def load_atlas_init(source=None, n_components=20):
if source == 'smith':
if n_components == 70:
init = fetch_atlas_smith_2009().rsn70
elif n_components == 20:
init = fetch_atlas_smith_2009().rsn20
else:
raise NotImplementedError('Unexpected argument')
else:
init = None
return init
def load_data():
with open(expanduser('~/data/HCP_unmasked/data.json'), 'r') as f:
data = json.load(f)
for this_data in data:
this_data['array'] += '.npy'
mask_img = expanduser('~/data/HCP_mask/mask_img.nii.gz')
masker = NiftiMasker(mask_img=mask_img, smoothing_fwhm=4, standardize=True)
masker.fit()
smith2009 = fetch_atlas_smith_2009()
init = smith2009.rsn70
dict_init = masker.transform(init)
return masker, dict_init, sorted(data, key=lambda t: t['filename'])
def load_data():
with open(expanduser('~/data/HCP_unmasked/data.json'), 'r') as f:
data = json.load(f)
for this_data in data:
this_data['array'] += '.npy'
mask_img = expanduser('~/data/HCP_mask/mask_img.nii.gz')
masker = NiftiMasker(mask_img=mask_img, smoothing_fwhm=4,
standardize=True)
masker.fit()
smith2009 = fetch_atlas_smith_2009()
init = smith2009.rsn70
dict_init = masker.transform(init)
return masker, dict_init, sorted(data, key=lambda t: t['filename'])
def run(idx, reduction, alpha, mask, raw, n_components, init, func_filenames):
output_dir = join(trace_folder, 'experiment_%i' % idx)
try:
os.makedirs(output_dir)
except OSError:
pass
dict_fact = SpcaFmri(mask=mask,
smoothing_fwhm=3,
batch_size=40,
shelve=not raw,
n_components=n_components,
replacement=False,
dict_init=fetch_atlas_smith_2009().rsn70 if
init else None,
reduction=reduction,
alpha=alpha,
random_state=0,
n_epochs=2,
l1_ratio=0.5,
backend='c',
memory=expanduser("~/nilearn_cache"), memory_level=2,
verbose=5,
n_jobs=1,
trace_folder=output_dir
)
print('[Example] Learning maps')
t0 = time.time()
dict_fact.fit(func_filenames, raw=raw)
t1 = time.time() - t0
print('[Example] Dumping results')
# Decomposition estimator embeds their own masker
masker = dict_fact.masker_
components_img = masker.inverse_transform(dict_fact.components_)
components_img.to_filename(join(output_dir, 'components_final.nii.gz'))
print('[Example] Run in %.2f s' % t1)
# Show components from both methods using 4D plotting tools
import matplotlib.pyplot as plt
from nilearn.plotting import plot_prob_atlas, show
print('[Example] Displaying')
fig, axes = plt.subplots(2, 1)
plot_prob_atlas(components_img, view_type="filled_contours",
axes=axes[0])
plot_stat_map(index_img(components_img, 0),
axes=axes[1],
colorbar=False,
threshold=0)
plt.savefig(join(output_dir, 'components.pdf'))
show()
def run(idx, reduction, alpha, mask, raw, n_components, init, func_filenames):
output_dir = join(trace_folder, 'experiment_%i' % idx)
try:
os.makedirs(output_dir)
except OSError:
pass
dict_fact = SpcaFmri(
mask=mask,
smoothing_fwhm=3,
batch_size=40,
shelve=not raw,
n_components=n_components,
replacement=False,
dict_init=fetch_atlas_smith_2009().rsn70 if init else None,
reduction=reduction,
alpha=alpha,
random_state=0,
n_epochs=2,
l1_ratio=0.5,
backend='c',
memory=expanduser("~/nilearn_cache"),
memory_level=2,
verbose=5,
n_jobs=1,
trace_folder=output_dir)
print('[Example] Learning maps')
t0 = time.time()
dict_fact.fit(func_filenames, raw=raw)
t1 = time.time() - t0
print('[Example] Dumping results')
# Decomposition estimator embeds their own masker
masker = dict_fact.masker_
components_img = masker.inverse_transform(dict_fact.components_)
components_img.to_filename(join(output_dir, 'components_final.nii.gz'))
print('[Example] Run in %.2f s' % t1)
# Show components from both methods using 4D plotting tools
import matplotlib.pyplot as plt
from nilearn.plotting import plot_prob_atlas, show
print('[Example] Displaying')
fig, axes = plt.subplots(2, 1)
