Thanks for the idea Jacob, I am going to consider writing that article.

To answer your question. Random Forest in sklearn has feature_importances_ and LightGBM has plot_importance. Both output feature importance.

When working on feature engineering you look at feature importance and you try to engineer more new features similar to the most important one — with similar I don’t mean correlated, but looking at the problem from a perspective of that feature.

When you add a new feature, I also check how the model responds to it — how do lower /higher values of the feature influence the target. Let me know if you would like to learn more about these tools.

Written by

Senior Data Scientist, tweeting

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store