Skip to content
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

Fix vcat in case no data frames are passed #3081

Merged
merged 7 commits into from
Jun 19, 2022
Merged

Fix vcat in case no data frames are passed #3081

Show file tree
Hide file tree
Changes from 3 commits
Commits
Show all changes
7 commits
Select commit Hold shift + click to select a range
ed5112c
fix vcat in case no data frames are passed
bkamins Jun 18, 2022
026b271
Update test/dataframe.jl
bkamins Jun 18, 2022
611b34f
improve tests
bkamins Jun 18, 2022
c8dd212
more tests
bkamins Jun 18, 2022
0a07052
Update src/abstractdataframe/abstractdataframe.jl
bkamins Jun 18, 2022
8f4c892
add NEWS.md entry
bkamins Jun 18, 2022
80714b7
Merge branch 'bk/vcat_fix' of https://github.com/JuliaData/DataFrames…
bkamins Jun 18, 2022
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
2 changes: 1 addition & 1 deletion src/abstractdataframe/abstractdataframe.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1945,7 +1945,7 @@ end
function _vcat(dfs::AbstractVector{AbstractDataFrame};
cols::Union{Symbol, AbstractVector{Symbol},
AbstractVector{<:AbstractString}}=:setequal)

# note that DataFrame() objects are dropped from dfs before we call _vcat
bkamins marked this conversation as resolved.
Show resolved Hide resolved
if isempty(dfs)
cols isa Symbol && return DataFrame()
return DataFrame([col => Missing[] for col in cols])
Expand Down
33 changes: 24 additions & 9 deletions test/dataframe.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2052,7 +2052,7 @@ end
cols=:orderequal)
end

@testset "vcat with source and reduce" begin
@testset "vcat with source and reduce(vcat, ...)" begin
df1 = DataFrame(A=1:3, B=1:3)
df2 = DataFrame(A=4:6, B=4:6)
df3 = DataFrame(A=7:9, C=7:9)
Expand All @@ -2067,16 +2067,14 @@ end
C=[fill(missing, 6); 7:9],
source=[1, 1, 1, 2, 2, 2, 3, 3, 3])
res = vcat(df1, df2, df3, df4, cols=:union, source=col => categorical(-4:-1))
@test res ≅ DataFrame(A=1:9, B=[1:6; fill(missing, 3)],
C=[fill(missing, 6); 7:9],
source=[-4, -4, -4, -3, -3, -3, -2, -2, -2])
@test res.source isa CategoricalVector
@test isequal_coltyped(res, DataFrame(A=1:9, B=[1:6; fill(missing, 3)],
C=[fill(missing, 6); 7:9],
source=categorical([-4, -4, -4, -3, -3, -3, -2, -2, -2])))

res = reduce(vcat, [df1, df2, df3, df4], cols=:union, source=col => categorical(-4:-1))
@test res ≅ DataFrame(A=1:9, B=[1:6; fill(missing, 3)],
C=[fill(missing, 6); 7:9],
source=[-4, -4, -4, -3, -3, -3, -2, -2, -2])
@test res.source isa CategoricalVector
@test isequal_coltyped(res, DataFrame(A=1:9, B=[1:6; fill(missing, 3)],
C=[fill(missing, 6); 7:9],
source=categorical([-4, -4, -4, -3, -3, -3, -2, -2, -2])))

@test reduce(vcat, DataFrame[]) == DataFrame()
@test isequal_coltyped(reduce(vcat, DataFrame[], source=:src),
Expand All @@ -2095,6 +2093,23 @@ end
@test_throws TypeError reduce(vcat, [df1, df2, df3, df4], cols=:union, source=:a => 1)
@test_throws ArgumentError reduce(vcat, [df1, df2, df3, df4], cols=:union, source=:C)
@test_throws ArgumentError reduce(vcat, [df1, df2, df3, df4], cols=:union, source=:a => [1])

@test vcat(DataFrame(), DataFrame()) ==
reduce(vcat, [DataFrame(), DataFrame()]) ==
DataFrame()
@test isequal_coltyped(vcat(DataFrame(), DataFrame(), cols=[:a, :b]),
DataFrame(a=Missing[], b=Missing[]))
@test isequal_coltyped(reduce(vcat, (DataFrame(), DataFrame()), cols=[:a, :b]),
DataFrame(a=Missing[], b=Missing[]))
@test isequal_coltyped(vcat(DataFrame(a=1:2), DataFrame(), cols=[:a, :b]),
DataFrame(a=1:2, b=missing))
@test isequal_coltyped(reduce(vcat, (DataFrame(a=1:2), DataFrame()), cols=[:a, :b]),
DataFrame(a=1:2, b=missing))
@test vcat(DataFrame(a=1), DataFrame(b=2), cols=[:a]) ≅ DataFrame(a=[1, missing])
@test vcat(DataFrame(a=1), DataFrame(b=2), cols=[:b]) ≅ DataFrame(b=[missing, 2])
@test vcat(DataFrame(a=1), DataFrame(b=2), cols=Symbol[]) == DataFrame()
@test isequal_coltyped(vcat(DataFrame(a=1), DataFrame(b=2), cols=[:c]),
DataFrame(c=[missing, missing]))
end

@testset "push! with :subset" begin
Expand Down