find_harmonics(y, m)

chronax.tbats_core.find_harmonics

Find optimal number of harmonics for period m using AIC.

Results are cached by (n, m, sum, std) so warm runs are free.

Parameter	Type	Default	Description
y	jnp.ndarray	-	(undocumented)
m	int	-	(undocumented)

Returns: Tuple[int, jnp.ndarray] (k, z_deseasonalised)

tbats_model_generator(y, seasonal_periods, k_vector, use_boxcox, bc_lower, bc_upper, use_trend, use_damped_trend, use_arma_errors, ar_coeffs, ma_coeffs, seasonal_blocks=None)

chronax.tbats_core.tbats_model_generator

Fit a single TBATS specification (Box-Cox + optimisation + filter).

Parameter	Type	Default	Description
y	jnp.ndarray	-	(undocumented)
seasonal_periods	Sequence[int]	-	(undocumented)
k_vector	jnp.ndarray	-	(undocumented)
use_boxcox	bool	-	(undocumented)
bc_lower	float	-	(undocumented)
bc_upper	float	-	(undocumented)
use_trend	bool	-	(undocumented)
use_damped_trend	bool	-	(undocumented)
use_arma_errors	bool	-	(undocumented)
ar_coeffs	Optional[jnp.ndarray]	-	(undocumented)
ma_coeffs	Optional[jnp.ndarray]	-	(undocumented)
seasonal_blocks	Optional[jnp.ndarray]	None	(undocumented)

Returns: Dict

The returned dictionary contains the fitted model components: * fitted: jnp.ndarray * errors: jnp.ndarray * sigma2: jnp.ndarray * aic: jnp.ndarray * optim_params: jnp.ndarray * F: jnp.ndarray * w_transpose: jnp.ndarray * g: jnp.ndarray * x: jnp.ndarray * k_vector: jnp.ndarray * BoxCox_lambda: jnp.ndarray or None * p: int * q: int * ar_coeffs: jnp.ndarray or None * ma_coeffs: jnp.ndarray or None * seed_states: jnp.ndarray * y_mu: jnp.ndarray * y_sigma: jnp.ndarray * description: Dict

tbats_model(y, seasonal_periods, k_vector, use_boxcox, bc_lower, bc_upper, use_trend, use_damped_trend, use_arma_errors)

chronax.tbats_core.tbats_model

Convenience wrapper: fit a single TBATS spec with no ARMA.

| Parameter | Type | Default | Description | |-----------|---------------|-------------| | y | jnp.ndarray | - | (undocumented) | | seasonal_periods | Sequence[int] | - | (undocumented) | | k_vector | jnp.ndarray | - | (undocumented) | | use_boxcox | bool | - | (undocumented) | | bc_lower | float | - | (undocumented) | | bc_upper | float | - | (undocumented) | | use_trend | bool | - | (undocumented) | | use_damped_trend | bool | - | (undocumented) | | use_arma_errors | bool | - | (undocumented) |

Returns: Dict (Same structure as tbats_model_generator.)

tbats_selection(y, seasonal_periods, use_boxcox, bc_lower, bc_upper, use_trend, use_damped_trend, use_arma_errors, early_stop_patience=None, early_stop_tol=0.5, k_vector=None)

chronax.tbats_core.tbats_selection

Auto-select the best TBATS configuration via AIC comparison.

Parameter	Type	Default	Description
y	jnp.ndarray	-	(undocumented)
seasonal_periods	Sequence[int]	-	(undocumented)
use_boxcox	Optional[bool]	-	(undocumented)
bc_lower	float	-	(undocumented)
bc_upper	float	-	(undocumented)
use_trend	Optional[bool]	-	(undocumented)
use_damped_trend	Optional[bool]	-	(undocumented)
use_arma_errors	bool	-	(undocumented)
early_stop_patience	Optional[int]	None	(undocumented)
early_stop_tol	float	0.5	(undocumented)
k_vector	Optional[jnp.ndarray]	None	(undocumented)

Returns: Dict (The fitted model dictionary of the best configuration.) Raises: ValueError

tbats_forecast(mod, h)

chronax.tbats_core.tbats_forecast

Multi-step mean forecast from a fitted model dictionary.

Parameter	Type	Default	Description
mod	Dict	-	(undocumented)
h	int	-	(undocumented)

Returns: Dict[str, jnp.ndarray]

The returned dictionary contains: * mean: The mean forecast (untransformed if Box-Cox was used). * mean_bc: The mean forecast in the Box-Cox transformed space (or None if Box-Cox was not used).

compute_sigmah(mod, h)

chronax.tbats_core.compute_sigmah

Parametric forecast standard deviations from a fitted model dictionary.

Parameter	Type	Default	Description
mod	Dict	-	(undocumented)
h	int	-	(undocumented)

Returns: jnp.ndarray

tbats_forecast_batch(F, w, x_last, h)

chronax.tbats_core.tbats_forecast_batch

Vectorised forecasts: x_last has shape (B, d).

Parameter	Type	Default	Description
F	jnp.ndarray	-	(undocumented)
w	jnp.ndarray	-	(undocumented)
x_last	jnp.ndarray	-	(undocumented)
h	int	-	(undocumented)

Returns: jnp.ndarray

compute_sigmah_batch(F, w, g, sigma2, y_sigma, h, use_boxcox)

chronax.tbats_core.compute_sigmah_batch

Vectorised sigmah: sigma2 and y_sigma have shape (B,).

Parameter	Type	Default	Description
F	jnp.ndarray	-	(undocumented)
w	jnp.ndarray	-	(undocumented)
g	jnp.ndarray	-	(undocumented)
sigma2	jnp.ndarray	-	(undocumented)
y_sigma	jnp.ndarray	-	(undocumented)
h	int	-	(undocumented)
use_boxcox	bool	-	(undocumented)

Returns: jnp.ndarray