2023-07-05 09:01:25 +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 09:01:25 +08:00
|
|
|
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
|
|
class SummScreenDataset(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 09:01:25 +08:00
|
|
|
import json
|
|
|
|
import os
|
|
|
|
dataset_dict = DatasetDict()
|
|
|
|
split = 'dev'
|
|
|
|
dev_list = []
|
|
|
|
fd_folder = os.path.join(path, 'SummScreen_raw', 'fd')
|
|
|
|
files = os.listdir(fd_folder)
|
|
|
|
for file in files:
|
|
|
|
filename = os.path.join(fd_folder, file)
|
|
|
|
with open(filename, 'r') as f:
|
|
|
|
data = json.load(f)
|
|
|
|
summary = ''.join(data['Recap'])
|
|
|
|
content = '\n'.join(data['Transcript'])
|
|
|
|
dev_list.append({
|
|
|
|
'content': content,
|
|
|
|
'summary': summary,
|
|
|
|
})
|
|
|
|
|
|
|
|
tms_folder = os.path.join(path, 'SummScreen_raw', 'tms')
|
|
|
|
files = os.listdir(tms_folder)
|
|
|
|
for file in files:
|
|
|
|
filename = os.path.join(tms_folder, file)
|
|
|
|
with open(filename, 'r') as f:
|
|
|
|
data = json.load(f)
|
|
|
|
summary = ''.join(data['Recap'])
|
|
|
|
content = '\n'.join(data['Transcript'])
|
|
|
|
dev_list.append({
|
|
|
|
'content': content,
|
|
|
|
'summary': summary,
|
|
|
|
})
|
|
|
|
dataset_dict[split] = Dataset.from_list(dev_list)
|
|
|
|
return dataset_dict
|