def test_fetch_localizer_calculation_task():
local_url = "file://" + get_datadir()
ids = np.asarray(['S%2d' % i for i in range(94)])
ids = ids.view(dtype=[('subject_id', 'S3')])
get_file_mock().add_csv('cubicwebexport.csv', ids)
get_file_mock().add_csv('cubicwebexport2.csv', ids)
# Disabled: cannot be tested without actually fetching covariates CSV file
# All subjects
dataset = datasets.fetch_localizer_calculation_task(data_dir=get_tmpdir(),
url=local_url,
verbose=0)
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_equal(dataset.ext_vars.size, 94)
assert_equal(len(dataset.cmaps), 94)
# 20 subjects
dataset = datasets.fetch_localizer_calculation_task(n_subjects=20,
data_dir=get_tmpdir(),
url=local_url,
verbose=0)
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_equal(dataset.ext_vars.size, 20)
assert_equal(len(dataset.cmaps), 20)
def test_fail_fetch_harvard_oxford():
# specify non-existing atlas item
assert_raises_regex(ValueError, 'Invalid atlas name',
datasets.fetch_harvard_oxford, 'not_inside')
# specify existing atlas item
target_atlas = 'cort-maxprob-thr0-1mm'
target_atlas_fname = 'HarvardOxford-' + target_atlas + '.nii.gz'
HO_dir = os.path.join(get_tmpdir(), 'harvard_oxford')
os.mkdir(HO_dir)
nifti_dir = os.path.join(HO_dir, 'HarvardOxford')
os.mkdir(nifti_dir)
target_atlas_nii = os.path.join(nifti_dir, target_atlas_fname)
datasets.load_mni152_template().to_filename(target_atlas_nii)
dummy = open(os.path.join(HO_dir, 'HarvardOxford-Cortical.xml'), 'w')
dummy.write("<?xml version='1.0' encoding='us-ascii'?> "
"<metadata>"
"</metadata>")
dummy.close()
out_nii, arr = datasets.fetch_harvard_oxford(target_atlas,
data_dir=get_tmpdir())
assert_true(isinstance(nibabel.load(out_nii), nibabel.Nifti1Image))
assert_true(isinstance(arr, np.ndarray))
assert_true(len(arr) > 0)
def test_fetch_localizer_calculation_task():
local_url = "file://" + get_datadir()
ids = np.asarray(['S%2d' % i for i in range(94)])
ids = ids.view(dtype=[('subject_id', 'S3')])
get_file_mock().add_csv('cubicwebexport.csv', ids)
get_file_mock().add_csv('cubicwebexport2.csv', ids)
# Disabled: cannot be tested without actually fetching covariates CSV file
# All subjects
dataset = datasets.fetch_localizer_calculation_task(data_dir=get_tmpdir(),
url=local_url,
verbose=0)
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_equal(dataset.ext_vars.size, 94)
assert_equal(len(dataset.cmaps), 94)
# 20 subjects
dataset = datasets.fetch_localizer_calculation_task(n_subjects=20,
data_dir=get_tmpdir(),
url=local_url,
verbose=0)
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_equal(dataset.ext_vars.size, 20)
assert_equal(len(dataset.cmaps), 20)
def test_fail_fetch_haxby_simple():
# Test a dataset fetching failure to validate sandboxing
local_url = "file://" + os.path.join(get_datadir(), "pymvpa-exampledata.tar.bz2")
datasetdir = os.path.join(get_tmpdir(), 'haxby2001_simple', 'pymvpa-exampledata')
os.makedirs(datasetdir)
# Create a dummy file. If sandboxing is successful, it won't be overwritten
dummy = open(os.path.join(datasetdir, 'attributes.txt'), 'w')
dummy.write('stuff')
dummy.close()
path = 'pymvpa-exampledata'
opts = {'uncompress': True}
files = [
(os.path.join(path, 'attributes.txt'), local_url, opts),
# The following file does not exists. It will cause an abortion of
# the fetching procedure
(os.path.join(path, 'bald.nii.gz'), local_url, opts)
]
assert_raises(IOError, fetchers.fetch_files,
os.path.join(get_tmpdir(), 'haxby2001_simple'), files,
verbose=0)
dummy = open(os.path.join(datasetdir, 'attributes.txt'), 'r')
stuff = dummy.read(5)
dummy.close()
assert_equal(stuff, 'stuff')
def test_fail_fetch_harvard_oxford():
