ivan-mitb

# load READY.DAT (56 cols)
from dataload import load_object
x_train, x_test, y_train, y_test = load_object('ready.dat')
x_train.max(axis=0)
del x_test, y_test      # we don't need the test set for now

# under-sample the big classes to make the set manageable
from imblearn.under_sampling import RandomUnderSampler
rus = RandomUnderSampler(ratio={'normal':50000, 'dos':50000}, random_state=4129)
x_train, y_train = rus.fit_sample(x_train, y_train.attack_type)