2023-07-04 21:34:55 +08:00
|
|
|
import json
|
|
|
|
|
|
|
|
from datasets import Dataset
|
|
|
|
|
|
|
|
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 MultiRCDataset(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)
|
2023-07-04 21:34:55 +08:00
|
|
|
with open(path, 'r', errors='ignore') as in_f:
|
|
|
|
rows = []
|
|
|
|
for line in in_f:
|
|
|
|
sample = json.loads(line.strip())
|
|
|
|
passage = sample['passage']
|
|
|
|
text = passage['text']
|
|
|
|
questions = passage['questions']
|
|
|
|
for question_dict in questions:
|
|
|
|
question = question_dict['question']
|
|
|
|
answers = question_dict['answers']
|
|
|
|
for answer_dict in answers:
|
|
|
|
answer = answer_dict['text']
|
|
|
|
label = answer_dict['label']
|
|
|
|
rows.append({
|
|
|
|
'text': text,
|
|
|
|
'question': question,
|
|
|
|
'answer': answer,
|
|
|
|
'label': label
|
|
|
|
})
|
|
|
|
dataset = Dataset.from_dict({
|
|
|
|
'text': [row['text'] for row in rows],
|
|
|
|
'question': [row['question'] for row in rows],
|
|
|
|
'answer': [row['answer'] for row in rows],
|
|
|
|
'label': [row['label'] for row in rows]
|
|
|
|
})
|
|
|
|
return dataset
|
|
|
|
|
|
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
[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
|
|
|
class MultiRCDatasetV2(BaseDataset):
|
2023-07-04 21:34:55 +08:00
|
|
|
|
|
|
|
@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)
|
2023-07-04 21:34:55 +08:00
|
|
|
with open(path, 'r', errors='ignore') as in_f:
|
|
|
|
rows = []
|
|
|
|
for line in in_f:
|
|
|
|
sample = json.loads(line.strip())
|
|
|
|
text = sample['passage']['text']
|
|
|
|
for question_dict in sample['passage']['questions']:
|
|
|
|
question = question_dict['question']
|
|
|
|
answers = question_dict['answers']
|
|
|
|
for answer in answers:
|
|
|
|
rows.append({
|
|
|
|
'text': text,
|
|
|
|
'question': question,
|
|
|
|
'answer': answer['text'],
|
|
|
|
'label': 'BA'[answer['label']]
|
|
|
|
})
|
|
|
|
return Dataset.from_list(rows)
|