plot_prob_atlas(components_img, view_type="filled_contours", axes=axes[0])
plot_stat_map(index_img(components_img, 0),
axes=axes[1],
colorbar=False,
threshold=0)
plt.savefig(join(output_dir, 'components.pdf'))
show()
def test_fetch_atlas_smith_2009():
bunch = datasets.fetch_atlas_smith_2009(data_dir=tmpdir, verbose=0)
keys = ("rsn20", "rsn10", "rsn70", "bm20", "bm10", "bm70")
filenames = [
"rsn20.nii.gz",
"PNAS_Smith09_rsn10.nii.gz",
"rsn70.nii.gz",
"bm20.nii.gz",
"PNAS_Smith09_bm10.nii.gz",
"bm70.nii.gz",
]
assert_equal(len(url_request.urls), 6)
for key, fn in zip(keys, filenames):
assert_equal(bunch[key], os.path.join(tmpdir, 'smith_2009', fn))
def get_atlas(name):
if name == "destrieux_2009":
atlas = datasets.fetch_atlas_destrieux_2009()
atlas_filename = atlas['maps']
elif name == "harvard_oxford":
atlas = datasets.fetch_atlas_harvard_oxford("cort-maxprob-thr25-2mm")
atlas_filename = atlas['maps']
elif name == "aal":
atlas = datasets.fetch_atlas_aal()
atlas_filename = atlas['maps']
elif name == "smith_2009":
atlas = datasets.fetch_atlas_smith_2009()
atlas_filename = atlas['rsn70']
else:
raise ValueError('Atlas name unkown')
return atlas_filename
def test_fetch_atlas_smith_2009():
bunch = datasets.fetch_atlas_smith_2009(data_dir=tmpdir, verbose=0)
keys = ("rsn20", "rsn10", "rsn70",
"bm20", "bm10", "bm70")
filenames = [
"rsn20.nii.gz",
"PNAS_Smith09_rsn10.nii.gz",
"rsn70.nii.gz",
"bm20.nii.gz",
"PNAS_Smith09_bm10.nii.gz",
"bm70.nii.gz",
]
assert_equal(len(url_request.urls), 6)
for key, fn in zip(keys, filenames):
assert_equal(bunch[key], os.path.join(tmpdir, 'smith_2009', fn))
def get_established_parcellation(parcellation="Harvard_Oxford",
target_img=None,
parcellation_dir=None):
if parcellation == "Harvard_Oxford":
name = "Harvard_Oxford_cort-prob-2mm"
data = datasets.fetch_atlas_harvard_oxford('cort-prob-2mm',
data_dir=parcellation_dir)
parcel = nibabel.load(data['maps'])
labels = data['labels'][1:] # first label is background
atlas_threshold = 25
elif parcellation == "smith":
name = "smith_rsn70"
data = datasets.fetch_atlas_smith_2009(
data_dir=parcellation_dir)['rsn70']
parcel = nibabel.load(data)
labels = range(parcel.shape[-1])
atlas_threshold = 4
elif parcellation == "glasser":
glasser_dir = path.join(parcellation_dir, 'glasser')
data = image.load_img(
path.join(glasser_dir, 'HCP-MMP1_on_MNI152_ICBM2009a_nlin.nii.gz'))
parcel = image.new_img_like(data, (data.get_fdata() + .01).astype(int))
labels = list(
np.genfromtxt(path.join(glasser_dir,
'HCP-MMP1_on_MNI152_ICBM2009a_nlin.txt'),
dtype=str,
usecols=1))
name = 'glasser'
atlas_threshold = None
# split down midline into lateralized ROIs
data_coords = np.where(parcel.get_data())
right_coords = *(i[data_coords[0] > parcel.shape[0] // 2]
for i in data_coords), # tuple comprehension
parcel.get_data()[right_coords] += len(labels)
labels = labels + [l.replace('L_', 'R_') for l in labels]
if target_img:
parcel = image.resample_to_img(parcel,
target_img,
interpolation='nearest')
return parcel, labels, name, atlas_threshold
def get_init_objective(output_dir):
mask, func_filenames = get_hcp_data(data_dir=data_dir, raw=True)
masker = NiftiMasker(mask_img=mask, smoothing_fwhm=None, standardize=False)
masker.fit()
rsn70 = fetch_atlas_smith_2009().rsn70
components = masker.transform(rsn70)
print(components.shape)
enet_scale(components.T, inplace=True)
print(np.sum(np.abs(components), axis=1))
test_data = func_filenames[(-n_test_records * 2)::2]
n_samples, n_voxels = np.load(test_data[-1], mmap_mode='r').shape
X = np.empty((n_test_records * n_samples, n_voxels))
for i, this_data in enumerate(test_data):
X[i * n_samples:(i + 1) * n_samples] = np.load(this_data,
mmap_mode='r')
exp_var = {}
for alpha in [1e-2, 1e-3, 1e-4]:
exp_var[alpha] = objective_function(X, components, alpha)
