Merge pull request #1240 from Mattriks/Stat_errorbar

Stat.dodge

NEWS.md

@@ -3,6 +3,7 @@ This is a log of major changes in Gadfly between releases. It is not exhaustive.
 Each release typically has a number of minor bug fixes beyond what is listed here.
 
 # Version 1.1.0
+ * Add `Stat.dodge` (#1240) 
  * `Stat.smooth(method=:lm)` confidence bands (#1231)
 
 

docs/src/gallery/geometries.md

@@ -160,15 +160,48 @@ hstack(pa,pb,pc)
 
 ```@example
 using Gadfly, RDatasets, Distributions, Random
-set_default_plot_size(14cm, 8cm)
+set_default_plot_size(21cm, 8cm)
 Random.seed!(1234)
-sds = [1, 1/2, 1/4, 1/8, 1/16, 1/32]
 n = 10
-ys = [mean(rand(Normal(0, sd), n)) for sd in sds]
-ymins = ys .- (1.96 * sds / sqrt(n))
-ymaxs = ys .+ (1.96 * sds / sqrt(n))
-plot(x=1:length(sds), y=ys, ymin=ymins, ymax=ymaxs,
-     Geom.point, Geom.errorbar)
+sds = [1, 1/2, 1/4, 1/8, 1/16, 1/32]
+ys = mean.(rand.(Normal.(0, sds), n))
+df = DataFrame(x=1:length(sds), y=ys,
+  mins=ys.-(1.96*sds/sqrt(n)), maxs=ys.+(1.96*sds/sqrt(n)),
+    g=repeat(["a","b"], inner=3))
+p1 = plot(df, x=1:length(sds), y=:y, ymin=:mins, ymax=:maxs, color=:g, 
+    Geom.point, Geom.errorbar)
+p2 = plot(df, y=1:length(sds), x=:y, xmin=:mins, xmax=:maxs, color=:g, 
+    Geom.point, Geom.errorbar)
+hstack(p1, p2)
+```
+
+```@example
+using Compose, DataFrames, Gadfly, RDatasets, Statistics
+set_default_plot_size(21cm, 8cm)
+salaries = dataset("car","Salaries")
+salaries.Salary /= 1000.0
+salaries.Discipline = ["Discipline $(x)" for x in salaries.Discipline]
+df = by(salaries, [:Rank,:Discipline], :Salary=>mean, :Salary=>std)
+[df[i] = df.Salary_mean.+j*df.Salary_std for (i,j) in zip([:ymin, :ymax], [-1, 1.0])]
+df[:label] = string.(round.(Int, df.Salary_mean))
+
+p1 = plot(df, x=:Discipline, y=:Salary_mean, color=:Rank, 
+    Scale.x_discrete(levels=["Discipline A", "Discipline B"]),
+    ymin=:ymin, ymax=:ymax, Geom.errorbar, Stat.dodge,
+    Geom.bar(position=:dodge), 
+    Scale.color_discrete(levels=["Prof", "AssocProf", "AsstProf"]),
+    Guide.colorkey(title="", pos=[0.76w, -0.38h]),
+    Theme(bar_spacing=0mm, stroke_color=c->"black")
+)
+p2 = plot(df, y=:Discipline, x=:Salary_mean, color=:Rank, 
+    Coord.cartesian(yflip=true), Scale.y_discrete,
+    xmin=:ymin, xmax=:ymax, Geom.errorbar, Stat.dodge(axis=:y),
+    Geom.bar(position=:dodge, orientation=:horizontal), 
+    Scale.color_discrete(levels=["Prof", "AssocProf", "AsstProf"]),
+    Guide.yticks(orientation=:vertical), Guide.ylabel(nothing),
+    Theme(bar_spacing=0mm, stroke_color=c->"gray")
+)
+hstack(p1,p2)
 ```
 
 

docs/src/gallery/statistics.md

@@ -35,6 +35,33 @@ p2 = plot(vcat(Db...), x=:x, color=:u,
 hstack(p1,p2)
 ```
 
+## [`Stat.dodge`](@ref)
+
+```@example
+using DataFrames, Gadfly, RDatasets, Statistics
+set_default_plot_size(21cm, 8cm)
+salaries = dataset("car","Salaries")
+salaries.Salary /= 1000.0
+salaries.Discipline = ["Discipline $(x)" for x in salaries.Discipline]
+df = by(salaries, [:Rank,:Discipline], :Salary=>mean, :Salary=>std)
+[df[i] = df.Salary_mean.+j*df.Salary_std for (i,j) in zip([:ymin, :ymax], [-1, 1.0])]
+df[:label] = string.(round.(Int, df.Salary_mean))
+
+p1 = plot(df, x=:Discipline, y=:Salary_mean, color=:Rank, 
+    Scale.x_discrete(levels=["Discipline A", "Discipline B"]),
+    label=:label, Geom.label(position=:centered), Stat.dodge(position=:stack),
+    Geom.bar(position=:stack)
+)
+p2 = plot(df, y=:Discipline, x=:Salary_mean, color=:Rank, 
+    Coord.cartesian(yflip=true), Scale.y_discrete,
+    label=:label, Geom.label(position=:right), Stat.dodge(axis=:y),
+    Geom.bar(position=:dodge, orientation=:horizontal), 
+    Scale.color_discrete(levels=["Prof", "AssocProf", "AsstProf"]),
+    Guide.yticks(orientation=:vertical), Guide.ylabel(nothing)
+)
+hstack(p1, p2)
+```
+
 ## [`Stat.qq`](@ref)
 
