dengemann

# License: simplified BSD (3 clause)
# Author: Denis-Alexander Engemann <denis.engemann@gmail.com>

class MNERunRime(object):

    def __init__(self, config, paths, subjects, run_id=None):
        """Initialize the MNE environment for running scripts

        Parameters
        ----------

dengemann

# Author: denis.engemann@gmail.com
# License: simplified BSD (3 clause)
# Note: code is based on scipy.stats.pearsonr
from scipy import stats

def compute_corr(x, y):
    x = np.asarray(x)
    y = np.asarray(y)
    mx = x.mean(axis=-1)
    my = y.mean(axis=-1)

dengemann

#!/usr/bin/env python
# License: simplified BSD (3 clause)
# Author: Denis A. Engemann <denis.engemann@gmail.com>

"""
Simple wrapper around GNU parallel
----------------------------------
Use this script to dispatch distributed processes and
Take care of n_jobs for child process.

dengemann

"""
========================================================
Extract epochs, average and save evoked response to disk
========================================================

This script shows how to read the epochs from a raw file given
a list of events. The epochs are averaged to produce evoked
data and then saved to disk.

"""

dengemann

import numpy as np
import mne
from mne.decoding import GeneralizationAcrossTime as GAT
from sklearn.metrics import roc_auc_score
from sklearn.preprocessing import StandardScaler
from sklearn.svm import SVC
from sklearn.pipeline import make_pipeline
from sklearn.cross_validation import StratifiedKFold
from meeg_preprocessing.utils import setup_provenance

dengemann

# Authors:  Denis A. Engemann <denis.engemann@gmail.com>
#
# License:  simplified BSD 3 clause

from sklearn.cross_validation import StratifiedKFold


def repeated_folds(y, n_folds, n_repeats, seeds):
    use_seeds = seeds[:n_repeats]
    cv = [list(  # resample

dengemann

from mne.report import Report
from mne.datasets import sample
from mne import read_evokeds
report = Report(verbose=True)

path = sample.data_path()
fname = path + '/MEG/sample/sample_audvis-ave.fif'
evoked = read_evokeds(fname, condition='Left Auditory', baseline=(None, 0),
                      verbose=True)
fig = evoked.plot()

dengemann

# Authors: Denis Engemann <denis.engemann@gmail.com>
#
# License: Simplified BSD


def _apply_inverse_epochs_morph(epochs, inverse_operator, lambda2, method,
                                subjects_dir, morph_params, pick_ori,
                                subject_to):
    """Helper to compute stc and morph them to another subject"""
    stcs = apply_inverse_epochs(

dengemann

# Author: Alexandre Gramfort <alexandre.gramfort@telecom-paristech.fr>
#         Denis Engemann <denis.engemann@gmail.com>
#
# License: BSD (3-clause)

import os.path as op

from nose.tools import assert_true, assert_equal
from numpy.testing import assert_array_almost_equal, assert_array_equal
from nose.tools import assert_raises

dengemann

import numpy as np
from scipy.stats import zscore
import mne

from mne.fixes import nanmean
from mne.utils import logger

def detect_bad_channels(raw, picks=None, thresh=3):
    """Detect bad channels
    """