def preprocess1(org_qstn):
orgqstn = org_qstn.split()
#row[1] = row[1].dict_trim_by_keys(gl.text_analytics.stopwords(), exclude=True)
k = ""
for word in orgqstn:
if word in ('.', ',', '?', '!', ';', ':'):
orgqstn.remove(word)
word = word.rstrip('.,!?;:')
word = ab.main(word)
word = spell.main(word)
k = k + word + " "
orgqstn = k.split()
for word in orgqstn:
if word.isdigit():
orgqstn.remove(word)
elif word.lower() in qwords:
orgqstn.remove(word)
elif word.lower() in stop_word:
orgqstn.remove(word)
org_qstn = " ".join(orgqstn)
return org_qstn
def preprocess1(org_qstn):
qwords=('what','who','when','where','which','do','how', 'why','does',' ',"what's")
#f=[w for w in word_t if not w in stopword]
stop_word = set(stopwords.words('english'))
orgqstn= org_qstn.split()
k=""
for word in orgqstn:
if word in ('.',',','?','!',';',':'):
orgqstn.remove(word)
word = word.rstrip('.,!?;:')
word=ab.main(word)
word=spell.main(word)
k = k+word+" "
orgqstn= k.split()
for word in orgqstn:
if word.isdigit():
orgqstn.remove(word)
elif word.lower() in qwords:
orgqstn.remove(word)
elif word.lower() in stop_word:
orgqstn.remove(word)
org_qstn=" ".join(orgqstn)
return org_qstn
#!python
# -*- coding: utf-8 -*-
# (C) 2016-2018 Muthiah Annamalai
import imp
import sys
try:
reload # Python 2.7
except NameError:
try:
from importlib import reload # Python 3.4+
except ImportError:
from imp import reload # Python 3.0 - 3.3
imp.reload(sys)
# sys.setdefaultencoding('utf-8')
# This file is part of open-tamil package
import spell
if __name__ == "__main__":
spell.main()
#!python
# -*- coding: utf-8 -*-
#(C) 2016-2018 Muthiah Annamalai
import sys
try:
reload # Python 2.7
except NameError:
try:
from importlib import reload # Python 3.4+
except ImportError:
from imp import reload # Python 3.0 - 3.3
reload(sys)
sys.setdefaultencoding('utf-8')
#This file is part of open-tamil package
import spell
if __name__ == u"__main__":
spell.main()