Creates independent, boundary-concentrated, or coherent-patch errors for mask-cleaning experiments.
Usage
corrupt_categorical_mask(
mask,
mechanism = c("impulse", "boundary", "patch"),
rate = 0.15,
seed = 1L
)
Arguments
- mask
A reference categorical matrix or three-dimensional array.
- mechanism
One of "impulse", "boundary", or "patch".
- rate
Fraction of non-missing cells whose labels are replaced.
- seed
One integer random seed.
Value
A mask with the same representation as mask and a reproducible set of changed labels. Exactly round(rate * n) non-missing cells are changed while at least one correct exemplar of every reference class is retained; a rate that makes this impossible is rejected.