Synthetic data

Autoregressive model

class sekupy.simulation.autoregressive.AutoRegressiveModel(name='ar_model', order=10, noise=0.01, **kwargs)

fit(dynamics_model)

class sekupy.simulation.autoregressive.DelayedModel(name='delayed_model', order=5, noise=1, delay=0.0195, **kwargs)

fit(dynamics_model)

class sekupy.simulation.autoregressive.PhaseDelayedModel(name='phase_delayed_model', **kwargs)

class sekupy.simulation.autoregressive.SimulationModel(name='simulation_model', order=None, noise=None, delay=None, snr=1000000.0, **kwargs)

fit(dynamics_model)

transform(ds)

Transform the provided dataset.

This method applies the transformation to the dataset and records the transformation in the dataset’s preprocessing history.

Parameters:

ds (Dataset) – The dataset to transform

Returns:

The transformed dataset

Return type:

Dataset

class sekupy.simulation.autoregressive.TimeDelayedModel(name='time_delayed_model', order=5, noise=1, delay=0.0195, fsample=256, **kwargs)

Kuramoto model

Connectivity simulator

class sekupy.simulation.connectivity.ConnectivityStateSimulator(n_nodes=10, max_edges=5, fsamp=128, n_brain_states=6, length_dynamics=100, state_duration={'max_time': 3.5, 'min_time': 2.5}, method='random')

fit()

generate_duration()

simulate_dynamics(method='random')

transform(ds)

The state simulator using transform generates the dynamics of the system.

Loader

class sekupy.simulation.loader.SimulationLoader(conf_file, task, name='simulator', **kwargs)

fetch(n_subjects=10, **kwargs)

save(fname)