# specify non-existing atlas item
assert_raises_regex(ValueError, 'Invalid atlas name',
datasets.fetch_harvard_oxford, 'not_inside')
# specify existing atlas item
target_atlas = 'cort-maxprob-thr0-1mm'
target_atlas_fname = 'HarvardOxford-' + target_atlas + '.nii.gz'
HO_dir = os.path.join(get_tmpdir(), 'harvard_oxford')
os.mkdir(HO_dir)
nifti_dir = os.path.join(HO_dir, 'HarvardOxford')
os.mkdir(nifti_dir)
target_atlas_nii = os.path.join(nifti_dir, target_atlas_fname)
datasets.load_mni152_template().to_filename(target_atlas_nii)
dummy = open(os.path.join(HO_dir, 'HarvardOxford-Cortical.xml'), 'w')
dummy.write("<?xml version='1.0' encoding='us-ascii'?> "
"<metadata>"
"</metadata>")
dummy.close()
out_nii, arr = datasets.fetch_harvard_oxford(target_atlas, data_dir=get_tmpdir())
assert_true(isinstance(nibabel.load(out_nii), nibabel.Nifti1Image))
assert_true(isinstance(arr, np.ndarray))
assert_true(len(arr) > 0)
def test_fetch_oasis_vbm():
local_url = "file://" + get_datadir()
ids = np.asarray(['OAS1_%4d' % i for i in range(457)])
ids = ids.view(dtype=[('ID', 'S9')])
get_file_mock().add_csv('oasis_cross-sectional.csv', ids)
# Disabled: cannot be tested without actually fetching covariates CSV file
dataset = datasets.fetch_oasis_vbm(data_dir=get_tmpdir(), url=local_url,
verbose=0)
assert_equal(len(dataset.gray_matter_maps), 403)
assert_equal(len(dataset.white_matter_maps), 403)
assert_true(isinstance(dataset.gray_matter_maps[0], _basestring))
assert_true(isinstance(dataset.white_matter_maps[0], _basestring))
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.data_usage_agreement, _basestring))
assert_equal(len(get_url_request().urls), 3)
dataset = datasets.fetch_oasis_vbm(data_dir=get_tmpdir(), url=local_url,
dartel_version=False, verbose=0)
assert_equal(len(dataset.gray_matter_maps), 415)
assert_equal(len(dataset.white_matter_maps), 415)
assert_true(isinstance(dataset.gray_matter_maps[0], _basestring))
assert_true(isinstance(dataset.white_matter_maps[0], _basestring))
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.data_usage_agreement, _basestring))
assert_equal(len(get_url_request().urls), 4)
def test_fetch_haxby_simple():
local_url = "file://" + os.path.join(get_datadir(), "pymvpa-exampledata.tar.bz2")
haxby = datasets.fetch_haxby_simple(data_dir=get_tmpdir(), url=local_url,
verbose=0)
datasetdir = os.path.join(get_tmpdir(), 'haxby2001_simple', 'pymvpa-exampledata')
for key, file in [
('session_target', 'attributes.txt'),
('func', 'bold.nii.gz'),
('mask', 'mask.nii.gz'),
('conditions_target', 'attributes_literal.txt')]:
assert_equal(haxby[key], os.path.join(datasetdir, file))
assert_true(os.path.exists(os.path.join(datasetdir, file)))
def test_fetch_smith_2009_atlas():
bunch = datasets.fetch_smith_2009(data_dir=get_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(get_url_request().urls), 6)
for key, fn in zip(keys, filenames):
assert_equal(bunch[key], os.path.join(get_tmpdir(), 'smith_2009', fn))
def test_miyawaki2008():
dataset = datasets.fetch_miyawaki2008(data_dir=get_tmpdir(), verbose=0)
assert_equal(len(dataset.func), 32)
assert_equal(len(dataset.label), 32)
assert_true(isinstance(dataset.mask, _basestring))
assert_equal(len(dataset.mask_roi), 38)
assert_equal(len(get_url_request().urls), 1)
def test_fetch_craddock_2012_atlas():
bunch = datasets.fetch_craddock_2012_atlas(data_dir=get_tmpdir(), verbose=0)
keys = ("scorr_mean", "tcorr_mean",
"scorr_2level", "tcorr_2level",
"random")
filenames = [
"scorr05_mean_all.nii.gz",
"tcorr05_mean_all.nii.gz",
"scorr05_2level_all.nii.gz",
"tcorr05_2level_all.nii.gz",
"random_all.nii.gz",
]
assert_equal(len(get_url_request().urls), 1)
for key, fn in zip(keys, filenames):
assert_equal(bunch[key], os.path.join(get_tmpdir(), 'craddock_2012', fn))
