chronax.deepnpts_losses

Pluggable point-loss functions for the DeepNPTS forecaster. Self-contained (no dependency on other models' loss modules). Each loss has signature (pred, target) -> scalar and reduces by mean over all elements. Functions are module-level so they pickle cleanly when stored as the loss attribute of a fitted DeepNPTS. NF DeepNPTS defaults to MAE() and rejects any non-point loss.

mae(pred, target)

chronax.deepnpts_losses.mae

Mean absolute error: mean(|pred - target|).

Parameter	Type	Default	Description
pred	jnp.ndarray	-	(undocumented)
target	jnp.ndarray	-	(undocumented)

Returns: jnp.ndarray (scalar loss value).

mse(pred, target)

chronax.deepnpts_losses.mse

Mean squared error: mean((pred - target)**2).

Parameter	Type	Default	Description
pred	jnp.ndarray	-	(undocumented)
target	jnp.ndarray	-	(undocumented)

Returns: jnp.ndarray (scalar loss value).

huber(pred, target)

chronax.deepnpts_losses.huber

Huber loss with delta = 1.0. Quadratic for |r| <= 1, linear outside.

| Parameter | Type | Default | Description | |-----------|---------------|-------------| | pred | jnp.ndarray | - | (undocumented) | | target | jnp.ndarray | - | (undocumented) |

Returns: jnp.ndarray (scalar loss value).

LOSSES

chronax.deepnpts_losses.LOSSES

Mapping of available loss functions registered by string name.

Type: Mapping[str, LossFn]

resolve(loss)

chronax.deepnpts_losses.resolve

Return a callable loss from either a registry string or a callable.

Parameter	Type	Default	Description
loss	str | LossFn	-	(undocumented)

Returns: LossFn (A callable loss function). Raises: ValueError (If the provided string loss name is unknown).