2023-07-04 21:34:55 +08:00
|
|
|
import csv
|
|
|
|
|
|
|
|
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
|
2023-07-04 21:34:55 +08:00
|
|
|
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
|
|
class JigsawMultilingualDataset(BaseDataset):
|
|
|
|
|
|
|
|
@staticmethod
|
|
|
|
def load(path, label, lang):
|
[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)
|
|
|
|
label = get_data_path(label, local_mode=True)
|
|
|
|
|
2023-07-04 21:34:55 +08:00
|
|
|
assert lang in ['es', 'fr', 'it', 'pt', 'ru', 'tr']
|
|
|
|
dataset = DatasetDict()
|
|
|
|
|
|
|
|
data_list = list()
|
|
|
|
idx = 0
|
|
|
|
with open(path) as file, open(label) as label:
|
|
|
|
text_reader = csv.reader(file)
|
|
|
|
label_reader = csv.reader(label)
|
|
|
|
for text, target in zip(text_reader, label_reader):
|
|
|
|
if text[2] == lang:
|
|
|
|
assert text[0] == target[0]
|
|
|
|
data_list.append({
|
|
|
|
'idx': idx,
|
|
|
|
'text': text[1],
|
|
|
|
'label': int(target[1]),
|
|
|
|
'choices': ['no', 'yes']
|
|
|
|
})
|
|
|
|
idx += 1
|
|
|
|
|
|
|
|
dataset['test'] = Dataset.from_list(data_list)
|
|
|
|
return dataset
|