physbo.gp.lik.gauss module

class physbo.gp.lik.gauss.gauss(std=1, max_params=1000000.0, min_params=1e-06)[ソース]

ベースクラス: object

Gaussian likelihood function

get_cand_params(t)[ソース]

Getting candidate parameters.

パラメータ

t (numpy.ndarray) -- N dimensional array. The negative energy of each search candidate (value of the objective function to be optimized).

戻り値

log[ standard deviation of t] - log 10.0

戻り値の型

numpy.ndarray

get_cov(num_data, params=None)[ソース]

Get a covariance matrix

パラメータ

  • num_data (int) --

  • params (numpy.ndarray) -- Parameters for optimization. Array of real elements of size (n,), where ‘n’ is the number of independent variables.

戻り値

Diagonal element matrix of exp(2.0*params)

戻り値の型

numpy.ndarray

get_grad(num_data, params=None)[ソース]

Get a gradient matrix

パラメータ

  • num_data (int) --

  • params (numpy.ndarray) -- Parameters for optimization. Array of real elements of size (n,), where ‘n’ is the number of independent variables.

戻り値

Diagonal element matrix of 2.0 * exp(2.0*params)

戻り値の型

numpy.ndarray

get_params_bound()[ソース]

Get boundary array.

戻り値

bound -- A num_params-dimensional array with the tuple (min_params, max_params).

戻り値の型

list

sampling(fmean)[ソース]

Sampling by adding noise

パラメータ

fmean (numpy.ndarray) --

set_params(params)[ソース]

Set parameters.

パラメータ

params (numpy.ndarray) -- Parameters for optimization. Array of real elements of size (n,), where ‘n’ is the number of independent variables.

supp_params(params=None)[ソース]

Set maximum (minimum) values for parameters when the parameter is greater(less) than this value.

パラメータ

params (numpy.ndarray) -- Parameters for optimization. Array of real elements of size (n,), where ‘n’ is the number of independent variables.

trans_params(params=None)[ソース]

Get exp[params].

パラメータ

params (numpy.ndarray) -- Parameters for optimization. Array of real elements of size (n,), where ‘n’ is the number of independent variables.

戻り値

std

戻り値の型

numpy.ndarray