empirical.jl and hist.jl

Author: nalimilan

docs/make.jl

@@ -13,7 +13,8 @@ makedocs(
              "scalarstats.md",
              "cov.md",
              "robust.md",
-             "ranking.md"]
+             "ranking.md",
+             "empirical.md"]
 )
 
 deploydocs(

docs/src/empirical.md

@@ -0,0 +1,30 @@
+# Empirical Estimation of Distributions
+
+## Histograms
+
+The `Histogram` type represents data that has been tabulated into intervals
+(known as *bins*) along the real line, or in higher dimensions, over the real
+plane.
+
+Histograms can be fitted to data using the `fit` method.
+
+```@docs
+fit(::Type{Histogram}, args...; kwargs...)
+```
+
+Additional methods
+```@docs
+merge!
+merge
+midpoints
+norm
+normalize
+normalize!
+zero
+```
+
+## Empirical Cumulative Distribution Function
+
+```@docs
+ecdf
+```

docs/src/index.md

@@ -10,6 +10,7 @@ Statistics can be weighted, and several weights types are distinguished to apply
 corrections where necessary.
 
 ```@contents
-Pages = ["weights.md", "scalarstats.md", "cov.md", "robust.md", "ranking.jl"]
+Pages = ["weights.md", "scalarstats.md", "cov.md", "robust.md", "ranking.jl",
+         "empirical.md"]
 Depth = 2
 ```

src/Statistics.jl

@@ -35,8 +35,12 @@ export std, stdm, var, varm, mean!, mean,
     trim, trim!, trimvar, winsor, winsor!,
     # ranking.jl
     ordinalrank, competerank, denserank, tiedrank,
-    # rankcorr
-    corkendall, corspearman
+    # rankcorr.jl
+    corkendall, corspearman,
+    # empirical.jl
+    ecdf, ECDF,
+    # hist.jl
+    fit, AbstractHistogram, Histogram, midpoints, norm, normalize, normalize!
 
 include("common.jl")
 include("weights.jl")
@@ -50,6 +54,8 @@ include("signalcorr.jl")
 include("robust.jl")
 include("ranking.jl")
 include("rankcorr.jl")
+include("empirical.jl")
+include("hist.jl")
 
 ##### mean #####
 

src/empirical.jl

@@ -49,8 +49,8 @@ function is inside the interval ``(0,1)``; the function is defined for the whole
 """
 ecdf(X::RealVector{T}) where T<:Real = ECDF(sort(X))
 
-minimum(ecdf::ECDF) = first(ecdf.sorted_values)
+Base.minimum(ecdf::ECDF) = first(ecdf.sorted_values)
 
-maximum(ecdf::ECDF) = last(ecdf.sorted_values)
+Base.maximum(ecdf::ECDF) = last(ecdf.sorted_values)
 
-extrema(ecdf::ECDF) = (minimum(ecdf), maximum(ecdf))
+Base.extrema(ecdf::ECDF) = (minimum(ecdf), maximum(ecdf))

src/hist.jl

@@ -96,7 +96,7 @@ function histrange(lo::F, hi::F, n::Integer, closed::Symbol=:left) where F
             len += one(F)
         end
     end
-    Base.floatrange(start,step,len,divisor)
+    Base.floatrange(start,step,Int(len),divisor)
 end
 
 histrange(vs::NTuple{N,AbstractVector},nbins::NTuple{N,Integer},closed::Symbol) where {N} =
@@ -397,7 +397,7 @@ arrays appropriately. See description of `normalize` for details. Returns `h`.
                 if mode == :pdf || mode == :density
                     # Divide weights by bin volume, for :pdf also divide by sum of weights
                     SumT = norm_type(h)
-                    vs_0 = (mode == :pdf) ? sum(SumT(x) for x in weights) : one(SumT)
+                    vs_0 = (mode == :pdf) ? sum(SumT, weights) : one(SumT)
                     @inbounds @nloops $N i weights d->(vs_{$N-d+1} = vs_{$N-d} * _edge_binvolume(SumT, edges[d], i_d)) begin
                         (@nref $N weights i) /= $(Symbol("vs_$N"))
                         for A in aux_weights

test/empirical.jl

@@ -1,4 +1,4 @@
-using StatsBase
+using Statistics
 using Test
 
 @testset "ECDF" begin

test/hist.jl

@@ -1,7 +1,7 @@
-using StatsBase
+using Statistics
 using LinearAlgebra, Random, Test
 
