prepareSentence.py

from sklearn.neural_network import MLPRegressor
from nltk.stem.lancaster import LancasterStemmer
from nltk.corpus import stopwords
import re
from operator import itemgetter

def prepareSentence(s):
    stemmer = LancasterStemmer()
    ignore_words = set(stopwords.words('english'))
    regpattern = re.compile('[\W_]+" "')
    s = re.sub('[^A-Za-z ]+', '', s)
    words = nltk.word_tokenize(s.lower())
    return [stemmer.stem(w.lower()) for w in words if w not in ignore_words]