output_file += '_msdl' np.savez(output_file, covariance=gsc.covariances_[..., i], precision=gsc.precisions_[..., i], sparsity=sparsity, roi_names=roi_names, roi_coords=roi_coords) return gsc, roi_names, roi_coords ############################################################################## preprocessing_folder = 'pipeline_1' prefix = 'swr' #preprocessing_folder = 'pipeline_2' #prefix = 'resampled_wr' msdl = False dataset = load_dynacomp(preprocessing_folder=preprocessing_folder, prefix=prefix) for session_i in ['func1', 'func2']: for i in range(len(dataset.subjects)): print dataset.subjects[i], session_i compute_pearson_connectivity(dataset.subjects[i], dataset.group[i], session=session_i, preprocessing_folder=preprocessing_folder, plot=True, save=True, save_file=True, msdl=msdl) compute_graph_lasso_covariance(dataset.subjects[i],
# -*- coding: utf-8 -*- """ Extract from each specific ROI Created on Fri Mar 27 16:39:01 2015 @author: [email protected] """ import os, time import numpy as np from loader import load_dynacomp, dict_to_list from nilearn.input_data import NiftiMapsMasker dataset = load_dynacomp(preprocessing_folder='pipeline_2', prefix='resampled_wr') # func1, func2 for idx, func in enumerate([dataset.func1, dataset.func2]): # all the subjects for i in range(len(dataset.subjects)): tic = time.clock() output_path, _ = os.path.split(func[i]) print dataset.subjects[i] maps_img = dict_to_list(dataset.rois[i]) # add mask, smoothing, filtering and detrending masker = NiftiMapsMasker(maps_img=maps_img, mask_img=dataset.mask, low_pass=.1, high_pass=.01, smoothing_fwhm=6.,
return best_w, best_acc ############################################################################## # Load data preprocs = [] preprocs.append({'preprocessing_folder': 'pipeline_2', 'prefix': 'resampled_wr'}) preprocs.append({'preprocessing_folder': 'pipeline_1', 'prefix': 'swr'}) for pr in preprocs: preprocessing_folder = pr['preprocessing_folder'] prefix = pr['prefix'] dataset = load_dynacomp(preprocessing_folder, prefix) for session in ['avg', 'func1', 'func2']: for msdl in [False, True]: print preprocessing_folder, prefix, session, msdl # Roi names and coords if msdl: roi_names, roi_coords = load_msdl_names_and_coords() msdl_str='msdl' else: roi_names, roi_coords = load_roi_names_and_coords(dataset.subjects[0]) msdl_str = '' # Take only the lower diagonal values ind = np.tril_indices(len(roi_names), k=-1)
# -*- coding: utf-8 -*- """ Created on Fri Mar 27 17:01:31 2015 @author: [email protected] """ from loader import load_dynacomp from nilearn.input_data import NiftiMasker, MultiNiftiMasker from nilearn.plotting import plot_roi CACHE_DIR = '.' dataset = load_dynacomp() def compute_all_subjects_mask(): """ Computes the mask of all the subjects and the sesssions """ masker = MultiNiftiMasker(mask_strategy='epi', memory=CACHE_DIR, memory_level=2, n_jobs=10, verbose=5) imgs = dataset.func1 + dataset.func2 masker.fit(imgs) masker.mask_img_.to_filename('all_subjects.nii.gz') plot_roi(masker.mask_img_)
import os import numpy as np import nibabel as nib from loader import load_dynacomp, load_msdl_names_and_coords,\ load_dynacomp_fc, load_roi_names_and_coords,\ set_figure_base_dir from nilearn.image import concat_imgs, mean_img from nilearn.plotting import plot_roi, plot_stat_map, plot_img from sklearn.decomposition import PCA from sklearn.manifold import MDS, Isomap import matplotlib.pyplot as plt msdl = False dataset = load_dynacomp() roi_names, roi_coords = load_roi_names_and_coords(dataset.subjects[0]) if msdl: roi_names, roi_coords = load_msdl_names_and_coords() ind = np.tril_indices(len(roi_names), k=-1) x = [] for subject_id in dataset.subjects: c = load_dynacomp_fc(subject_id=subject_id, session='func2', metric='gl', msdl=msdl, preprocessing_folder='pipeline_2') x.append(c[ind]) x = np.array(x)
# -*- coding: utf-8 -*- """ Extract from each specific ROI Created on Fri Mar 27 16:39:01 2015 @author: [email protected] """ import os, time import numpy as np from loader import load_dynacomp, dict_to_list from nilearn.input_data import NiftiMapsMasker dataset = load_dynacomp(preprocessing_folder='pipeline_2', prefix='resampled_wr') # func1, func2 for idx, func in enumerate([dataset.func1, dataset.func2]): # all the subjects for i in range(len(dataset.subjects)): tic = time.clock() output_path, _ = os.path.split(func[i]) print dataset.subjects[i] maps_img = dict_to_list(dataset.rois[i]) # add mask, smoothing, filtering and detrending masker = NiftiMapsMasker(maps_img=maps_img, mask_img=dataset.mask, low_pass=.1, high_pass=.01, smoothing_fwhm=6., t_r=1.05,
""" Created on Tue May 12 09:42:23 2015 @author: [email protected] """ import loader import numpy as np from nilearn.datasets import fetch_nyu_rest from nilearn.input_data import NiftiMapsMasker from sklearn.covariance import GraphLassoCV ############################################################################## # Dynacomp rs-fMRI ############################################################################## dyn_dataset = loader.load_dynacomp() roi_imgs = loader.dict_to_list(loader.load_dynacomp_rois()[0]) roi_names, roi_coords = loader.load_roi_names_and_coords( dyn_dataset.subjects[0]) ind = np.tril_indices(len(roi_names), k=-1) dyn_fc = [] for subject in dyn_dataset.subjects: dyn_fc.append( loader.load_dynacomp_fc(subject_id=subject, session='func1', metric='pc', msdl=False, preprocessing_folder='pipeline_1')[ind]) dyn_fc = np.asarray(dyn_fc)
Created on Tue May 12 09:42:23 2015 @author: [email protected] """ import loader import numpy as np from nilearn.datasets import fetch_nyu_rest from nilearn.input_data import NiftiMapsMasker from sklearn.covariance import GraphLassoCV ############################################################################## # Dynacomp rs-fMRI ############################################################################## dyn_dataset = loader.load_dynacomp() roi_imgs = loader.dict_to_list(loader.load_dynacomp_rois()[0]) roi_names, roi_coords = loader.load_roi_names_and_coords(dyn_dataset.subjects[0]) ind = np.tril_indices(len(roi_names), k=-1) dyn_fc = [] for subject in dyn_dataset.subjects: dyn_fc.append(loader.load_dynacomp_fc(subject_id=subject, session='func1', metric='pc', msdl=False, preprocessing_folder='pipeline_1')[ind]) dyn_fc = np.asarray(dyn_fc) ############################################################################## # NYU rs-fMRI ##############################################################################