NaturalLanguageToolkit/chunking.py at master · haroldjcastillo/NaturalLanguageToolkit · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
import nltk
from nltk.corpus import state_union
from nltk.tokenize import PunktSentenceTokenizer

train_text = state_union.raw("2005-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: {<RB.?>*<VB.?>*<NNP><NN>?}"""
            chunkParser = nltk.RegexpParser(chunkGram)
            chunked = chunkParser.parse(tagged)
            print(chunked)
    except Exception as e:
        print(str(e))


process_content()