move base/statistics.jl to Statistics stdlib

fix JuliaLang#27374

base/deprecated.jl

@@ -293,12 +293,6 @@ deprecate(Base, :DSP, 2)
 using .DSP
 export conv, conv2, deconv, filt, filt!, xcorr
 
-# PR #21709
-@deprecate cov(x::AbstractVector, corrected::Bool) cov(x, corrected=corrected)
-@deprecate cov(x::AbstractMatrix, vardim::Int, corrected::Bool) cov(x, dims=vardim, corrected=corrected)
-@deprecate cov(X::AbstractVector, Y::AbstractVector, corrected::Bool) cov(X, Y, corrected=corrected)
-@deprecate cov(X::AbstractVecOrMat, Y::AbstractVecOrMat, vardim::Int, corrected::Bool) cov(X, Y, dims=vardim, corrected=corrected)
-
 # PR #22325
 # TODO: when this replace is removed from deprecated.jl:
 # 1) rename the function replace_new from strings/util.jl to replace
@@ -1372,16 +1366,6 @@ export readandwrite
 @deprecate findmax(A::AbstractArray, dims) findmax(A, dims=dims)
 @deprecate findmin(A::AbstractArray, dims) findmin(A, dims=dims)
 
-@deprecate mean(A::AbstractArray, dims) mean(A, dims=dims)
-@deprecate varm(A::AbstractArray, m::AbstractArray, dims; kwargs...) varm(A, m; kwargs..., dims=dims)
-@deprecate var(A::AbstractArray, dims; kwargs...) var(A; kwargs..., dims=dims)
-@deprecate std(A::AbstractArray, dims; kwargs...) std(A; kwargs..., dims=dims)
-@deprecate cov(X::AbstractMatrix, dim::Int; kwargs...) cov(X; kwargs..., dims=dim)
-@deprecate cov(x::AbstractVecOrMat, y::AbstractVecOrMat, dim::Int; kwargs...) cov(x, y; kwargs..., dims=dim)
-@deprecate cor(X::AbstractMatrix, dim::Int) cor(X, dims=dim)
-@deprecate cor(x::AbstractVecOrMat, y::AbstractVecOrMat, dim::Int) cor(x, y, dims=dim)
-@deprecate median(A::AbstractArray, dims; kwargs...) median(A; kwargs..., dims=dims)
-
 @deprecate mapreducedim(f, op, A::AbstractArray, dims) mapreduce(f, op, A, dims=dims)
 @deprecate mapreducedim(f, op, A::AbstractArray, dims, v0) mapreduce(f, op, v0, A, dims=dims)
 @deprecate reducedim(op, A::AbstractArray, dims) reduce(op, A, dims=dims)
@@ -1704,6 +1688,9 @@ end
 # PR #25168
 @deprecate ipermute!(a, p::AbstractVector) invpermute!(a, p)
 
+# #27140, #27152
+@deprecate_moved linreg "StatsBase"
+
 # ?? more special functions to SpecialFunctions.jl
 @deprecate_moved gamma "SpecialFunctions"
 @deprecate_moved lgamma "SpecialFunctions"

base/exports.jl

@@ -626,21 +626,6 @@ export
  get_zero_subnormals,
  set_zero_subnormals,
 
-# statistics
- cor,
- cov,
- mean!,
- mean,
- median!,
- median,
- middle,
- quantile!,
- quantile,
- std,
- stdm,
- var,
- varm,
-
 # iteration
  done,
  next,

base/range.jl

@@ -847,13 +847,6 @@ function sum(r::AbstractRange{<:Real})
  : (step(r) * l) * ((l-1)>>1))
 end
 
-function mean(r::AbstractRange{<:Real})
- isempty(r) && throw(ArgumentError("mean of an empty range is undefined"))
- (first(r) + last(r)) / 2
-end
-
-median(r::AbstractRange{<:Real}) = mean(r)
-
 function _in_range(x, r::AbstractRange)
  if step(r) == 0
  return !isempty(r) && first(r) == x

base/sysimg.jl

@@ -413,9 +413,6 @@ using .StackTraces
 
 include("initdefs.jl")
 
