What aggregating method is used by BaggingClassifier and BaggingRegressor in sklearn? Do they use soft voting or hard voting or averaging? The sklearn docs don't seem to clearly specify it.
I figured it out myself. BaggingClassifier uses soft voting (averaging probabilities) if the base estimator has a predict_proba() method and hard voting otherwise. On the other hand, BaggingRegressor uses averaging. Makes sense.