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?

Currently, Spacy artifact code is not tested: https://codecov.io/gh/bentoml/BentoML/tree/master/bentoml/frameworks

We would want to add an integration test suit to test its functionalities including save, load, and run inference from API server. The setup should be similar to other integration tests that can be found here: https://github.com/bentoml/BentoML/tree/master/tests/integration