HistoricAverage

chronax.models.HistoricAverage · inherits BaseForecaster

Historic Average forecasting in JAX. Forecast = mean of all historical observations. Native intervals: $\sigma_h = \sigma \cdot \sqrt{1 + 1/n}$.

Attribute	Type	Description
uses_exog	bool	Whether the model supports exogenous variables (False).
alias	str	Model name.
conformal_params	ConformalIntervals or None	Optional object to enable conformal interval computation.
model_	dict	Dictionary storing fitted artifacts, e.g. mean, fitted values, sigma, n.

__init__(self, alias: str = "HistoricAverage", conformal_params: ConformalIntervals | None = None) -> None

Initializes the HistoricAverage model.

Parameter	Type	Default	Description
alias	str	"HistoricAverage"	(undocumented)
conformal_params	ConformalIntervals \| None	None	(undocumented)

fit(self, y: jnp.ndarray, X: jnp.ndarray | None = None) -> Self

Fit the HistoricAverage model.

Computes the historical mean of the series, stores fitted values, residual standard deviation, and series length for use in predict(). If conformal_params is configured, conformity scores are cached.

Parameters:

Parameter	Type	Default	Description
y	jnp.ndarray	-	Clean time series of shape (t,).
X	jnp.ndarray \| None	None	Exogenous variables (unused; included for API compatibility).

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

predict(self, h: int, X: jnp.ndarray | None = None, level: list[int] | None = None) -> dict

Generate h-step ahead forecasts using the fitted model.

All h forecasts equal the historical mean. Optionally adds prediction intervals using either native normal approximation or conformal method.

Parameters:

Parameter	Type	Default	Description
h	int	-	Forecast horizon (number of steps ahead).
X	jnp.ndarray \| None	None	Exogenous variables (unused; included for API compatibility).
level	list[int] \| None	None	Confidence levels (0-100) for prediction intervals, e.g. [80, 95]. If None, only point forecasts are returned.

Returns: dict Dictionary containing:

• "mean": Point forecasts of shape (h,), all equal to the historical mean.
• "lo-{l}" / "hi-{l}": Interval bounds for each level l (only present when level is not None).

predict_in_sample(self, level: list[int] | None = None) -> dict

Return in-sample fitted values from the last fit() call.

All fitted values equal the historical mean. Optionally adds prediction intervals around each fitted point using the normal approximation $\sigma_h = \sigma \cdot \sqrt{1 + 1/n}$.

Parameters:

Parameter	Type	Default	Description
level	list[int] \| None	None	Confidence levels (0-100) for fitted prediction intervals, e.g. [80, 95].

Returns: dict Dictionary containing:

• "fitted": In-sample predictions of shape (t,).
• "fitted-lo-{l}" / "fitted-hi-{l}": Fitted interval bounds for each level l (only present when level is not None).

forecast(self, y: jnp.ndarray, h: int, X: jnp.ndarray | None = None, X_future: jnp.ndarray | None = None, level: list[int] | None = None, fitted: bool = False) -> dict

Memory-efficient stateless fit+predict in one call.

Computes the historical mean of y and generates h-step ahead forecasts without storing any model state. Optionally returns in-sample fitted values and prediction intervals.

Parameters:

Parameter	Type	Default	Description
y	jnp.ndarray	-	Clean time series of shape (t,).
h	int	-	Forecast horizon (number of steps ahead).
X	jnp.ndarray \| None	None	In-sample exogenous variables (unused; included for API compatibility).
X_future	jnp.ndarray \| None	None	Future exogenous variables (unused; included for API compatibility).
level	list[int] \| None	None	Confidence levels (0-100) for prediction intervals, e.g. [80, 95].
fitted	bool	False	Whether to include in-sample fitted values in the output.

Returns: dict Dictionary containing:

• "mean": Point forecasts of shape (h,), all equal to the historical mean.
• "fitted": In-sample fitted values of shape (t,) (only if fitted=True).
• "lo-{l}" / "hi-{l}": Forecast interval bounds for each level l (only present when level is not None).
• "fitted-lo-{l}" / "fitted-hi-{l}": Fitted interval bounds (only present when both fitted=True and level is not None).