Final major Beta release- deep learning and LightGBM and lots of minor usability improvements

This will be our final release before v2.

Includes many recent changes- Deep Learning with Keras/TensorFlow, more efficient hyperparameter optimization, Microsoft's LightGBM, more advanced logging for scoring, and quite a few minor usability improvements (like improved logging when input is not as expected).

Pandas support, parallel training of subpredictors

As of the 1.3 release, we now support taking in Pandas DataFrames, in addition to a list of dictionaries.

This is much more memory efficient, allowing us to now train subpredictors in parallel.

There's also better input validation and message logging to the users.