mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
689ffe5b63
* update commonsenseqa * update drop * update flores_first100 * update gsm8k * update humaneval * update lambda * update obqa * update piqa * update race * update siqa * update story_cloze * update strategyqa * update tydiqa * update winogrande * update doc * update hellaswag * fix obqa * update collections * update .zip name
57 lines
1.9 KiB
Python
57 lines
1.9 KiB
Python
import json
|
|
|
|
from datasets import Dataset
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class OBQADataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path):
|
|
dataset_list = []
|
|
with open(path, 'r') as f:
|
|
for line in f:
|
|
line = json.loads(line)
|
|
item = {
|
|
'A': line['question']['choices'][0]['text'],
|
|
'B': line['question']['choices'][1]['text'],
|
|
'C': line['question']['choices'][2]['text'],
|
|
'D': line['question']['choices'][3]['text'],
|
|
'question_stem': line['question']['stem'],
|
|
'answerKey': line['answerKey'],
|
|
}
|
|
if 'fact1' in line:
|
|
item['fact1'] = line['fact1']
|
|
dataset_list.append(item)
|
|
return Dataset.from_list(dataset_list)
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class OBQADataset_V2(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path):
|
|
dataset_list = []
|
|
with open(path, 'r') as f:
|
|
for line in f:
|
|
line = json.loads(line)
|
|
question = line['question']['stem']
|
|
if not question.endswith('?'):
|
|
question += ' what?'
|
|
item = {
|
|
'A': line['question']['choices'][0]['text'],
|
|
'B': line['question']['choices'][1]['text'],
|
|
'C': line['question']['choices'][2]['text'],
|
|
'D': line['question']['choices'][3]['text'],
|
|
'question_stem': question,
|
|
'answerKey': line['answerKey'],
|
|
}
|
|
if 'fact1' in line:
|
|
item['fact1'] = line['fact1']
|
|
dataset_list.append(item)
|
|
return Dataset.from_list(dataset_list)
|