generate_nn_groups: Given an n-dimensional matrix, try some KNN-esque clustering...

In elsayed-lab/hpgltools: A pile of (hopefully) useful R functions

Given an n-dimensional matrix, try some KNN-esque clustering on it.

Description

I want some functions to help me understand clustering. This is a first pass at that goal.

Usage

generate_nn_groups(
  mtrx,
  resolution = 1,
  k = 10,
  type = "snn",
  full = TRUE,
  merge_to = NULL,
  ...
)

Arguments

mtrx	Matrix to cluster, usually 2d from a point plot.
resolution	Used after cluster generation for making neighbor groups.
k	Used during cluster generation.
type	Define the type of clustering to perform, currently only KNN/SNN
full	Get the full set of metrics from bluster.
merge_to	Use the neighborhood collapse function to set a hard ceiling on the number of clusters in the final result.
...	Extra args for bluster.

Value

List containing the resulting groups and some information about them.

elsayed-lab/hpgltools documentation built on May 9, 2024, 5:02 a.m.