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>
50 lines
1.3 KiB
Python
50 lines
1.3 KiB
Python
import json
|
|
import os.path as osp
|
|
|
|
from datasets import Dataset
|
|
|
|
from opencompass.openicl.icl_evaluator import BaseEvaluator
|
|
from opencompass.registry import ICL_EVALUATORS, LOAD_DATASET
|
|
from opencompass.utils import get_data_path
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class OpenFinDataDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path: str, name: str):
|
|
path = get_data_path(path, local_mode=True)
|
|
with open(osp.join(path, f'{name}.json'), 'r') as f:
|
|
data = json.load(f)
|
|
return Dataset.from_list(data)
|
|
|
|
|
|
@ICL_EVALUATORS.register_module()
|
|
class OpenFinDataKWEvaluator(BaseEvaluator):
|
|
|
|
def __init__(self, ):
|
|
super().__init__()
|
|
|
|
def score(self, predictions, references):
|
|
assert len(predictions) == len(references)
|
|
|
|
scores = []
|
|
results = dict()
|
|
|
|
for i in range(len(references)):
|
|
all_hit = True
|
|
judgement = references[i].split('、')
|
|
for item in judgement:
|
|
if item not in predictions[i]:
|
|
all_hit = False
|
|
break
|
|
if all_hit:
|
|
scores.append(True)
|
|
else:
|
|
scores.append(False)
|
|
|
|
results['accuracy'] = round(sum(scores) / len(scores), 4) * 100
|
|
return results
|