SpaMetric.reference_centers#

SpaMetric.reference_centers(adata, n_centers, method='MiniBatchKMeans', n_pcs=None, use_rep=None, random_state=0, copy=False)[source]#

Select reference centers for mini-batch metric learning.

Parameters:
adata : AnnData

Annotated data matrix.

n_centers : int

Number of reference centers to be selected.

method : {‘MiniBatchKMeans’, ‘KMeans’, ‘Random’}Literal[‘MiniBatchKMeans’, ‘KMeans’, ‘Random’] (default: 'MiniBatchKMeans')

Method to use for reference center selection.

  • 'MiniBatchKMeans'

    Use scikit-learn MiniBatchKMeans to select reference centers.

  • 'KMeans'

    Use scikit-learn KMeans to select reference centers.

  • 'Random'

    Randomly choose reference centers.

n_pcs : int | NoneOptional[int] (default: None)

Use this many PCs. If n_pcs==0 use .X if use_rep is None.

use_rep : str | NoneOptional[str] (default: None)

Use the indicated representation. ‘X’ or any key for .obsm is valid. If None, the representation is chosen automatically: For .n_vars < 50, .X is used, otherwise ‘X_pca’ is used. If ‘X_pca’ is not present, it’s computed with default parameters.

random_state : int (default: 0)

Change to use different initial states for the optimization.

copy : bool (default: False)

Return a copy instead of writing to adata.

Return type:

AnnData | NoneOptional[AnnData]

Returns:

Depending on copy, returns or updates adata with the following fields.

.obs[‘reference_centers’]

Boolean indicator of reference centers.