GaussianProcessTreegp

class lsst.meas.algorithms.GaussianProcessTreegp(std=1.0, correlation_length=1.0, white_noise=0.0, mean=0.0)

Bases: object

Gaussian Process Treegp class for Gaussian Process interpolation.

The basic GP regression, which uses Cholesky decomposition.

Parameters:

stdfloat, optional

Standard deviation of the Gaussian Process kernel. Default is 1.0.

correlation_lengthfloat, optional

Correlation length of the Gaussian Process kernel. Default is 1.0.

white_noisefloat, optional

White noise level of the Gaussian Process. Default is 0.0.

meanfloat, optional

Mean value of the Gaussian Process. Default is 0.0.

Methods Summary

fit(x_train, y_train)	Fit the Gaussian Process to the given training data.
predict(x_predict)	Predict the target values for the given input features.

Methods Documentation

fit(x_train, y_train)

Fit the Gaussian Process to the given training data.

Parameters:

x_trainnp.array

Input features for the training data.

y_trainnp.array

Target values for the training data.

predict(x_predict)

Predict the target values for the given input features.

Parameters:

x_predictnp.array

Input features for the prediction.

Returns:

y_prednp.array

Predicted target values.