Exponential Smoother

The ExpSmoother is a torch.nn.Module which generates forecasts using exponential smoothing.

This class inherits most of its methods from torchcast.state_space.StateSpaceModel.

class torchcast.exp_smooth.exp_smooth.ExpSmoother(processes: Sequence[torchcast.process.base.Process], measures: Optional[Sequence[str]] = None, measure_covariance: Optional[torchcast.covariance.base.Covariance] = None, smoothing_matrix: Optional[torchcast.exp_smooth.smoothing_matrix.SmoothingMatrix] = None)

Bases: torchcast.state_space.base.StateSpaceModel

Uses exponential smoothing to generate forecasts.

Parameters

  • processes – A list of Process modules.

  • measures – A list of strings specifying the names of the dimensions of the time-series being measured.

  • measure_covariance – A module created with Covariance.from_measures(measures).

  • predict_smoothing – A torch.nn.Module which predicts the smoothing parameters. The module should predict these as real-values and they will be constrained to 0-1 internally.