Density contours: geom_density_2d

Mix.install([
  {:giggly, path: Path.join(__DIR__, "..")},
  {:kino, "~> 0.19"}
  ])

About this notebook

This notebook follows the examples on ggplot2's reference page for geom_density_2d(), which covers geom_density_2d_filled(), stat_density_2d() and stat_density_2d_filled() too, in the order the page gives them. Each example shows ggplot2's code first and then Giggly's. An example Giggly cannot draw yet keeps its ggplot2 code and names what it is waiting for, so the page is also a list of what remains.

These estimate the density of points in two dimensions, with MASS::kde2d(), and draw it as contours: geom_density_2d() as lines and geom_density_2d_filled() as filled bands. They are the two-dimensional geom_density(), and a way through overplotting. With contouring turned off, the stats give the density on a grid for other geoms to draw. Giggly has none of this yet.

Contour lines

m <- ggplot(faithful, aes(x = eruptions, y = waiting)) +
 geom_point() +
 xlim(0.5, 6) +
 ylim(40, 110)
# contour lines
m + geom_density_2d()

Not in Giggly yet: geom_density_2d() and the faithful dataset.

Contour bands

# contour bands
m + geom_density_2d_filled(alpha = 0.5)

Not in Giggly yet: geom_density_2d_filled() and the faithful dataset.

Bands and lines

# contour bands and contour lines
m + geom_density_2d_filled(alpha = 0.5) +
  geom_density_2d(linewidth = 0.25, colour = "black")

Not in Giggly yet: geom_density_2d_filled() and geom_density_2d(), and the faithful dataset.

Contours for each cut

R samples 1,000 of the diamonds at random, from a seed.

set.seed(4393)
dsmall <- diamonds[sample(nrow(diamonds), 1000), ]
d <- ggplot(dsmall, aes(x, y))
# If you map an aesthetic to a categorical variable, you will get a
# set of contours for each value of that variable
d + geom_density_2d(aes(colour = cut))

Not in Giggly yet: geom_density_2d().

Filled contours in facets

# If you draw filled contours across multiple facets, the same bins are
# used across all facets
d + geom_density_2d_filled() + facet_wrap(vars(cut))

The facets are in Giggly: facet_wrap(vars(cut)) is Giggly.Plot.facet_wrap(plot, :cut). Not in Giggly yet: geom_density_2d_filled().

What the contours measure

# If you want to make sure the peak intensity is the same in each facet,
# use `contour_var = "ndensity"`.
d + geom_density_2d_filled(contour_var = "ndensity") + facet_wrap(vars(cut))
# If you want to scale intensity by the number of observations in each group,
# use `contour_var = "count"`.
d + geom_density_2d_filled(contour_var = "count") + facet_wrap(vars(cut))

Not in Giggly yet: geom_density_2d_filled() and its contour_var option.

The density as tiles

# If we turn contouring off, we can use other geoms, such as tiles:
d + stat_density_2d(
  geom = "raster",
  aes(fill = after_stat(density)),
  contour = FALSE
) + scale_fill_viridis_c()

Not in Giggly yet: stat_density_2d() and its contour option, giving a stat a geom by name, here geom = "raster", and geom_raster().

The density as points

# Or points:
d + stat_density_2d(geom = "point", aes(size = after_stat(density)), n = 20, contour = FALSE)

Not in Giggly yet: stat_density_2d() and its n and contour options, and giving a stat a geom by name, here geom = "point".