gluonts.mx.distribution.distribution_output module#
- class gluonts.mx.distribution.distribution_output.ArgProj(args_dim: ~typing.Dict[str, int], domain_map: ~typing.Callable[[...], ~typing.Tuple[~typing.Union[~mxnet.ndarray.ndarray.NDArray, ~mxnet.symbol.symbol.Symbol]]], dtype: ~typing.Type = <class 'numpy.float32'>, prefix: ~typing.Optional[str] = None, **kwargs)[source]#
Bases:
HybridBlock
A block that can be used to project from a dense layer to distribution arguments.
- Parameters:
dim_args – Dictionary with string key and int value dimension of each arguments that will be passed to the domain map, the names are used as parameters prefix.
domain_map – Function returning a tuple containing one tensor a function or a HybridBlock. This will be called with num_args arguments and should return a tuple of outputs that will be used when calling the distribution constructor.
- class gluonts.mx.distribution.distribution_output.DistributionOutput[source]#
Bases:
Output
Class to construct a distribution given the output of a network.
- args_dim: Dict[str, int]#
- distr_cls: type#
- distribution(distr_args, loc: Optional[Union[NDArray, Symbol]] = None, scale: Optional[Union[NDArray, Symbol]] = None) Distribution [source]#
Construct the associated distribution, given the collection of constructor arguments and, optionally, a scale tensor.
- Parameters:
distr_args – Constructor arguments for the underlying Distribution type.
loc – Optional tensor, of the same shape as the batch_shape+event_shape of the resulting distribution.
scale – Optional tensor, of the same shape as the batch_shape+event_shape of the resulting distribution.
- domain_map(F, *args: Union[NDArray, Symbol])[source]#
Converts arguments to the right shape and domain.
The domain depends on the type of distribution, while the correct shape is obtained by reshaping the trailing axis in such a way that the returned tensors define a distribution of the right event_shape.
- property event_dim: int#
Number of event dimensions, i.e., length of the event_shape tuple, of the distributions that this object constructs.
- property event_shape: Tuple#
Shape of each individual event contemplated by the distributions that this object constructs.
- property value_in_support: float#
A float that will have a valid numeric value when computing the log- loss of the corresponding distribution; by default 0.0.
This value will be used when padding data series.