusters_,
(rows, cols)), 1)
def test_perfect_checkerboard():
raise SkipTest("This test is failing on the buildbot, but cannot"
" reproduce. Temporarily disabling it until it can be"
" reproduced and fixed.")
model = SpectralBiclustering(3, svd_method="arpack", random_state=0)
S, rows, cols = make_checkerboard((30, 30), 3, noise=0, random_state=0)
model.fit(S)
assert_equal(consensus_score(model.biclusters_, (rows, cols)), 1)
S, rows, cols = make_checkerboard((40, 30), 3, noise=0, random_state=0)
model.fit(S)
assert_equal(consensus_score(model.biclusters_, (rows, cols)), 1)
S, rows, cols = make_checkerboard((30, 40), 3, noise=0, random_state=0)
model.fit(S)
assert_equal(consensus_score(model.biclusters_, (rows, cols)), 1)
def test_perfect_checkerboard():
model = SpectralBiclustering(3, svd_method="arpack", random_state=0)
S, rows, cols = make_checkerboard((30, 30), 3, noise=0,
random_state=0)
model.fit(S)
assert_equal(consensus_score(model.biclusters_,
(rows, cols)), 1)
S, rows, cols = make_checkerboard((40, 30), 3, noise=0,
random_state=0)
model.fit(S)
assert_equal(consensus_score(model.biclusters_,
(rows, cols)), 1)
S, rows, cols = make_checkerboard((30, 40), 3, noise=0,
random_state=0)
model.fit(S)
assert_equal(consensus_score(model.biclusters_,
(rows, cols)), 1)
def test_perfect_checkerboard():
raise SkipTest("This test is failing on the buildbot, but cannot"
" reproduce. Temporarily disabling it until it can be"
" reproduced and fixed.")
model = SpectralBiclustering(3, svd_method="arpack", random_state=0)
S, rows, cols = make_checkerboard((30, 30), 3, noise=0,
random_state=0)
model.fit(S)
assert_equal(consensus_score(model.biclusters_,
(rows, cols)), 1)
S, rows, cols = make_checkerboard((40, 30), 3, noise=0,
random_state=0)
model.fit(S)
assert_equal(consensus_score(model.biclusters_,
(rows, cols)), 1)
S, rows, cols = make_checkerboard((30, 40), 3, noise=0,
random_state=0)
model.fit(S)
assert_equal(consensus_score(model.biclusters_,
(rows, cols)), 1)
def test_spectral_biclustering():
"""Test Kluger methods on a checkerboard dataset."""
S, rows, cols = make_checkerboard((30, 30), 3, noise=0.5,
random_state=0)
non_default_params = {'method': ['scale', 'log'],
'svd_method': ['arpack'],
'n_svd_vecs': [20],
'mini_batch': [True]}
for mat in (S, csr_matrix(S)):
for param_name, param_values in non_default_params.items():
for param_value in param_values:
model = SpectralBiclustering(
n_clusters=3,
n_init=3,
init='k-means++',
random_state=0,
)
model.set_params(**dict([(param_name, param_value)]))
if issparse(mat) and model.get_params().get('method') == 'log':
# cannot take log of sparse matrix
assert_raises(ValueError, model.fit, mat)
continue
else:
model.fit(mat)
assert_equal(model.rows_.shape, (9, 30))
assert_equal(model.columns_.shape, (9, 30))
assert_array_equal(model.rows_.sum(axis=0),
np.repeat(3, 30))
assert_array_equal(model.columns_.sum(axis=0),
np.repeat(3, 30))
assert_equal(consensus_score(model.biclusters_,
(rows, cols)), 1)
