lemmatization.py

import nltk
nltk.download('wordnet')

from nltk.stem import WordNetLemmatizer
from nltk import word_tokenize

wnl = WordNetLemmatizer()

def lemmatize_text(text):
    tokens = word_tokenize(text)
    lemmatized_tokens = [wnl.lemmatize(token) for token in tokens if not (isNumber(token) and token!='.' and token!=',')]
    lemmatized_sentence = ' '.join(lemmatized_tokens)
    return lemmatized_sentence