osl_dynamics.simulation.MSess_MVN#

class osl_dynamics.simulation.MSess_MVN(session_means, session_covariances, n_modes=None, n_channels=None, n_covariances_act=1, embedding_vectors=None, n_sessions=None, embeddings_dim=None, spatial_embeddings_dim=None, embeddings_scale=None, n_groups=None, between_group_scale=None, observation_error=0.0)#

Bases: MVN

Class that generates data from a multivariate normal distribution for multiple sessions.

Parameters:
session_meansnp.ndarray or str

Mean vector for each mode for each session, shape should be (n_sessions, n_modes, n_channels). Either a numpy array or 'zero' or 'random'.

session_covariancesnp.ndarray or str

Covariance matrix for each mode for each session, shape should be (n_sessions, n_modes, n_channels, n_channels). Either a numpy array or 'random'.

n_modesint, optional

Number of modes.

n_channelsint, optional

Number of channels.

n_covariances_actint, optional

Number of iterations to add activations to covariance matrices.

embedding_vectorsnp.ndarray, optional

Embedding vectors for each session, shape should be (n_sessions, embeddings_dim).

n_sessionsint, optional

Number of sessions.

embeddings_dimint, optional

Dimension of embeddings.

spatial_embeddings_dimint, optional

Dimension of spatial embeddings.

embeddings_scalefloat, optional

Standard deviation when generating embeddings with a normal distribution.

n_groupsint, optional

Number of groups when generating embeddings.

between_group_scalefloat, optional

Standard deviation when generating centroids of groups of embeddings.

observation_errorfloat, optional

Standard deviation of the error added to the generated data.

n_covariances_act = 1#
observation_error = 0.0#
embeddings_dim = None#
spatial_embeddings_dim = None#
embeddings_scale = None#
n_groups = None#
between_group_scale = None#
validate_embedding_parameters(embedding_vectors)#
create_embeddings(embedding_vectors)#
create_linear_transform(input_dim, output_dim, scale=0.1)#
create_session_means_deviations()#
create_session_covariances_deviations()#
create_session_means(option)#
create_session_covariances(eps=1e-06)#
simulate_session_data(session, mode_time_course)#

Simulate single session data.

Parameters:
sessionint

Session number.

mode_time_coursenp.ndarray

Mode time course. Shape is (n_samples, n_modes).

Returns:
datanp.ndarray

Simulated data. Shape is (n_samples, n_channels).

get_session_instantaneous_covariances(session, mode_time_course)#

Get ground truth covariances at each time point for a particular session.

Parameters:
sessionint

Session number.

mode_time_coursenp.ndarray

Mode time course. Shape is (n_samples, n_modes).

Returns:
inst_covsnp.ndarray

Instantaneous covariances for an session. Shape is (n_samples, n_channels, n_channels).

get_instantaneous_covariances(mode_time_courses)#

Get ground truth covariance at each time point for each session.

Parameters:
mode_time_coursesnp.ndarray

Mode time courses. Shape is (n_sessions, n_samples, n_modes).

Returns:
inst_covsnp.ndarray

Instantaneous covariances. Shape is (n_sessions, n_samples, n_channels, n_channels).

simulate_multi_session_data(mode_time_courses)#

Simulates data.

Parameters:
mode_time_coursesnp.ndarray

It contains n_sessions time courses. Shape is (n_sessions, n_samples, n_modes).

Returns:
datanp.ndarray

Simulated data for sessions. Shape is (n_sessions, n_samples, n_channels).