import numpy as np
import pandas as pd
from mne.io import RawArray
from mne.channels import read_montage
from mne.epochs import concatenate_epochs
from mne import create_info, find_events, Epochs, concatenate_raws, pick_types
from mne.decoding import CSP

from sklearn.linear_model import LogisticRegression
from glob import glob

from scipy.signal import butter, lfilter, convolve, boxcar
from joblib import Parallel, delayed

def creat_mne_raw_object(fname,read_events=True):
    """Create a mne raw instance from csv file"""
    # Read EEG file
    data = pd.read_csv(fname)
    
    # get chanel names
    ch_names = list(data.columns[1:])
    
    # read EEG standard montage from mne
    montage = read_montage('standard_1005',ch_names)

    ch_type = ['eeg']*len(ch_names)
    data = 1e-6*np.array(data[ch_names]).T
    
    if read_events:
        # events file
        ev_fname = fname.replace('_data','_events')
        # read event file
        events = pd.read_csv(ev_fname)
        events_names = events.columns[1:]
        events_data = np.array(events[events_names]).T
        
        # define channel type, the first is EEG, the last 6 are stimulations
        ch_type.extend(['stim']*6)
        ch_names.extend(events_names)
        # concatenate event file and data
        data = np.concatenate((data,events_data))
        
    # create and populate MNE info structure
    info = create_info(ch_names,sfreq=500.0, ch_types=ch_type, montage=montage)
    info['filename'] = fname
    
    # create raw object 
    raw = RawArray(data,info,verbose=True)
    
    return raw
    
subjects = range(1,13)
for subject in subjects:
    epochs_tot = []
    y = []

    ################ READ DATA ################################################
    fnames =  glob('../input/train/subj%d_series*_data.csv' % (subject))
    
    # read and concatenate all the files
    raw = concatenate_raws([creat_mne_raw_object(fname) for fname in fnames])