This now allows to run save/load tests, which indicate that at least predict_proba is not frozen from setting random_state as it should, in the nsfa>0 case (not in the nsfa=0 case where the same tests pass).'
Theoretically, it could also be an issue with the pickling, not random_state - then I would guess the most likely reason to be a loss of numerical precision occurring when you serialize or deserialize.
Hi @fkiraly thanks for pointing this out. This should be fixed now in the new version (0.0.5). It is due to a bug in setting SFA hyperparameters and python set behaves weirdly.
It seems like the pickling bug is indeed fixed!
This now allows to run save/load tests, which indicate that at least
predict_proba
is not frozen from settingrandom_state
as it should, in thensfa>0
case (not in thensfa=0
case where the same tests pass).'Theoretically, it could also be an issue with the pickling, not
random_state
- then I would guess the most likely reason to be a loss of numerical precision occurring when you serialize or deserialize.Error message below, full error log is in https://github.com/sktime/sktime/actions/runs/6000661723/job/16273328621?pr=5171