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>
42 lines
1.5 KiB
Python
42 lines
1.5 KiB
Python
import json
|
|
import os
|
|
|
|
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 GovRepcrsDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path: str):
|
|
path = get_data_path(path, local_mode=True)
|
|
|
|
dataset_dict = DatasetDict()
|
|
splits = ['train', 'valid', 'test']
|
|
dataset_lists = {x: [] for x in splits}
|
|
for split in splits:
|
|
split_fp = os.path.join(path, 'gov-report', 'split_ids',
|
|
'crs_' + split + '.ids')
|
|
with open(split_fp, 'r') as f:
|
|
for line in f.readlines():
|
|
xpath = os.path.join(path, 'gov-report', 'crs',
|
|
line.strip() + '.json')
|
|
with open(xpath, 'r') as df:
|
|
data = json.load(df)
|
|
content = data['title'] + '\n' + '\n'.join(
|
|
[(x['section_title'] if x['section_title'] else '')
|
|
+ '\n' + '\n'.join(x['paragraphs'])
|
|
for x in data['reports']['subsections']])
|
|
summary = '\n'.join(data['summary'])
|
|
dataset_lists[split].append({
|
|
'content': content,
|
|
'summary': summary,
|
|
})
|
|
dataset_dict[split] = Dataset.from_list(dataset_lists[split])
|
|
return dataset_dict
|