 ```@example

src/geom/bar.jl

@@ -21,7 +21,7 @@ Draw bars of height `y` centered at positions `x`, or from `xmin` to `xmax`.
 If orientation is `:horizontal` switch x for y.  Optionally categorically
 groups bars using the `color` aesthetic.  If `position` is `:stack` they will
 be placed on top of each other;  if it is `:dodge` they will be placed side by
-side.
+side.  For labelling dodged or stacked bar plots see [`Stat.dodge`](@ref).
 """
 const bar = BarGeometry
 
@@ -170,7 +170,7 @@ function render_dodged_bar(geom::BarGeometry,
                                     orientation::Symbol)
     # preserve factor orders of pooled data arrays
     if isa(aes.color, IndirectArray)
-        idxs = sortperm(aes.color.index, rev=true)
+        idxs = sortperm(aes.color.index, rev=false)
     else
         idxs = 1:length(aes.color)
     end

src/geom/errorbar.jl

@@ -1,7 +1,9 @@
 struct ErrorBarGeometry <: Gadfly.GeometryElement
+    default_statistic::Gadfly.StatisticElement
     tag::Symbol
 end
-ErrorBarGeometry(; tag=empty_tag) = ErrorBarGeometry(tag)
+ErrorBarGeometry(default_statistic=Gadfly.Stat.identity(); tag=empty_tag) = 
+    ErrorBarGeometry(default_statistic, tag)
 
 
 struct XErrorBarGeometry <: Gadfly.GeometryElement
@@ -42,9 +44,14 @@ color them with `color`.
 """
 const yerrorbar = YErrorBarGeometry
 
-element_aesthetics(::ErrorBarGeometry) = [:x, :y, :xmin, :xmax, :ymin, :ymax]
-element_aesthetics(::XErrorBarGeometry) = [:y, :xmin, :xmax]
-element_aesthetics(::YErrorBarGeometry) = [:x, :ymin, :ymax]
+
+
+
+element_aesthetics(::ErrorBarGeometry) = [:x, :y, :xmin, :xmax, :ymin, :ymax, :color]
+element_aesthetics(::XErrorBarGeometry) = [:y, :xmin, :xmax, :color]
+element_aesthetics(::YErrorBarGeometry) = [:x, :ymin, :ymax, :color]
+default_statistic(geom::ErrorBarGeometry) = geom.default_statistic
+
 
 # Generate a form for the errorbar geometry.
 #
@@ -58,12 +65,12 @@ element_aesthetics(::YErrorBarGeometry) = [:x, :ymin, :ymax]
 #
 function render(geom::ErrorBarGeometry, theme::Gadfly.Theme, aes::Gadfly.Aesthetics)
     # check for X and Y error bar aesthetics
-    if isempty(Gadfly.undefined_aesthetics(aes, element_aesthetics(xerrorbar())...))
+    if isempty(Gadfly.undefined_aesthetics(aes, :y, :xmin, :xmax))
         xctx = render(xerrorbar(), theme, aes)
     else
         xctx = nothing
     end
-    if isempty(Gadfly.undefined_aesthetics(aes, element_aesthetics(yerrorbar())...))
+    if isempty(Gadfly.undefined_aesthetics(aes, :x, :ymin, :ymax))
         yctx = render(yerrorbar(), theme, aes)
     else
         yctx = nothing
@@ -72,10 +79,8 @@ function render(geom::ErrorBarGeometry, theme::Gadfly.Theme, aes::Gadfly.Aesthet
 end
 
 function render(geom::YErrorBarGeometry, theme::Gadfly.Theme, aes::Gadfly.Aesthetics)
-    Gadfly.assert_aesthetics_defined("Geom.errorbar", aes,
-                                     element_aesthetics(geom)...)
-    Gadfly.assert_aesthetics_equal_length("Geom.errorbar", aes,
-                                          element_aesthetics(geom)...)
+    Gadfly.assert_aesthetics_defined("Geom.errorbar", aes, :x, :ymin, :ymax)
+    Gadfly.assert_aesthetics_equal_length("Geom.errorbar", aes, :x, :ymin, :ymax)
 
     default_aes = Gadfly.Aesthetics()
     default_aes.color = discretize_make_ia(RGB{Float32}[theme.default_color])
@@ -112,10 +117,8 @@ function render(geom::YErrorBarGeometry, theme::Gadfly.Theme, aes::Gadfly.Aesthe
 end
 
