db_kmeans: Density-based k-means clustering

In kbrulois/Dufy: A set of tools and algorithms for reducing the size of large datasets in a density-aware manner

Density-based k-means clustering

Description

This algorithm performs k-means clustering and sub-clustering such that the size of each cluster is proportional to the local density. This is done iteratively and the initial size of the kmeans clusters is updated until the desired number of total clusters is reached.

Usage

db_kmeans(data = dat, clusters = 400, d = NULL, iter_max = 100, label = "")

Arguments

data	A numeric matrix of data where cells correspond to rows and genes correspond to columns
clusters	The number of clusters
d	A numeric vector of density values corresponding to rows of data.
iter_max	The maximum number of iterations allowed.
label	(Optional) A label to be prepended to cluster names and used in messages

Value

A list that includes the following elements:

cluster

A vector of length nrow(data) containing cluster assignments.

d

A vector of length nrow(data) containing density values.

Author(s)

Kevin Brulois

kbrulois/Dufy documentation built on May 4, 2022, 3:54 a.m.