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>
106 lines
3.0 KiB
Python
106 lines
3.0 KiB
Python
import json
|
|
import os.path as osp
|
|
import re
|
|
from os import environ
|
|
|
|
from datasets import Dataset
|
|
|
|
from opencompass.openicl.icl_evaluator import BaseEvaluator
|
|
from opencompass.registry import (ICL_EVALUATORS, LOAD_DATASET,
|
|
TEXT_POSTPROCESSORS)
|
|
from opencompass.utils import get_data_path
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class BBHDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path: str, name: str):
|
|
path = get_data_path(path)
|
|
if environ.get('DATASET_SOURCE') == 'ModelScope':
|
|
from modelscope import MsDataset
|
|
dataset = MsDataset.load(path, subset_name=name, split='test')
|
|
else:
|
|
with open(osp.join(path, f'{name}.json'), 'r') as f:
|
|
data = json.load(f)['examples']
|
|
dataset = Dataset.from_list(data)
|
|
return dataset
|
|
|
|
|
|
@TEXT_POSTPROCESSORS.register_module('bbh-mcq')
|
|
def bbh_mcq_postprocess(text: str) -> str:
|
|
ans = text
|
|
ans_line = ans.split('answer is ')
|
|
if len(ans_line) != 1:
|
|
ans = ans_line[1].strip()
|
|
match = re.search(r'\(([A-Z])\)*', ans)
|
|
if match:
|
|
return match.group(1)
|
|
match = re.search(r'([A-Z])', ans)
|
|
if match:
|
|
return match.group(1)
|
|
return ans
|
|
|
|
|
|
@TEXT_POSTPROCESSORS.register_module('bbh-freeform')
|
|
def bbh_freeform_postprocess(text: str) -> str:
|
|
ans = text
|
|
ans_line = ans.split('answer is ')
|
|
if len(ans_line) != 1:
|
|
ans = ans_line[1].strip()
|
|
ans = ans.split('\n')[0]
|
|
if ans.endswith('.'):
|
|
ans = ans[:-1]
|
|
return ans
|
|
|
|
|
|
@ICL_EVALUATORS.register_module()
|
|
class BBHEvaluator(BaseEvaluator):
|
|
|
|
def score(self, predictions, references):
|
|
if len(predictions) != len(references):
|
|
return {
|
|
'error': 'predictions and references have different '
|
|
'length'
|
|
}
|
|
|
|
predictions = [bbh_freeform_postprocess(pred) for pred in predictions]
|
|
|
|
details = []
|
|
cnt = 0
|
|
for pred, ref in zip(predictions, references):
|
|
detail = {'pred': pred, 'answer': ref, 'correct': False}
|
|
if pred == ref:
|
|
cnt += 1
|
|
detail['correct'] = True
|
|
details.append(detail)
|
|
|
|
score = cnt / len(predictions) * 100
|
|
|
|
return {'score': score, 'details': details}
|
|
|
|
|
|
@ICL_EVALUATORS.register_module()
|
|
class BBHEvaluator_mcq(BaseEvaluator):
|
|
|
|
def score(self, predictions, references):
|
|
if len(predictions) != len(references):
|
|
return {
|
|
'error': 'predictions and references have different '
|
|
'length'
|
|
}
|
|
details = []
|
|
cnt = 0
|
|
for pred, ref in zip(predictions, references):
|
|
detail = {'pred': pred, 'answer': ref, 'correct': False}
|
|
if pred == ref:
|
|
cnt += 1
|
|
detail['correct'] = True
|
|
details.append(detail)
|
|
|
|
score = cnt / len(predictions) * 100
|
|
|
|
return {'score': score, 'details': details}
|