1
2
3
4
5
6
7
8
9 """
10 Names Corpus, Version 1.3 (1994-03-29)
11 Copyright (C) 1991 Mark Kantrowitz
12 Additions by Bill Ross
13
14 This corpus contains 5001 female names and 2943 male names, sorted
15 alphabetically, one per line.
16 (Used in NLTK with permission. See the README file for details.)
17 """
18
19 from nltk_lite.corpora import get_basedir
20 import os
21
22 items = ['female', 'male']
23
24 item_name = {
25 'female': 'Female names',
26 'male': 'Male names'
27 }
28
29 -def raw(files = ['female', 'male']):
36
38 from nltk_lite.corpora import names
39 from random import shuffle
40 from pprint import pprint
41
42 print "20 female names"
43 female = list(names.raw('female'))
44 shuffle(female)
45 pprint(female[:20])
46
47 print "20 male names"
48 male = list(names.raw('male'))
49 shuffle(male)
50 pprint(male[:20])
51
52 if __name__ == '__main__':
53 demo()
54