library(spatstat)

# Swedish pine data

data(swedishpines)

# Plot the point process

plot(swedishpines)

# Plot the point process with a density estimate

plot(density.ppp(swedishpines))
points(swedishpines)

# You can specify your own sigma

plot(density.ppp(swedishpines, sigma=5))
points(swedishpines)

# An adaptive density estimate

plot(adaptive.density(swedishpines))
points(swedishpines)

# Repeat the randomization and average

plot(adaptive.density(swedishpines, nrep=50))
points(swedishpines)

# Test of CSR based on quadrats,

t = quadrat.test(swedishpines, nx=3, ny=3)
print(t)
plot(t, col='red')
points(swedishpines)


# Some data that is not CSR

p = rSSI(0.05, 200)
print(quadrat.test(p, 3))
plot(quadrat.test(p, 3), col='red')
points(p)

# Some data that is not CSR

p = rThomas(20, 0.1, 10)
print(quadrat.test(p, 3))
plot(quadrat.test(p, 3), col='red')
points(p)

# Point process of location of tropical trees

data(bei)
plot(bei)

# Some measure of the slope of the terrain

Z = bei.extra$grad
plot(Z)
points(bei)

# Do a similar test of CSR but using different regions

b = quantile(Z, probs = (0:4)/4)
Zcut <- cut(Z, breaks = b, labels = 1:4)
V <- tess(image = Zcut)
plot(V)
points(bei)
print(quadrat.test(bei, tess = V))