def test_fetch_craddock_2012_atlas():
bunch = datasets.fetch_craddock_2012_atlas(data_dir=get_tmpdir(),
verbose=0)
keys = ("scorr_mean", "tcorr_mean", "scorr_2level", "tcorr_2level",
"random")
filenames = [
"scorr05_mean_all.nii.gz",
"tcorr05_mean_all.nii.gz",
"scorr05_2level_all.nii.gz",
"tcorr05_2level_all.nii.gz",
"random_all.nii.gz",
]
assert_equal(len(get_url_request().urls), 1)
for key, fn in zip(keys, filenames):
assert_equal(bunch[key], os.path.join(get_tmpdir(), 'craddock_2012',
fn))
def test_fetch_smith_2009_atlas():
bunch = datasets.fetch_smith_2009(data_dir=get_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(get_url_request().urls), 6)
for key, fn in zip(keys, filenames):
assert_equal(bunch[key], os.path.join(get_tmpdir(), 'smith_2009', fn))
def test_fetch_yeo_2011_atlas():
dataset = datasets.fetch_yeo_2011_atlas(data_dir=get_tmpdir(), verbose=0)
assert_true(isinstance(dataset.anat, _basestring))
assert_true(isinstance(dataset.colors_17, _basestring))
assert_true(isinstance(dataset.colors_7, _basestring))
assert_true(isinstance(dataset.thick_17, _basestring))
assert_true(isinstance(dataset.thick_7, _basestring))
assert_true(isinstance(dataset.thin_17, _basestring))
assert_true(isinstance(dataset.thin_7, _basestring))
assert_equal(len(get_url_request().urls), 1)
def test_fetch_yeo_2011_atlas():
dataset = datasets.fetch_yeo_2011_atlas(data_dir=get_tmpdir(), verbose=0)
assert_true(isinstance(dataset.anat, _basestring))
assert_true(isinstance(dataset.colors_17, _basestring))
assert_true(isinstance(dataset.colors_7, _basestring))
assert_true(isinstance(dataset.thick_17, _basestring))
assert_true(isinstance(dataset.thick_7, _basestring))
assert_true(isinstance(dataset.thin_17, _basestring))
assert_true(isinstance(dataset.thin_7, _basestring))
assert_equal(len(get_url_request().urls), 1)
def test_fetch_icbm152_2009():
dataset = datasets.fetch_icbm152_2009(data_dir=get_tmpdir(), verbose=0)
assert_true(isinstance(dataset.csf, _basestring))
assert_true(isinstance(dataset.eye_mask, _basestring))
assert_true(isinstance(dataset.face_mask, _basestring))
assert_true(isinstance(dataset.gm, _basestring))
assert_true(isinstance(dataset.mask, _basestring))
assert_true(isinstance(dataset.pd, _basestring))
assert_true(isinstance(dataset.t1, _basestring))
assert_true(isinstance(dataset.t2, _basestring))
assert_true(isinstance(dataset.t2_relax, _basestring))
assert_true(isinstance(dataset.wm, _basestring))
assert_equal(len(get_url_request().urls), 1)
def test_fetch_icbm152_2009():
dataset = datasets.fetch_icbm152_2009(data_dir=get_tmpdir(), verbose=0)
assert_true(isinstance(dataset.csf, _basestring))
assert_true(isinstance(dataset.eye_mask, _basestring))
assert_true(isinstance(dataset.face_mask, _basestring))
assert_true(isinstance(dataset.gm, _basestring))
assert_true(isinstance(dataset.mask, _basestring))
assert_true(isinstance(dataset.pd, _basestring))
assert_true(isinstance(dataset.t1, _basestring))
assert_true(isinstance(dataset.t2, _basestring))
assert_true(isinstance(dataset.t2_relax, _basestring))
assert_true(isinstance(dataset.wm, _basestring))
assert_equal(len(get_url_request().urls), 1)
def test_fetch_haxby():
for i in range(1, 6):
haxby = datasets.fetch_haxby(data_dir=get_tmpdir(), n_subjects=i,
verbose=0)
assert_equal(len(get_url_request().urls), 1 + (i == 1)) # subject_data + md5
assert_equal(len(haxby.func), i)
assert_equal(len(haxby.anat), i)
assert_equal(len(haxby.session_target), i)
assert_equal(len(haxby.mask_vt), i)
assert_equal(len(haxby.mask_face), i)
assert_equal(len(haxby.mask_house), i)
assert_equal(len(haxby.mask_face_little), i)
assert_equal(len(haxby.mask_house_little), i)
