%useLatestDescriptors
%use lets-plot

import java.util.Random

val N = 5000 
val smallGroup = 3
val largeGroup = N - smallGroup

val rand = Random(123)
val data = mapOf (
    "x" to List(N) { rand.nextGaussian() },
    "y" to List(N) { rand.nextGaussian() },
    "cond" to List(smallGroup) { 'A' } + List(largeGroup) { 'B' }
)

// Data points in group 'A' (small group) are overplotted by the dominant group 'B'.
val p = ggplot(data) { x="x"; y="y"; color="cond" } + 
        scaleColorManual(values=listOf("red", "#1C9E77"), breaks=listOf('A', 'B'))
p + geomPoint(size=5, alpha=.2)

// The 'random' sampling loses the group 'A' altogether.
p + geomPoint(size=5, sampling=samplingRandom(50, seed=2))

// Stratified sampling ensures that group 'A' is represented.
p + geomPoint(size=5, sampling=samplingRandomStratified(50, seed=2))