├── README
├── conf
    ├── emotion_dict.txt
    └── emotion_match.txt
└── src
    └── deal_text.py


/README:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/wendy1990/HotTopic_emotion_classification/645e4075d3ba7fe602dc9612cd7039bbbdd6f6c2/README


--------------------------------------------------------------------------------
/conf/emotion_match.txt:
--------------------------------------------------------------------------------
 1 | PA	1	1	快乐
 2 | PE	2	1	安心
 3 | PD	3	2	尊敬
 4 | PH	4	2	赞扬
 5 | PG	5	2	相信
 6 | PB	6	2	喜爱
 7 | PK	7	2	祝愿
 8 | NA	8	3	愤怒
 9 | NB	9	4	悲伤
10 | NJ	10	4	失望
11 | NH	11	4	疚
12 | PF	12	4	思
13 | NI	13	5	慌
14 | NC	14	5	恐惧
15 | NG	15	5	羞
16 | NE	16	6	烦闷
17 | ND	17	6	憎恶
18 | NN	18	6	贬责
19 | NK	19	6	妒忌
20 | NL	20	6	怀疑
21 | PC	21	7	惊奇
22 | 


--------------------------------------------------------------------------------
/src/deal_text.py:
--------------------------------------------------------------------------------
 1 | #!/user/bin/python
 2 | # -*- coding: utf-8 -*-
 3 | 
 4 | 
 5 | import string
 6 | import sys
 7 | import os
 8 | import argparse
 9 | import re
10 | import chardet
11 | 
12 | def process(inp,outp):
13 |     dict_1={}
14 |     input_file= inp
15 |     
16 |     f_in=open(input_file,'r')
17 |     pos_1_lines=f_in.readlines()
18 |     f_in.close()
19 |     for pos_1 in pos_1_lines:
20 |         tmp_pos_1=pos_1.rstrip()
21 |         tmp_pos=re.sub('#[^#]*#','',tmp_pos_1)
22 |         #print tmp_pos
23 |         if tmp_pos in dict_1:
24 |             continue
25 |         else:
26 |             dict_1[tmp_pos]=1
27 |     print len(dict_1)
28 | 
29 |     dict_file=open('../conf/emotion_dict.txt','r')
30 |     dict_lines=dict_file.readlines()
31 |     dict_file.close()
32 |     all_dict={}
33 |     for dict_line in dict_lines:
34 |         dict_line=dict_line.split('\t')[0]
35 |         if dict_line in all_dict:
36 |             continue
37 |         else:
38 |             all_dict[dict_line] =1
39 |     print len(all_dict)
40 |     
41 |     output_file=outp
42 |     f_save=open(output_file,'w')
43 |     for k,v in dict_1.items():
44 |         f_flag=0
45 |         #print chardet.detect(k)
46 |         for k1,v2 in all_dict.items():
47 |             #print chardet.detect(k1)
48 |             if k1 in k :
49 |                 f_flag=1
50 |                 break
51 |             else:
52 |                 continue
53 |         #print ("%s\t%s"%(f_flag,k))
54 |         f_save.write("%s\t%s"%(f_flag,k))
55 |         f_save.write("\n")
56 |         f_save.flush()
57 |         
58 |     
59 | 
60 | if __name__ == "__main__":
61 |     input_file="train_2014.07.14.txt"
62 |     output_file="flag_train_2014.07.14.txt"
63 |     process(input_file,output_file)
64 | 
65 | 


--------------------------------------------------------------------------------