exit(1)
# Mask the map
masked_map_data = np.ma.masked_equal(map_data, 0.0)
# Add it to the visualizer
visualizer.add_image(masked_map_data, colormap=color_map)
""" LOAD DATA TO SHOW CURVES """
print('Loading results data...')
print()
for directory in dirs:
full_path = path.join(output_dir, directory)
pathname = glob(path.join(full_path, '*prediction_parameters' + results_io.extension))
# If there is no coincidence, ignore this directory
if len(pathname) == 0:
print('{} does not exist or contain any result.'.format(full_path))
continue
n, cat, pred_p, corr_p, proc = helper_functions.get_results_from_path(
pathname[0], results_io, subjects, predictors_names, correctors_names, predictors, correctors,
processing_parameters, type_data
)
plot_label = '{} / '.format(n)
plot_label += cat if cat is not None else 'All subjects'
visualizer.add_curve_processor(processor=proc, prediction_parameters=pred_p, correction_parameters=corr_p,
label=plot_label)
""" SHOW VISUALIZER """
visualizer.show()
affine_matrix, output_dir, results_io, type_data = helper_functions.load_data_from_config_file(config_file)
# Lists to store the necessary data to show the curves
names = []
prediction_parameters = []
correction_parameters = []
processors = []
""" LOAD DATA TO SHOW CURVES """
if dirs is None:
print('Loading results data...')
print()
# Find prediction parameters inside results folder
pathname = path.join(output_dir, '**', '*prediction_parameters.nii.gz')
for p in glob(pathname):
n, _, pred_p, corr_p, proc = helper_functions.get_results_from_path(
p, subjects, predictors_names, correctors_names, predictors,
correctors, processing_parameters)
names.append(n)
prediction_parameters.append(pred_p)
correction_parameters.append(corr_p)
processors.append(proc)
else:
print('Loading results data...')
print()
for directory in dirs:
full_path = path.join(output_dir, directory)
pathname = glob(
path.join(full_path, '*prediction_parameters.nii.gz'))
# If there is no coincidence, ignore this directory
if len(pathname) == 0: