BayesSearchCV callback error
[Progress monitoring and control using callback argument of fit method example in this binder works OK - https://mybinder.org/v2/gh/scikit-optimize/scikit-optimize/a2369ddbc332d16d8ff173b12404b03fea472492?urlpath=lab%2Ftree%2Fnotebooks%2Fauto_examples%2Fsklearn-gridsearchcv-replacement.ipynb]
When I try to run the Progress monitoring and control example on my computer using SKopt 0.9.0 and Sklearn 1.0.1, the callback fails. Implementing a debugger, searchcv has the following Attribute Error
*** AttributeError: 'BayesSearchCV' object has no attribute 'best_score_'
still the same error in '0.9.0' version. Please, fix it!
Also having the same issue - any updates here please?
Same issue here.
def on_step(optim_result):
score = opt.best_score_
print("best score: %s" % score)
if score >= 0.95:
print('Interrupting!')
return True
opt.fit(X, y, callback = on_step)