Adding support for more auto histogram methods

src/hist.jl

@@ -112,6 +112,52 @@ function sturges(n)  # Sturges' formula
     ceil(Integer, log2(n))+1
 end
 
+sturges(v::AbstractVector{T}) where {T <: Real} = sturges(length(v))
+
+function _ptp(v::AbstractVector)
+    e = extrema(v)
+    return e[2] - e[1]
+end
+
+function scott(v::AbstractVector{T}) where {T <: Real}
+    n = length(v)
+    h = 3.5 * std(v) * n^(-1/3)
+    # in the case of a 0 std we need to ensure we 
+    # don't divide by 0
+    if (h>0)
+        return ceil(Integer, _ptp(v)/h)
+    end
+    return 1
+end
+
+function FD(v::AbstractVector{T}) where {T <: Real}
+    n = length(v)
+    h = 2 * iqr(v) * n ^ (-1 / 3)
+
+    if (h > 0)
+        return ceil(Integer, _ptp(v)/h)
+    end
+
+    return 1
+end
+
+bin_estimator(estimator::Int, v::AbstractVector{T}) where {T<:Real} = estimator
+
+function bin_estimator(estimator::Symbol, v::AbstractVector{T}) where {T<:Real}
+    if (estimator == :sturges)
+        nbins = sturges(length(v))
+    elseif (estimator == :scott)
+        nbins = scott(v)
+    elseif (estimator == :FD || estimator == :fd)
+        nbins = FD(v)
+    else
+        throw(ArgumentError("estimator must be one of :sturges, :scott, FD"))
+    end
+    # println("Using $estimator, calculated $nbins")
+    return nbins
+end
+
+
 abstract type AbstractHistogram{T<:Real,N,E} end
 
 # N-dimensional histogram object
@@ -271,12 +317,18 @@ append!(h::AbstractHistogram{T,1}, v::AbstractVector, wv::Union{AbstractVector,A
 
 fit(::Type{Histogram{T}},v::AbstractVector, edg::AbstractVector; closed::Symbol=:left) where {T} =
     fit(Histogram{T},(v,), (edg,), closed=closed)
-fit(::Type{Histogram{T}},v::AbstractVector; closed::Symbol=:left, nbins=sturges(length(v))) where {T} =
-    fit(Histogram{T},(v,); closed=closed, nbins=nbins)
+
+# fit(::Type{Histogram{T}},v::AbstractVector, bins::Symbol; closed::Symbol=:left) where {T} =
+#     fit(Histogram{T},(v,), (edg,), closed=closed, nbins=bin_estimator(bins, v))
+# fit(::Type{Histogram{T}},v::AbstractVector, bins::Int; closed::Symbol=:left) where {T} =
+#     fit(Histogram{T},(v,), (edg,), closed=closed, nbins=bins)
+
+fit(::Type{Histogram{T}},v::AbstractVector; closed::Symbol=:left, nbins=:sturges) where {T} =
+    fit(Histogram{T},(v,); closed=closed, nbins=bin_estimator(nbins, v))
 fit(::Type{Histogram{T}},v::AbstractVector, wv::AbstractWeights, edg::AbstractVector; closed::Symbol=:left) where {T} =
     fit(Histogram{T},(v,), wv, (edg,), closed=closed)
-fit(::Type{Histogram{T}},v::AbstractVector, wv::AbstractWeights; closed::Symbol=:left, nbins=sturges(length(v))) where {T} =
-    fit(Histogram{T}, (v,), wv; closed=closed, nbins=nbins)
+fit(::Type{Histogram{T}},v::AbstractVector, wv::AbstractWeights; closed::Symbol=:left, nbins=:sturges) where {T} =
+    fit(Histogram{T}, (v,), wv; closed=closed, nbins=bin_estimator(nbins, v))
 
 fit(::Type{Histogram}, v::AbstractVector, wv::AbstractWeights{W}, args...; kwargs...) where {W} = fit(Histogram{W}, v, wv, args...; kwargs...)
 

test/hist.jl

@@ -224,4 +224,16 @@ end
     @test StatsBase.midpoints(range(0, stop = 1, length = 5)) == 0.125:0.25:0.875
 end
 
+@testset "Histogram autorange" begin
+
+    # check we still default to sturges
+    @test fit(Histogram,[1:100; 500:1000],closed=:right).weights ==  [100, 0, 0, 0, 1, 100, 100, 100, 100, 100]
+    @test fit(Histogram,[1:100; 500:1000],nbins=:sturges, closed=:right).weights ==  [100, 0, 0, 0, 1, 100, 100, 100, 100, 100]
+
+    @test fit(Histogram,[1:100; 500:1000],nbins=:scott,closed=:right).weights == [100, 0, 101, 200, 200]
+    @test fit(Histogram,[1:100; 500:1000],nbins=:fd,closed=:right).weights == [100, 0, 0, 0, 1, 100, 100, 100, 100, 100]
+
+end
+
+
 end # @testset "StatsBase.Histogram"