utilities.generate_realistic_simulated_data()

Generate simulated mixed-frequency regional data in long format.

Usage

utilities.generate_realistic_simulated_data(T: int = ..., R: int = ..., J: int = ..., n_factors: int = ..., n_macro: int = ..., lag_qtrs: int = ..., seed: int = ..., w_true: npt.NDArray[np.float64] | None = ..., return_truth: Literal[False] = ...) -> pd.DataFrame
 
utilities.generate_realistic_simulated_data(T: int = ..., R: int = ..., J: int = ..., n_factors: int = ..., n_macro: int = ..., lag_qtrs: int = ..., seed: int = ..., w_true: npt.NDArray[np.float64] | None = ..., return_truth: Literal[True]) -> tuple[pd.DataFrame, dict]
 
utilities.generate_realistic_simulated_data(T: int = ..., R: int = ..., J: int = ..., n_factors: int = ..., n_macro: int = ..., lag_qtrs: int = ..., seed: int = ..., w_true: npt.NDArray[np.float64] | None = ..., return_truth: bool = ...) -> pd.DataFrame | tuple[pd.DataFrame, dict]

Produces a pd.DataFrame resembling real-world data suitable for initialising an ~ambric.Ambric model, including UK quarterly growth, macro series, regional covariates, and lagged annual regional growth.

Parameters

T: int = 130

Number of quarterly time periods.

R: int = 12

Number of regions.

J: int = 4

Number of regional covariate panels.

n_factors: int = 2

Number of latent factors in the DGP.

n_macro: int = 2

Number of macro indicator series.

lag_qtrs: int = 6

Publication lag in quarters for annual regional data.

seed: int = 34

Random seed for reproducibility.

w_true: npt.NDArray[np.float64] | None = None

Regional weights, shape (R,), used to form national growth. Defaults to equal weights.

return_truth: bool = False

If True, also return the quantities the model is trying to recover.

Returns

pd.DataFrame | tuple[pd.DataFrame, dict]

pd.DataFrame | tuple[pd.DataFrame, dict]: Long-format frame with columns datetime, measure, region, value. With return_truth=True, a tuple of that frame and a dict with keys datetime (T,), region_names, y_reg_true (T, R) true quarterly regional growth, y_annual_no_lag (T, R) annual regional growth including the unpublished recent values, w_true (R,), and the noise scales sigma_eps, sigma_uk, sigma_annual.