def sanitize(text): ret = [] for word in text: word = tolower(word) word = goodify(word) word = correct(word) if word not in stop_words: word = stem(word) ret.append(word) else: continue return ret
def sanitize(text): ret = [] for word in text: word = tolower(word) #word = goodify(word) #print word word = corrector.correct(word) ret.append(word) '''if word not in stop_words: word = stem(word) else: continue''' return ret
def stem(word): # word = stemmer.stem(word) word = correct(word) return word