-@testset "StatsBase.Histogram" begin
+@testset "Histogram" begin
 
 
 @testset "Histogram binindex and binvolume" begin
@@ -14,15 +14,15 @@ using LinearAlgebra, Random, Test
 
     @test h1 == Histogram(edg1, :left, false)
 
-    @test @inferred StatsBase.binindex(h1, -0.5) == 4
-    @test @inferred StatsBase.binindex(h2, (1.5, 2)) == (8, 3)
+    @test @inferred Statistics.binindex(h1, -0.5) == 4
+    @test @inferred Statistics.binindex(h2, (1.5, 2)) == (8, 3)
 
-    @test [StatsBase.binvolume(h1, i) for i in axes(h1.weights, 1)] ≈ diff(edg1)
-    @test [StatsBase.binvolume(h2, (i,j)) for i in axes(h2.weights, 1), j in axes(h2.weights, 2)] ≈ diff(edg1) * diff(edg2)'
+    @test [Statistics.binvolume(h1, i) for i in axes(h1.weights, 1)] ≈ diff(edg1)
+    @test [Statistics.binvolume(h2, (i,j)) for i in axes(h2.weights, 1), j in axes(h2.weights, 2)] ≈ diff(edg1) * diff(edg2)'
 
-    @test typeof(@inferred(StatsBase.binvolume(h2, (1,1)))) == Float64
-    @test typeof(@inferred(StatsBase.binvolume(h3, (1,1)))) == Float32
-    @test typeof(@inferred(StatsBase.binvolume(Float64, h3, (1,1)))) == Float64
+    @test typeof(@inferred(Statistics.binvolume(h2, (1,1)))) == Float64
+    @test typeof(@inferred(Statistics.binvolume(h3, (1,1)))) == Float32
+    @test typeof(@inferred(Statistics.binvolume(Float64, h3, (1,1)))) == Float64
 end
 
 
@@ -75,44 +75,44 @@ end
 
 @testset "histrange" begin
     # Note: atm histrange must be qualified
-    @test @inferred(StatsBase.histrange(Float64[], 0, :left)) == 0.0:1.0:0.0
-    @test StatsBase.histrange(Float64[1:5;], 1, :left) == 0.0:5.0:10.0
-    @test StatsBase.histrange(Float64[1:10;], 1, :left) == 0.0:10.0:20.0
-    @test StatsBase.histrange(1.0, 10.0, 1, :left) == 0.0:10.0:20.0
-
-    @test StatsBase.histrange([0.201,0.299], 10, :left) == 0.2:0.01:0.3
-    @test StatsBase.histrange([0.2,0.299], 10, :left) == 0.2:0.01:0.3
-    @test StatsBase.histrange([0.2,0.3], 10, :left)  == 0.2:0.01:0.31
-    @test StatsBase.histrange(0.2, 0.3,  10, :left)  == 0.2:0.01:0.31
-    @test StatsBase.histrange([0.2,0.3], 10, :right) == 0.19:0.01:0.3
-    @test StatsBase.histrange(0.2, 0.3,  10, :right) == 0.19:0.01:0.3
-
-    @test StatsBase.histrange([200.1,299.9], 10, :left) == 200.0:10.0:300.0
-    @test StatsBase.histrange([200.0,299.9], 10, :left) == 200.0:10.0:300.0
-    @test StatsBase.histrange([200.0,300.0], 10, :left) == 200.0:10.0:310.0
-    @test StatsBase.histrange([200.0,300.0], 10, :right) == 190.0:10.0:300.0
-
-    @test @inferred(StatsBase.histrange(Int64[1:5;], 1, :left)) == 0:5:10
-    @test StatsBase.histrange(Int64[1:10;], 1, :left) == 0:10:20
-
-    @test StatsBase.histrange([0, 1, 2, 3], 4, :left) == 0.0:1.0:4.0
-    @test StatsBase.histrange([0, 1, 1, 3], 4, :left) == 0.0:1.0:4.0
-    @test StatsBase.histrange([0, 9], 4, :left) == 0.0:5.0:10.0
-    @test StatsBase.histrange([0, 19], 4, :left) == 0.0:5.0:20.0
-    @test StatsBase.histrange([0, 599], 4, :left) == 0.0:200.0:600.0
-    @test StatsBase.histrange([-1, -1000], 4, :left) == -1000.0:500.0:0.0
+    @test @inferred(Statistics.histrange(Float64[], 0, :left)) == 0.0:1.0:0.0
+    @test Statistics.histrange(Float64[1:5;], 1, :left) == 0.0:5.0:10.0
+    @test Statistics.histrange(Float64[1:10;], 1, :left) == 0.0:10.0:20.0
+    @test Statistics.histrange(1.0, 10.0, 1, :left) == 0.0:10.0:20.0
+
+    @test Statistics.histrange([0.201,0.299], 10, :left) == 0.2:0.01:0.3
+    @test Statistics.histrange([0.2,0.299], 10, :left) == 0.2:0.01:0.3
+    @test Statistics.histrange([0.2,0.3], 10, :left)  == 0.2:0.01:0.31
+    @test Statistics.histrange(0.2, 0.3,  10, :left)  == 0.2:0.01:0.31
+    @test Statistics.histrange([0.2,0.3], 10, :right) == 0.19:0.01:0.3
+    @test Statistics.histrange(0.2, 0.3,  10, :right) == 0.19:0.01:0.3
+
+    @test Statistics.histrange([200.1,299.9], 10, :left) == 200.0:10.0:300.0
+    @test Statistics.histrange([200.0,299.9], 10, :left) == 200.0:10.0:300.0
+    @test Statistics.histrange([200.0,300.0], 10, :left) == 200.0:10.0:310.0
+    @test Statistics.histrange([200.0,300.0], 10, :right) == 190.0:10.0:300.0
+
+    @test @inferred(Statistics.histrange(Int64[1:5;], 1, :left)) == 0:5:10
+    @test Statistics.histrange(Int64[1:10;], 1, :left) == 0:10:20
+
+    @test Statistics.histrange([0, 1, 2, 3], 4, :left) == 0.0:1.0:4.0
+    @test Statistics.histrange([0, 1, 1, 3], 4, :left) == 0.0:1.0:4.0
+    @test Statistics.histrange([0, 9], 4, :left) == 0.0:5.0:10.0
+    @test Statistics.histrange([0, 19], 4, :left) == 0.0:5.0:20.0
+    @test Statistics.histrange([0, 599], 4, :left) == 0.0:200.0:600.0
+    @test Statistics.histrange([-1, -1000], 4, :left) == -1000.0:500.0:0.0
 
