XGboost4j spark model online prediction using Python Client

Hi members,

Is there a way to export a XGboost4j spark model to a format that can be loaded and executed by Python client for real-time model prediction ?

We use Spark as our training framework. The model execution platform we are trying to integrate with only supports python based packaging and inference of models.

Maybe you can get the prediction by using XGBoost4j-spark?