KamalakerDadi

import pandas as pd
import numpy as np
from os.path import join

from sklearn.utils import Bunch
from nilearn import datasets
from nilearn.datasets.utils import _get_dataset_dir, _fetch_files

KamalakerDadi

# Download atlas with this link https://neurovault.org/images/23262/

import numpy as np
import nibabel
from nilearn import image

labels_data = nibabel.load('aparcaseg.nii.gz').get_fdata()
unique_labels = np.unique(labels_data)

# Append each image to concat in 4th dimension

KamalakerDadi

"""Merge two atlases, cortical and sub-cortical atlases dispatched from
Harvard Oxford
"""
import numpy as np
from nilearn import datasets

cortical = datasets.fetch_atlas_harvard_oxford(
    atlas_name='cort-maxprob-thr25-2mm', symmetric_split=True)

sub_cortical = datasets.fetch_atlas_harvard_oxford(

KamalakerDadi

"""Utilities developed based on Nilearn
"""

import collections
import warnings

import numpy as np
import pandas as pd

from sklearn.datasets.base import Bunch

KamalakerDadi

""Processing pipeline example for resting state fMRI datasets
"""
import os
import numpy as np

import pandas as pd

from sklearn.neighbors import KNeighborsClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier

KamalakerDadi

import numpy as np

from nilearn import masking
from nilearn import signal, _utils
from nilearn.image import high_variance_confounds, resample_img, new_img_like
from nilearn._utils.compat import get_affine
from nilearn._utils.niimg_conversions import _check_same_fov


def compute_confounds(imgs, mask_img, n_confounds=5, get_randomized_svd=False,

KamalakerDadi

"""Plot Brain rois per each atlas across datasets
"""

###########################################################################
# Brain ROIs path
import os

rois_path = 'BrainROIs'
dataset_paths = dict()
dataset_names = ['ADNI']

KamalakerDadi

"""Small example with issue #1522 in Nilearn
"""
from nilearn import datasets

# Functional data - 2 subjects
adhd = datasets.fetch_adhd(n_subjects=2)

# Harvard Oxford atlas
atlas_data = datasets.fetch_atlas_harvard_oxford(atlas_name='cort-maxprob-thr25-2mm')
labels_img = atlas_data.maps

KamalakerDadi

from nilearn import datasets
# AAL
aal = datasets.fetch_atlas_aal()
atlas_img = aal.maps

# Structural data
dataset_files = datasets.fetch_oasis_vbm(n_subjects=5)

# Grab each ROI
rois = []

KamalakerDadi

""" Functions to plot connectivity matrices, either as a square or circular.
"""

import numbers
import collections
import matplotlib.pyplot as plt
import numpy as np

from nilearn._utils.compat import _basestring