scib_metrics.utils.compute_simpson_index#
- scib_metrics.utils.compute_simpson_index(knn_dists, knn_idx, row_idx, labels, n_labels, perplexity=30, tol=1e-05)[source]#
Compute the Simpson index for each cell.
- Parameters:
knn_dists (
Union
[ndarray
,Array
]) – KNN distances of size (n_cells, n_neighbors).knn_idx (
Union
[ndarray
,Array
]) – KNN indices of size (n_cells, n_neighbors) corresponding to distances.row_idx (
Union
[ndarray
,Array
]) – Idx of each row (n_cells, 1).labels (
Union
[ndarray
,Array
]) – Cell labels of size (n_cells,).n_labels (
int
) – Number of labels.perplexity (
float
(default:30
)) – Measure of the effective number of neighbors.tol (
float
(default:1e-05
)) – Tolerance for binary search.
- Return type:
- Returns:
simpson_index Simpson index of size (n_cells,).