Category : customization

In my regression problem, when using LGBM’s built-in poisson loss, I got very good model performance. Now I’m trying to reproduce LGBM’s poisson loss in my customized objective function. Here’s the LGBM’s source code of its poission function: https://github.com/microsoft/LightGBM/blob/7076cb8a3ac3a7b32dcf37be5593dddf27bf7f16/src/objective/regression_objective.hpp#L446 max_delta_step=0.7 is configured here: https://github.com/microsoft/LightGBM/blob/7076cb8a3ac3a7b32dcf37be5593dddf27bf7f16/include/LightGBM/config.h#L792 Therefore, when creating customized objective function, my understanding for poission loss ..

Read more

I followed this tutorial https://simpleisbetterthancomplex.com/tutorial/2017/08/01/how-to-setup-amazon-s3-in-a-django-project.html to setup an S3 integration of my Django application with S3. I tested with AWS and it works fine, but for production uses I want to use a different S3 provider: OpenTelekomCloud aka OTC. Using the following client-code I can access both OTC and AWS, depending on the endpoint_url: session ..

Read more