-
Notifications
You must be signed in to change notification settings - Fork 5
/
sim-fastText.py
57 lines (37 loc) · 1.07 KB
/
sim-fastText.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
#!/bin/bash
#python2.7
# pip install gensim
# need to install this crawl-300d-2M.vec
#https://fasttext.cc/docs/en/english-vectors.html
import gensim
from gensim.models import Word2Vec
from gensim.models import FastText
embedding_dict = gensim.models.KeyedVectors.load_word2vec_format("crawl-300d-2M.vec", binary=False)
embedding_dict.save_word2vec_format('saved_model_gensim1'+".bin", binary=True)
model = gensim.models.KeyedVectors.load_word2vec_format('saved_model_gensim1'+".bin", binary=True)
file1 = []
file2 = []
with open('object-1.txt','rU') as f:
for line in f:
#print line.rstrip()
file1.append(line.rstrip())
with open('object-2.txt','rU') as f1:
for line1 in f1:
file2.append(line1.rstrip())
resutl=[]
f=open('sim-fast-text.txt', "w")
for i in range(len(file1)):
temp =[]
try :
w = model.similarity(file1[i],file2[i])
except KeyError :
print('out_of_dict')
w = 0
print "1", file1
print "2", file2
temp.append(w)
result= file1[i]+','+file2[i]+','+str(w)
f.write(result)
f.write('\n')
print w
f.close()