2023-07-05 10:22:40 +08:00
|
|
|
from datasets import Dataset, DatasetDict
|
|
|
|
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
[Feature] Support ModelScope datasets (#1289)
* 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>
2024-07-29 13:48:32 +08:00
|
|
|
from opencompass.utils import get_data_path
|
2023-07-05 10:22:40 +08:00
|
|
|
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
|
|
class TriviaQArcDataset(BaseDataset):
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
def load(path: str):
|
[Feature] Support ModelScope datasets (#1289)
* 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>
2024-07-29 13:48:32 +08:00
|
|
|
path = get_data_path(path, local_mode=True)
|
2023-07-05 10:22:40 +08:00
|
|
|
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
|