def test_convert_neurosynth_to_dataset_smoke():
"""Smoke test for Neurosynth file conversion."""
coordinates_file = os.path.join(
get_test_data_path(),
"data-neurosynth_version-7_coordinates.tsv.gz",
)
metadata_file = os.path.join(
get_test_data_path(),
"data-neurosynth_version-7_metadata.tsv.gz",
)
features = {
"features":
os.path.join(
get_test_data_path(),
"data-neurosynth_version-7_vocab-terms_source-abstract_type-tfidf_features.npz",
),
"vocabulary":
os.path.join(get_test_data_path(),
"data-neurosynth_version-7_vocab-terms_vocabulary.txt"),
}
dset = io.convert_neurosynth_to_dataset(
coordinates_file,
metadata_file,
annotations_files=features,
)
assert isinstance(dset, nimare.dataset.Dataset)
assert "terms_abstract_tfidf__abilities" in dset.annotations.columns
def macm_workflow(ns_data_dir, output_dir, prefix, mask_fn):
# download neurosynth dataset if necessary
dataset_file = op.join(ns_data_dir, 'neurosynth_dataset.pkl.gz')
if not op.isfile(dataset_file):
if not op.isdir(ns_data_dir):
os.mkdir(ns_data_dir)
download(ns_data_dir, unpack=True)
###############################################################################
# Convert Neurosynth database to NiMARE dataset file
# --------------------------------------------------
dset = convert_neurosynth_to_dataset(
op.join(ns_data_dir, 'database.txt'),
op.join(ns_data_dir, 'features.txt'))
dset.save(dataset_file)
dset = Dataset.load(dataset_file)
mask_ids = dset.get_studies_by_mask(mask_fn)
maskdset = dset.slice(mask_ids)
nonmask_ids = sorted(list(set(dset.ids) - set(mask_ids)))
nonmaskdset = dset.slice(nonmask_ids)
ale = ALE(kernel__fwhm=15)
ale.fit(maskdset)
corr = FWECorrector(method='permutation',
n_iters=10,
n_cores=-1,
voxel_thresh=0.001)
cres = corr.transform(ale.results)
cres.save_maps(output_dir=output_dir, prefix=prefix)
def test_convert_neurosynth_to_dataset_smoke():
"""
Smoke test for Sleuth text file conversion.
"""
db_file = op.join(get_test_data_path(), 'test_neurosynth_database.txt')
features_file = op.join(get_test_data_path(),
'test_neurosynth_features.txt')
dset = io.convert_neurosynth_to_dataset(db_file, features_file)
assert isinstance(dset, nimare.dataset.Dataset)
def neurosynth_download(ns_data_dir):
dataset_file = op.join(ns_data_dir, "neurosynth_dataset.pkl.gz")
os.makedirs(ns_data_dir, exist_ok=True)
download(ns_data_dir, unpack=True)
###############################################################################
# Convert Neurosynth database to NiMARE dataset file
# --------------------------------------------------
dset = convert_neurosynth_to_dataset(op.join(ns_data_dir, "database.txt"),
op.join(ns_data_dir, "features.txt"))
dset.save(dataset_file)
def neurosynth_download(ns_data_dir=None):
if ns_data_dir is None:
raise Exception('A valid directory is required for downloading Neurosynth data!')
dataset_file = op.join(ns_data_dir, 'neurosynth_dataset.pkl.gz')
if not op.isdir(ns_data_dir):
os.mkdir(ns_data_dir)
download(ns_data_dir, unpack=True)
###############################################################################
# Convert Neurosynth database to NiMARE dataset file
# --------------------------------------------------
dset = convert_neurosynth_to_dataset(
op.join(ns_data_dir, 'database.txt'),
op.join(ns_data_dir, 'features.txt'))
dset.save(dataset_file)
database, rather than handling it locally with NiMARE.
"""
###############################################################################
# Start with the necessary imports
# --------------------------------
import os.path as op
from os import mkdir
from neurosynth.base.dataset import download
from nimare.io import convert_neurosynth_to_dataset
from nimare.dataset import Dataset
###############################################################################
# Download Neurosynth
# --------------------------------
out_dir = op.abspath('../example_data/')
if not op.isdir(out_dir):
mkdir(out_dir)
if not op.isfile(op.join(out_dir, 'database.txt')):
download(out_dir, unpack=True)
###############################################################################
# Convert Neurosynth database to NiMARE dataset file
# --------------------------------------------------
dset = convert_neurosynth_to_dataset(op.join(out_dir, 'database.txt'),
op.join(out_dir, 'features.txt'))
gz_file = op.join(out_dir, 'neurosynth_dataset.pkl.gz')
dset.save(gz_file)
data_dir=out_dir,
version="7",
overwrite=False,
source="abstract",
vocab="terms",
)
# Note that the files are saved to a new folder within "out_dir" named "neurosynth".
pprint(files)
neurosynth_db = files[0]
###############################################################################
# Convert Neurosynth database to NiMARE dataset file
# -----------------------------------------------------------------------------
neurosynth_dset = convert_neurosynth_to_dataset(
coordinates_file=neurosynth_db["coordinates"],
metadata_file=neurosynth_db["metadata"],
annotations_files=neurosynth_db["features"],
)
neurosynth_dset.save(os.path.join(out_dir, "neurosynth_dataset.pkl.gz"))
print(neurosynth_dset)
###############################################################################
# Add article abstracts to dataset
# -----------------------------------------------------------------------------
# This is only possible because Neurosynth uses PMIDs as study IDs.
#
# Make sure you replace the example email address with your own.
neurosynth_dset = download_abstracts(neurosynth_dset, "*****@*****.**")
neurosynth_dset.save(
os.path.join(out_dir, "neurosynth_dataset_with_abstracts.pkl.gz"))