[ENH] Add `class_weight` parameter to classifiers that use sklearn based estimators with testing

[hadifawaz1999]

Describe the feature or idea you want to propose

following #1776

Describe your proposed solution

other classifiers need this update as well, like feature based for example
Also should add testing for this setup

Describe alternatives you've considered, if relevant

we should make sure we cover all of them

Additional context

No response

[TonyBagnall]

hi @hadifawaz1999 is this issue resolved, or, if not, a list of classifiers effected would be useful.

[hadifawaz1999]

hi @hadifawaz1999 is this issue resolved, or, if not, a list of classifiers effected would be useful.

no idea if it was resolved would need to check some classifiers still missing it

[MatthewMiddlehurst]

see #2434, some of these are not correct.

IMO wouldn't a general kwargs for the estimator be better for this?

[baraline]

Think it's good to expose it to show explicitly that it can be used by the classifier. One thing we could do is add a check which takes into account the supported values of the classifier to give users an exception that gives a list of expected values?