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

make DataFrame constructor more flexible #2859

Merged
merged 5 commits into from
Sep 7, 2021
Merged

make DataFrame constructor more flexible #2859

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
b81170c
make DataFrame constructor more flexible
bkamins Sep 5, 2021
93b49e8
allow copycols in matrix constructor
bkamins Sep 6, 2021
0c47dd7
fix old test
bkamins Sep 6, 2021
1ccaefa
Apply suggestions from code review
bkamins Sep 6, 2021
00da256
Merge branch 'main' into bk/more_flexible_constructor
bkamins Sep 6, 2021
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
4 changes: 4 additions & 0 deletions NEWS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,10 @@
(with `false` default) that specifies if columns should be inserted after
or before `col`.
([#2829](https://github.com/JuliaData/DataFrames.jl/pull/2829))
* the `DataFrame` constructor when column names are passed to it as a second
argument now determines if a passed vector of column names is valid based on
its contents and not element type
([#2829](https://github.com/JuliaData/DataFrames.jl/pull/2859))

## Bug fixes

Expand Down
20 changes: 13 additions & 7 deletions src/dataframe/dataframe.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -322,19 +322,26 @@ function DataFrame(columns::AbstractVector, cnames::AbstractVector{Symbol};
copycols=copycols)
end

DataFrame(columns::AbstractVector, cnames::AbstractVector{<:AbstractString};
function _name2symbol(str::AbstractVector)
if !(all(x -> x isa AbstractString, str) || all(x -> x isa Symbol, str))
throw(ArgumentError("All passed column names must be strings or Symbols"))
end
return Symbol[Symbol(s) for s in str]
end

DataFrame(columns::AbstractVector, cnames::AbstractVector;
makeunique::Bool=false, copycols::Bool=true) =
DataFrame(columns, Symbol.(cnames), makeunique=makeunique, copycols=copycols)
DataFrame(columns, _name2symbol(cnames), makeunique=makeunique, copycols=copycols)

DataFrame(columns::AbstractVector{<:AbstractVector}, cnames::AbstractVector{Symbol};
makeunique::Bool=false, copycols::Bool=true)::DataFrame =
DataFrame(collect(AbstractVector, columns),
Index(convert(Vector{Symbol}, cnames), makeunique=makeunique),
copycols=copycols)

DataFrame(columns::AbstractVector{<:AbstractVector}, cnames::AbstractVector{<:AbstractString};
DataFrame(columns::AbstractVector{<:AbstractVector}, cnames::AbstractVector;
makeunique::Bool=false, copycols::Bool=true) =
DataFrame(columns, Symbol.(cnames); makeunique=makeunique, copycols=copycols)
DataFrame(columns, _name2symbol(cnames); makeunique=makeunique, copycols=copycols)

function DataFrame(columns::AbstractVector, cnames::Symbol; copycols::Bool=true)
if cnames !== :auto
Expand All @@ -350,9 +357,9 @@ DataFrame(columns::AbstractMatrix, cnames::AbstractVector{Symbol}; makeunique::B
DataFrame(AbstractVector[columns[:, i] for i in 1:size(columns, 2)], cnames,
makeunique=makeunique, copycols=false)

DataFrame(columns::AbstractMatrix, cnames::AbstractVector{<:AbstractString};
DataFrame(columns::AbstractMatrix, cnames::AbstractVector;
makeunique::Bool=false) =
DataFrame(columns, Symbol.(cnames); makeunique=makeunique)
DataFrame(columns, _name2symbol(cnames); makeunique=makeunique)

function DataFrame(columns::AbstractMatrix, cnames::Symbol)
if cnames !== :auto
Expand Down Expand Up @@ -388,7 +395,6 @@ DataFrame(column_eltypes::AbstractVector{<:Type}, cnames::AbstractVector{<:Abstr
"not supported. Pass explicitly created columns to a " *
"`DataFrame` constructor instead."))


##############################################################################
##
## AbstractDataFrame interface
Expand Down
19 changes: 19 additions & 0 deletions test/constructors.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -363,6 +363,8 @@ end
@test_throws ArgumentError DataFrame([Int, Float64], [:a, :b], 2)
@test_throws ArgumentError DataFrame([Int, Float64], ["a", "b"])
@test_throws ArgumentError DataFrame([Int, Float64], ["a", "b"], 2)
@test_throws ArgumentError DataFrame([Int, Float64], ["a", :b])
@test_throws MethodError DataFrame([Int, Float64], ["a", :b], 2)
end

@testset "threading correctness tests" begin
Expand All @@ -372,4 +374,21 @@ end
end
end

@testset "non-specific vector of column names" begin
ref = DataFrame(a=1:2, b=3:4)
for x in ([1 3; 2 4], [[1, 2], [3, 4]], [1:2, 3:4], Any[[1, 2], [3, 4]], Any[1:2, 3:4])
@test DataFrame(x, Any[:a, :b]) == ref
@test DataFrame(x, Any["a", "b"]) == ref
@test DataFrame(x, Union{String, Symbol}[:a, :b]) == ref
@test DataFrame(x, Union{String, Symbol}["a", "b"]) == ref
@test_throws ArgumentError DataFrame(x, Any["a", :b])
@test_throws ArgumentError DataFrame(x, Union{String, Symbol}["a", :b])
end
@test DataFrame([], []) == DataFrame()
@test DataFrame(fill(0, 0, 0), []) == DataFrame()
@test_throws ArgumentError DataFrame(Type[], Symbol[])
@test_throws ArgumentError DataFrame(Type[], String[])
@test_throws MethodError DataFrame(Type[], [])
end

end # module