computes shared nearest neighbors from embedding.
Arguments
- x
A numeric matrix (with features as columns and items as rows) from which nearest neighbors will be computed.
- k
The number of nearest neighbors.
- type
A string specifying the type of weighting scheme to use for shared neighbors. Possible choices include "rank", "number", and "jaccard". See
typeinbluster::neighborsToSNNGraph()for details.- BNPARAM
A BiocNeighbors parameter object to compute kNNs. Ignored unless the input is a matrix or data.frame. If omitted, the Annoy approximation will be used if there are more than 500 elements.
Examples
d1 <- mockData()
emb2snn(as.matrix(d1[,seq_len(2)]),k=5)
#> IGRAPH 0bd1360 U-W- 40 257 --
#> + attr: weight (e/n)
#> + edges from 0bd1360:
#> [1] 1-- 3 3-- 4 2-- 4 1-- 5 3-- 6 1-- 6 4-- 6 1-- 7 5-- 7 6-- 7
#> [11] 3-- 7 4-- 7 4-- 8 3-- 8 7-- 8 5-- 9 7-- 9 8-- 9 2--10 3--10
#> [21] 6--10 8--11 9--11 7--11 3--11 4--11 1--12 3--12 6--12 7--12
#> [31] 4--12 8--12 11--12 2--13 10--13 4--13 4--14 8--14 11--14 9--14
#> [41] 2--15 10--15 13--15 4--15 3--15 8--15 2--16 4--16 13--16 15--16
#> [51] 10--16 3--16 8--16 3--17 6--17 10--17 12--17 4--17 1--17 7--17
#> [61] 17--18 1--18 6--18 12--18 3--18 7--18 7--19 9--19 11--19 8--19
#> [71] 5--19 3--19 4--19 12--19 14--19 1--19 2--20 10--20 13--20 15--20
#> + ... omitted several edges