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>
69 lines
2.4 KiB
Python
69 lines
2.4 KiB
Python
import json
|
|
|
|
from datasets import Dataset
|
|
|
|
from opencompass.openicl.icl_evaluator import BaseEvaluator
|
|
from opencompass.utils import get_data_path
|
|
from opencompass.utils.text_postprocessors import general_postprocess
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
class SQuAD20Dataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(path: str):
|
|
path = get_data_path(path, local_mode=True)
|
|
with open(path, 'r') as f:
|
|
data = json.load(f)
|
|
data = data['data']
|
|
dataset = []
|
|
for article in data:
|
|
for paragraph in article['paragraphs']:
|
|
for qa in paragraph['qas']:
|
|
is_impossible = qa['is_impossible']
|
|
if not is_impossible:
|
|
answers = list(
|
|
set([answer['text'] for answer in qa['answers']]))
|
|
else:
|
|
answers = list(
|
|
set([
|
|
answer['text']
|
|
for answer in qa['plausible_answers']
|
|
]))
|
|
answers += ['impossible to answer']
|
|
item = {
|
|
'context': paragraph['context'],
|
|
'question': qa['question'],
|
|
'answers': answers,
|
|
}
|
|
dataset.append(item)
|
|
dataset = Dataset.from_list(dataset)
|
|
return dataset
|
|
|
|
|
|
class SQuAD20Evaluator(BaseEvaluator):
|
|
|
|
def score(self, predictions, references):
|
|
if len(predictions) != len(references):
|
|
return {
|
|
'error': 'predictions and references have different '
|
|
'length'
|
|
}
|
|
processed_predictions = []
|
|
for prediction in predictions:
|
|
prediction = prediction.split('\n')[0].lower()
|
|
if 'answer is' in prediction:
|
|
prediction = prediction.split('answer is')[-1]
|
|
prediction = general_postprocess(prediction)
|
|
processed_predictions.append(prediction)
|
|
processed_answers = [[general_postprocess(j).lower() for j in i]
|
|
for i in references]
|
|
|
|
cnt = 0
|
|
for pred, cand_ans in zip(processed_predictions, processed_answers):
|
|
cnt += int(any([cand == pred for cand in cand_ans]))
|
|
score = cnt / len(predictions) * 100
|
|
|
|
return {'score': score}
|