NormalDistributionLoss

class pytorch_forecasting.metrics.NormalDistributionLoss(name: Optional[str] = None, quantiles: List[float] = [0.02, 0.1, 0.25, 0.5, 0.75, 0.9, 0.98], reduction='mean')

Bases: pytorch_forecasting.metrics.DistributionLoss

Normal distribution loss.

Requirements for original target normalizer:

• not normalized in log space (use LogNormalDistributionLoss)

• not coerced to be positive

Initialize metric

Parameters

• name (str) – metric name. Defaults to class name.

• quantiles (List[float], optional) – quantiles for probability range. Defaults to [0.02, 0.1, 0.25, 0.5, 0.75, 0.9, 0.98].

• reduction (str, optional) – Reduction, “none”, “mean” or “sqrt-mean”. Defaults to “mean”.

Methods

map_x_to_distribution(x)	Map the a tensor of parameters to a probability distribution.
rescale_parameters(parameters, target_scale, …)	Rescale normalized parameters into the scale required for the distribution.

Attributes

distribution_arguments

distribution_class

alias of torch.distributions.normal.Normal

map_x_to_distribution(x: torch.Tensor) → torch.distributions.normal.Normal

Map the a tensor of parameters to a probability distribution.

Parameters

x (torch.Tensor) – parameters for probability distribution. Last dimension will index the parameters

Returns

torch probability distribution as defined in the

class attribute distribution_class

Return type

distributions.Distribution

rescale_parameters(parameters: torch.Tensor, target_scale: torch.Tensor, encoder: sklearn.base.BaseEstimator) → torch.Tensor

Rescale normalized parameters into the scale required for the distribution.

Parameters

• parameters (torch.Tensor) – normalized parameters (indexed by last dimension)

• target_scale (torch.Tensor) – scale of parameters (n_batch_samples x (center, scale))

• encoder (BaseEstimator) – original encoder that normalized the target in the first place

Returns

parameters in real/not normalized space

Return type

torch.Tensor

NegativeBinomialDistributionLoss PoissonLoss