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>
67 lines
2.3 KiB
Python
67 lines
2.3 KiB
Python
import json
|
|
|
|
from datasets import Dataset
|
|
|
|
from opencompass.registry import LOAD_DATASET
|
|
from opencompass.utils import get_data_path
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class MultiRCDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path: str):
|
|
path = get_data_path(path, local_mode=True)
|
|
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()
|
|
class MultiRCDatasetV2(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path: str):
|
|
path = get_data_path(path, local_mode=True)
|
|
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)
|