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>
46 lines
1.4 KiB
Python
46 lines
1.4 KiB
Python
from datasets import Dataset, DatasetDict
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
|
from opencompass.utils import get_data_path
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class QASPERDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path: str):
|
|
path = get_data_path(path, local_mode=True)
|
|
import json
|
|
import os
|
|
dataset_dict = DatasetDict()
|
|
split = 'dev'
|
|
dev_list = []
|
|
|
|
dev = os.path.join(path, 'qasper-dev-v0.3.json')
|
|
with open(dev, 'r') as f:
|
|
dev_json = json.load(f)
|
|
|
|
for article_id in dev_json.keys():
|
|
full_article = '\n'.join([
|
|
(x['section_name'] if x['section_name'] else '') + '\n' +
|
|
'\n'.join(x['paragraphs']) + '\n'
|
|
for x in dev_json[article_id]['full_text']
|
|
])
|
|
for qa in dev_json[article_id]['qas']:
|
|
question = qa['question']
|
|
answers = []
|
|
for x in qa['answers']:
|
|
answers.extend(x['answer']['extractive_spans'])
|
|
if answers:
|
|
dev_list.append({
|
|
'answer': answers,
|
|
'question': question,
|
|
'evidence': full_article,
|
|
})
|
|
else:
|
|
continue
|
|
dataset_dict[split] = Dataset.from_list(dev_list)
|
|
return dataset_dict
|