Just gave a talk today at MLConf 2016 in San Francisco on Interpreting Black-Box Models with Applications to Healthcare.  Was great to publicly release the first version of our ML Insights package for python.  The github repository complete with code can be found here together with some nicely worked-out examples.  Additional documentation can be found here.

Thanks to Courtney and Nick for giving me the opportunity to present.  The slides are here: mlc_model_interp_talk

To whet your appetite, here are some visualizations you can easily create in a few lines after “pip install ml_insights”:

screen-shot-2016-11-10-at-5-24-01-pm screen-shot-2016-11-10-at-5-24-21-pm screen-shot-2016-11-10-at-5-18-21-pmscreen-shot-2016-11-10-at-7-24-55-pm