-
Notifications
You must be signed in to change notification settings - Fork 0
/
PartOfSpeech.py
60 lines (53 loc) · 1.67 KB
/
PartOfSpeech.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
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
import nltk
from nltk.tokenize import PunktSentenceTokenizer
from nltk.corpus import state_union
train_text = state_union.raw("2005-GWBush.txt")
_text = input("Enter a text:")
#sample_text=wikipedia.summary(_text,sentences=1)
custom_SentTok = PunktSentenceTokenizer(train_text)
tokenized = custom_SentTok.tokenize(_text)
def process_content () :
try:
for i in tokenized:
words = nltk.word_tokenize(i)
tagged = nltk.pos_tag(words)
print(tagged)
except Exception as e:
print(str(e))
process_content()
#POS tag list:
#CC coordinating conjunction
#CD cardinal digit
#DT determiner
#EX existential there (like: "there is" ... think of it like "there exists")
#FW foreign word
#IN preposition/subordinating conjunction
#JJ adjective 'big'
#JJR adjective, comparative 'bigger'
#JJS adjective, superlative 'biggest'
#LS list marker 1)
#MD modal could, will
#NN noun, singular 'desk'
#NNS noun plural 'desks'
#NNP proper noun, singular 'Harrison'
#NNPS proper noun, plural 'Americans'
#PDT predeterminer 'all the kids'
#POS possessive ending parent's
#PRP personal pronoun I, he, she
#PRP$ possessive pronoun my, his, hers
#RB adverb very, silently,
#RBR adverb, comparative better
#RBS adverb, superlative best
#RP particle give up
#TO to go 'to' the store.
#UH interjection errrrrrrrm
#VB verb, base form take
#VBD verb, past tense took
#VBG verb, gerund/present participle taking
#VBN verb, past participle taken
#VBP verb, sing. present, non-3d take
#VBZ verb, 3rd person sing. present takes
#WDT wh-determiner which
#WP wh-pronoun who, what
#WP$ possessive wh-pronoun whose
#WRB wh-abverb where, when