ctf4science.data_module.get_prediction_timesteps

ctf4science.data_module.get_prediction_timesteps(dataset_name: str, pair_id: int, subset: str = 'test') → ndarray

Return time steps at which prediction matrices must be evaluated after training.

Uses dataset metadata (matrix shape, start index, delta_t) to build a 1D array of time steps for the given subset matrix of the pair.

Parameters:

dataset_namestr

Name of the dataset (e.g. 'ODE_Lorenz', 'PDE_KS').

pair_idint

ID of the train-test pair.

subset{‘test’, ‘initialization’}, optional

Which matrix to use. Default is 'test'.

Returns:

ndarray

1D array of time steps for evaluation.

Raises:

ValueError

If pair_id is missing, subset matrix or metadata (e.g. matrix_shapes, matrix_start_index, delta_t) is missing.