AnnoyIndex: The AnnoyIndex class

In LTLA/kmknn: Nearest Neighbor Detection for Bioconductor Packages

The AnnoyIndex class

Description

A class to hold indexing structures for the Annoy algorithm for approximate nearest neighbor identification.

Usage

AnnoyIndex(data, path, search.mult = 50, NAMES = NULL, distance = "Euclidean")

Arguments

data	A numeric matrix with data points in columns and dimensions in rows.
path	A string specifying the path to the index file.
search.mult	Numeric scalar, multiplier for the number of points to search.
NAMES	A character vector of sample names or NULL.
distance	A string specifying the distance metric to use.

Details

The AnnoyIndex class holds the indexing structure required to run the Annoy algorithm. Users should never need to call the constructor explicitly, but should generate instances of AnnoyIndex classes with buildAnnoy.

Users can get values from an AnnoyIndex object with the usual [[ syntax. All parameters listed in the constructor can be extracted in this manner.

Value

An instance of the AnnoyIndex class.

Author(s)

Aaron Lun

See Also

buildAnnoy, for the index construction.

BiocNeighborIndex, for the parent class and its available methods.

Examples

example(buildAnnoy)
out[['path']]
bndistance(out)
str(bndata(out))

LTLA/kmknn documentation built on Feb. 5, 2024, 6:03 p.m.