mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
b3cbef3226
* [feat] add clozeTesst_maxmin dataset * [feat] add py150 datasets * [feat] change __init__.py in opencompass/datasets * [fix] pre-commit check * [fix] rename py150 and masxmin datasets in configs * [feat] add gen.py of py150 and maxmin in configs/datasets
39 lines
1.0 KiB
Python
39 lines
1.0 KiB
Python
import json
|
|
import re
|
|
|
|
from datasets import Dataset
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
def py150_post_process(code):
|
|
code = code.replace('<NUM_LIT>',
|
|
'0').replace('<STR_LIT>',
|
|
'').replace('<CHAR_LIT>', '')
|
|
pattern = re.compile(r'<(STR|NUM|CHAR)_LIT:(.*?)>', re.S)
|
|
lit_s = re.findall(pattern, code)
|
|
for lit in lit_s:
|
|
code = code.replace(f'<{lit[0]}_LIT:{lit[1]}>', lit[1])
|
|
code = json.loads(code)
|
|
code['input'] = code['input'].replace('<s>', '').split('<EOL>')
|
|
for code_line in code['input']:
|
|
code_line = code_line.strip()
|
|
code['input'] = '\n'.join(code['input'])
|
|
code.pop('id', None)
|
|
return code
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class Py150Dataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path):
|
|
lines = open(path, 'r').readlines()
|
|
rows = []
|
|
for line in lines:
|
|
row = py150_post_process(line)
|
|
rows.append(row)
|
|
return Dataset.from_list(rows)
|