microsoft/SynapseML
Auf GitHub ansehen[LightGBM] Regression: how to penalize negative predictions
Open
#918 geöffnet am 2. Sept. 2020
area/lightgbmenhancementgood first issue
Repository-Metriken
- Stars
- (5.228 Stars)
- PR-Merge-Metriken
- (Durchschn. Merge 23h 16m) (2 gemergte PRs in 30 T)
Beschreibung
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!