PartialDependenceVariance cannot be saved

[ascillitoe]

Issue

The save method of the PartialDependenceVariance explainer returns the following error:

AttributeError: 'PartialDependenceVariance' object has no attribute 'predictor'

This is because the predictor attribute belongs to the wrapped PartialDependence/TreePartialDependence explainer:

print(explainer.pd_explainer.predictor)
>>> <bound method MLPRegressor.predict of MLPRegressor(max_iter=10000, random_state=0)>

Possible fixes

We could fix this by adding a predictor property to the PartialDependenceVariance class (if we wanted predictor to be publicly accessible), otherwise we could change the behaviour when deleting predictor at save time (this needs updating anyway #930).