get_url_request().reset()
def test_fetch_localizer_contrasts():
local_url = "file://" + get_datadir()
ids = np.asarray([('S%2d' % i).encode() for i in range(94)])
ids = ids.view(dtype=[('subject_id', 'S3')])
get_file_mock().add_csv('cubicwebexport.csv', ids)
get_file_mock().add_csv('cubicwebexport2.csv', ids)
# Disabled: cannot be tested without actually fetching covariates CSV file
# All subjects
dataset = datasets.fetch_localizer_contrasts(["checkerboard"],
data_dir=get_tmpdir(),
url=local_url,
verbose=0)
assert_true(dataset.anats is None)
assert_true(dataset.tmaps is None)
assert_true(dataset.masks is None)
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_equal(dataset.ext_vars.size, 94)
assert_equal(len(dataset.cmaps), 94)
# 20 subjects
dataset = datasets.fetch_localizer_contrasts(["checkerboard"],
n_subjects=20,
data_dir=get_tmpdir(),
url=local_url,
verbose=0)
assert_true(dataset.anats is None)
assert_true(dataset.tmaps is None)
assert_true(dataset.masks is None)
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_equal(len(dataset.cmaps), 20)
assert_equal(dataset.ext_vars.size, 20)
# Multiple contrasts
dataset = datasets.fetch_localizer_contrasts(
["checkerboard", "horizontal checkerboard"],
n_subjects=20, data_dir=get_tmpdir(),
verbose=0)
assert_true(dataset.anats is None)
assert_true(dataset.tmaps is None)
assert_true(dataset.masks is None)
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_equal(len(dataset.cmaps), 20 * 2) # two contrasts are fetched
assert_equal(dataset.ext_vars.size, 20)
# get_anats=True
dataset = datasets.fetch_localizer_contrasts(["checkerboard"],
data_dir=get_tmpdir(),
url=local_url,
get_anats=True,
verbose=0)
assert_true(dataset.masks is None)
assert_true(dataset.tmaps is None)
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.anats[0], _basestring))
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_equal(dataset.ext_vars.size, 94)
assert_equal(len(dataset.anats), 94)
assert_equal(len(dataset.cmaps), 94)
# get_masks=True
dataset = datasets.fetch_localizer_contrasts(["checkerboard"],
data_dir=get_tmpdir(),
url=local_url,
get_masks=True,
verbose=0)
assert_true(dataset.anats is None)
assert_true(dataset.tmaps is None)
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_true(isinstance(dataset.masks[0], _basestring))
assert_equal(dataset.ext_vars.size, 94)
assert_equal(len(dataset.cmaps), 94)
assert_equal(len(dataset.masks), 94)
# get_tmaps=True
dataset = datasets.fetch_localizer_contrasts(["checkerboard"],
data_dir=get_tmpdir(),
url=local_url,
get_tmaps=True,
verbose=0)
assert_true(dataset.anats is None)
assert_true(dataset.masks is None)
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_true(isinstance(dataset.tmaps[0], _basestring))
assert_equal(dataset.ext_vars.size, 94)
assert_equal(len(dataset.cmaps), 94)
assert_equal(len(dataset.tmaps), 94)
# all get_*=True
dataset = datasets.fetch_localizer_contrasts(["checkerboard"],
data_dir=get_tmpdir(),
url=local_url,
get_anats=True,
get_masks=True,
get_tmaps=True,
verbose=0)
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.anats[0], _basestring))
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_true(isinstance(dataset.masks[0], _basestring))
assert_true(isinstance(dataset.tmaps[0], _basestring))
assert_equal(dataset.ext_vars.size, 94)
assert_equal(len(dataset.anats), 94)
assert_equal(len(dataset.cmaps), 94)
assert_equal(len(dataset.masks), 94)
assert_equal(len(dataset.tmaps), 94)
def test_fetch_msdl_atlas():
dataset = datasets.fetch_msdl_atlas(data_dir=get_tmpdir(), verbose=0)
assert_true(isinstance(dataset.labels, _basestring))
assert_true(isinstance(dataset.maps, _basestring))
assert_equal(len(get_url_request().urls), 1)
