actsnclass.DataBase.build_samples

DataBase.build_samples(initial_training: str, nclass=2, screen=False, queryable=False)

Separate train and test samples.

Populate properties: train_features, train_header, test_features, test_header, queryable_ids (if flag available), train_labels and test_labels.

Parameters:

• initial_training (str or int) – Choice of initial training sample. If ‘original’: begin from the train sample flagged in the file If int: choose the required number of samples at random, ensuring that at least half are SN Ia.

• nclass (int (optional)) – Number of classes to consider in the classification Currently only nclass == 2 is implemented.

• screen (bool (optional)) – If True display the dimensions of training and test samples.

• queryable (bool (optional)) – If True build also queryable sample for time domain analysis. Default is False.