How to encode and pad texts for machine learning using Keras

text_sequence_preprocessing.py

from tensorflow.keras.preprocessing.sequence import pad_sequences
from tensorflow.keras.preprocessing.text import hashing_trick

def preprocessing(questions, questions_max_length, vocabulary_size):
    """
        Stateless preprocessing the text questions to a one-hot encoding and pads to max length questions.
        
        The one-hot encodings max value is the vocabulary size.
        The padding is attached at the end of each question up to the maximal question length.
        
        @param questions: the text questions as list 
        @param vocalbulary_size: the (globally) amount of known words
        @param questions_max_length: the (globally) maximal length of a question
        @return: the padded and encoded questions
    """
    encoded_questions = [hashing_trick(question, round(vocabulary_size * 1.3), hash_function="md5") for question in questions]
    padded_questions = pad_sequences(encoded_questions, maxlen=questions_max_length, padding="post")
    return padded_questions