rapids_singlecell.pp.normalize_total

rapids_singlecell.pp.normalize_total(adata, *, target_sum=None, layer=None, inplace=True, copy=False)

Normalizes rows in matrix so they sum to target_sum

Parameters:

adata AnnData

AnnData object

target_sum int | None (default: None)

If None, after normalization, each observation (cell) has a total count equal to the median of total counts for observations (cells) before normalization.

layer int | str (default: None)

Layer to normalize instead of X. If None, X is normalized.

inplace bool (default: True)

Whether to update adata or return the matrix.

copy bool (default: False)

Whether to return a copy or update adata. Not compatible with inplace=False.

Return type:

AnnData | sparse.csr_matrix | cp.ndarray | None

Returns:

Returns a normalized copy or updates adata with a normalized version of the original adata.X and adata.layers['layer'], depending on inplace.