/
chinkikng.py
37 lines (27 loc) · 940 Bytes
/
chinkikng.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
# -*- coding: utf-8 -*-
"""
Created on Thu Nov 19 09:15:11 2015
@author: nilakant
"""
import nltk
from nltk.corpus import state_union
from nltk.tokenize import PunktSentenceTokenizer
#unsupervised tokenizer
train_text = state_union.raw("2006-GWBush.txt")
sample_text = state_union.raw("2006-GWBush.txt")
custom_sent_tokenizer = PunktSentenceTokenizer(train_text)
tokenized = custom_sent_tokenizer.tokenize(sample_text)
def process_content():
try:
for i in tokenized:
words = nltk.word_tokenize(i)
tagged = nltk.pos_tag(words)
chunkGram = r"""Chunk: {<.*>+}
}<VB.?|IN|DT|TO>+{"""
chunkParser = nltk.RegexpParser(chunkGram)
chunked = chunkParser.parse(tagged)
chunked.draw()
#print(tagged)
except Exception as e:
print(str(e))
process_content()