def process_answords(answords):
answords = nltk.word_tokenize(answords)
answords_sent = ' '.join(answords).lower()
answords_sent = tools.replace_punct(answords_sent)
answords_sent = tools.replace_number(answords_sent)
answords = answords_sent.split()
return answords
def process_answords(answords):
answords = nltk.word_tokenize(answords)
answords_sent = ' '.join(answords).lower()
answords_sent = tools.replace_punct(answords_sent)
answords_sent = tools.replace_number(answords_sent)
answords = answords_sent.split()
return answords
def process_sentence(sent):
sent = sent.lower()
words = nltk.word_tokenize(sent)
sent = " ".join(words)
sent = tools.replace_punct(sent)
sent = tools.replace_number(sent)
sent = " ".join([w.strip() for w in sent.split() if len(w.strip()) > 0]) # Remove extra spaces
return sent
def process_sentence(sent):
sent = sent.lower()
words = nltk.word_tokenize(sent)
sent = ' '.join(words)
sent = tools.replace_punct(sent)
sent = tools.replace_number(sent)
sent = ' '.join([w.strip() for w in sent.split()
if len(w.strip()) > 0]) #Remove extra spaces
return sent
def process_qwords(qwords):
qwords = ' '.join(qwords)
qwords = nltk.word_tokenize(qwords)
qwords_sent = ' '.join(qwords).lower()
qwords_sent = tools.replace_punct(qwords_sent)
qwords_sent = tools.replace_number(qwords_sent)
qwords = qwords_sent.split()
qwords = ' '.join([tools.START_TOKEN] + qwords + [tools.END_TOKEN])
return qwords
def process_qwords(qwords):
qwords = ' '.join(qwords)
qwords = nltk.word_tokenize(qwords)
qwords_sent = ' '.join(qwords).lower()
qwords_sent = tools.replace_punct(qwords_sent)
qwords_sent = tools.replace_number(qwords_sent)
qwords = qwords_sent.split()
qwords = ' '.join([tools.START_TOKEN] + qwords + [tools.END_TOKEN])
return qwords