from sklearn.model_selection import train_test_split
from nltk.corpus import stopwords
from RMDL import text_feature_extraction as txt
from RMDL import RMDL_Text as RMDL


nltk.download('stopwords')
nltk.download('punkt')

articles_text = [txt.text_cleaner(a, deep_clean=True) for a in articles['text'].values]

np.random.seed(7)
X_train, X_test, y_train, y_test = train_test_split(articles_text, labels, test_size=0.2, random_state=4)

batch_size = 64
sparse_categorical = 0
n_epochs = [50, 50, 50]  ## DNN--RNN-CNN
Random_Deep = [3, 3, 3]  ## DNN--RNN-CNN

RMDL.Text_Classification(X_train, y_train, X_test, y_test,
                         batch_size=batch_size,
                         sparse_categorical=sparse_categorical,
                         random_deep=Random_Deep,
                         epochs=n_epochs,
                         GloVe_file='/content/glove.6B.50d.txt',
                         random_optimizor=False,
                         plot=True)