genre_text_cleaning

genre_text_cleaning.py

# function for text cleaning 
def clean_text(text):
    # remove backslash-apostrophe 
    text = re.sub("\'", "", text) 
    # remove everything except alphabets 
    text = re.sub("[^a-zA-Z]"," ",text) 
    # remove whitespaces 
    text = ' '.join(text.split()) 
    # convert text to lowercase 
    text = text.lower() 
    
    return text