dbscan (version 0.9-8)

hullplot: Plot Convex Hulls of Clusters

Description

This function produces a two-dimensional scatter plot with added convex hulls for clusters.

Usage

hullplot(x, cl, col = NULL, cex = 0.5, hull_lwd = 1, hull_lty = 1,
	 main = "Convex Cluster Hulls", solid=FALSE, alpha = .2, ...)

Arguments

x

a data matrix (only the first two columns are used to produce the scatter plot).

cl

a clustering. Either a numeric cluster assignment vector or a clustering object (a list with an element named cluster).

col

colors used for clusters. Defaults to the standard palette. The first color is used for noise/unassigned points (cluster id 0).

cex

expansion factor for symbols.

hull_lwd, hull_lty

line width and line type used for the convex hull.

main

main title.

solid, alpha

draw filled polygons instead of lines for the convex hulls. alpha controls the alpha shading.

...

additional arguments passed on to plot.

Examples

set.seed(2)
n <- 400

x <- cbind(
  x = runif(4, 0, 1) + rnorm(n, sd=0.1),
  y = runif(4, 0, 1) + rnorm(n, sd=0.1)
  )
cl <- rep(1:4, time = 100)

### original data with true clustering
### (also with differnt symbols, just the hulls or polygons)
hullplot(x, cl, main = "True clusters")
hullplot(x, cl, main = "True clusters", pch = cl)
hullplot(x, cl, main = "True clusters", pch = NA)
hullplot(x, cl, main = "True clusters", solid = TRUE, hull_lwd = 0)


### run some clustering algorithms and plot the resutls
db <- dbscan(x, eps = .07, minPts = 10)
hullplot(x, db, main = "DBSCAN")

op <- optics(x, eps = 10, minPts = 10, eps_cl = 0.07)
hullplot(x, op, main = "OPTICS")

opXi <- opticsXi(op, xi = 0.05)
hullplot(x, opXi, main = "OPTICSXi")

km <- kmeans(x, centers = 4)
hullplot(x, km, main = "k-means")

hc <- cutree(hclust(dist(x)), k = 4)
hullplot(x, hc, main = "Hierarchical Clustering")