Add Random Forest model

[Andrew Williams]

Basically a wrapper around the scikit-learn implementation.

Notes:

• Random Forests have relatively few hyperparameters, but it should be possible to pass these as keywords to the model.
• The predict method will just return a mean, with variance=None, similar to the neural net.

[Andrew Williams]

To do:

• scikit's RF implementation only accepts/returns target variables of shape (n_samples, n_outputs). So for cases where we're training over a (lat, lon) grid, the model will have to .flatten() and then .reshape().

I think apart from that it's not too difficult to wrap into GCEm