def test_omp_return_path_prop_with_gram():
path = orthogonal_mp(X, y, n_nonzero_coefs=5, return_path=True,
precompute=True)
last = orthogonal_mp(X, y, n_nonzero_coefs=5, return_path=False,
precompute=True)
assert path.shape == (n_features, n_targets, 5)
assert_array_almost_equal(path[:, :, -1], last)
def test_omp_path():
path = orthogonal_mp(X, y, n_nonzero_coefs=5, return_path=True)
last = orthogonal_mp(X, y, n_nonzero_coefs=5, return_path=False)
assert path.shape == (n_features, n_targets, 5)
assert_array_almost_equal(path[:, :, -1], last)
path = orthogonal_mp_gram(G, Xy, n_nonzero_coefs=5, return_path=True)
last = orthogonal_mp_gram(G, Xy, n_nonzero_coefs=5, return_path=False)
assert path.shape == (n_features, n_targets, 5)
assert_array_almost_equal(path[:, :, -1], last)
def test_unreachable_accuracy():
assert_array_almost_equal(
orthogonal_mp(X, y, tol=0),
orthogonal_mp(X, y, n_nonzero_coefs=n_features))
assert_array_almost_equal(
assert_warns(RuntimeWarning, orthogonal_mp, X, y, tol=0,
precompute=True),
orthogonal_mp(X, y, precompute=True,
n_nonzero_coefs=n_features))
def test_perfect_signal_recovery():
idx, = gamma[:, 0].nonzero()
gamma_rec = orthogonal_mp(X, y[:, 0], 5)
gamma_gram = orthogonal_mp_gram(G, Xy[:, 0], 5)
assert_array_equal(idx, np.flatnonzero(gamma_rec))
assert_array_equal(idx, np.flatnonzero(gamma_gram))
assert_array_almost_equal(gamma[:, 0], gamma_rec, decimal=2)
assert_array_almost_equal(gamma[:, 0], gamma_gram, decimal=2)
def test_swapped_regressors():
gamma = np.zeros(n_features)
# X[:, 21] should be selected first, then X[:, 0] selected second,
# which will take X[:, 21]'s place in case the algorithm does
# column swapping for optimization (which is the case at the moment)
gamma[21] = 1.0
gamma[0] = 0.5
new_y = np.dot(X, gamma)
new_Xy = np.dot(X.T, new_y)
gamma_hat = orthogonal_mp(X, new_y, 2)
gamma_hat_gram = orthogonal_mp_gram(G, new_Xy, 2)
assert_array_equal(np.flatnonzero(gamma_hat), [0, 21])
assert_array_equal(np.flatnonzero(gamma_hat_gram), [0, 21])
def compute_bench(samples_range, features_range):
it = 0
results = dict()
lars = np.empty((len(features_range), len(samples_range)))
lars_gram = lars.copy()
omp = lars.copy()
omp_gram = lars.copy()
max_it = len(samples_range) * len(features_range)
for i_s, n_samples in enumerate(samples_range):
for i_f, n_features in enumerate(features_range):
it += 1
n_informative = n_features / 10
print('====================')
print('Iteration %03d of %03d' % (it, max_it))
print('====================')
# dataset_kwargs = {
# 'n_train_samples': n_samples,
# 'n_test_samples': 2,
# 'n_features': n_features,
# 'n_informative': n_informative,
# 'effective_rank': min(n_samples, n_features) / 10,
# #'effective_rank': None,
# 'bias': 0.0,
# }
dataset_kwargs = {
'n_samples': 1,
'n_components': n_features,
'n_features': n_samples,
'n_nonzero_coefs': n_informative,
'random_state': 0
}
print("n_samples: %d" % n_samples)
print("n_features: %d" % n_features)
y, X, _ = make_sparse_coded_signal(**dataset_kwargs)
X = np.asfortranarray(X)
gc.collect()
print("benchmarking lars_path (with Gram):", end='')
sys.stdout.flush()
tstart = time()
G = np.dot(X.T, X) # precomputed Gram matrix
Xy = np.dot(X.T, y)
lars_path_gram(Xy=Xy, Gram=G, n_samples=y.size,
max_iter=n_informative)
delta = time() - tstart
print("%0.3fs" % delta)
lars_gram[i_f, i_s] = delta
gc.collect()
print("benchmarking lars_path (without Gram):", end='')
sys.stdout.flush()
tstart = time()
lars_path(X, y, Gram=None, max_iter=n_informative)
delta = time() - tstart
print("%0.3fs" % delta)
lars[i_f, i_s] = delta
gc.collect()
print("benchmarking orthogonal_mp (with Gram):", end='')
sys.stdout.flush()
tstart = time()
orthogonal_mp(X, y, precompute=True,
n_nonzero_coefs=n_informative)
delta = time() - tstart
print("%0.3fs" % delta)
omp_gram[i_f, i_s] = delta
gc.collect()
print("benchmarking orthogonal_mp (without Gram):", end='')
sys.stdout.flush()
tstart = time()
orthogonal_mp(X, y, precompute=False,
n_nonzero_coefs=n_informative)
delta = time() - tstart
print("%0.3fs" % delta)
omp[i_f, i_s] = delta
results['time(LARS) / time(OMP)\n (w/ Gram)'] = (lars_gram / omp_gram)
results['time(LARS) / time(OMP)\n (w/o Gram)'] = (lars / omp)
return results
def test_with_without_gram_tol():
assert_array_almost_equal(
orthogonal_mp(X, y, tol=1.),
orthogonal_mp(X, y, tol=1., precompute=True))
def test_with_without_gram():
assert_array_almost_equal(
orthogonal_mp(X, y, n_nonzero_coefs=5),
orthogonal_mp(X, y, n_nonzero_coefs=5, precompute=True))
def test_tol():
tol = 0.5
gamma = orthogonal_mp(X, y[:, 0], tol=tol)
gamma_gram = orthogonal_mp(X, y[:, 0], tol=tol, precompute=True)
assert np.sum((y[:, 0] - np.dot(X, gamma)) ** 2) <= tol
assert np.sum((y[:, 0] - np.dot(X, gamma_gram)) ** 2) <= tol
def test_n_nonzero_coefs():
assert np.count_nonzero(orthogonal_mp(X, y[:, 0], n_nonzero_coefs=5)) <= 5
assert np.count_nonzero(orthogonal_mp(X, y[:, 0],
n_nonzero_coefs=5,
precompute=True)) <= 5
def test_correct_shapes():
assert (orthogonal_mp(X, y[:, 0], n_nonzero_coefs=5).shape ==
(n_features,))
assert (orthogonal_mp(X, y, n_nonzero_coefs=5).shape ==
(n_features, 3))