def init(random_state=None, a=-.4, b=.28, n_samples=16):
if random_state is None:
random_state = np.random.randint(2 ** 31 - 1)
random_state = check_random_state(random_state)
tree = htree.construct_tree(arity=4, depth=2)
# Create sample
Theta = phase_transition._get_mx(a, b, mx_type='smith')
X = random_state.normal(size=(n_samples, Theta.shape[0]))
return tree, X, Theta
from nilearn import masking
from nilearn import signal
import htree
if getuser() == 'rphlypo' and socket.gethostname() != 'drago':
ROOT_DIR = '/volatile'
else:
ROOT_DIR = '/storage'
subject_dirs = sorted(glob.glob(
os.path.join(ROOT_DIR, 'data/HCP/Q2/*/MNINonLinear/Results')))
N_JOBS = min(cpu_count() - 4, 36)
TREE = htree.construct_tree()
def out_brain_confounds(epi_img, mask_img):
""" Return the 5 principal components of the signal outside the
brain.
"""
mask_img = check_niimg(mask_img)
mask_img = nibabel.Nifti1Image(
np.logical_not(mask_img.get_data()).astype(np.int),
mask_img.get_affine())
sigs = masking.apply_mask(epi_img, mask_img)
# Remove the constant signals
non_constant = np.any(np.diff(sigs, axis=0) != 0, axis=0)
sigs = sigs[:, non_constant]
sigs = signal.clean(sigs, detrend=True)