File size: 1,629 Bytes
4daa863
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import json
with open("sub_mbpp.json", "r", encoding="utf-8") as f:
    data = json.load(f)

# token_counts=[33,33,34]
# token_counts_I=token_counts[0]*0.01*974
# token_counts_II=token_counts[1]*0.01*974
# token_counts_III=164-token_counts_I-token_counts_II
#
# cyclomatic_complexity=[33,33,34]
# cyclomatic_complexity_I=cyclomatic_complexity[0]*0.01*974
# cyclomatic_complexity_II=cyclomatic_complexity[1]*0.01*974
# cyclomatic_complexity_III=164-cyclomatic_complexity_II-cyclomatic_complexity_I

token_counts=[33,33,34]
token_counts_I=token_counts[0]*0.01*500
token_counts_II=token_counts[1]*0.01*500
token_counts_III=164-token_counts_I-token_counts_II

cyclomatic_complexity=[33,33,34]
cyclomatic_complexity_I=cyclomatic_complexity[0]*0.01*500
cyclomatic_complexity_II=cyclomatic_complexity[1]*0.01*500
cyclomatic_complexity_III=164-cyclomatic_complexity_II-cyclomatic_complexity_I



data.sort(key=lambda x: x['token'])
for i, item in enumerate(data):
    if i < token_counts_I:
        item['token_diff'] = 0
    elif i < token_counts_I + token_counts_II:
        item['token_diff'] = 1
    else:
        item['token_diff'] = 2

data.sort(key=lambda x: x['cc'])
for i, item in enumerate(data):
    if i < cyclomatic_complexity_I:
        item['CC_diff'] = 0
    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II:
        item['CC_diff'] = 1
    else:
        item['CC_diff'] = 2


data.sort(key=lambda x: x['id'])
# 将更新后的数据写回JSON文件
with open('QS.json', 'w', encoding='utf-8') as file:
    json.dump(data, file, ensure_ascii=False, indent=4)