Class emulator_interpm_krige_table (o2scl)¶
-
template<class vec2_t = boost::numeric::ublas::vector<double>, class vec_t = boost::numeric::ublas::vector<double>, class mat_t = boost::numeric::ublas::matrix<double>, class mat_inv_t = o2scl_linalg::matrix_invert_det_cholesky<boost::numeric::ublas::matrix<double>>>
class emulator_interpm_krige_table : public o2scl::emulator_unc<boost::numeric::ublas::vector<double>, boost::numeric::ublas::vector<double>, boost::numeric::ublas::vector<double>>¶ Emulate data stored in a table object with interpm_krige.
This class is experimental.
Note
Currently, this emulator only works if the data object from the MCMC class is a vector type so that it knows how to find the “log weight” output
Public Functions
-
inline emulator_interpm_krige_table()¶
Create an emulator.
-
inline void set(size_t np, size_t n_out, size_t ix_log_wgt, table<> &t, std::vector<std::string> list)¶
Set the emulator.
Set the emulator using a table containing
np
parameters andn_out
output quantities. The variableix_log_wgt
should be the index of the log_weight among all of the output variables, from 0 ton_out-1
. The list,list
, should include the column names of the parameters and then the output quantities (including the log weight column), in order.
Public Members
-
interpm_krige_optim<std::vector<mcovar_funct_rbf_noise>, ubvector, mat_x_t, mat_x_row_t, mat_y_t, mat_y_row_t, mat_t, mat_inv_t> iko¶
The internal interpolation object.
-
std::vector<mcovar_funct_rbf_noise> mfrn¶
The covariance functions.
Protected Types
-
typedef boost::numeric::ublas::vector<double> ubvector¶
-
typedef boost::numeric::ublas::matrix<double> ubmatrix¶
-
typedef o2scl::matrix_view_table mat_x_t¶
-
typedef const matrix_row_gen<mat_x_t> mat_x_row_t¶
-
typedef const matrix_column_gen<mat_x_t> mat_x_col_t¶
-
typedef o2scl::matrix_view_table_transpose mat_y_t¶
-
typedef const matrix_row_gen<mat_y_t> mat_y_row_t¶
Protected Attributes
-
size_t ix¶
Index of the “log weight” in the MCMC data vector.
-
inline emulator_interpm_krige_table()¶