NegativeBinomialDistributionLoss#

class pytorch_forecasting.metrics.distributions.NegativeBinomialDistributionLoss(name: str | None = None, quantiles: List[float] = [0.02, 0.1, 0.25, 0.5, 0.75, 0.9, 0.98], reduction='mean')[source]#

Bases: DistributionLoss

Negative binomial loss, e.g. for count data.

Requirements for original target normalizer:

  • not centered normalization (only rescaled)

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 output.

to_prediction(y_pred)

Convert network prediction into a point prediction.
distribution_class#

alias of NegativeBinomial

map_x_to_distribution(x: Tensor) → NegativeBinomial[source]#

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: Tensor, target_scale: Tensor, encoder: BaseEstimator) → Tensor[source]#

Rescale normalized parameters into the scale required for the output.

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

to_prediction(y_pred: Tensor) → Tensor[source]#

Convert network prediction into a point prediction. In the case of this distribution prediction we need to derive the mean (as a point prediction) from the distribution parameters

Parameters:

  • y_pred – prediction output of network

  • binomial (in this case the two parameters for the negative) –

Returns:

mean prediction

Return type:

torch.Tensor