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

""" check single trial morphing + time series extraction

The Problem 
-----------
establish equivalence across morphing + label extraction paths

mode : single trial, single trial averaged, evoked

morphing : sample,  fsaverage

dengemann

# License: BSD (3-clause)
# Author: Denis A. Engemann <denis-alexander.engemann@inria.fr>

# Based on :

import platform
import psutil
import datetime
from time import time
import os

dengemann

# License: BSD (3-clause)
# Author: Denis A. Engemann <denis-alexander.engemann@inria.fr>

# Based on :
# https://gist.github.com/markus-beuckelmann/8bc25531b11158431a5b09a45abd6276

import platform
import psutil
import datetime
from time import time

dengemann

# License: BSD (3-clause)
# Author: Denis A. Engemann <denis-alexander.engemann@inria.fr>

library(ggplot2)
library(tidymodels)
library(readr)
library(wesanderson)

hotels <-
  read_csv('https://tidymodels.org/start/case-study/hotels.csv') %>%

dengemann

# License: BSD (3-clause)
# Author: Denis A. Engemann <denis-alexander.engemann@inria.fr>

library(tidymodels)
library(readr)
library(microbenchmark)

hotels <- 
  read_csv('https://tidymodels.org/start/case-study/hotels.csv') %>%
  mutate_if(is.character, as.factor) 

dengemann

# Author: Denis A. Engemann <d.engemann@fz-juelich.de>
#
# License: BSD (3-clause)

""" Profile fast_dot versus np.dot

Dependencies
------------
scikit-learn
https://github.com/fabianp/memory_profiler

dengemann

# Author Denis A. Engemann <d.engemann@gmail.com>
#
# License: BSD (3-clause)

import numpy as np
import pandas as pd

def ci_within(df, indexvar, withinvars, measvar, confint=0.95,
                      copy=True):
    """ Compute CI / SEM correction factor

dengemann

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

""" Run complete ICA for MEG and EEG

This tutorial demonstrates how to perform an entire
preprocessing workflow for one subject and for different sensor types.

1) Filtering

dengemann

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

from copy import deepcopy
import numpy as np
import matplotlib.pyplot as plt
import mne

data_path = mne.datasets.somato.data_path()