EncoderNormalizer

class pytorch_forecasting.data.encoders.EncoderNormalizer(method: str = 'standard', center: bool = True, transformation: Optional[Union[str, Tuple[Callable, Callable]]] = None, eps: float = 1e-08)[source]

Bases: pytorch_forecasting.data.encoders.TorchNormalizer

Special Normalizer that is fit on each encoding sequence.

If used, this transformer will be fitted on each encoder sequence separately. This normalizer can be particularly useful as target normalizer.

Initialize

Parameters

  • method (str, optional) – method to rescale series. Either “identity”, “standard” (standard scaling) or “robust” (scale using quantiles 0.25-0.75). Defaults to “standard”.

  • center (bool, optional) – If to center the output to zero. Defaults to True.

  • transformation (Union[str, Tuple[Callable, Callable]] optional) –

    Transform values before applying normalizer. Available options are

    • None (default): No transformation of values

    • log: Estimate in log-space leading to a multiplicative model

    • logp1: Estimate in log-space but add 1 to values before transforming for stability

      (e.g. if many small values <<1 are present). Note, that inverse transform is still only torch.exp() and not torch.expm1().

    • logit: Apply logit transformation on values that are between 0 and 1

    • softplus: Apply softplus to output (inverse transformation) and x + 1 to input (transformation)

    • relu: Apply max(0, x) to output

    • Tuple[Callable, Callable] of PyTorch functions that transforms and inversely transforms values.

  • eps (float, optional) – Number for numerical stability of calculations. Defaults to 1e-8.

Inherited-members

Methods

fit(y)

Fit transformer, i.e. determine center and scale of data.

fit_transform(X[, y])

Fit to data, then transform it.

get_parameters(*args, **kwargs)

Returns parameters that were used for encoding.

get_params([deep])

Get parameters for this estimator.

inverse_preprocess(y)

Inverse preprocess re-scaled data (e.g.

inverse_transform(y)

Inverse scale.

preprocess(y)

Preprocess input data (e.g.

set_params(**params)

Set the parameters of this estimator.

transform(y[, return_norm, target_scale])

Rescale data.

Attributes

TRANSFORMATIONS

pytorch_forecasting.data.encoders._plus_one GroupNormalizer