rapids_singlecell.pp.scale

rapids_singlecell.pp.scale(data, *, zero_center=True, max_value=None, copy=False, layer=None, obsm=None, mask_obs=None, inplace=True)

Scales matrix to unit variance and clips values

Parameters:

data Union[AnnData, ndarray, csc_matrix, csr_matrix, Array]

The (annotated) data matrix of shape n_obs × n_vars. Rows correspond to cells and columns to genes. If a matrix is passed instead of an AnnData object, the scaled matrix is returned.

zero_center bool (default: True)

If False, omit zero-centering variables, which allows to handle sparse input efficiently.

max_value float | None (default: None)

Clip (truncate) to this value after scaling. If None, do not clip.

copy bool (default: False)

Whether this function should be performed inplace. If an AnnData object is passed, this also determines if a copy is returned. Only applies to AnnData input.

layer str | None (default: None)

If provided, which element of layers to scale.

obsm str | None (default: None)

If provided, which element of obsm to scale.

mask_obs ndarray | str | None (default: None)

Restrict both the derivation of scaling parameters and the scaling itself to a certain set of observations. The mask is specified as a boolean array or a string referring to an array in obs. If the matrix is in csc format and a mask is provided, the matrix will be transformed to csr format.

inplace bool (default: True)

If True, update AnnData with results. Otherwise, return results. See below for details of what is returned. For matrix input the scaled matrix is always returned.

Return type:

Union[spmatrix, ndarray, None]

Returns:

Returns a scaled copy or updates data with a scaled version of the original X and data.layers['layer'], depending on inplace. If a matrix is passed, the scaled matrix is returned.