Title cleaning function

title_cleaning_function.py

import re

# Lowercase, remove punctuation and numbers from kernel titles
def clean_title(title):
    '''
    Function to lowercase, remove punctuation and numbers from kernel titles
    '''
    # lowercase
    title = str(title).lower()
    # replace punctuation into spaces
    title = re.sub(r"[,.;@#?!&$%<>-_*/\()~='+:`]+\ *", " ", title)
    title = re.sub('-', ' ', title)
    title = re.sub("''", ' ', title)
    # replace numbers into spaces
    title = re.sub(r"[0123456789]+\ *", " ", title)
    #remove duplicated spaces
    title = re.sub(' +', ' ', title)
    
    return title.strip()