def save_dataset_instance(db_filename, kw_filename, instance_filename):
# Create a new Dataset instance
dataset = Dataset('./raw_data/' + db_filename + '.txt')
# Add some features
dataset.add_features('./raw_data/' + kw_filename + '.txt')
# Save new file
dataset.save('./raw_data/' + instance_filename + '.pkl')
return dataset
def test_dataset_initializes(self):
""" Test whether dataset initializes properly. """
Dataset(get_test_data_path() + 'test_dataset.txt', get_test_data_path() + 'test_features.txt')
self.assertIsNotNone(self.dataset.masker)
self.assertIsNotNone(self.dataset.image_table)
self.assertEqual(len(self.dataset.mappables), 5)
self.assertIsNotNone(self.dataset.masker)
self.assertIsNotNone(self.dataset.r)
self.assertIsNotNone(self.dataset.mappables[0].data['extra_field'].iloc[2], 'field')
def neurosynthInit(dbsize):
"""Initialize Neurosynth Database, return database object"""
print "Initializing Neurosynth database..."
db = Dataset('data/' + str(dbsize) + 'terms/database.txt')
db.add_features('data/' + str(dbsize) + 'terms/features.txt')
#print "Loading standard space brain..."
#img = nb.load("data/MNI152_T1_2mm_brain.nii.gz")
#standard = img.get_data()
return db
def __init__(self,
db,
dataset=None,
studies=None,
features=None,
reset_db=False,
reset_dataset=False,
download_data=False):
"""
Initialize instance from a pickled Neurosynth Dataset instance or a
pair of study and analysis .txt files.
Args:
db: the SQLAlchemy database connection to use.
dataset: an optional filename of a pickled neurosynth Dataset
instance.
studies: name of file containing activation data. If passed, a new
Dataset instance will be constructed.
features: name of file containing feature data.
reset_db: if True, will drop and re-create all database tables
before adding new content. If False (default), will add content
incrementally.
reset_dataset: if True, will regenerate the pickled Neurosynth
dataset.
download_data: if True, ignores any existing files and downloads
the latest Neurosynth data files from GitHub.
"""
if (studies is not None and not os.path.exists(studies)) \
or settings.RESET_ASSETS:
print("WARNING: RESETTING ALL NEUROSYNTH ASSETS!")
self.reset_assets(download_data)
# Load or create Neurosynth Dataset instance
if dataset is None or reset_dataset or (isinstance(dataset, str) and
not os.path.exists(dataset)):
print("\tInitializing a new Dataset...")
if (studies is None) or (features is None):
raise ValueError(
"To generate a new Dataset instance, both studies and "
"analyses must be provided.")
dataset = Dataset(studies)
dataset.add_features(features)
dataset.save(settings.PICKLE_DATABASE)
else:
print("Loading existing Dataset...")
dataset = Dataset.load(dataset)
if features is not None:
dataset.add_features(features)
self.dataset = dataset
self.db = db
if reset_db:
print("WARNING: RESETTING DATABASE!!!")
self.reset_database()
def get_dataset(self, force_load=False):
if os.path.exists(os.path.join(self.datadir,
'dataset.pkl')) and not force_load:
print('loading database from',
os.path.join(self.datadir, 'dataset.pkl'))
self.dataset = Dataset.load(
os.path.join(self.datadir, 'dataset.pkl'))
else:
print('loading database - this takes a few minutes')
self.dataset = Dataset(os.path.join(self.datadir, 'database.txt'))
self.dataset.add_features(
os.path.join(self.datadir, 'features.txt'))
self.dataset.save(os.path.join(self.datadir, 'dataset.pkl'))
def fetch_neurosynth_dataset(data_dir, return_pkl=True):
"""Downloads the Neurosynth dataset
Parameters
----------
data_dir : str
Directory in which to download the dataset.
return_pkl : bool
If true, creates and returns the .pkl file. Otherwise returns
the dataset and features files.
Returns
-------
tuple, str
If save_pkl is false, returns a tuple containing the path to the
database.txt and the features.txt file. Otherwise returns the path
to the .pkl file.
"""
if not os.path.isdir(data_dir):
os.mkdir(data_dir)
dataset_file = os.path.join(data_dir, "database.txt")
if not os.path.isfile(dataset_file):
logging.info("Downloading the Neurosynth dataset.")
download(data_dir, unpack=True)
feature_file = os.path.join(data_dir, "features.txt")
if return_pkl:
pkl_file = os.path.join(data_dir, "dataset.pkl")
if not os.path.isfile(pkl_file):
logging.info(
"Converting Neurosynth data to a .pkl file. This may take a while."
)
dataset = Dataset(dataset_file, feature_file)
dataset.save(pkl_file)
return pkl_file
return (dataset_file, feature_file)
from neurosynth.base.dataset import Dataset
from neurosynth.analysis import meta
import os
dataset = Dataset('database.txt')
dataset.add_features('features.txt')
print dataset.get_feature_names()
ids = dataset.get_ids_by_features('emo*', threshold=0.001)
print len(ids)
ma = meta.MetaAnalysis(dataset, ids)
ma.save_results('emotion')
if mask_img_data.shape != (91, 109, 91):
resampled_roi = resample_to_img(
roi, mni152_2mm, interpolation="nearest", copy=True
)
resampled_file = join(map_dir, "{0}_mni2mm.nii.gz".format(file))
resampled_roi.to_filename(resampled_file)
roi_files[i] = resampled_file
plot_glass_brain(
resampled_file,
output_file=join(map_dir, "{0}_mni2mm.png".format(basename(file))),
)
print("loading dataset...")
