Shap

This release brings a significant interface change. The expected value of the model is no longer included as the last column of the returned shap_values array. Instead it can be accessed as `explainer.expected_value`. This should make things much cleaner going forward, since the shape of the shap_values matrix will now be exactly the same as the input array to the model. This is particularly important for deep learning models with many dimensional input tensors. Note that because of this change `shap.force_plot()` now requires the model's expected (base) value as the first argument.

Adds support for embedding layers and LSTM dropout among other things.

DeepExplainer now supports the TensorFlow components used by LSTM's.

Fully functional implementations of DeepExplainer and GradientExplainer now available.

Fixes an important bug when explaining sklearn models (137).

This marks the final release before potential interface changes to support multi-dimensional inputs in DeepExplainer.