stat-density-ridges
Ridgeline statistic: Gaussian kernel density estimate of x per y bucket.
For every distinct y value, emits n evenly spaced rows along x where height is the estimated density scaled to a shared maximum of 1 across all buckets, plus the after-stat columns _density (estimated density), _scaled (density scaled per bucket), and _n (the bucket’s observation count).
(R’s bw.nrd0); pass a positive number to fix it.
adjust: 0.5 halves the smoothing.
per bucket.
false (default) extends the grid by three bandwidths on each side so every ridge decays to its baseline.
Usage
stat-density-ridges(
bw: auto,
adjust: 1,
n: 512,
trim: false,
)Parameters
| Parameter | Default | Description |
|---|---|---|
bw |
auto |
Kernel bandwidth. auto applies Silverman’s rule of thumb |
adjust |
1 |
Bandwidth multiplier: the kernels use adjust * bw, so |
n |
512 |
Number of evenly spaced grid points the density is evaluated at |
trim |
false |
Whether to restrict each curve to its bucket’s x range. |
Returns
Statistic object with name: "density-ridges", consumed by geom-density-ridges.
Outputs
x.y.height._density._scaled._n.
Examples
Sharper ridges via adjust on the backing statistic.
#let xs = (1, 2, 2, 3, 5, 6, 6, 7)
#let d = ()
#for (i, grp) in ("a", "b", "c").enumerate() {
for x in xs {
d.push((grp: grp, x: x + i))
}
}
#plot(
data: d,
mapping: aes(x: "x", y: "grp"),
layers: (geom-density-ridges(scale: 1.4, stat: stat-density-ridges(adjust: 0.5)),),
scales: scales(y: scale-discrete(expand: (auto, 45%))),
width: 10cm,
height: 6cm,
)
