SelectColumns#

class sdm.processing.common.SelectColumns(max_columns: int, method: Literal['first', 'round_robin'] = 'first')#

Select a subset of columns for each semantic type.

Parameters:

max_columns (int) – The maximum number of columns to keep per semantic type.
method (Literal['first', 'round_robin']) – The column selection method. "first" keeps the first columns according to their order within each semantic block. "round_robin" assigns each ensemble member the next consecutive chunk, wrapping to the first column after the last. For five columns and max_columns=2, members 0, 1, and 2 receive columns (0, 1), (2, 3), and (4, 0).

Capabilities#

Handled Semantic Types	`categorical`, `datetime`, `id`, `numerical`, `text`
Requires Fitting	❌