cria Y.pkl

parseY.py

import os
import pickle
import numpy as np

basepath = '/caminho/ate/CSVs/' # altere conforme necessario
flist = [fname for fname in os.listdir(basepath) if '.csv' in fname]
grupos = []
classes = []
counter = 0
for fname in flist:
    fbuffer = open(basepath + fname, mode = 'rb')
    for line in fbuffer:
        idx1 = line.index(',')
        classe = line[:idx1]
        if classe[0] == '2':
            continue
        counter += 1
        for e in ['\xef', '\xbb', '\xbf']:
            classe = classe.replace(e, '')
        subline1 = line[idx1 + 1:]
        idx2 = subline1.index(',')
        grupo = subline1[:idx2]
        grupos.append(grupo)
        classes.append(classe)
        print counter

classes = np.array(classes)
pickle.dump(classes, open('Y.pkl', 'wb'))