json.dump(open(join(output_dir, 'init_objective.json'), 'r'))
def get_init_objective(output_dir):
mask, func_filenames = get_hcp_data(raw=True)
masker = NiftiMasker(mask_img=mask, smoothing_fwhm=None,
standardize=False)
masker.fit()
rsn70 = fetch_atlas_smith_2009().rsn70
components = masker.transform(rsn70)
print(components.shape)
enet_scale(components.T, inplace=True)
print(np.sum(np.abs(components), axis=1))
test_data = func_filenames[(-n_test_records * 2)::2]
n_samples, n_voxels = np.load(test_data[-1], mmap_mode='r').shape
X = np.empty((n_test_records * n_samples, n_voxels))
for i, this_data in enumerate(test_data):
X[i * n_samples:(i + 1) * n_samples] = np.load(this_data,
mmap_mode='r')
exp_var = {}
for alpha in [1e-2, 1e-3, 1e-4]:
exp_var[alpha] = objective_function(X, components, alpha)
json.dump(open(join(output_dir, 'init_objective.json'), 'r'))
# The file contains a 3D volume, we can easily visualize it as a # statistical map: from nilearn import plotting plotting.plot_stat_map(tmap_filename) ############################################################################### # Visualizing works better with a threshold plotting.plot_stat_map(tmap_filename, threshold=3) ############################################################################### # Visualizing one volume in a 4D file # ----------------------------------- # # We can download resting-state networks from the Smith 2009 study on # correspondance between rest and task rsn = datasets.fetch_atlas_smith_2009()['rsn10'] print(rsn) ############################################################################### # It is a 4D nifti file. We load it into the memory to print its # shape. from nilearn import image print(image.load_img(rsn).shape) ############################################################################### # We can retrieve the first volume (note that Python indexing starts at 0): first_rsn = image.index_img(rsn, 0) print(first_rsn.shape) ############################################################################### # first_rsn is a 3D image.
if isinstance(rs_file, list):
all_sub_rs_maps = concat_imgs(rs_file)
else:
all_sub_rs_maps = nib.load(rs_file)
cur_shape = all_sub_rs_maps.get_data().shape
size_in_GB = all_sub_rs_maps.get_data().nbytes / 1e9
print('% rs images: %.2f GB' % (cur_shape[-1], size_in_GB))
###############################################################################
# dump network projections
###############################################################################
# retrieve network projections
from nilearn import datasets as ds
smith_pkg = ds.fetch_atlas_smith_2009()
icas_path = smith_pkg['rsn20']
from nilearn.input_data import NiftiMapsMasker
nmm = NiftiMapsMasker(
mask_img=mask_file, maps_img=icas_path, resampling_target='mask',
standardize=True, detrend=True)
nmm.fit()
nmm.maps_img_.to_filename('dbg_ica_maps.nii.gz')
FS_netproj = nmm.transform(all_sub_rs_maps)
np.save('%i_nets_timeseries' % sub_id, FS_netproj)
# compute network sparse inverse covariance
from sklearn.covariance import GraphLassoCV
from nilearn.image import index_img
mask, func_filenames = get_hcp_data(data_dir='/storage/data')
func_filenames = func_filenames[:2]
# Apply our decomposition estimator with reduction
n_components = 70
n_jobs = 20
raw = True
init = True
dict_fact = SpcaFmri(mask=mask,
smoothing_fwhm=3,
shelve=not raw,
n_components=n_components,
dict_init=fetch_atlas_smith_2009().rsn70 if init else None,
reduction=12,
alpha=0.001,
random_state=0,
n_epochs=1,
memory=expanduser("~/nilearn_cache"), memory_level=2,
verbose=4,
n_jobs=1,
)
print('[Example] Learning maps')
timings = np.zeros(20)
for n_jobs in range(1, 21):
with num_threads(n_jobs):
t0 = time.time()
dict_fact.fit(func_filenames, raw=raw)
which is already defined.
