RoyalHaskoningDHV / sam

Python package for time series analysis and machine learning
MIT License
25 stars 6 forks source link

Improve feature engineering in SamQuantileMLP #15

Closed sbuergers closed 2 years ago

sbuergers commented 2 years ago

This should reduce the learning curve of using SAM. The current feature engineer in SamQuantile models are too complicated.

BuildRollingFeatures is also not a necessity, since pandas rolling functionality is providing the same. A way to provide a custom feature engineering function would make the required code for a simple model much easier.

abontsema commented 2 years ago

Resolved by #42