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

allow :col => AsTable and :col => cols #2780

Merged
merged 2 commits into from
Jun 9, 2021
+40 −6
Merged

allow :col => AsTable and :col => cols #2780

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
565962a
allow :col => AsTable and :col => cols
bkamins Jun 5, 2021
49d90a5
Update NEWS.md
bkamins Jun 5, 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
3 changes: 3 additions & 0 deletions NEWS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,9 @@
but preserved in right; in `innerjoin` missings are dropped in both data frames;
in `outerjoin` this value of keyword argument is not supported
([#2724](https://github.com/JuliaData/DataFrames.jl/pull/2724))
* correctly handle selectors of the form `:col => AsTable` and `:col => cols`
by expanding a single column into multiple columns
([#2780](https://github.com/JuliaData/DataFrames.jl/pull/2780))

## Bug fixes

Expand Down
2 changes: 1 addition & 1 deletion docs/src/man/split_apply_combine.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -53,7 +53,7 @@ each subset of the `DataFrame`. This specification can be of the following forms
3. a `cols => function => target_cols` form additionally explicitly specifying
the target column or columns.
4. a `col => target_cols` pair, which renames the column `col` to `target_cols`, which
must be single name (as a `Symbol` or a string).
must be single name (as a `Symbol` or a string), a vector of names or `AsTable`.
5. a `nrow` or `nrow => target_cols` form which efficiently computes the number of rows
in a group; without `target_cols` the new column is called `:nrow`, otherwise
it must be single name (as a `Symbol` or a string).
Expand Down
18 changes: 16 additions & 2 deletions src/abstractdataframe/selection.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ const TRANSFORMATION_COMMON_RULES =
3. a `cols => function => target_cols` form additionally explicitly specifying
the target column or columns.
4. a `col => target_cols` pair, which renames the column `col` to `target_cols`, which
must be single name (as a `Symbol` or a string).
must be single name (as a `Symbol` or a string), a vector of names or `AsTable`.
5. a `nrow` or `nrow => target_cols` form which efficiently computes the number of rows
in a group; without `target_cols` the new column is called `:nrow`, otherwise
it must be single name (as a `Symbol` or a string).
Expand Down Expand Up @@ -212,7 +212,13 @@ end

normalize_selection(idx::AbstractIndex, sel::Pair{<:ColumnIndex, <:AbstractString},
renamecols::Bool) =
normalize_selection(idx, first(sel) => Symbol(last(sel)), renamecols::Bool)
normalize_selection(idx, first(sel) => Symbol(last(sel)), renamecols)

normalize_selection(idx::AbstractIndex, sel::Pair{<:ColumnIndex,
<:Union{AbstractVector{Symbol},
AbstractVector{<:AbstractString}}},
renamecols::Bool) =
normalize_selection(idx, first(sel) => identity => last(sel), renamecols)

function normalize_selection(idx::AbstractIndex,
@nospecialize(sel::Pair{<:ColumnIndex,
Expand Down Expand Up @@ -287,6 +293,11 @@ function normalize_selection(idx::AbstractIndex,
@nospecialize(sel::Pair{<:ColumnIndex, <:Base.Callable}), renamecols::Bool)
c = idx[first(sel)]
fun = last(sel)

if fun === AsTable
return normalize_selection(idx, first(sel) => identity => AsTable, renamecols)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This looks good. No reason to worry about copies because it's only a vector of named tuples, so we always allocate.

Copy link
Member Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yes - AsTable as destination will always allocate:

julia> df = DataFrame(a=1)
1×1 DataFrame
 Row │ a
     │ Int64
─────┼───────
   1 │     1

julia> df2 = select(df, :a => identity => AsTable, copycols=false)
1×1 DataFrame
 Row │ x1
     │ Int64
─────┼───────
   1 │     1

julia> df2.x1 === df.a
false

end

if renamecols
newcol = Symbol(_names(idx)[c], "_", funname(fun))
else
Expand Down Expand Up @@ -320,6 +331,9 @@ function normalize_selection(idx::AbstractIndex,
end
end
fun = last(sel)

fun === AsTable && throw(ArgumentError("Passing AsTable in $sel is not supported"))

if length(c) > 3
prefix = join(@views(_names(idx)[c[1:2]]), '_')
if renamecols
Expand Down
23 changes: 20 additions & 3 deletions test/select.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1616,11 +1616,11 @@ end
@test DataFrames.normalize_selection(DataFrames.Index(Dict(:a => 1, :b => 2), [:a, :b]),
[:a] => sum, false) == (1 => (sum => :a))

@test DataFrames.normalize_selection(DataFrames.Index(Dict(:a => 1, :b => 2), [:a, :b]),
@test DataFrames.normalize_selection(DataFrames.Index(Dict(:a => 1, :b => 2), [:a, :b]),
[:a] => sum => [:new], false) == (1 => (sum => [:new]))

# Test that target col strings are converted to Symbols
@test DataFrames.normalize_selection(DataFrames.Index(Dict(:a => 1, :b => 2), [:a, :b]),
@test DataFrames.normalize_selection(DataFrames.Index(Dict(:a => 1, :b => 2), [:a, :b]),
[:a] => sum => ["new"], false) == (1 => (sum => [:new]))
end

Expand All @@ -1647,5 +1647,22 @@ end
@test df.a === a
end
end


@testset ":col => AsTable and :col => cols" begin
df = DataFrame(id=1:2, c1=[(a=1, b=2), (a=3, b=4)], c2=[(11, 12), (13, 14)])
@test select(df, :c1 => AsTable) == DataFrame(a=[1, 3], b=[2, 4])
@test select(df, :c1 => [:p, :q]) == DataFrame(p=[1, 3], q=[2, 4])
@test select(df, :c2 => AsTable) == DataFrame(x1=[11, 13], x2=[12, 14])
@test select(df, :c2 => [:p, :q]) == DataFrame(p=[11, 13], q=[12, 14])
@test_throws ArgumentError select(df, [:c1, :c2] => AsTable)
@test_throws ArgumentError select(df, [:c1, :c2] => AsTable)
gdf = groupby(df, :id)
@test select(gdf, :c1 => AsTable) == DataFrame(id=1:2, a=[1, 3], b=[2, 4])
@test select(gdf, :c1 => [:p, :q]) == DataFrame(id=1:2, p=[1, 3], q=[2, 4])
@test select(gdf, :c2 => AsTable) == DataFrame(id=1:2, x1=[11, 13], x2=[12, 14])
@test select(gdf, :c2 => [:p, :q]) == DataFrame(id=1:2, p=[11, 13], q=[12, 14])
@test_throws ArgumentError select(gdf, [:c1, :c2] => AsTable)
@test_throws ArgumentError select(gdf, [:c1, :c2] => AsTable)
end

end # module