divide_oversample.py

#oversampling the minority - this will be resource intensive

from sklearn.model_selection import train_test_split

#divide the classes to training and test sets
x_train, x_test, y_train, y_test \
     = train_test_split(df_raw.drop(['Bot'], axis=1), df_raw['Bot'], test_size = .2)

#oversample the minority
from imblearn.over_sampling import SMOTENC
smote_nc = SMOTENC(categorical_features=np.arange(3,14),  sampling_strategy='minority')
x_train_up, y_train_up = smote_nc.fit_sample(x_train, y_train)

columns_set = x_train.columns
x_train = pd.DataFrame(x_train_up)
x_train.columns = columns_set
y_train = y_train_up