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>
99 lines
2.6 KiB
Python
99 lines
2.6 KiB
Python
import re
|
|
from typing import List
|
|
|
|
from datasets import load_dataset
|
|
|
|
from opencompass.openicl.icl_evaluator import BaseEvaluator
|
|
from opencompass.registry import LOAD_DATASET
|
|
|
|
from .base import BaseDataset
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class CrowspairsDataset(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(**kwargs):
|
|
|
|
dataset = load_dataset(**kwargs)
|
|
|
|
def preprocess(example):
|
|
example['label'] = 0
|
|
return example
|
|
|
|
return dataset.map(preprocess)
|
|
|
|
|
|
@LOAD_DATASET.register_module()
|
|
class CrowspairsDatasetV2(BaseDataset):
|
|
|
|
@staticmethod
|
|
def load(**kwargs):
|
|
dataset = load_dataset(**kwargs)
|
|
|
|
def preprocess(example):
|
|
example['label'] = 'A'
|
|
return example
|
|
|
|
return dataset.map(preprocess)
|
|
|
|
|
|
def crowspairs_postprocess(text: str) -> str:
|
|
"""Cannot cover all the cases, try to be as accurate as possible."""
|
|
if re.search('Neither', text) or re.search('Both', text):
|
|
return 'invalid'
|
|
|
|
if text != '':
|
|
first_option = text[0]
|
|
if first_option.isupper() and first_option in 'AB':
|
|
return first_option
|
|
|
|
if re.search(' A ', text) or re.search('A.', text):
|
|
return 'A'
|
|
|
|
if re.search(' B ', text) or re.search('B.', text):
|
|
return 'B'
|
|
|
|
return 'invalid'
|
|
|
|
|
|
class CrowspairsEvaluator(BaseEvaluator):
|
|
"""Calculate accuracy and valid accuracy according the prediction for
|
|
crows-pairs dataset."""
|
|
|
|
def __init__(self) -> None:
|
|
super().__init__()
|
|
|
|
def score(self, predictions: List, references: List) -> dict:
|
|
"""Calculate scores and accuracy.
|
|
|
|
Args:
|
|
predictions (List): List of probabilities for each class of each
|
|
sample.
|
|
references (List): List of target labels for each sample.
|
|
|
|
Returns:
|
|
dict: calculated scores.
|
|
"""
|
|
if len(predictions) != len(references):
|
|
return {
|
|
'error': 'predictions and references have different length.'
|
|
}
|
|
all_match = 0
|
|
for i, j in zip(predictions, references):
|
|
all_match += i == j
|
|
|
|
valid_match = 0
|
|
valid_length = 0
|
|
for i, j in zip(predictions, references):
|
|
if i != 'invalid':
|
|
valid_length += 1
|
|
valid_match += i == j
|
|
|
|
accuracy = round(all_match / len(predictions), 4) * 100
|
|
valid_accuracy = round(valid_match / valid_length, 4) * 100
|
|
valid_frac = round(valid_length / len(predictions), 4) * 100
|
|
return dict(accuracy=accuracy,
|
|
valid_accuracy=valid_accuracy,
|
|
valid_frac=valid_frac)
|