def extract_rois_signals(preprocessing_folder ='pipeline_2', prefix= 'resampled_wr'):
dataset = load_dynacomp(preprocessing_folder = preprocessing_folder,prefix = prefix)
for idx, func in enumerate([dataset.func1, dataset.func2]):
for i in range(len(dataset.subjects)):
tic = time.clock()
print func[i]
output_path, _ = os.path.split(func[i])
print dataset.subjects[i]
maps_img = dict_to_list(dataset.rois[i])
#add mask, smoothing, filter and detrending
print 'Nifti'
masker = NiftiMapsMasker(maps_img=maps_img,
mask_img = dataset.mask,
low_pass = .1,
high_pass = .01,
smoothing_fwhm =6.,
t_r = 1.05,
detrend = True,
standardize = False,
resampling_target ='data',
memory_level = 0,
verbose=5)
#extract signal to x
print 'masker'
x = masker.fit_transform(func[i])
print x
np.save(os.path.join(PATH_TO_SAVE_DATA,'output' + str(i+1) +'_rois_filter'),x)
print time.clock() - tic
return x
import os
import numpy as np
from ICode.loader import load_dynacomp
from ICode.estimators.hurst_estimator import Hurst_Estimator
from statsmodels.sandbox.stats.multicomp import multipletests
from scipy.stats import ttest_ind, ttest_1samp
from mne.stats import permutation_t_test
import matplotlib.pyplot as plt
from nilearn.plotting import plot_stat_map
from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import StratifiedShuffleSplit
from sklearn.preprocessing import StandardScaler
from sklearn.datasets.base import Bunch
from matplotlib import rc as changefont
dataset = load_dynacomp(preprocessing_folder='pipeline_1', prefix='wr')
lr = LogisticRegression()
groups = [['av', 'v'], ['av', 'avn'], ['v', 'avn']]
def classify_group(group, fc):
"""Classification for a pair of groups
"""
ind = np.hstack(
(dataset.group_indices[group[0]], dataset.group_indices[group[1]]))
#X = fc[ind, :]
X = StandardScaler().fit_transform([fc[i] for i in ind])
y = np.array([1] * len(dataset.group_indices[group[0]]) +
[-1] * len(dataset.group_indices[group[1]]))
sss = StratifiedShuffleSplit(y, n_iter=50, test_size=.25, random_state=42)
import os
import numpy as np
from ICode.loader import load_dynacomp
from ICode.estimators.hurst_estimator import Hurst_Estimator
from statsmodels.sandbox.stats.multicomp import multipletests
from scipy.stats import ttest_ind, ttest_1samp
from mne.stats import permutation_t_test
import matplotlib.pyplot as plt
from nilearn.plotting import plot_stat_map
from sklearn.linear_model import LogisticRegression
from sklearn.cross_validation import StratifiedShuffleSplit
from sklearn.preprocessing import StandardScaler
from sklearn.datasets.base import Bunch
from matplotlib import rc as changefont
dataset = load_dynacomp(preprocessing_folder='pipeline_1',
prefix='wr')
lr = LogisticRegression()
groups = [ ['av', 'v'], ['av', 'avn'], ['v', 'avn'] ]
def classify_group(group, fc):
"""Classification for a pair of groups
"""
ind = np.hstack((dataset.group_indices[group[0]],
dataset.group_indices[group[1]]))
#X = fc[ind, :]
X = StandardScaler().fit_transform([fc[i] for i in ind])
y = np.array([1]* len(dataset.group_indices[group[0]]) +
[-1]* len(dataset.group_indices[group[1]]))
sss = StratifiedShuffleSplit(y, n_iter=50, test_size=.25, random_state=42)