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>
61 lines
2.0 KiB
Python
61 lines
2.0 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 TriviaQArcDataset(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 = []
|
|
|
|
web_dev = os.path.join(path, 'qa', 'verified-web-dev.json')
|
|
with open(web_dev, 'r') as f:
|
|
web_dev_json = json.load(f)
|
|
|
|
for x in web_dev_json['Data']:
|
|
cand_answers = x['Answer']['Aliases'] + x['Answer']['HumanAnswers']
|
|
question = x['Question']
|
|
evidence = ''
|
|
if x['SearchResults']:
|
|
x_path = os.path.join(path, 'evidence', 'web',
|
|
x['SearchResults'][0]['Filename'])
|
|
with open(x_path, 'r') as f:
|
|
evidence = f.read(100000)
|
|
dev_list.append({
|
|
'answer': cand_answers,
|
|
'question': question,
|
|
'evidence': evidence,
|
|
})
|
|
|
|
wiki_dev = os.path.join(path, 'qa', 'verified-wikipedia-dev.json')
|
|
with open(wiki_dev, 'r') as f:
|
|
wiki_dev_json = json.load(f)
|
|
|
|
for x in wiki_dev_json['Data']:
|
|
cand_answers = x['Answer']['Aliases']
|
|
question = x['Question']
|
|
evidence = ''
|
|
if x['EntityPages']:
|
|
x_path = os.path.join(path, 'evidence', 'wikipedia',
|
|
x['EntityPages'][0]['Filename'])
|
|
with open(x_path, 'r') as f:
|
|
evidence = f.read(100000)
|
|
dev_list.append({
|
|
'answer': cand_answers,
|
|
'question': question,
|
|
'evidence': evidence,
|
|
})
|
|
|
|
dataset_dict[split] = Dataset.from_list(dev_list)
|
|
return dataset_dict
|