phyloseq (version 1.16.2)

plot_clusgap: Create a ggplot summary of gap statistic results

Description

Create a ggplot summary of gap statistic results

Usage

plot_clusgap(clusgap, title = "Gap Statistic results")

Arguments

clusgap

(Required). An object of S3 class "clusGap", basically a list with components. See the clusGap documentation for more details. In most cases this will be the output of gapstat_ord, or clusGap if you called it directly.

title

(Optional). Character string. The main title for the graphic. Default is "Gap Statistic results".

Value

• A ggplot plot object. The rendered graphic should be a plot of the gap statistic score versus values for k, the number of clusters.

See Also

gapstat_ord

clusGap

ggplot

Examples

# Load and process data
data("soilrep")
soilr = rarefy_even_depth(soilrep, rngseed=888)
print(soilr)
sample_variables(soilr)
# Ordination
sord  = ordinate(soilr, "DCA")
# Gap Statistic
gs = gapstat_ord(sord, axes=1:4, verbose=FALSE)
# Evaluate results with plots, etc.
plot_scree(sord)
plot_ordination(soilr, sord,  color="Treatment")
plot_clusgap(gs)
print(gs, method="Tibs2001SEmax")
# Non-ordination example, use cluster::clusGap function directly
library("cluster")
pam1 = function(x, k){list(cluster = pam(x, k, cluster.only=TRUE))}
gs.pam.RU = clusGap(ruspini, FUN = pam1, K.max = 8, B = 60)
gs.pam.RU
plot(gs.pam.RU, main = "Gap statistic for the 'ruspini' data")
mtext("k = 4 is best .. and  k = 5  pretty close")
plot_clusgap(gs.pam.RU)