sakura.utils.data_splitter.DataSplitter.get_incremental_select_unselect_split

DataSplitter.get_incremental_select_unselect_split(base: ndarray, k: int) → ndarray

Obtain a split code from label vector, points labelled from 1~k are considered as selected (1), otherwise not selected (0).

Useful when determining overall train/test split directly from predefined labels.

Parameters:

• base (np.ndarray[base.dtype, np.integer]) – The predefined label vector to work with

• k (int) – Selection threshold k for the base label vector input

Returns:

A 0/1 label vector indicating selection of points

Return type:

np.ndarray[np.integer]