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>
80 lines
2.7 KiB
Python
80 lines
2.7 KiB
Python
import json
|
|
|
|
from datasets import Dataset
|
|
|
|
from opencompass.registry import LOAD_DATASET, TEXT_POSTPROCESSORS
|
|
from opencompass.utils import get_data_path
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class ReCoRDDataset(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 i, line in enumerate(in_f):
|
|
sample = json.loads(line.strip())
|
|
passage = sample['passage']
|
|
text = passage['text']
|
|
text = text.replace('@highlight', '')
|
|
|
|
qas = sample['qas']
|
|
for qas_dict in qas:
|
|
query = qas_dict['query']
|
|
query = query.replace('@placeholder', '____')
|
|
answers = qas_dict['answers']
|
|
answers_temp = []
|
|
for answer_dict in answers:
|
|
answer = answer_dict['text']
|
|
answers_temp.append(answer)
|
|
rows.append({
|
|
'text': text,
|
|
'question': query,
|
|
'answers': answers_temp
|
|
})
|
|
|
|
dataset = Dataset.from_dict({
|
|
'text': [row['text'] for row in rows],
|
|
'question': [row['question'] for row in rows],
|
|
'answers': [row['answers'] for row in rows]
|
|
})
|
|
return dataset
|
|
|
|
|
|
class ReCoRDDatasetV2(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 i, line in enumerate(in_f):
|
|
sample = json.loads(line.strip())
|
|
text = sample['passage']['text'].replace('@highlight',
|
|
'').replace(
|
|
'\n\n', '\n')
|
|
for qas_dict in sample['qas']:
|
|
query = qas_dict['query'].replace('@placeholder', '____')
|
|
answers = [
|
|
answer_dict['text']
|
|
for answer_dict in qas_dict['answers']
|
|
]
|
|
rows.append({
|
|
'text': text,
|
|
'question': query,
|
|
'answers': answers
|
|
})
|
|
|
|
dataset = Dataset.from_list(rows)
|
|
return dataset
|
|
|
|
|
|
@TEXT_POSTPROCESSORS.register_module('ReCoRD')
|
|
def ReCoRD_postprocess(text: str) -> str:
|
|
text = text.strip().split('\n')[0].replace('Answer: ', '').strip()
|
|
return text
|