def _run_test_for_invalid_separator(filepath, delimiter_name):
if delimiter_name not in ('tab', 'comma'):
with pytest.raises(ValueError):
_check_events_file_uses_tab_separators(events_files=filepath)
else:
result = _check_events_file_uses_tab_separators(events_files=filepath)
assert result is None
def test_binary_bytearray_of_ints_data():
temp_data_bytearray_from_ints = bytearray([0, 1, 0, 11, 10])
with InTemporaryDirectory():
temp_bin_file = 'temp_bin.bin'
with open(temp_bin_file, 'wb') as temp_bin_obj:
temp_bin_obj.write(temp_data_bytearray_from_ints)
with pytest.raises(ValueError):
_check_events_file_uses_tab_separators(
events_files=temp_bin_file)
def test_binary_opening_an_image():
img_data = bytearray(
b'GIF87a\x01\x00\x01\x00\xe7*\x00\x00\x00\x00\x01\x01\x01\x02\x02'
b'\x07\x08\x08\x08\x0b\x0b\x0b\x0c\x0c\x0c\r;')
with InTemporaryDirectory():
temp_img_file = 'temp_img.gif'
with open(temp_img_file, 'wb') as temp_img_obj:
temp_img_obj.write(img_data)
with pytest.raises(ValueError):
_check_events_file_uses_tab_separators(
events_files=temp_img_file)
def test_with_1D_dataframe():
data_for_pandas_dataframe, _ = make_data_for_test_runs()
for dataframe_ in data_for_pandas_dataframe:
events_pandas_dataframe = pd.DataFrame(dataframe_)
result = _check_events_file_uses_tab_separators(
events_files=events_pandas_dataframe)
assert result is None
def fit(self, run_imgs, events=None, confounds=None,
design_matrices=None):
""" Fit the GLM
For each run:
1. create design matrix X
2. do a masker job: fMRI_data -> Y
3. fit regression to (Y, X)
Parameters
----------
run_imgs: Niimg-like object or list of Niimg-like objects,
See http://nilearn.github.io/manipulating_images/input_output.html#inputing-data-file-names-or-image-objects # noqa:E501
Data on which the GLM will be fitted. If this is a list,
the affine is considered the same for all.
events: pandas Dataframe or string or list of pandas DataFrames or
strings
fMRI events used to build design matrices. One events object
expected per run_img. Ignored in case designs is not None.
If string, then a path to a csv file is expected.
confounds: pandas Dataframe, numpy array or string or
list of pandas DataFrames, numpy arays or strings
Each column in a DataFrame corresponds to a confound variable
to be included in the regression model of the respective run_img.
The number of rows must match the number of volumes in the
respective run_img. Ignored in case designs is not None.
If string, then a path to a csv file is expected.
design_matrices: pandas DataFrame or list of pandas DataFrames,
Design matrices that will be used to fit the GLM. If given it
takes precedence over events and confounds.
"""
# Local import to prevent circular imports
from nilearn.input_data import NiftiMasker # noqa
# Check arguments
# Check imgs type
if events is not None:
_check_events_file_uses_tab_separators(events_files=events)
if not isinstance(run_imgs, (list, tuple)):
run_imgs = [run_imgs]
if design_matrices is None:
if events is None:
raise ValueError('events or design matrices must be provided')
if self.t_r is None:
raise ValueError('t_r not given to FirstLevelModel object'
' to compute design from events')
else:
design_matrices = _check_run_tables(run_imgs, design_matrices,
'design_matrices')
# Check that number of events and confound files match number of runs
# Also check that events and confound files can be loaded as DataFrame
if events is not None:
events = _check_run_tables(run_imgs, events, 'events')
if confounds is not None:
confounds = _check_run_tables(run_imgs, confounds, 'confounds')
# Learn the mask
if self.mask_img is False:
# We create a dummy mask to preserve functionality of api
ref_img = check_niimg(run_imgs[0])
self.mask_img = Nifti1Image(np.ones(ref_img.shape[:3]),
ref_img.affine)
if not isinstance(self.mask_img, NiftiMasker):
self.masker_ = NiftiMasker(mask_img=self.mask_img,
smoothing_fwhm=self.smoothing_fwhm,
target_affine=self.target_affine,
standardize=self.standardize,
mask_strategy='epi',
t_r=self.t_r,
memory=self.memory,
verbose=max(0, self.verbose - 2),
target_shape=self.target_shape,
memory_level=self.memory_level
)
self.masker_.fit(run_imgs[0])
else:
if self.mask_img.mask_img_ is None and self.masker_ is None:
self.masker_ = clone(self.mask_img)
for param_name in ['target_affine', 'target_shape',
'smoothing_fwhm', 't_r', 'memory',
'memory_level']:
our_param = getattr(self, param_name)
if our_param is None:
continue
if getattr(self.masker_, param_name) is not None:
warn('Parameter %s of the masker'
' overriden' % param_name)
setattr(self.masker_, param_name, our_param)
self.masker_.fit(run_imgs[0])
else:
