Add a missing indicator to encode 'missingness' as a feature

preview_player
Показать описание
When imputing missing values, you can preserve info about which values were missing and use THAT as a feature!

Why? Sometimes there's a relationship between "missingness" and the target/label you are trying to predict.

👉 New tips every TUESDAY and THURSDAY! 👈

=== WANT TO GET BETTER AT MACHINE LEARNING? ===

3) LET'S CONNECT!
Рекомендации по теме
Комментарии
Автор

If you liked this video, watch out for tip 11 (coming out next week) in which I explain two other scikit-learn imputers, KNNImputer and IterativeImputer!

dataschool
Автор

That was a great addition to DS tool kit.Thanks for your contribution .

jaikishank
Автор

Great as always. keep up the good work Thanks Mark!

da_ta
Автор

I encountered a problem when i added this ...add_indicator=True...
Inside a working (good) pipeline. After adding this indicator my entire pipeline failed. Any recommendations what to change in pipeline so the addition (of the above) will not compromise the pipeline?

RA-svbv
join shbcf.ru