CleaningData.py

# Doing a first cleaning of the texts
def clean_text(text):
    text = text.lower()
    text = re.sub(r"i'm", "i am", text)
    text = re.sub(r"he's", "he is", text)
    text = re.sub(r"she's", "she is", text)
    text = re.sub(r"that's", "that is", text)
    text = re.sub(r"what's", "what is", text)
    text = re.sub(r"where's", "where is", text)
    text = re.sub(r"\'ll", " will", text)
    text = re.sub(r"\'ve", " have", text)
    text = re.sub(r"\'re", " are", text)
    text = re.sub(r"\'d", " would", text)
    text = re.sub(r"won't", "will not", text)
    text = re.sub(r"can't", "cannot", text)
    text = re.sub(r"[-()\"#/@;:<>{}+=~|.?,]", "", text)
    return text
 
# Cleaning the questions
clean_questions = []
for question in questions:
    clean_questions.append(clean_text(question))
 
# Cleaning the answers
clean_answers = []
for answer in answers:
    clean_answers.append(clean_text(answer))