neiinfo: Compute info on 'neighbor widths'

In ksharp: Cluster Sharpening

Description

This function provides information on how well each data point belongs to its cluster. For each query point, the function considers n of its nearest neighbors. The neighbor widths are defined as the fraction of those neighbors that belong to the same cluster as the query point. These values are termed 'widths' in analogy to silhouette widths, another measure of cluster membership.

Usage

neiinfo(cluster, dist)

Arguments

cluster	vector with assignments of data elements to clusters
dist	distance object or matrix

Details

The function follows a similar signature as silinfo from this package.

Value

list with component widths. The wdiths object is a matrix with one row per data item, wth column neighborhood holding the sharpness value.

Examples

# construct a manual clustering of the iris dataset
iris.data = iris[, 1:4]
rownames(iris.data) = paste0("iris_", seq_len(nrow(iris)))
iris.dist = dist(iris.data)
iris.clusters = setNames(as.integer(iris$Species), rownames(iris.data))

# compute neighbor-based sharpness widths
neiinfo(iris.clusters, iris.dist)

ksharp documentation built on Jan. 26, 2020, 5:06 p.m.