MultiNormalizer#

class pytorch_forecasting.data.encoders.MultiNormalizer(normalizers: List[TorchNormalizer])[source]#

Bases: TorchNormalizer

Normalizer for multiple targets.

This normalizers wraps multiple other normalizers.

Parameters:

normalizers (List[TorchNormalizer]) – list of normalizers to apply to targets

Inherited-members:

Methods

extra_repr()

fit(y[, X])

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.

get_transform(transformation)

Return transformation functions.

inverse_preprocess(y)

Inverse preprocess re-scaled data (e.g.

inverse_transform(y)

Inverse scale.

preprocess(y)

Preprocess input data (e.g.

set_output(*[, transform])

Set output container.

set_params(**params)

Set the parameters of this estimator.

transform(y[, X, return_norm, target_scale])

Scale input data.

Attributes

TRANSFORMATIONS

fit(y: DataFrame | ndarray | Tensor, X: DataFrame | None = None)[source]#

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

Parameters:

y (Union[pd.Series, np.ndarray, torch.Tensor]) – input data

Returns:

self

Return type:

MultiNormalizer

get_parameters(*args, **kwargs) → List[Tensor][source]#

Returns parameters that were used for encoding.

Returns:

First element is center of data and second is scale

Return type:

List[torch.Tensor]

transform(y: DataFrame | ndarray | Tensor, X: DataFrame = None, return_norm: bool = False, target_scale: List[Tensor] = None) → List[Tuple[ndarray | Tensor, ndarray]] | List[ndarray | Tensor][source]#

Scale input data.

Parameters:

  • y (Union[pd.DataFrame, np.ndarray, torch.Tensor]) – data to scale

  • X (pd.DataFrame) – dataframe with groups columns. Only necessary if GroupNormalizer is among normalizers

  • return_norm (bool, optional) – If to return . Defaults to False.

  • target_scale (List[torch.Tensor]) – target scale to use instead of fitted center and scale

Returns:

List of scaled data, if return_norm=True, returns also scales as second element

Return type:

Union[List[Tuple[Union[np.ndarray, torch.Tensor], np.ndarray]], List[Union[np.ndarray, torch.Tensor]]]