microsoft/SynapseML

[LightGBM] Regression: how to penalize negative predictions

Open

#918 aperta il 2 set 2020

Vedi su GitHub
 (18 commenti) (0 reazioni) (2 assegnatari)Scala (861 fork)batch import
area/lightgbmenhancementgood first issue

Metriche repository

Star
 (5228 star)
Metriche merge PR
 (Merge medio 23h 16m) (2 PR mergiate in 30 g)

Descrizione

I have a simple regression task (using a LightGBMRegressor) where I want to penalize negative predictions more than positive ones. Is there a way to achieve this with the default regression LightGBM objectives (see https://lightgbm.readthedocs.io/en/latest/Parameters.html)? If not, is it somehow possible to define (many example for default LightGBM model) and pass a custom regression objective?

Thx in advance!

Guida contributor