max_words = 1000
tokenize = keras.preprocessing.text.Tokenizer(num_words=max_words, char_level=False)
tokenize.fit_on_texts(train_text) # fit tokenizer to our training text data
x_train = tokenize.texts_to_matrix(train_text)
x_test = tokenize.texts_to_matrix(test_text)

array([[0., 1., 1., ..., 0., 0., 0.],
       [0., 1., 1., ..., 0., 0., 0.],
       [0., 1., 1., ..., 0., 0., 0.],
       ...,
       [0., 1., 1., ..., 0., 0., 0.],
       [0., 1., 1., ..., 0., 0., 0.],
       [0., 1., 1., ..., 0., 0., 0.]])