-
Notifications
You must be signed in to change notification settings - Fork 8
/
create_vocabulary
83 lines (60 loc) · 1.86 KB
/
create_vocabulary
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
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
import nltk
import pickle
import numpy as np
import re
from collections import Counter
from nltk.corpus import stopwords
nltk.download('stopwords')
nltk.download('punkt')
stoplist = stopwords.words('english')
class Vocabulary(object):
def __init__(self):
self.word2idx = {}
self.idx2word = {}
self.idx = 0
def add_word(self, word):
if not word in self.word2idx:
self.word2idx[word] = self.idx
self.idx2word[self.idx] = word
self.idx += 1
def __call__(self, word):
if not word in self.word2idx:
return self.word2idx['<unk>']
return self.word2idx[word]
def __len__(self):
return len(self.word2idx)
def build_vocab(counter,threshold=3):
# Ignore rare words
words = [[cnt,word] for word, cnt in counter.items() if ((cnt >= threshold))]
words.sort(reverse=True)
words = [e[1] for e in words[:50000]]
f = open('vocab_file.txt','w')
# Create a vocabulary and initialize with special tokens
vocab = Vocabulary()
vocab.add_word('<start>')
vocab.add_word('<end>')
vocab.add_word('<pad>')
vocab.add_word('<unk>')
# Add the all the words
for i, word in enumerate(words):
vocab.add_word(word)
return vocab
if __name__ == '__main__':
emb = dict()
f = open('glove.6B.200d.txt','r',encoding='utf-8')
e = f.readline()
while e:
line = e.split(' ')
emb[line[0]] = line[1:]
e = f.readline()
corpus = list(np.load('document.npy', allow_pickle=True))
counter = Counter()
i=0
for sent in corpus:
#sent = sent[1]
tokens=sent.split()
#tokens.extend(q.split())
#tokens = nltk.tokenize.word_tokenize(sent.lower())
counter.update(tokens)
vocab = build_vocab(counter)
np.save('vocab_kp20k.npy', vocab)