surrogate.simple_kriging

surrogate.simple_kriging

Simplified SimpleKriging surrogate model for SpotOptim.

This is a streamlined version adapted from spotpython.surrogate.kriging for use with the SpotOptim optimizer.

Classes

Name	Description
SimpleKriging	A simplified Kriging (Gaussian Process) surrogate model for SpotOptim.

SimpleKriging

surrogate.simple_kriging.SimpleKriging(
    noise=None,
    kernel='gauss',
    n_theta=None,
    min_theta=-3.0,
    max_theta=2.0,
    seed=None,
)

A simplified Kriging (Gaussian Process) surrogate model for SpotOptim.

This class provides a scikit-learn compatible interface with fit() and predict() methods, making it suitable for use as a surrogate in SpotOptim.

Parameters

Name	Type	Description	Default
noise	float	Regularization parameter (nugget effect). If None, uses sqrt(eps). Defaults to None.	`None`
kernel	str	Kernel type. Currently only ‘gauss’ (Gaussian/RBF) is supported. Defaults to ‘gauss’.	`'gauss'`
n_theta	int	Number of theta parameters. If None, uses k (number of dimensions). Defaults to None.	`None`
min_theta	float	Minimum log10(theta) bound for optimization. Defaults to -3.0.	`-3.0`
max_theta	float	Maximum log10(theta) bound for optimization. Defaults to 2.0.	`2.0`
seed	int	Random seed for reproducibility. Defaults to None.	`None`

Attributes

Name	Type	Description
X_	`ndarray`	Training data, shape (n_samples, n_features).
y_	`ndarray`	Training targets, shape (n_samples,).
theta_	`ndarray`	Optimized theta parameters (log10 scale).
mu_	float	Mean of the SimpleKriging predictor.
sigma2_	float	Variance of the SimpleKriging predictor.

Examples

>>> import numpy as np
>>> from spotoptim.surrogate import SimpleKriging
>>> X = np.array([[0.0], [0.5], [1.0]])
>>> y = np.array([0.0, 0.25, 1.0])
>>> model = SimpleKriging()
>>> model.fit(X, y)
>>> predictions = model.predict(np.array([[0.25], [0.75]]))

Methods

Name	Description
fit	Fit the SimpleKriging model to training data.
predict	Predict using the SimpleKriging model.

fit

surrogate.simple_kriging.SimpleKriging.fit(X, y)

Fit the SimpleKriging model to training data.

Parameters

Name	Type	Description	Default
X	`ndarray`	Training input data, shape (n_samples, n_features).	required
y	`ndarray`	Training target values, shape (n_samples,).	required

Returns

Name	Type	Description
SimpleKriging	SimpleKriging	Fitted estimator (self).

predict

surrogate.simple_kriging.SimpleKriging.predict(X, return_std=False)

Predict using the SimpleKriging model.

Parameters

Name	Type	Description	Default
X	`ndarray`	Points to predict at, shape (n_samples, n_features).	required
return_std	bool	If True, return standard deviations as well. Defaults to False.	`False`

Returns

Name	Type	Description
	np.ndarray	ndarray or tuple: If return_std is False, returns predicted values (n_samples,). If return_std is True, returns tuple of (predictions, std_devs) both shape (n_samples,).