microsoft/SynapseML

[LightGBM] Regression: how to penalize negative predictions

Open

#918 aberto em 2 de set. de 2020

Ver no GitHub
 (18 comments) (0 reactions) (2 assignees)Scala (861 forks)batch import
area/lightgbmenhancementgood first issue

Métricas do repositório

Stars
 (5.228 stars)
Métricas de merge de PR
 (Mesclagem média 23h 16m) (2 fundiu PRs em 30d)

Description

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!

Guia do colaborador