How to retrieve trained hyperparameters from sklearn GaussianProcessRegressor model

Question

Calling model.fit(X,y); model.get_params() returns the values that I initialized my kernels with. How do I get the hyperparameters of the trained model?

Answer 1

The model.get_params() as mentioned in documentation will return the parameters passed into the initialization of the GPR.

It optimizes the passed kernel's internal parameters which is available using model.kernel_.

See the documentation and associated examples for more details.

• http://scikit-learn.org/stable/modules/gaussian_process.html#gaussian-process-regression-gpr
• http://scikit-learn.org/stable/auto_examples/gaussian_process/plot_gpr_co2.html#sphx-glr-auto-examples-gaussian-process-plot-gpr-co2-py