Using MLJ with Gaussian Process Regression

I have a data set on which I would like to perform binary classification, and I would like to see how well Gaussian Process Regression (GPR) does with it. Since I’ve already been experimenting with MLJ, I figured I might as well learn to run GPR inside of it, but I’m having a bit of trouble getting started. The key issues that I need to understand are:

  1. How should I format my data for MLJ + GPR? Each point in my data set is composed of O(1000) complex numbers. Can I work directly with the complex data type, or should I split it into real/imaginary parts? If I use a DataFrame, should each column be one of the O(1000) measurements, or can the type be an Array?
  2. How do I get started with GPR in MLJ? I know that this can be accessed via scikit-learn (and I have that binding installed), but it would be good to have an example.

Any suggestions are appreciated.