See :ref:`plotting` for more information to know how to tune the parameters.
"""
# Load 4D probabilistic atlases
from nilearn import datasets
# Harvard Oxford Atlas
harvard_oxford = datasets.fetch_atlas_harvard_oxford('cort-prob-2mm')
harvard_oxford_sub = datasets.fetch_atlas_harvard_oxford('sub-prob-2mm')
# Multi Subject Dictionary Learning Atlas
msdl = datasets.fetch_atlas_msdl()
# Smith ICA Atlas and Brain Maps 2009
smith = datasets.fetch_atlas_smith_2009()
# ICBM tissue probability
icbm = datasets.fetch_icbm152_2009()
# Visualization
import matplotlib.pyplot as plt
from nilearn import plotting
atlas_types = {'Harvard_Oxford': harvard_oxford.maps,
'Harvard_Oxford sub': harvard_oxford_sub.maps,
'MSDL': msdl.maps, 'Smith 2009 10 RSNs': smith.rsn10,
'Smith2009 20 RSNs': smith.rsn20,
'Smith2009 70 RSNs': smith.rsn70,
'Smith2009 10 Brainmap': smith.bm10,
'Smith2009 20 Brainmap': smith.bm20,
which is already defined.
See :ref:`plotting` for more information to know how to tune the parameters.
"""
# Load 4D probabilistic atlases
from nilearn import datasets
# Harvard Oxford Atlas
harvard_oxford = datasets.fetch_atlas_harvard_oxford('cort-prob-2mm')
harvard_oxford_sub = datasets.fetch_atlas_harvard_oxford('sub-prob-2mm')
# Multi Subject Dictionary Learning Atlas
msdl = datasets.fetch_atlas_msdl()
# Smith ICA Atlas and Brain Maps 2009
smith = datasets.fetch_atlas_smith_2009()
# ICBM tissue probability
icbm = datasets.fetch_icbm152_2009()
# Visualization
import matplotlib.pyplot as plt
from nilearn import plotting
atlas_types = {
'Harvard_Oxford': harvard_oxford.maps,
'Harvard_Oxford sub': harvard_oxford_sub.maps,
'MSDL': msdl.maps,
'Smith 2009 10 RSNs': smith.rsn10,
'Smith2009 20 RSNs': smith.rsn20,
'Smith2009 70 RSNs': smith.rsn70,
# statistical map: from nilearn import plotting plotting.plot_stat_map(tmap_filename) ############################################################################### # Visualizing works better with a threshold plotting.plot_stat_map(tmap_filename, threshold=3) ############################################################################### # Visualizing one volume in a 4D file # ----------------------------------- # # We can download resting-state networks from the Smith 2009 study on # correspondance between rest and task rsn = datasets.fetch_atlas_smith_2009()['rsn10'] print(rsn) ############################################################################### # It is a 4D nifti file. We load it into the memory to print its # shape. from nilearn import image print(image.load_img(rsn).shape) ############################################################################### # We can retrieve the first volume (note that Python indexing starts at 0): first_rsn = image.index_img(rsn, 0) print(first_rsn.shape) ############################################################################### # first_rsn is a 3D image.
from modl.plotting.fmri import display_maps
from modl.utils.system import get_cache_dirs
n_components = 20
batch_size = 50
learning_rate = .92
method = 'masked'
step_size = 0.01
reduction = 12
alpha = 1e-3
n_epochs = 2
verbose = 15
n_jobs = 2
smoothing_fwhm = 6
dict_init = fetch_atlas_smith_2009().rsn20
dataset = fetch_adhd(n_subjects=40)
data = dataset.rest.values
train_data, test_data = train_test_split(data, test_size=1, random_state=0)
train_imgs, train_confounds = zip(*train_data)
test_imgs, test_confounds = zip(*test_data)
mask = dataset.mask
memory = Memory(cachedir=get_cache_dirs()[0], verbose=2)
cb = rfMRIDictionaryScorer(test_imgs, test_confounds=test_confounds)
dict_fact = fMRIDictFact(
smoothing_fwhm=smoothing_fwhm,
method=method,
step_size=step_size,
mask=mask,
def __init__(self, atlas_name=''):
from nilearn import datasets
smith = datasets.fetch_atlas_smith_2009()
self.dataset = getattr(smith, atlas_name)
