There are three broad classes of spatial pattern on a continuum from
complete regularity (evenly spaced hexagons where every individual is the same distance from its nearest neighbour) to
complete aggregation (all the individuals clustered into a single clump):
we call these regular, random and aggregated patterns and they look like this:
point <- function(r) {
angle <- runif(1)*2*pi
length <- runif(1)*r
x <- length*sin(angle)
y <- length*cos(angle)
return (data.frame(x,y))
}
e0 <- 10
n0 <- 10
plot(e0,n0,ylab="",xlab="",ylim=c(0,2*n0),xlim=c(0,2*e0),type="n")
n <- 1000
r <- 10
for (i in 1:n) {
a <- point(r)
e <- e0+a[1]
n <- n0+a[2]
points(e,n,pch=16,col="blue")
}
e0 <- 10
n0 <- 10
plot(e0,n0,ylab="",xlab="",ylim=c(0,2*n0),xlim=c(0,2*e0),type="n")
n <- 1000
r <- 10
for (i in 1:n) {
a <- point(r)
e <- e0+a[1]
n <- n0+a[2]
lines(c(e0,e),c(n0,n),col= "red")
}
n <- 10000
side <- 10
library(maptools)
space <- cbind((runif(n)*side),(runif(n)*side))
plot(space)
circle <- function(e,n,r) {
angle <- seq(0,2*pi,2*pi/360)
x - r*sin(angle)
y - r*cos(angle)
return (cbind((x+e),(y+n)))
}
xc - 8
yc <- 8
rc <- 1
outline <- circle(xc,yc,rc)
wanted <- point.in.polygon(space[,1],space[,2],outline[,1],outline[,2])
points(space[,1][wanted==1],space[,2][wanted==1], col="blue",pch=16)
xc <- 5
yc <- 5
rc <- 2
outline<-circle(xc,yc,rc)
wanted<-point.in.polygon(space[,1],space[,2],outline[,1],outline[,2])
points(space[,1][wanted==1],space[,2][wanted==1], col="red",pch=16)
xc - 8
yc <- 8
rc <- 1
outline <- circle(xc,yc,rc)
wanted <- point.in.polygon(space[,1],space[,2],outline[,1],outline[,2])
points(space[,1][wanted==1],space[,2][wanted==1], col="blue",pch=16)
xc <- 5
yc <- 5
rc <- 2
outline<-circle(xc,yc,rc)
wanted<-point.in.polygon(space[,1],space[,2],outline[,1],outline[,2])
points(space[,1][wanted==1],space[,2][wanted==1], col="red",pch=16)