tds = datetime.now()
dataset = Dataset("/Users/kbottenh/Dropbox/Data/neurosynth-v0.7/database.txt")
tdf = datetime.now()
print("dataset loaded! only took {0}".format((tdf - tds)))
for i in np.arange(0, len(mask_names)):
print("{0}\nmeta-analyzing {1}...".format(datetime.now(), mask_names[i]))
tmas = datetime.now()
ids = dataset.get_studies(
mask=roi_files[i],
)
ma = meta.MetaAnalysis(dataset, ids)
ma.save_results(
output_dir=sink_dir,
prefix=mask_names[i],
import neurosynth.base.dataset
from neurosynth.base.dataset import Dataset
print neurosynth.base.dataset.__file__
dataset = Dataset('../data/unprocessed/abstract/full_database_revised.txt')
dataset.add_features('../data/unprocessed/abstract/abstract_features.txt')
dataset.save('../data/datasets/dataset_abs_words_pandas.pkl')
dataset = Dataset('../data/unprocessed/abstract/full_database_revised.txt')
dataset.add_features('../data/unprocessed/abstract_topics/doc_features100.txt')
dataset.save('../data/datasets/dataset_abs_topics_pandas.pkl')
def get_test_dataset():
test_data_path = get_test_data_path()
dataset = Dataset(test_data_path + 'test_dataset.txt')
dataset.add_features(test_data_path + 'test_features.txt')
return dataset
resampled_roi = resample_to_img(roi,
mni152_2mm,
interpolation='nearest',
copy=True)
resampled_file = join(map_dir, '{0}_mni2mm.nii.gz'.format(file))
resampled_roi.to_filename(resampled_file)
roi_files[i] = resampled_file
plot_glass_brain(resampled_file,
output_file=join(
map_dir, '{0}_mni2mm.png'.format(basename(file))))
# In[16]:
print('loading dataset...')
tds = datetime.now()
dataset = Dataset('/Users/Katie/Dropbox/Data/neurosynth-v0.7/database.txt')
dataset.add_features('/Users/Katie/Dropbox/Data/neurosynth-v0.7/features.txt')
tdf = datetime.now()
print('dataset loaded! only took {0}'.format((tdf - tds)))
for i in np.arange(0, len(mask_names)):
print('{0}\nmeta-analyzing {1}...'.format(datetime.now(), mask_names[i]))
tmas = datetime.now()
ids = dataset.get_studies(mask=roi_files[i], )
ma = meta.MetaAnalysis(dataset, ids)
ma.save_results(
output_dir=sink_dir,
prefix=mask_names[i],
image_list=['association-test_z', 'association-test_z_FDR_0.01'])
tmaf = datetime.now()
def get_test_dataset(prefix='test'):
test_data_path = get_test_data_path()
dataset = Dataset(test_data_path + '%s_dataset.txt' % prefix)
dataset.add_features(test_data_path + '%s_features.txt' % prefix)
return dataset
xfm2vol.run()
#make masks to input into neurosynth
def cluster2masks(clusterfile):
clustermap = nb.load(clusterfile).get_data()
for x in range(1, clustermap.max() + 1):
clustermask = (clustermap == x).astype(int)
nImg = nb.Nifti1Image(clustermask, None)
nb.save(
nImg,
os.path.abspath(clusterfile + '_clustermask' + str(x) + '.nii'))
cluster2masks(volume_file)
dataset_file = '/home/raid3/watanabe/neurosynth/data/dataset.pkl'
if not os.path.exists(dataset_file):
dataset = Dataset('/home/raid3/watanabe/neurosynth/data/database.txt')
dataset.add_features('/home/raid3/watanabe/neurosynth/data/features.txt')
dataset.save(dataset_file)
else:
dataset = cPickle.load(open(dataset_file, 'rb'))
clustermask = volume_file + '_clustermask' + str(3) + '.nii'
ids = dataset.get_ids_by_mask(clustermask)
features = dataset.feature_table.get_features_by_ids(ids)
#mri_surf2vol --identity fsaverage4 --surfval /scr/ilz1/Data/attemptsurface.nii --hemi 'lh' --o /scr/ilz1/Data/results/surf2volume.nii --template /scr/ilz1/Data/freesurfer/fsaverage4/mri/orig.mgz
def __init__(self,dbsize):
print "Initializing Neurosynth database..."
self.db = Dataset('data/' + str(dbsize) + 'terms/database.txt')
self.db.add_features('data/' + str(dbsize) + 'terms/features.txt')
self.ids = self.getIDs()
self.decoder = None
from neurosynth.analysis import meta
from neurosynth.base.dataset import Dataset
""" Create a new Dataset instance from a database file and load features.
This is basically the example from the quickstart in the README.
Assumes you have database.txt and features.txt files in the current dir.
"""
""" Load a Dataset and generate a full set of meta-analysis
images--i.e., run a meta-analysis on every single feature.
"""
neurosynth_data_dir = "/home/data/nbc/misc-projects/niconn-macm/code/neurosynth/"
if not op.isfile(op.join(neurosynth_data_dir, "dataset.pkl")):
# Create Dataset instance from a database file.
dataset = Dataset(op.join(neurosynth_data_dir, "database.txt"))
# Load features from file
dataset.add_features(op.join(neurosynth_data_dir, "features.txt"))
# Pickle the Dataset to file so we can use Dataset.load() next time
# instead of having to sit through the generation process again.
dataset.save(op.join(neurosynth_data_dir, "dataset.pkl"))
# Load pickled Dataset--assumes you've previously saved it. If not,
# follow the create_a_new_dataset_and_load_features example.
dataset = Dataset.load(op.join(neurosynth_data_dir, "dataset.pkl"))
# Get the full list of feature names
feature_list = dataset.get_feature_names()
