Open esmit61 opened 2 years ago
Hi. I would like to suggest if there could be a Negative Binomial distribution for the regression tasks with NGBRegressor, i.e.,
ngb = NGBRegressor(Dist=NegativeBinomial).fit(X_train, Y_train)
@esmit61 You might want to use XGBoostLSS, that supports Negative Binomial Distribution Type I
https://github.com/StatMixedML/XGBoostLSS
Hi. I would like to suggest if there could be a Negative Binomial distribution for the regression tasks with NGBRegressor, i.e.,
ngb = NGBRegressor(Dist=NegativeBinomial).fit(X_train, Y_train)