gluonts.mx.representation.embedding module

class gluonts.mx.representation.embedding.Embedding(num_bins: int, size: Optional[int] = None, *args, **kwargs)

Bases: Representation

A class representing an embedding operation on top of a given binning. Note that this representation is intended to applied on top of categorical/binned data.

Parameters:

• num_bins – The number of categories/bins of the data on which this representation is applied.

• size – The desired embedding size. By default, the following heuristic is used: https://developers.googleblog.com/2017/11/introducing-tensorflow-feature-columns.html (default: round(num_bins**(1/4)))

hybrid_forward(F, data: Union[NDArray, Symbol], observed_indicator: Union[NDArray, Symbol], scale: Optional[Union[NDArray, Symbol]], rep_params: List[Union[NDArray, Symbol]], **kwargs) → Tuple[Union[NDArray, Symbol], Union[NDArray, Symbol], List[Union[NDArray, Symbol]]]

Transform the data into the desired representation.

Parameters:

• F –

• data – Target data.

• observed_indicator – Target observed indicator.

• scale – Pre-computed scale.

• rep_params – Additional pre-computed representation parameters.

• **kwargs – Additional block-specfic parameters.

:param : Additional block-specfic parameters.

Returns:

Tuple consisting of the transformed data, the computed scale, and additional parameters to be passed to post_transform.

Return type:

Tuple[Tensor, Tensor, List[Tensor]]