simplex_uniform_kraemer

mlquantify.utils.simplex_uniform_kraemer(n_dim: int, n_prev: int, n_iter: int, min_val: float = 0.0, max_val: float = 1.0, max_tries: int = 1000, random_state: int | None = None) → ndarray

Generates n_prev prevalence vectors of n_dim classes uniformly distributed on the simplex, with optional lower and upper bounds.

Based on the algorithm of Kramer et al. for uniform sampling on a simplex.

Parameters:

n_dimint

Number of dimensions (classes).

n_prevint

Number of prevalence vectors to generate.

min_valfloat, optional

Minimum allowed prevalence for each class (default=0.0).

max_valfloat, optional

Maximum allowed prevalence for each class (default=1.0).

max_triesint, optional

Maximum number of sampling iterations to reach the target n_prev.

Returns:

np.ndarray

Array of shape (n_prev, n_dim) with valid prevalence vectors.