-# statistics
-include("statistics.jl")
-
 # worker threads
 include("threadcall.jl")
 
@@ -525,6 +522,7 @@ let
  :Pkg,
  :Test,
  :REPL,
+ :Statistics,
  ]
 
  maxlen = maximum(textwidth.(string.(stdlibs)))
@@ -746,7 +744,6 @@ end
  # @deprecate_stdlib kron LinearAlgebra true
  @deprecate_stdlib ldltfact LinearAlgebra true
  @deprecate_stdlib ldltfact! LinearAlgebra true
- @deprecate_stdlib linreg LinearAlgebra true
  @deprecate_stdlib logabsdet LinearAlgebra true
  @deprecate_stdlib logdet LinearAlgebra true
  @deprecate_stdlib lu LinearAlgebra true
@@ -896,6 +893,20 @@ end
  @deprecate_stdlib send Sockets true
  @deprecate_stdlib TCPSocket Sockets true
  @deprecate_stdlib UDPSocket Sockets true
+
+ @deprecate_stdlib cor Statistics true
+ @deprecate_stdlib cov Statistics true
+ @deprecate_stdlib std Statistics true
+ @deprecate_stdlib stdm Statistics true
+ @deprecate_stdlib var Statistics true
+ @deprecate_stdlib varm Statistics true
+ @deprecate_stdlib mean! Statistics true
+ @deprecate_stdlib mean Statistics true
+ @deprecate_stdlib median! Statistics true
+ @deprecate_stdlib median Statistics true
+ @deprecate_stdlib middle Statistics true
+ @deprecate_stdlib quantile! Statistics true
+ @deprecate_stdlib quantile Statistics true
 end
 end
 

doc/src/base/math.md

@@ -177,21 +177,3 @@ Base.widemul
 Base.Math.@evalpoly
 Base.FastMath.@fastmath
 ```
-
-## Statistics
-
-```@docs
-Base.mean
-Base.mean!
-Base.std
-Base.stdm
-Base.var
-Base.varm
-Base.middle
-Base.median
-Base.median!
-Base.quantile
-Base.quantile!
-Base.cov
-Base.cor
-```

doc/src/manual/interfaces.md

@@ -65,7 +65,6 @@ julia> struct Squares
  end
 
 julia> Base.iterate(S::Squares, state=1) = state > S.count ? nothing : (state*state, state+1)
-
 ```
 
 With only [`iterate`](@ref) definition, the `Squares` type is already pretty powerful.
@@ -84,12 +83,16 @@ julia> for i in Squares(7)
 49
 ```
 
-We can use many of the builtin methods that work with iterables, like [`in`](@ref), [`mean`](@ref) and [`std`](@ref):
+We can use many of the builtin methods that work with iterables,
+like [`in`](@ref), or [`mean`](@ref) and [`std`](@ref) from the
+`Statistics` standard library module:
 
