TorchNormalizer#

class pytorch_forecasting.data.encoders.TorchNormalizer(method: str = 'standard', center: bool = True, transformation: str | tuple[Callable, Callable] = None, method_kwargs: dict[str, Any] | None = None)[source]#

Bases: InitialParameterRepresenterMixIn, BaseEstimator, TransformerMixin, TransformMixIn

Basic target transformer that can be fit also on torch tensors.

Parameters:

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

  • method_kwargs (Dict[str, Any], optional, default=None) –

    Dictionary of method specific arguments as listed below

    • ”robust” method: “upper”, “lower”, “center” quantiles defaulting to 0.75, 0.25 and 0.5

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

  • transformation (Union[str, Dict[str, Callable]] optional, default=None) –

    Transform values before applying normalizer. Available options are

    • None (default): No transformation of values

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

    • log1p: 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

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

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

    • relu: Apply max(0, x) to output

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

      forward and reverse entries are required. inverse transformation is optional and should be defined if reverse is not the inverse of the forward transformation. inverse_torch can be defined to provide a torch distribution transform for inverse transformations.

Inherited-members:

Methods

extra_repr()

Return extra information about parameters for representation/logging.

fit(y)

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

fit_transform(X[, y])

Fit to data, then transform it.

get_metadata_routing()

Get metadata routing of this object.

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. take exp).

inverse_transform(y)

Inverse scale.

preprocess(y)

Preprocess input data (e.g. take log).

set_output(*[, transform])

Set output container.

set_params(**params)

Set the parameters of this estimator.

set_transform_request(*[, return_norm, ...])

Configure whether metadata should be requested to be passed to the transform method.

transform(y[, return_norm, target_scale])

Rescale data.

Attributes

TRANSFORMATIONS

fit(y: Series | ndarray | Tensor)[source]#

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

Parameters:

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

Returns:

TorchNormalizer

Return type:

self

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

Returns parameters that were used for encoding.

Returns:

First element is center of data and second is scale

Return type:

torch.Tensor

inverse_transform(y: Tensor | ndarray) → Tensor[source]#

Inverse scale.

Parameters:

y (Union[torch.Tensor, np.ndarray])) – scaled data

Returns:

de-scaled data

Return type:

torch.Tensor

set_transform_request(*, return_norm: bool | None | str = '$UNCHANGED$', target_scale: bool | None | str = '$UNCHANGED$') → TorchNormalizer#

Configure whether metadata should be requested to be passed to the transform method.

Note that this method is only relevant when this estimator is used as a sub-estimator within a meta-estimator and metadata routing is enabled with enable_metadata_routing=True (see sklearn.set_config()). Please check the User Guide on how the routing mechanism works.

The options for each parameter are:

  • True: metadata is requested, and passed to transform if provided. The request is ignored if metadata is not provided.

  • False: metadata is not requested and the meta-estimator will not pass it to transform.

  • None: metadata is not requested, and the meta-estimator will raise an error if the user provides it.

  • str: metadata should be passed to the meta-estimator with this given alias instead of the original name.

The default (sklearn.utils.metadata_routing.UNCHANGED) retains the existing request. This allows you to change the request for some parameters and not others.

Added in version 1.3.

Parameters:

  • return_norm (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for return_norm parameter in transform.

  • target_scale (str, True, False, or None, default=sklearn.utils.metadata_routing.UNCHANGED) – Metadata routing for target_scale parameter in transform.

Returns:

self – The updated object.

Return type:

object

transform(y: Series | ndarray | Tensor, return_norm: bool = False, target_scale: Tensor = None) → tuple[ndarray | Tensor, ndarray] | ndarray | Tensor[source]#

Rescale data.

Parameters:

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

  • return_norm (bool, optional, default=False) – [description]. Defaults to False.

  • target_scale (torch.Tensor, optional, default=None) – target scale to use instead of fitted center and scale

Returns:

rescaled data with type depending on input type. returns second element if return_norm=True

Return type:

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