dividing_into_different_subsets_mbpp/4/QS/even.py

import json
with open("sub_mbpp.json","r",encoding="utf-8") as f:
    data = json.load(f)


# token_counts=[25,25,25,25]
# token_counts_I=token_counts[0]*0.01*974
# token_counts_II=token_counts[1]*0.01*974
# token_counts_III=token_counts[2]*0.01*974
# token_counts_IV=token_counts[3]*0.01*974
#
#
#
# cyclomatic_complexity=[25,25,25,25]
# cyclomatic_complexity_I=cyclomatic_complexity[0]*0.01*974
# cyclomatic_complexity_II=cyclomatic_complexity[1]*0.01*974
# cyclomatic_complexity_III=cyclomatic_complexity[2]*0.01*974
# cyclomatic_complexity_IV=cyclomatic_complexity[3]*0.01*974
token_counts=[25,25,25,25]
token_counts_I=token_counts[0]*0.01*500
token_counts_II=token_counts[1]*0.01*500
token_counts_III=token_counts[2]*0.01*500
token_counts_IV=token_counts[3]*0.01*500



cyclomatic_complexity=[25,25,25,25]
cyclomatic_complexity_I=cyclomatic_complexity[0]*0.01*500
cyclomatic_complexity_II=cyclomatic_complexity[1]*0.01*500
cyclomatic_complexity_III=cyclomatic_complexity[2]*0.01*500
cyclomatic_complexity_IV=cyclomatic_complexity[3]*0.01*500




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
    elif i < token_counts_I + token_counts_II+token_counts_III:
        item['token_diff'] = 2
    else:
        item['token_diff'] = 3

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
    elif i < cyclomatic_complexity_I + cyclomatic_complexity_II+cyclomatic_complexity_III:
        item['CC_diff'] = 2

    else:
        item['CC_diff'] = 3



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)