romcomma.user.sample.GaussianNoise

class GaussianNoise(N, variance)

Bases: object

Sample multivariate, zero-mean Gaussian noise.

Parameters:

• N (int) –

• variance (NP.MatrixLike) –

__init__(N, variance)

Generate N samples of L-dimensional Gaussian noise, sampled from \(\mathsf{N}[0,variance]\).

Parameters:

• N (int) – Number of samples (rows).

• variance (int | float | Sequence[int | float] | ndarray | Sequence[int | float | Sequence[int | float] | ndarray]) – (L,L) covariance matrix for homoskedastic noise.

Methods

__init__(N, variance)

Generate N samples of L-dimensional Gaussian noise, sampled from \(\mathsf{N}[0,variance]\).

Attributes

variance

class Variance(L, magnitude, is_covariant=False, is_determined=True)

Bases: object

An artificially generated (co)variance matrix for GaussianNoise, with a useful labelling scheme.

Parameters:

• L (int) –

• magnitude (float) –

• is_covariant (bool) –

• is_determined (bool) –

property matrix: ndarray

Variance as an (L,L) covariance matrix, suitable for constructing GaussianNoise.

property meta: Dict[str, Any]

Meta data for providing to data.storage. This matches the initials in self.__format__().