[Feauture] Confidence interval bands + errorbars

[icweaver]

Howdy, GLM.jl has this in the works. After some discussion on slack, it sounded like this would be a good thing to fold into AoG if it's ever merged. Will keep this as a draft for now.

Below are some brief usage examples on the following sample data:

julia> using AlgebraOfGraphics, CairoMakie, GLM

julia> colors = Makie.wong_colors()

julia> using Random

julia> Random.seed!(111)

julia> df = let
           x = 1:5
           y_err = randn(length(x))
           y = x .+ y_err
           y_unc = abs.(y_err)
           (; x, y, y_unc)
       end

julia> data(df) * mapping(:x, :y) * (
           (visual(Scatter) + mapping(:y_unc) * visual(Errorbars)) * visual(; label = "data") +
           mapping(; weights = :y_unc) * linear() * visual(; color = colors[1], label = "model")
       ) |> draw

Before

After

This uses fweights by default to match current behavior, but different weights can be passed via the new weightkinds keyword, along with an optional new weighttransform keyword to perform any needed transformations before passing to the GLM machinery:

julia> specs = data(df) * mapping(:x, :y) * (
           (visual(Scatter) + mapping(:y_unc) * visual(Errorbars)) * visual(; label = "data") +
           mapping(; weights = :y_unc) * (
               linear(; weightkind = :aweights, weighttransform = x -> inv.(x .^ 2)) * visual(; color = colors[1], label = "aweights") +
               linear(; weightkind = :fweights) * visual(; color = colors[2], label = "fweights") +
               linear(; weightkind = :pweights) * visual(; color = colors[3], label = "pweights")
           )
       ) |> draw

Still playing around with the design. Comments welcome!

Related

• Confidence Interval Band #366

[icweaver]

Whoo, JuliaStats/GLM.jl#487 is in now! I've updated the PR here to match current functionality. Once the design looks ok to y'all, could I have some help with adding any additional docs + desired tests?