 ```jldoctest squaretype
 julia> 25 in Squares(10)
 true
 
+julia> using Statistics
+
 julia> mean(Squares(100))
 3383.5
 
@@ -388,8 +391,8 @@ julia> A[SquaresVector(3)]
  4.0
  9.0
 
-julia> mean(A)
-5.0
+julia> sum(A)
+45.0
 ```
 
 If you are defining an array type that allows non-traditional indexing (indices that start at

doc/src/manual/missing.md

@@ -294,7 +294,7 @@ julia> sum(skipmissing([1, missing]))
 
 This convenience function returns an iterator which filters out `missing` values
 efficiently. It can therefore be used with any function which supports iterators
-```jldoctest
+```jldoctest; setup = :(using Statistics)
 julia> maximum(skipmissing([3, missing, 2, 1]))
 3
 

stdlib/LinearAlgebra/docs/src/index.md

@@ -370,7 +370,6 @@ Base.inv(::AbstractMatrix)
 LinearAlgebra.pinv
 LinearAlgebra.nullspace
 Base.kron
-LinearAlgebra.linreg
 LinearAlgebra.exp(::StridedMatrix{<:LinearAlgebra.BlasFloat})
 LinearAlgebra.log(::StridedMatrix)
 LinearAlgebra.sqrt(::StridedMatrix{<:Real})

stdlib/LinearAlgebra/src/LinearAlgebra.jl

@@ -103,7 +103,6 @@ export
  ldiv!,
  ldlt!,
  ldlt,
- linreg,
  logabsdet,
  logdet,
  lowrankdowndate,

stdlib/LinearAlgebra/src/generic.jl

@@ -1143,46 +1143,6 @@ isdiag(A::AbstractMatrix) = isbanded(A, 0, 0)
 isdiag(x::Number) = true
 
 
-"""
- linreg(x, y)
-
-Perform simple linear regression using Ordinary Least Squares. Returns `a` and `b` such
-that `a + b*x` is the closest straight line to the given points `(x, y)`, i.e., such that
-the squared error between `y` and `a + b*x` is minimized.
-
-# Examples
-```julia
-using PyPlot
-x = 1.0:12.0
-y = [5.5, 6.3, 7.6, 8.8, 10.9, 11.79, 13.48, 15.02, 17.77, 20.81, 22.0, 22.99]
-a, b = linreg(x, y) # Linear regression
-plot(x, y, "o") # Plot (x, y) points
-plot(x, a + b*x) # Plot line determined by linear regression
-```
-
-See also:
-
-`\\`, [`cov`](@ref), [`std`](@ref), [`mean`](@ref).
-
-"""
-function linreg(x::AbstractVector, y::AbstractVector)
- # Least squares given
- # Y = a + b*X
- # where
- # b = cov(X, Y)/var(X)
- # a = mean(Y) - b*mean(X)
- if size(x) != size(y)
- throw(DimensionMismatch("x has size $(size(x)) and y has size $(size(y)), " *
- "but these must be the same size"))
- end
- mx = mean(x)
- my = mean(y)
- # don't need to worry about the scaling (n vs n - 1) since they cancel in the ratio
- b = Base.covm(x, mx, y, my)/Base.varm(x, mx)
- a = my - b*mx
- return (a, b)
-end
-
 # BLAS-like in-place y = x*α+y function (see also the version in blas.jl
 # for BlasFloat Arrays)
 function axpy!(α, x::AbstractArray, y::AbstractArray)

stdlib/LinearAlgebra/test/generic.jl

@@ -89,53 +89,6 @@ n = 5 # should be odd
  end
 end
 
-@testset "linrange" begin
- # make sure unequal input arrays throw an error
- x = [2; 5; 6]
- y = [3; 7; 10; 10]
- @test_throws DimensionMismatch linreg(x, y)
- x = [2 5 6]
- y = [3; 7; 10]
- @test_throws MethodError linreg(x, y)
-
- # check (UnitRange, Array)
- x = 1:12
- y = [5.5; 6.3; 7.6; 8.8; 10.9; 11.79; 13.48; 15.02; 17.77; 20.81; 22.0; 22.99]
- @test [linreg(x,y)...] ≈ [2.5559090909090867, 1.6960139860139862]
