scanpy.Neighbors

class scanpy.Neighbors(adata, *, n_dcs=None, use=None, diffmap=None, neighbors_key=None)

Bases:

Data represented as graph of nearest neighbors.

Represent a data matrix as a graph of nearest neighbor relations (edges) among data points (nodes).

Parameters:

adata AnnData

Annotated data object.

n_dcs int | None (default: None)

Number of diffusion components to use.

use GraphAcc | str | None (default: None)

The neighborhood graph (connectivities) to use, e.g. A.obsp['k'], by default the one neighbors() wrote by default. Distances and parameters are found where neighbors() put them alongside it, if they exist.

diffmap MultiAcc | str | None (default: None)

Where diffmap() wrote its results, i.e. the out passed to it: None for the default place, or an accessor like A.obsm['k'].

neighbors_key str | None (default: None)

Where to look in .uns and .obsp for neighbors data.

Attributes

connectivities	Connectivities between data points (sparse matrix).
distances	Distances between data points (sparse matrix).
distances_dpt	DPT distances.
eigen_basis	Eigen basis of transition matrix.
eigen_values	Eigen values of transition matrix.
rp_forest	PyNNDescent index.
transitions	Transition matrix (sparse matrix).
transitions_sym	Symmetrized transition matrix (sparse matrix).

Methods

compute_eigen(*[, n_comps, sort, sym])	Compute eigen decomposition of transition matrix.
compute_neighbors([n_neighbors, n_pcs, use, ...])	Compute distances and connectivities of neighbors.
compute_transitions(*[, density_normalize])	Compute transition matrix.
to_igraph()	Generate igraph from connectiviies.