I have submit Validation Phase -Task3，but the status is Falied bacause validation y_true contains NaN, which lead to the error：
Traceback (most recent call last):
File "/tmp/codalab/tmpfxnkhp/run/program/score.py", line 47, in <module>
res = classification_metrics(y_true=y_true_cls, y_score=y_score)
File "/tmp/codalab/tmpfxnkhp/run/program/score.py", line 14, in classification_metrics
auroc = roc_auc_score(y_true, y_score)
File "/opt/conda/lib/python3.7/site-packages/sklearn/utils/validation.py", line 63, in inner_f
return f(*args, **kwargs)
File "/opt/conda/lib/python3.7/site-packages/sklearn/metrics/_ranking.py", line 522, in roc_auc_score
y_type = type_of_target(y_true)
File "/opt/conda/lib/python3.7/site-packages/sklearn/utils/multiclass.py", line 303, in type_of_target
_assert_all_finite(y)
File "/opt/conda/lib/python3.7/site-packages/sklearn/utils/validation.py", line 106, in _assert_all_finite
msg_dtype if msg_dtype is not None else X.dtype)
ValueError: Input contains NaN, infinity or a value too large for dtype('float64').
I think the competition organizer should confirm the validation y_true. Thanks!
Posted by: yyydido @ June 4, 2024, 11:37 a.m.Hi,
Thanks for pointing this out, we have fixed this bug.
UWF4DR Ogranizers
Posted by: uwf4dr @ June 4, 2024, 2:32 p.m.