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>
62 lines
2.0 KiB
Python
62 lines
2.0 KiB
Python
import json
|
|
|
|
from datasets import Dataset
|
|
|
|
from opencompass.openicl.icl_evaluator import BaseEvaluator
|
|
from opencompass.registry import LOAD_DATASET
|
|
from opencompass.utils import get_data_path
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class QuALITYDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path: str):
|
|
path = get_data_path(path, local_mode=True)
|
|
dataset_list = []
|
|
with open(path, 'r', encoding='utf-8') as f:
|
|
for line in f:
|
|
line = json.loads(line)
|
|
for question in line['questions']:
|
|
dataset_list.append({
|
|
'article':
|
|
line['article'],
|
|
'question':
|
|
question['question'],
|
|
'A':
|
|
question['options'][0],
|
|
'B':
|
|
question['options'][1],
|
|
'C':
|
|
question['options'][2],
|
|
'D':
|
|
question['options'][3],
|
|
'gold_label':
|
|
'ABCD'[question['gold_label'] - 1],
|
|
'difficult':
|
|
question['difficult']
|
|
})
|
|
return Dataset.from_list(dataset_list)
|
|
|
|
|
|
class QuALITYEvaluator(BaseEvaluator):
|
|
|
|
def score(self, predictions, references, test_set):
|
|
assert len(predictions) == len(references)
|
|
easy, hard, all = [], [], []
|
|
for pred, refer, test in zip(predictions, references, test_set):
|
|
if pred == refer:
|
|
answer = True
|
|
else:
|
|
answer = False
|
|
all.append(answer)
|
|
if test['difficult'] == 0:
|
|
easy.append(answer)
|
|
else:
|
|
hard.append(answer)
|
|
return dict(easy_acc=sum(easy) / len(easy) * 100,
|
|
hard_acc=sum(hard) / len(easy) * 100,
|
|
all_acc=sum(all) / len(all) * 100)
|