- @test [linreg(view(x,1:6),view(y,1:6))...] ≈ [3.8366666666666642,1.3271428571428574]
-
- # check (LinRange, UnitRange)
- x = range(1.0, stop=12.0, length=100)
- y = -100:-1
- @test [linreg(x, y)...] ≈ [-109.0, 9.0]
-
- # check (UnitRange, UnitRange)
- x = 1:12
- y = 12:-1:1
- @test [linreg(x, y)...] ≈ [13.0, -1.0]
-
- # check (LinRange, LinRange)
- x = range(-5, stop=10, length=100)
- y = range(50, stop=200, length=100)
- @test [linreg(x, y)...] ≈ [100.0, 10.0]
-
- # check (Array, Array)
- # Anscombe's quartet (https://en.wikipedia.org/wiki/Anscombe%27s_quartet)
- x123 = [10.0; 8.0; 13.0; 9.0; 11.0; 14.0; 6.0; 4.0; 12.0; 7.0; 5.0]
- y1 = [8.04; 6.95; 7.58; 8.81; 8.33; 9.96; 7.24; 4.26; 10.84; 4.82; 5.68]
- @test [linreg(x123,y1)...] ≈ [3.0,0.5] atol=15e-5
-
- y2 = [9.14; 8.14; 8.74; 8.77; 9.26; 8.10; 6.12; 3.10; 9.13; 7.26; 4.74]
- @test [linreg(x123,y2)...] ≈ [3.0,0.5] atol=10e-3
-
- y3 = [7.46; 6.77; 12.74; 7.11; 7.81; 8.84; 6.08; 5.39; 8.15; 6.42; 5.73]
- @test [linreg(x123,y3)...] ≈ [3.0,0.5] atol=10e-3
-
- x4 = [8.0; 8.0; 8.0; 8.0; 8.0; 8.0; 8.0; 19.0; 8.0; 8.0; 8.0]
- y4 = [6.58; 5.76; 7.71; 8.84; 8.47; 7.04; 5.25; 12.50; 5.56; 7.91; 6.89]
- @test [linreg(x4,y4)...] ≈ [3.0,0.5] atol=10e-3
-end
-
 @testset "diag" begin
  A = Matrix(1.0I, 4, 4)
  @test diag(A) == fill(1, 4)

stdlib/Markdown/test/runtests.jl

@@ -427,20 +427,20 @@ end
 
 ref(x) = Reference(x)
 
-ref(mean)
+ref(sum)
 
 show(io::IO, m::MIME"text/plain", r::Reference) =
  print(io, "$(r.ref) (see Julia docs)")
 
-mean_ref = md"Behaves like $(ref(mean))"
-@test plain(mean_ref) == "Behaves like mean (see Julia docs)\n"
-@test html(mean_ref) == "<p>Behaves like mean &#40;see Julia docs&#41;</p>\n"
+sum_ref = md"Behaves like $(ref(sum))"
+@test plain(sum_ref) == "Behaves like sum (see Julia docs)\n"
+@test html(sum_ref) == "<p>Behaves like sum &#40;see Julia docs&#41;</p>\n"
 
 show(io::IO, m::MIME"text/html", r::Reference) =
  Markdown.withtag(io, :a, :href=>"test") do
  Markdown.htmlesc(io, Markdown.plaininline(r))
  end
-@test html(mean_ref) == "<p>Behaves like <a href=\"test\">mean &#40;see Julia docs&#41;</a></p>\n"
+@test html(sum_ref) == "<p>Behaves like <a href=\"test\">sum &#40;see Julia docs&#41;</a></p>\n"
 
 @test md"""
 ````julia

stdlib/Pkg/src/GraphType.jl

@@ -1422,7 +1422,7 @@ function prune_graph!(graph::Graph)
 
  # Done
 
- log_event_global!(graph, "pruned graph — stats (n. of packages, mean connectivity): before = ($np,$(mean(spp))) after = ($new_np,$(mean(new_spp)))")
+ log_event_global!(graph, "pruned graph — stats (n. of packages, mean connectivity): before = ($np,$(sum(spp)/length(spp))) after = ($new_np,$(sum(new_spp)/length(new_spp)))")
 
  # Replace old data with new
  data.pkgs = new_pkgs

stdlib/REPL/src/docview.jl

@@ -378,7 +378,7 @@ function fuzzyscore(needle, haystack)
  score += (acro ? 2 : 1)*length(is) # Matched characters
  score -= 2(length(needle)-length(is)) # Missing characters
  !acro && (score -= avgdistance(is)/10) # Contiguous
- !isempty(is) && (score -= mean(is)/100) # Closer to beginning
+ !isempty(is) && (score -= sum(is)/length(is)/100) # Closer to beginning
  return score
 end