MoiraiHyperparams

moirai_model.MoiraiHyperparams · inherits PydanticBaseModel

(No description provided in source.)

MoiraiModel

moirai_model.MoiraiModel · inherits BaseModel

(No description provided in source.)

__init__(self, params, settings)

Initialize Moirai model.

Parameter	Type	Default	Description
params	Dict[str, Any]	-	Model parameters dictionary
settings	Dict[str, Any]	-	Settings dictionary containing device, python_version, etc.

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

"Train" the Moirai model (no training required for foundation models).

Parameters:

Parameter	Type	Default	Description
y_context	np.ndarray	-	Past target values (not used for training, for compatibility)
y_target	np.ndarray	-	Future target values (not used for training, for compatibility)
timestamps_context	np.ndarray	-	Timestamps for y_context (not used)
timestamps_target	np.ndarray	-	Timestamps for y_target (not used)
x_context	Optional[np.ndarray]	None	(undocumented)
x_target	Optional[np.ndarray]	None	(undocumented)
**kwargs	Any	-	Additional keyword arguments

Returns: MoiraiModel (The fitted model instance (for compatibility)).

predict(self, y_context, timestamps_context, timestamps_target, x_context=None, x_target=None, **kwargs) -> np.ndarray

Make predictions using the Moirai model.

Parameters:

Parameter	Type	Default	Description
y_context	np.ndarray	-	Recent/past target values, shape (context_steps, num_targets)
timestamps_context	np.ndarray	-	Timestamps for y_context (not used for prediction)
timestamps_target	np.ndarray	-	Timestamps for the prediction horizon (used to determine forecast length)
x_context	Optional[np.ndarray]	None	(undocumented)
x_target	Optional[np.ndarray]	None	(undocumented)
**kwargs	Any	-	(undocumented)

Returns: np.ndarray (Model prediction samples with shape (num_samples, forecast_horizon, num_targets)). Raises: ValueError (If model is not fitted, freq is not provided, or forecast length cannot be determined).