I have n binary classifiers, and I'd like to see what results I get by combining their predictions, just like a VotingClassifier would do, using majority voting or the sum of the individual predict_proba to determine the final prediction.
(Looking on google I already found here some guy's implementation of what I need and the code seems correct, I'm just looking for the "sklearn way" of achieving this)
My problem is that sklearn.ensemble.VotingClassifier is a Soft Voting/Majority Rule classifier for unfitted estimators.
Does sklearn provide something for fitted estimators?
By looking at sklearn.ensemble's documentation it would seem it does not, but isn't weird that such a functionality would be missing from such a complete library? Am I missing something? Can I get that functionality using features from sklearn or do I have to implement it by myself?