ArimaModel

arima_model.ArimaModel

ARIMA model for univariate time series forecasting.

Supports both standard ARIMA(p, d, q) and seasonal ARIMA by specifying a seasonality period s. Implements traditional statsmodels ARIMA fitting, with future expandability to exogenous variables and rolling window forecasts.

__init__(self, params: Dict[str, Any], settings: Dict[str, Any])

(undocumented)

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

train(self, y_context: np.ndarray, y_target: np.ndarray, timestamps_context: np.ndarray, timestamps_target: np.ndarray, x_context: Optional[np.ndarray] = None, x_target: Optional[np.ndarray] = None, **kwargs: dict) -> ArimaModel

Trains a separate ARIMA model for each variate in a (potentially multivariate) time series.

Expects y_context and y_target as 2D arrays: (num_steps, num_targets).

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	dict	-	(undocumented)

Returns: Self (the fitted forecaster; sets self.is_fitted).

predict(self, y_context: np.ndarray, timestamps_context: np.ndarray, timestamps_target: np.ndarray, x_context: Optional[np.ndarray] = None, x_target: Optional[np.ndarray] = None, **kwargs: dict) -> np.ndarray

Predicts future values for each variate and concatenates the results.

Parameter	Type	Default	Description
y_context	np.ndarray	-	Context values, shape (num_steps, num_variates).
timestamps_context	np.ndarray	-	Timestamps for context data.
timestamps_target	np.ndarray	-	Timestamps for target/future data.
x_context	Optional[np.ndarray]	None	Optional covariate data for context.
x_target	Optional[np.ndarray]	None	Optional covariate data for prediction horizon.
**kwargs	dict	-	Should include 'freq' key.

Returns: np.ndarray (Predictions with shape (forecast_horizon, num_variates)). Raises: ValueError (If the model has not been fitted.)