Provide standard error of mean (scipy.stats.sem) for feature importances in `BaseRecursiveSelector`

feature-engine / feature_engine

Feature engineering package with sklearn like functionality

https://feature-engine.trainindata.com/

BSD 3-Clause "New" or "Revised" License

1.79k stars 304 forks source link

Provide standard error of mean (scipy.stats.sem) for feature importances in `BaseRecursiveSelector` #775

Open jolespin opened 1 week ago

jolespin commented 1 week ago

Is your feature request related to a problem? Please describe. I really like that the feature importances include the mean of the cross-validation. Could you also provide SEM from scipy.stats too? This would be good for getting a sense of the spread across different splits.

Describe the solution you'd like See above

Describe alternatives you've considered I'm currently making a custom class and reimplementing the fit method to have this feature.

Additional context NA

solegalli commented 9 hours ago

Yes, we should do that. Thanks for raising the issue!