The PerformanceCriticalCode submodule

This submodule contains the Cython code equivalent to the original R code in InlineFunctions.R from the original MHN repo as well as some functions to solve linear equations involving [I-Q].

mhn.full_state_space.PerformanceCriticalCode.compute_inverse(double[:, :] theta, double[:] dg, double[:] b, double[:] xout, bool transp)

Computes the solution for [I - Q] * x = b using forward (and backward) substitution.

Parameters:

• theta (np.ndarray) – Thetas used to construct Q.

• dg (np.ndarray) – Vector containing the diagonal values of [I-Q].

• b (np.ndarray) – A double vector representing the right-hand side of the equation.

• xout (np.ndarray) – Double vector that will contain the solution after running this function.

• transp (bool) – If True, returns solution for [I - Q]^T * x = b.

mhn.full_state_space.PerformanceCriticalCode.kron_vec(double[:, :] theta_mat, int i, double[:] x_vec, bool diag=False, bool transp=False) → np.ndarray

Multiplies the Kronecker product of the ith row of the theta matrix with a vector. This is a Python wrapper for the more efficient Cython implementation.

Parameters:

• theta_mat (np.ndarray) – Matrix containing the theta values.

• i (int) – Row of theta used for the Kronecker product.

• x_vec (np.ndarray) – Vector that is multiplied with the Kronecker product matrix.

• diag (bool, optional) – If False, the diagonal of the Kronecker product matrix is set to zero. Defaults to False.

• transp (bool, optional) – If True, the Kronecker product matrix is transposed. Defaults to False.

Returns:

Vector that will contain the result of the multiplication.

Return type:

np.ndarray