 function render(geom::XErrorBarGeometry, theme::Gadfly.Theme, aes::Gadfly.Aesthetics)
-    Gadfly.assert_aesthetics_defined("Geom.errorbar", aes,
-                                     element_aesthetics(geom)...)
-    Gadfly.assert_aesthetics_equal_length("Geom.errorbar", aes,
-                                          element_aesthetics(geom)...)
+    Gadfly.assert_aesthetics_defined("Geom.errorbar", aes, :y, :xmin, :xmax)
+    Gadfly.assert_aesthetics_equal_length("Geom.errorbar", aes, :y, :xmin, :xmax)
 
     default_aes = Gadfly.Aesthetics()
     default_aes.color = discretize_make_ia(RGB{Float32}[theme.default_color])

src/statistics.jl

@@ -2019,6 +2019,63 @@ function apply_statistic(stat::EllipseStatistic,
     aes.y = ellipse_y
     linestyle_scale = get(scales, :linestyle, Scale.linestyle_discrete())
     Scale.apply_scale(linestyle_scale, [aes], Gadfly.Data(linestyle = aes.linestyle))
+end
+
+
+struct DodgeStatistic <: Gadfly.StatisticElement
+    position::Symbol
+    axis::Symbol
+end
+DodgeStatistic(; position::Symbol=:dodge, axis::Symbol=:x) = DodgeStatistic(position, axis)
+
+input_aesthetics(stat::DodgeStatistic) = [:x, :y]
+output_aesthetics(stat::DodgeStatistic) = [:x, :y]
+default_scales(stat::DodgeStatistic) = [Gadfly.Scale.x_continuous(), Gadfly.Scale.y_continuous()]
+
+"""
+    Stat.dodge[(; position=:dodge, axis=:x)]
+
+Transform the points in $(aes2str(input_aesthetics(dodge()))) into set of dodged or stacked points
+ in $(aes2str(output_aesthetics(dodge()))).  `position` is `:dodge` or `:stack`.
+`axis` is `:x` or `:y`.
+"""
+const dodge = DodgeStatistic
+
+
+function apply_statistic(stat::DodgeStatistic,
+                            scales::Dict{Symbol, Gadfly.ScaleElement},
+                            coord::Gadfly.CoordinateElement,
+                            aes::Gadfly.Aesthetics)
+
+    aes.color==nothing && return
+    nbars = length(unique(aes.color))
+    othervar = (stat.axis == :x) ? :y : :x
+    vals = getfield(aes, stat.axis)
+
+    if stat.position==:dodge
+        nbars == length(aes.color) && return
+        offset = range(-0.5+0.5/nbars, 0.5, step=1/nbars)
+        dodge = getindex(offset, aes.color.index)
+        setfield!(aes, stat.axis, vals.+dodge)
+    elseif stat.position==:stack
+        ovals = getfield(aes, othervar)
+        if nbars == length(aes.color)
+            setfield!(aes, othervar, 0.5*ovals)
+        else
+            idxs = isa(aes.color, IndirectArray) ? sortperm(aes.color.index, rev=true) : 1:length(aes.color)
+            idxs2 = sortperm(idxs)
+            m1 = reshape(idxs, :, nbars)
+            m2 = cumsum(ovals[m1], dims=2) .- 0.5*ovals[m1]
+            setfield!(aes, othervar, m2[idxs2])
+        end
+    else
+        error("position can be :dodge (default) or :stack")
     end
+end
+
+
+
+
+
 
 end # module Stat

test/testscripts/stat_dodge.jl

@@ -0,0 +1,25 @@
+using Compose, DataFrames, Gadfly, RDatasets, Statistics
+set_default_plot_size(21cm, 8cm)
+
+salaries = dataset("car","Salaries")
+salaries.Salary /= 1000.0
+salaries.Discipline = ["Discipline $(x)" for x in salaries.Discipline]
+df = by(salaries, [:Rank,:Discipline], :Salary=>mean, :Salary=>std)
+[df[i] = df.Salary_mean.+j*df.Salary_std for (i,j) in zip([:ymin, :ymax], [-1, 1.0])]
+df[:label] = string.(round.(Int, df.Salary_mean))
+
+p1 = plot(df, x=:Discipline, y=:Salary_mean, color=:Rank, 
+    Scale.x_discrete(levels=["Discipline A", "Discipline B"]),
+    ymin=:ymin, ymax=:ymax, Geom.errorbar, Stat.dodge,
+    Geom.bar(position=:dodge), 
+    Scale.color_discrete(levels=["Prof", "AssocProf", "AsstProf"]),
+    Guide.colorkey(title="", pos=[0.76w, -0.38h]),
+    Theme(bar_spacing=0mm, stroke_color=c->"black")
+)
+p2 = plot(df, x=:Salary_mean, y=:Discipline, color=:Rank, 
+    Scale.y_discrete(levels=["Discipline A", "Discipline B"]),
+    label=:label, Geom.label(position=:centered), Stat.dodge(position=:stack, axis=:y),
+    Geom.bar(position=:stack, orientation=:horizontal),
+    Guide.yticks(orientation=:vertical), Guide.ylabel(nothing)
+)
+hstack(p1, p2)