mcmodels.regressors.nonparametric.kernels.Biweight¶
-
class
mcmodels.regressors.nonparametric.kernels.
Biweight
(support=1.0, support_bounds=(0, 100000.0))[source]¶ Biweight kernel.
Identical to Polynomial(shape=2)
Parameters: - support : float, optional, default: 1.0
The support (symmetric) of the kernel such that the kernel is equal to exactly zero where
d(x, y) > support
.- support_bounds : pair of floats >= 0, optional, default: (1e-5, 1e5)
The lower and upper bound on support.
See also
Attributes: - anisotropic
bounds
Returns the log-transformed bounds on the theta.
coefficient
Coefficient to scale the kernel to have
int_D K(u)du == 1
- hyperparameter_support
hyperparameters
Returns a list of all hyperparameter specifications.
n_dims
Returns the number of non-fixed hyperparameters of the kernel.
theta
Returns the (flattened, log-transformed) non-fixed hyperparameters.
Methods
__call__
(self, X[, Y, eval_gradient])Return the kernel k(X, Y) and optionally its gradient. clone_with_theta
(self, theta)Returns a clone of self with given hyperparameters theta. diag
(self, X)Returns the diagonal of the kernel k(X, X). get_params
(self[, deep])Get parameters of this kernel. is_stationary
(self)Returns whether the kernel is stationary. set_params
(self, \*\*params)Set the parameters of this kernel. Methods
__init__
(self[, support, support_bounds])clone_with_theta
(self, theta)Returns a clone of self with given hyperparameters theta. diag
(self, X)Returns the diagonal of the kernel k(X, X). get_params
(self[, deep])Get parameters of this kernel. is_stationary
(self)Returns whether the kernel is stationary. set_params
(self, \*\*params)Set the parameters of this kernel.