some PyOD models will fail while being used with SUOD

[yzhao062]

The reason is sklearn.clone will lead to issues if the hyperparameters are not well used.

Problem can be reproduced by cloning models:

This includes:

• COD

[yerbby]

I don't know if this is related, or there is another cause, but LOF also fails when used with SUOD, raising the following error:

ZeroDivisionError: float division by zero

Code to reproduce the error: the exact template provided in https://pyod.readthedocs.io/en/latest/fast_train.html

Dataset: https://raw.githubusercontent.com/numenta/NAB/master/data/artificialNoAnomaly/art_daily_small_noise.csv

However, LOF works correctly with this dataset when used normally, without SUOD.