TiRexModel

chronax.models.tirex_model.TiRexModel · inherits BaseModel

TiRex zero-shot forecasting model.

__init__(self, params, settings)

Initializes the TiRex model wrapper and checks for the required tirex-ts dependency.

Parameter	Type	Default	Description
params	Dict[str, Any]	-	(undocumented)
settings	Dict[str, Any]	-	(undocumented)

train(self, y_context, y_target, timestamps_context, timestamps_target, x_context=None, x_target=None, **kwargs)

Loads the underlying TiRex model checkpoint. Since TiRex is a zero-shot model, this method performs setup rather than training.

Parameter	Type	Default	Description
y_context	np.ndarray	-	(undocumented)
y_target	np.ndarray	-	(undocumented)
timestamps_context	np.ndarray	-	(undocumented)
timestamps_target	np.ndarray	-	(undocumented)
x_context	Optional[np.ndarray]	None	(undocumented)
x_target	Optional[np.ndarray]	None	(undocumented)
**kwargs		-	(undocumented)

Returns: TiRexModel (the fitted forecaster; sets self._model).

predict(self, y_context, timestamps_context, timestamps_target, x_context=None, x_target=None, **kwargs)

Parameter	Type	Default	Description
y_context	np.ndarray	-	(undocumented)
timestamps_context	np.ndarray	-	(undocumented)
timestamps_target	np.ndarray	-	(undocumented)
x_context	Optional[np.ndarray]	None	(undocumented)
x_target	Optional[np.ndarray]	None	(undocumented)
**kwargs		-	(undocumented)

Returns: np.ndarray (Forecast samples derived from quantiles, typically of shape (N_samples, H, N_targets)).

TirexModel

chronax.models.tirex_model.TirexModel · inherits BaseModel

Alias for TiRexModel.