Function for preparing any text for ML

text_prepare.py

import nltk
nltk.download('stopwords')
from nltk.corpus import stopwords

REPLACE_BY_SPACE_RE = re.compile('[/(){}\[\]\|@,;]')
BAD_SYMBOLS_RE = re.compile('[^0-9a-z #+_]')
STOPWORDS = set(stopwords.words('english'))

def text_prepare(text):
    """
        text: a string
        
        return: modified initial string
    """
    text = text.lower()  # To lowercase
    text = re.sub(REPLACE_BY_SPACE_RE, ' ', text)  # replace REPLACE_BY_SPACE_RE symbols by space in text
    text = re.sub(BAD_SYMBOLS_RE, '', text)  # delete symbols which are in BAD_SYMBOLS_RE from text
    querywords = text.split()
    text = ' '.join([word for word in querywords if word.lower() not in STOPWORDS])  # delete stopwords from text
    return text

# text_prepare("Hola {que ta/^^#l} the [done] of buff")

def test_text_prepare():
    examples = ["SQL Server - any equivalent of Excel's CHOOSE function?",
                "How to free c++ memory vector<int> * arr?"]
    answers = ["sql server equivalent excels choose function", 
               "free c++ memory vectorint arr"]
    for ex, ans in zip(examples, answers):
        if text_prepare(ex) != ans:
            return "Wrong answer for the case: '%s'" % ex
    return 'Basic tests are passed.'

print(test_text_prepare())

Thank you for providing the solution