kingjr

# ad hoc: Scaled Logistic Regression with probabilistic output

class force_predict(object):
    def __init__(self, clf, mode='predict_proba', axis=0):
        self._mode = mode
        self._axis = axis
        self._clf = clf

    def fit(self, X, y, **kwargs):
        self._clf.fit(X, y, **kwargs)

kingjr

import matplotlib.pyplot as plt
from mne.stats import spatio_temporal_cluster_1samp_test

# Gather all scores
scores = np.array([gat.scores_ for gat in gat_list])
gat_mean = copy.deepcopy(gat_list[0])
gat_mean.scores_ = np.mean(scores, axis=0)

# STATS
chance = 0.5  # chance level; if it's an AUC, it has to be .5

kingjr

"""
=============================================================
Decoding source space data with ROI - sliding window approach
=============================================================

Decoding, a.k.a MVPA or supervised machine learning applied to MEG
data in source space on the left cortical surface. Here f-test feature
selection is employed to confine the classification to the potentially
relevant features. The classifier then is trained to selected features of
epochs in source space. A different classifier is trained i) in each 

kingjr

"""
======================================================
Example for Chris: Decoding source space data with ROI
======================================================

"""

# Author: Jean-Remi King <jeanremi.king@gmail.com
#
# License: BSD-Simplified

kingjr

import numpy as np
import mne
from mne import io
from mne.datasets import sample
data_path = sample.data_path()
raw_fname = data_path + '/MEG/sample/sample_audvis_filt-0-40_raw.fif'
event_fname = data_path + '/MEG/sample/sample_audvis_filt-0-40_raw-eve.fif'
raw = io.Raw(raw_fname, preload=True)
raw.filter(1, 20, method='iir')
events = mne.read_events(event_fname)

kingjr

import numpy as np
import matplotlib.pyplot as plt
from sklearn.metrics import roc_auc_score, roc_curve


def roc(n=1e4, bit=1.):
    X = np.random.randn(n)
    y = np.zeros(n)
    y[:n/2] = 1
    X[y==1] += bit

kingjr

def pairwise(X, Y, func, n_jobs=-1):
    from mne.parallel import parallel_func
    if X.shape != Y.shape:
        raise ValueError('X and Y must have identical shapes')
    parallel, p_pairwise, n_jobs = parallel_func(_pairwise, n_jobs)
    dims = X.shape
    X = np.reshape(X, [dims[0], np.prod(dims[1:])])
    Y = np.reshape(Y, [dims[0], np.prod(dims[1:])])
    n_cols = X.shape[1]
    n_chunks = min(n_cols, n_jobs)

kingjr

def share_clim(axes, clim=None):
    """Share clim across multiple axes
    Parameters
    ----------
    axes : plt.axes
    clim : np.array | list, shape(2,), optional
        Defaults is min and max across axes.clim.
    """
    # Find min max of clims
    if clim is None:

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
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