Skip to content

fixed corkendall(RealMatrix, RealVector) #673

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from
Closed

fixed corkendall(RealMatrix, RealVector) #673

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 8 additions & 7 deletions src/rankcorr.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -143,8 +143,8 @@ function corkendall!(x::RealVector, y::RealVector, permx::AbstractVector{<:Integ
if x[i - 1] == x[i]
k += 1
elseif k > 0
# Sort the corresponding chunk of y, so the rows of hcat(x,y) are
# sorted first on x, then (where x values are tied) on y. Hence
# Sort the corresponding chunk of y, so the rows of hcat(x,y) are
# sorted first on x, then (where x values are tied) on y. Hence
# double ties can be counted by calling countties.
sort!(view(y, (i - k - 1):(i - 1)))
ntiesx += div(widen(k) * (k + 1), 2) # Must use wide integers here
Expand Down Expand Up @@ -176,8 +176,9 @@ matrices or vectors.
corkendall(x::RealVector, y::RealVector) = corkendall!(copy(x), copy(y))

function corkendall(X::RealMatrix, y::RealVector)
n = size(X, 2)
permy = sortperm(y)
return([corkendall!(copy(y), X[:,i], permy) for i in 1:size(X, 2)])
return(reshape([corkendall!(copy(y), X[:,i], permy) for i in 1:n], n, 1))
end

function corkendall(x::RealVector, Y::RealMatrix)
Expand Down Expand Up @@ -217,7 +218,7 @@ end
"""
countties(x::RealVector, lo::Integer, hi::Integer)

Return the number of ties within `x[lo:hi]`. Assumes `x` is sorted.
Return the number of ties within `x[lo:hi]`. Assumes `x` is sorted.
"""
function countties(x::AbstractVector, lo::Integer, hi::Integer)
# Use of widen below prevents possible overflow errors when
Expand Down Expand Up @@ -246,9 +247,9 @@ const SMALL_THRESHOLD = 64
# merge_sort! copied from Julia Base
# (commit 28330a2fef4d9d149ba0fd3ffa06347b50067647, dated 20 Sep 2020)
"""
merge_sort!(v::AbstractVector, lo::Integer, hi::Integer, t::AbstractVector=similar(v, 0))
merge_sort!(v::AbstractVector, lo::Integer, hi::Integer, t::AbstractVector=similar(v, 0))

Mutates `v` by sorting elements `x[lo:hi]` using the merge sort algorithm.
Mutates `v` by sorting elements `x[lo:hi]` using the merge sort algorithm.
This method is a copy-paste-edit of sort! in base/sort.jl, amended to return the bubblesort distance.
"""
function merge_sort!(v::AbstractVector, lo::Integer, hi::Integer, t::AbstractVector=similar(v, 0))
Expand Down Expand Up @@ -300,7 +301,7 @@ midpoint(lo::Integer, hi::Integer) = midpoint(promote(lo, hi)...)
"""
insertion_sort!(v::AbstractVector, lo::Integer, hi::Integer)

Mutates `v` by sorting elements `x[lo:hi]` using the insertion sort algorithm.
Mutates `v` by sorting elements `x[lo:hi]` using the insertion sort algorithm.
This method is a copy-paste-edit of sort! in base/sort.jl, amended to return the bubblesort distance.
"""
function insertion_sort!(v::AbstractVector, lo::Integer, hi::Integer)
Expand Down
58 changes: 27 additions & 31 deletions test/rankcorr.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,14 +35,14 @@ c22 = corspearman(x2, x2)
@test isnan(corkendall([1,1,1], [1,2,3]))
@test corkendall([-Inf,-0.0,Inf],[1,2,3]) == 1.0

# Test, with exact equality, some known results.
# Test, with exact equality, some known results.
# RealVector, RealVector
@test corkendall(x1, y) == -1/sqrt(90)
@test corkendall(x2, y) == -1/sqrt(72)
# RealMatrix, RealVector
@test corkendall(X, y) == [-1/sqrt(90), -1/sqrt(72)]
@test corkendall(X, y) == reshape([-1/sqrt(90), -1/sqrt(72)], 2, 1)
# RealVector, RealMatrix
@test corkendall(y, X) == [-1/sqrt(90) -1/sqrt(72)]
@test corkendall(y, X) == [-1/sqrt(90) -1/sqrt(72)]

