ctf4science.data_module.get_validation_prediction_timesteps#
- ctf4science.data_module.get_validation_prediction_timesteps(dataset_name, pair_id, train_split=0.8)#
Return prediction timesteps for the validation split.
For pair_ids 2 and 4 (reconstruction), prediction timesteps equal training. For pair_ids 8 and 9, the timesteps come from the second or third training matrix. For 1, 3, 5, 6, 7, the tail of the single matrix (after train_split) is used as the validation prediction window.
- Parameters:
- dataset_namestr
Name of the dataset to load.
- pair_idint
Data pair (1–9; special handling for 2, 4, 8, 9).
- train_splitfloat, optional
Fraction of data for training in (0, 1). Default is 0.8. Ignored for pair_ids 2, 4, 8, 9.
- Returns:
- ndarray
Timesteps for the validation prediction window.
- Raises:
- ValueError
If train_split is not in (0, 1) or pair_id is not in 1–9.