def test_fetch_msdl_atlas():
dataset = datasets.fetch_msdl_atlas(data_dir=get_tmpdir(), verbose=0)
assert_true(isinstance(dataset.labels, _basestring))
assert_true(isinstance(dataset.maps, _basestring))
assert_equal(len(get_url_request().urls), 1)
def test_fetch_localizer_contrasts():
local_url = "file://" + get_datadir()
ids = np.asarray([('S%2d' % i).encode() for i in range(94)])
ids = ids.view(dtype=[('subject_id', 'S3')])
get_file_mock().add_csv('cubicwebexport.csv', ids)
get_file_mock().add_csv('cubicwebexport2.csv', ids)
# Disabled: cannot be tested without actually fetching covariates CSV file
# All subjects
dataset = datasets.fetch_localizer_contrasts(["checkerboard"],
data_dir=get_tmpdir(),
url=local_url,
verbose=0)
assert_true(dataset.anats is None)
assert_true(dataset.tmaps is None)
assert_true(dataset.masks is None)
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_equal(dataset.ext_vars.size, 94)
assert_equal(len(dataset.cmaps), 94)
# 20 subjects
dataset = datasets.fetch_localizer_contrasts(["checkerboard"],
n_subjects=20,
data_dir=get_tmpdir(),
url=local_url,
verbose=0)
assert_true(dataset.anats is None)
assert_true(dataset.tmaps is None)
assert_true(dataset.masks is None)
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_equal(len(dataset.cmaps), 20)
assert_equal(dataset.ext_vars.size, 20)
# Multiple contrasts
dataset = datasets.fetch_localizer_contrasts(
["checkerboard", "horizontal checkerboard"],
n_subjects=20,
data_dir=get_tmpdir(),
verbose=0)
assert_true(dataset.anats is None)
assert_true(dataset.tmaps is None)
assert_true(dataset.masks is None)
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_equal(len(dataset.cmaps), 20 * 2) # two contrasts are fetched
assert_equal(dataset.ext_vars.size, 20)
# get_anats=True
dataset = datasets.fetch_localizer_contrasts(["checkerboard"],
data_dir=get_tmpdir(),
url=local_url,
get_anats=True,
verbose=0)
assert_true(dataset.masks is None)
assert_true(dataset.tmaps is None)
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.anats[0], _basestring))
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_equal(dataset.ext_vars.size, 94)
assert_equal(len(dataset.anats), 94)
assert_equal(len(dataset.cmaps), 94)
# get_masks=True
dataset = datasets.fetch_localizer_contrasts(["checkerboard"],
data_dir=get_tmpdir(),
url=local_url,
get_masks=True,
verbose=0)
assert_true(dataset.anats is None)
assert_true(dataset.tmaps is None)
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_true(isinstance(dataset.masks[0], _basestring))
assert_equal(dataset.ext_vars.size, 94)
assert_equal(len(dataset.cmaps), 94)
assert_equal(len(dataset.masks), 94)
# get_tmaps=True
dataset = datasets.fetch_localizer_contrasts(["checkerboard"],
data_dir=get_tmpdir(),
url=local_url,
get_tmaps=True,
verbose=0)
assert_true(dataset.anats is None)
assert_true(dataset.masks is None)
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_true(isinstance(dataset.tmaps[0], _basestring))
assert_equal(dataset.ext_vars.size, 94)
assert_equal(len(dataset.cmaps), 94)
assert_equal(len(dataset.tmaps), 94)
# all get_*=True
dataset = datasets.fetch_localizer_contrasts(["checkerboard"],
data_dir=get_tmpdir(),
url=local_url,
get_anats=True,
get_masks=True,
get_tmaps=True,
verbose=0)
assert_true(isinstance(dataset.ext_vars, np.recarray))
assert_true(isinstance(dataset.anats[0], _basestring))
assert_true(isinstance(dataset.cmaps[0], _basestring))
assert_true(isinstance(dataset.masks[0], _basestring))
assert_true(isinstance(dataset.tmaps[0], _basestring))
assert_equal(dataset.ext_vars.size, 94)
assert_equal(len(dataset.anats), 94)
assert_equal(len(dataset.cmaps), 94)
assert_equal(len(dataset.masks), 94)
assert_equal(len(dataset.tmaps), 94)