mirror of
https://github.com/open-compass/opencompass.git
synced 2025-05-30 16:03:24 +08:00
44 lines
1010 B
Python
44 lines
1010 B
Python
import json
|
||
|
||
from datasets import Dataset, load_dataset
|
||
|
||
from opencompass.registry import LOAD_DATASET
|
||
|
||
from .base import BaseDataset
|
||
|
||
|
||
@LOAD_DATASET.register_module()
|
||
class CslDataset(BaseDataset):
|
||
|
||
@staticmethod
|
||
def load(**kwargs):
|
||
|
||
dataset = load_dataset(**kwargs)
|
||
|
||
def preprocess(example):
|
||
keywords = '，'.join(example['keyword'])
|
||
example['keywords'] = keywords
|
||
|
||
return example
|
||
|
||
dataset = dataset.map(preprocess)
|
||
return dataset
|
||
|
||
|
||
@LOAD_DATASET.register_module()
|
||
class CslDataset_V2(BaseDataset):
|
||
|
||
@staticmethod
|
||
def load(path):
|
||
data = []
|
||
with open(path, 'r') as f:
|
||
for line in f:
|
||
line = json.loads(line)
|
||
item = {
|
||
'abst': line['abst'],
|
||
'keywords': '，'.join(line['keyword']),
|
||
'label': 'AB'[int(line['label'])],
|
||
}
|
||
data.append(item)
|
||
return Dataset.from_list(data)
|