A python script which cleans the raw corpus

clean.py

import re
from nltk.corpus import stopwords 
from nltk.stem.wordnet import WordNetLemmatizer

def clean(raw_str):
    en_stopwords = set(stopwords.words('english'))
    lemma = WordNetLemmatizer()
    lower_str = raw_str.lower()
    punc_free_str = ' '.join(re.findall(r'\w+', lower_str))
    stop_free_str = ' '.join([i for i in punc_free_str.split() if i not in en_stopwords])
    cleaned_str = ' '.join(lemma.lemmatize(word) for word in stop_free_str.split())
    return cleaned_str