Skip to content

sampling_random_stratified 

sampling_random_stratified(
    n: int,
    seed: int | None = None,
    min_subsample: int | None = None,
) -> FeatureSpec

lets_plot's stratified random sampling. Not applied by ggrust.

Built as lets_plot builds it, so ported code runs; rendering warns (GgrustWarning) and draws every row. Use sampling_random instead.

Parameters:

  • n (int) –

    Number of rows to keep.

  • seed (int, default: None ) –

    Seed of the random generator.

  • min_subsample (int, default: None ) –

    Smallest sample per group.

Returns:

  • FeatureSpec –

    The lets_plot spec.

Examples:

>>> from ggrust import *
>>> sampling_random_stratified(100, seed=1).as_dict()
{'name': 'random_stratified', 'n': 100, 'seed': 1}