     # Base issue #13326
-    l,h = extrema(StatsBase.histrange([typemin(Int),typemax(Int)], 10, :left))
+    l,h = extrema(Statistics.histrange([typemin(Int),typemax(Int)], 10, :left))
     @test l <= typemin(Int)
     @test h >= typemax(Int)
 
-    @test_throws ArgumentError StatsBase.histrange([1, 10], 0, :left)
-    @test_throws ArgumentError StatsBase.histrange([1, 10], -1, :left)
-    @test_throws ArgumentError StatsBase.histrange([1.0, 10.0], 0, :left)
-    @test_throws ArgumentError StatsBase.histrange([1.0, 10.0], -1, :left)
-    @test_throws ArgumentError StatsBase.histrange(Float64[],-1, :left)
-    @test_throws ArgumentError StatsBase.histrange([0.], 0, :left)
+    @test_throws ArgumentError Statistics.histrange([1, 10], 0, :left)
+    @test_throws ArgumentError Statistics.histrange([1, 10], -1, :left)
+    @test_throws ArgumentError Statistics.histrange([1.0, 10.0], 0, :left)
+    @test_throws ArgumentError Statistics.histrange([1.0, 10.0], -1, :left)
+    @test_throws ArgumentError Statistics.histrange(Float64[],-1, :left)
+    @test_throws ArgumentError Statistics.histrange([0.], 0, :left)
 end
 
 
@@ -220,8 +220,8 @@ end
 end
 
 @testset "midpoints" begin
-    @test StatsBase.midpoints([1, 2, 4]) == [1.5, 3.0]
-    @test StatsBase.midpoints(range(0, stop = 1, length = 5)) == 0.125:0.25:0.875
+    @test Statistics.midpoints([1, 2, 4]) == [1.5, 3.0]
+    @test Statistics.midpoints(range(0, stop = 1, length = 5)) == 0.125:0.25:0.875
 end
 
-end # @testset "StatsBase.Histogram"
+end # @testset "Statistics.Histogram"

test/runtests.jl

@@ -896,4 +896,6 @@ include("partialcor.jl")
 include("signalcorr.jl")
 include("robust.jl")
 include("ranking.jl")
-include("rankcorr.jl")
+include("rankcorr.jl")
+include("empirical.jl")
+include("hist.jl")