physbo.gp.inf.exact module

physbo.gp.inf.exact.eval_marlik(gp, X, t, params=None)[ソース]

Evaluating marginal likelihood.

パラメータ:
  • gp (physbo.gp.core.model) --
  • X (numpy.ndarray) -- N x d dimensional matrix. Each row of X denotes the d-dimensional feature vector of search candidate.
  • t (numpy.ndarray) -- N dimensional array. The negative energy of each search candidate (value of the objective function to be optimized).
  • params (numpy.ndarray) -- Parameters.
戻り値:

marlik -- Marginal likelihood.
戻り値の型:

float
physbo.gp.inf.exact.get_grad_marlik(gp, X, t, params=None)[ソース]

Evaluating gradiant of marginal likelihood.

パラメータ:
  • gp (physbo.gp.core.model) --
  • X (numpy.ndarray) -- N x d dimensional matrix. Each row of X denotes the d-dimensional feature vector of search candidate.
  • t (numpy.ndarray) -- N dimensional array. The negative energy of each search candidate (value of the objective function to be optimized).
  • params (numpy.ndarray) -- Parameters.
戻り値:

grad_marlik -- Gradiant of marginal likelihood.
戻り値の型:

numpy.ndarray
physbo.gp.inf.exact.get_post_fcov(gp, X, Z, params=None, diag=True)[ソース]

Calculating the covariance of posterior

パラメータ:
  • gp (physbo.gp.core.model) --
  • X (numpy.ndarray) -- N x d dimensional matrix. Each row of X denotes the d-dimensional feature vector of search candidate.
  • Z (numpy.ndarray) -- N x d dimensional matrix. Each row of Z denotes the d-dimensional feature vector of tests.
  • params (numpy.ndarray) -- Parameters.
  • diag (bool) -- If X is the diagonalization matrix, true.
戻り値:
戻り値の型:

numpy.ndarray
physbo.gp.inf.exact.get_post_fmean(gp, X, Z, params=None)[ソース]

Calculating the mean of posterior

パラメータ:
  • gp (physbo.gp.core.model) --
  • X (numpy.ndarray) -- N x d dimensional matrix. Each row of X denotes the d-dimensional feature vector of search candidate.
  • Z (numpy.ndarray) -- N x d dimensional matrix. Each row of Z denotes the d-dimensional feature vector of tests.
  • params (numpy.ndarray) -- Parameters.
戻り値:
戻り値の型:

numpy.ndarray
physbo.gp.inf.exact.prepare(gp, X, t, params=None)[ソース]
パラメータ:
  • gp (physbo.gp.core.model) --
  • X (numpy.ndarray) -- N x d dimensional matrix. Each row of X denotes the d-dimensional feature vector of search candidate.
  • t (numpy.ndarray) -- N dimensional array. The negative energy of each search candidate (value of the objective function to be optimized).
  • params (numpy.ndarray) -- Parameters.
戻り値:

stats
戻り値の型:

tupple