mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
edab1c07ba
* add ceval, gsm8k modelscope surpport * update race, mmlu, arc, cmmlu, commonsenseqa, humaneval and unittest * update bbh, flores, obqa, siqa, storycloze, summedits, winogrande, xsum datasets * format file * format file * update dataset format * support ms_dataset * udpate dataset for modelscope support * merge myl_dev and update test_ms_dataset * udpate dataset for modelscope support * update readme * update eval_api_zhipu_v2 * remove unused code * add get_data_path function * update readme * remove tydiqa japanese subset * add ceval, gsm8k modelscope surpport * update race, mmlu, arc, cmmlu, commonsenseqa, humaneval and unittest * update bbh, flores, obqa, siqa, storycloze, summedits, winogrande, xsum datasets * format file * format file * update dataset format * support ms_dataset * udpate dataset for modelscope support * merge myl_dev and update test_ms_dataset * update readme * udpate dataset for modelscope support * update eval_api_zhipu_v2 * remove unused code * add get_data_path function * remove tydiqa japanese subset * update util * remove .DS_Store * fix md format * move util into package * update docs/get_started.md * restore eval_api_zhipu_v2.py, add environment setting * Update dataset * Update * Update * Update * Update --------- Co-authored-by: Yun lin <yunlin@U-Q9X2K4QV-1904.local> Co-authored-by: Yunnglin <mao.looper@qq.com> Co-authored-by: Yun lin <yunlin@laptop.local> Co-authored-by: Yunnglin <maoyl@smail.nju.edu.cn> Co-authored-by: zhangsongyang <zhangsongyang@pjlab.org.cn>
50 lines
1.4 KiB
Python
50 lines
1.4 KiB
Python
import json
|
|
|
|
from datasets import Dataset
|
|
|
|
from opencompass.registry import LOAD_DATASET, TEXT_POSTPROCESSORS
|
|
from opencompass.utils import get_data_path
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class DRCDDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path: str):
|
|
path = get_data_path(path)
|
|
with open(path, 'r', encoding='utf-8') as f:
|
|
data = json.load(f)
|
|
# 将原始数据转换为所需的格式
|
|
rows = []
|
|
for index, paragraphs in enumerate(data['data']):
|
|
for paragraph in paragraphs['paragraphs']:
|
|
|
|
context = paragraph['context']
|
|
|
|
for question in paragraph['qas']:
|
|
answers = question['answers']
|
|
unique_answers = list(set([a['text'] for a in answers]))
|
|
rows.append({
|
|
'context': context,
|
|
'question': question['question'],
|
|
'answers': unique_answers
|
|
})
|
|
|
|
# 创建 Dataset
|
|
dataset = Dataset.from_dict({
|
|
'context': [row['context'] for row in rows],
|
|
'question': [row['question'] for row in rows],
|
|
'answers': [row['answers'] for row in rows]
|
|
})
|
|
|
|
return dataset
|
|
|
|
|
|
@TEXT_POSTPROCESSORS.register_module('drcd')
|
|
def drcd_postprocess(text: str) -> str:
|
|
if '答案是' in text:
|
|
text = text.split('答案是')[1]
|
|
return text
|