kingjr

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

kingjr

import numpy as np
from sklearn.svm import LinearSVR


class SVR_angle(LinearSVR):

    def __init__(self):
        from sklearn.svm import LinearSVR
        from sklearn.preprocessing import StandardScaler
        from sklearn.pipeline import Pipeline

kingjr

import numpy as np
import os.path as op
import matplotlib.pyplot as plt
import mne
from mne.decoding import GeneralizationAcrossTime
from mne.report import Report
from sklearn.pipeline import make_pipeline
from sklearn.preprocessing import StandardScaler
from sklearn.linear_model import LogisticRegression
# from sklearn.metrics import r2_score

kingjr

def scorer_auc(y_true, y_pred):
    from sklearn.metrics import roc_auc_score
    from sklearn.preprocessing import LabelBinarizer
    """Dedicated to 2class probabilistic outputs"""
    le = LabelBinarizer()
    y_true = le.fit_transform(y_true)
    return roc_auc_score(y_true, y_pred)

kingjr

import pickle
import numpy as np
from base import subjects, paths
from mne.stats import permutation_cluster_1samp_test
# load scores
all_scores = list()
for subject in subjects:
    print subject
    with open(paths('scores', subject=subject), 'rb') as f:
        scores = pickle.load(f)

kingjr

import numpy as np
import matplotlib.pyplot as plt
import itertools
import seaborn as sns
from base import paths
from sklearn.linear_model import LassoCV
import pickle

# load data
fname = paths('stats', subject='fsaverage', analysis='all')

kingjr

import numpy as np
import matplotlib.pyplot as plt
import mne
from mne.channels.layout import find_layout
from mne.datasets import sample
from mpl_toolkits.mplot3d import Axes3D

data_path = sample.data_path()
raw_fname = data_path + '/MEG/sample/sample_audvis_filt-0-40_raw.fif'
events_fname = data_path + '/MEG/sample/sample_audvis_filt-0-40_raw-eve.fif'

kingjr

import numpy as np


def simulate_data():
    """Simulate data"""
    from mne import create_info, EpochsArray
    n_trial, n_chan, n_time = 100, 64, 200
    soas = np.array([17, 33, 50, 67, 83])
    event_soa = soas[np.random.randint(0, len(soas), n_trial)]
    event_present = np.random.randint(0, 2, n_trial)

kingjr

# Author: Jean-Remi King
#
# Licence: BSD 3-clause
"""
This is a failed attempt to use a python implementation of Time Shift
PCA (https://github.com/pealco/python-meg-denoise) that aims as
denoising external MEG sources from the signals when we have reference
sensors available (e.g. in the KIT).

See http://audition.ens.fr/adc/NoiseTools/ for more info on TSPCA

kingjr

% Author: Jean-Remi King <jeanremi.king@gmail.com>
%
% Licence : To-be-determined

addpath('/media/DATA/Pro/Toolbox/NoiseTools/')  % http://audition.ens.fr/adc/NoiseTools/
demean = @(x) x - repmat(mean(x, 1), [size(x, 1), 1]);

%% Read data, prepare info
raw = load('raw.mat');
data_empty = transpose(raw.empty(1:160, :)); % empty room: chan x time