# n = 78_000 tests for overflow errors on 32 bit
# Testing for overflow errors on 64bit would require n be too large for practicality
Expand Down Expand Up @@ -94,19 +94,19 @@ z = [1 1 1;
@test corkendall(z) == [1 0 1/3; 0 1 0; 1/3 0 1]
@test corkendall(z, z) == [1 0 1/3; 0 1 0; 1/3 0 1]
@test corkendall(z[:,1], z) == [1 0 1/3]
@test corkendall(z, z[:,1]) == [1; 0; 1/3]
@test corkendall(z, z[:,1]) == reshape([1; 0; 1/3], 3, 1)

z = float(z)
@test corkendall(z) == [1 0 1/3; 0 1 0; 1/3 0 1]
@test corkendall(z, z) == [1 0 1/3; 0 1 0; 1/3 0 1]
@test corkendall(z[:,1], z) == [1 0 1/3]
@test corkendall(z, z[:,1]) == [1; 0; 1/3]
@test corkendall(z, z[:,1]) == reshape([1; 0; 1/3], 3, 1)

w = repeat(z, n)
@test corkendall(w) == [1 0 1/3; 0 1 0; 1/3 0 1]
@test corkendall(w, w) == [1 0 1/3; 0 1 0; 1/3 0 1]
@test corkendall(w[:,1], w) == [1 0 1/3]
@test corkendall(w, w[:,1]) == [1; 0; 1/3]
@test corkendall(w, w[:,1]) == reshape([1; 0; 1/3], 3, 1)

StatsBase.midpoint(1,10) == 5
StatsBase.midpoint(1,widen(10)) == 5
Expand All @@ -120,30 +120,26 @@ Ynan = copy(Y)
Ynan[2,1] = NaN

for f in (corspearman, corkendall)
@test isnan(f([1.0, NaN, 2.0], [2.0, 1.0, 3.4]))
@test all(isnan, f([1.0, NaN], [1 2; 3 4]))
@test all(isnan, f([1 2; 3 4], [1.0, NaN]))
@test isequal(f([1 NaN; NaN 4]), [1 NaN; NaN 1])
@test all(isnan, f([1 NaN; NaN 4], [1 NaN; NaN 4]))
@test all(isnan, f([1 NaN; NaN 4], [NaN 1; NaN 4]))

@test isequal(f(Xnan, Ynan),
[f(Xnan[:,i], Ynan[:,j]) for i in axes(Xnan, 2), j in axes(Ynan, 2)])
@test isequal(f(Xnan),
[i == j ? 1.0 : f(Xnan[:,i], Xnan[:,j])
for i in axes(Xnan, 2), j in axes(Xnan, 2)])
for k in 1:2
@test isequal(f(Xnan[:,k], Ynan),
[f(Xnan[:,k], Ynan[:,j]) for i in 1:1, j in axes(Ynan, 2)])
# TODO: fix corkendall (PR#659)
if f === corspearman
@test isequal(f(Xnan, Ynan[:,k]),
[f(Xnan[:,i], Ynan[:,k]) for i in axes(Xnan, 2), j in 1:1])
else
@test isequal(f(Xnan, Ynan[:,k]),
[f(Xnan[:,i], Ynan[:,k]) for i in axes(Xnan, 2)])
end
end
@test isnan(f([1.0, NaN, 2.0], [2.0, 1.0, 3.4]))
@test all(isnan, f([1.0, NaN], [1 2; 3 4]))
@test all(isnan, f([1 2; 3 4], [1.0, NaN]))
@test isequal(f([1 NaN; NaN 4]), [1 NaN; NaN 1])
@test all(isnan, f([1 NaN; NaN 4], [1 NaN; NaN 4]))
@test all(isnan, f([1 NaN; NaN 4], [NaN 1; NaN 4]))

@test isequal(f(Xnan, Ynan),
[f(Xnan[:,i], Ynan[:,j]) for i in axes(Xnan, 2), j in axes(Ynan, 2)])
@test isequal(f(Xnan),
[i == j ? 1.0 : f(Xnan[:,i], Xnan[:,j])
for i in axes(Xnan, 2), j in axes(Xnan, 2)])
for k in 1:2
# RealVector, RealMatrix
@test isequal(f(Xnan[:,k], Ynan),
[f(Xnan[:,k], Ynan[:,j]) for i in 1:1, j in axes(Ynan, 2)])
# RealMatrix, RealVector
@test isequal(f(Xnan, Ynan[:,k]),
[f(Xnan[:,i], Ynan[:,k]) for i in axes(Xnan, 2), j in 1:1])
end
end


Expand All @@ -158,4 +154,4 @@ end
@test_throws ErrorException corkendall([1], [1, 2])
@test_throws ErrorException corkendall([1], [1 2; 3 4])
@test_throws ErrorException corkendall([1 2; 3 4], [1])
@test_throws ArgumentError corkendall([1 2; 3 4: 4 6], [1 2; 3 4])
@test_throws ArgumentError corkendall([1 2; 3 4: 4 6], [1 2; 3 4])