self.masker_ = self.mask_img
# For each run fit the model and keep only the regression results.
self.labels_, self.results_, self.design_matrices_ = [], [], []
n_runs = len(run_imgs)
t0 = time.time()
for run_idx, run_img in enumerate(run_imgs):
# Report progress
if self.verbose > 0:
percent = float(run_idx) / n_runs
percent = round(percent * 100, 2)
dt = time.time() - t0
# We use a max to avoid a division by zero
if run_idx == 0:
remaining = 'go take a coffee, a big one'
else:
remaining = (100. - percent) / max(0.01, percent) * dt
remaining = '%i seconds remaining' % remaining
sys.stderr.write(
"Computing run %d out of %d runs (%s)\n"
% (run_idx + 1, n_runs, remaining))
# Build the experimental design for the glm
run_img = check_niimg(run_img, ensure_ndim=4)
if design_matrices is None:
n_scans = get_data(run_img).shape[3]
if confounds is not None:
confounds_matrix = confounds[run_idx].values
if confounds_matrix.shape[0] != n_scans:
raise ValueError('Rows in confounds does not match'
'n_scans in run_img at index %d'
% (run_idx,))
confounds_names = confounds[run_idx].columns.tolist()
else:
confounds_matrix = None
confounds_names = None
start_time = self.slice_time_ref * self.t_r
end_time = (n_scans - 1 + self.slice_time_ref) * self.t_r
frame_times = np.linspace(start_time, end_time, n_scans)
design = make_first_level_design_matrix(frame_times,
events[run_idx],
self.hrf_model,
self.drift_model,
self.high_pass,
self.drift_order,
self.fir_delays,
confounds_matrix,
confounds_names,
self.min_onset
)
else:
design = design_matrices[run_idx]
self.design_matrices_.append(design)
# Mask and prepare data for GLM
if self.verbose > 1:
t_masking = time.time()
sys.stderr.write('Starting masker computation \r')
Y = self.masker_.transform(run_img)
del run_img # Delete unmasked image to save memory
if self.verbose > 1:
t_masking = time.time() - t_masking
sys.stderr.write('Masker took %d seconds \n'
% t_masking)
if self.signal_scaling:
Y, _ = mean_scaling(Y, self.scaling_axis)
if self.memory:
mem_glm = self.memory.cache(run_glm, ignore=['n_jobs'])
else:
mem_glm = run_glm
# compute GLM
if self.verbose > 1:
t_glm = time.time()
sys.stderr.write('Performing GLM computation\r')
labels, results = mem_glm(Y, design.values,
noise_model=self.noise_model,
bins=100, n_jobs=self.n_jobs)
if self.verbose > 1:
t_glm = time.time() - t_glm
sys.stderr.write('GLM took %d seconds \n' % t_glm)
self.labels_.append(labels)
# We save memory if inspecting model details is not necessary
if self.minimize_memory:
for key in results:
results[key] = SimpleRegressionResults(results[key])
self.results_.append(results)
del Y
# Report progress
if self.verbose > 0:
sys.stderr.write("\nComputation of %d runs done in %i seconds\n\n"
% (n_runs, time.time() - t0))
return self
def test_for_pandas_dataframe():
events_pandas_dataframe = pd.DataFrame([['a', 'b', 'c'], [0, 1, 2]])
result = _check_events_file_uses_tab_separators(
events_files=events_pandas_dataframe)
assert result is None
def test_for_invalid_filepath():
filepath = 'junk_file_path.csv'
result = _check_events_file_uses_tab_separators(events_files=filepath)
assert result is None
