Allow multicolumn transformations for AbstractDataFrame (#2461)

NEWS.md

@@ -2,6 +2,10 @@
 
 ## Breaking changes
 
+* the rules for transformations passed to `select`/`select!`, `transform`/`transform!`,
+  and `combine` have been made more flexible; in particular now it is allowed to
+  return multiple columns from a transformation function
+  [#2461](https://github.com/JuliaData/DataFrames.jl/pull/2461)
 * CategoricalArrays.jl is no longer reexported: call `using CategoricalArrays`
   to use it [#2404]((https://github.com/JuliaData/DataFrames.jl/pull/2404)).
   In the same vein, the `categorical` and `categorical!` functions

docs/src/lib/types.md

@@ -55,7 +55,8 @@ The `ByRow` type is a special type used for selection operations to signal that
 to each element (row) of the selection.
 
 The `AsTable` type is a special type used for selection operations to signal that the columns selected by a wrapped
-selector should be passed as a `NamedTuple` to the function.
+selector should be passed as a `NamedTuple` to the function or to signal that it is requested
+to expand the return value of a transformation into multiple columns.
 
 ## [The design of handling of columns of a `DataFrame`](@id man-columnhandling)
 

docs/src/man/getting_started.md

@@ -632,6 +632,14 @@ julia> select(df, :x2, :x2 => ByRow(sqrt)) # transform columns by row
 ├─────┼───────┼─────────┤
 │ 1   │ 3     │ 1.73205 │
 │ 2   │ 4     │ 2.0     │
+
+julia> select(df, AsTable(:) => ByRow(extrema) => [:lo, :hi]) # return multiple columns
+2×2 DataFrame
+│ Row │ lo    │ hi    │
+│     │ Int64 │ Int64 │
+├─────┼───────┼───────┤
+│ 1   │ 1     │ 5     │
+│ 2   │ 2     │ 6     │
 ```
 
 It is important to note that `select` always returns a data frame,

src/groupeddataframe/splitapplycombine.jl

@@ -502,7 +502,7 @@ function _combine_prepare(gd::GroupedDataFrame,
     for p in cs
         if p === nrow
             push!(cs_vec, nrow => :nrow)
-        elseif p isa AbstractVector{<:Pair}
+        elseif p isa AbstractVecOrMat{<:Pair}
             append!(cs_vec, p)
         else
             push!(cs_vec, p)

test/grouping.jl

@@ -1989,8 +1989,10 @@ end
           [df DataFrame(x_function=[(-1,), (-2,) ,(-3,) ,(-4,) ,(-5,)],
                         y_function=[(-6,), (-7,) ,(-8,) ,(-9,) ,(-10,)])]
 
-    @test_throws ArgumentError combine(gdf, AsTable([:x, :y]) => ByRow(identity))
-    @test_throws ArgumentError combine(gdf, AsTable([:x, :y]) => ByRow(x -> df[1, :]))
+    @test combine(gdf, AsTable([:x, :y]) => ByRow(identity)) ==
+          DataFrame(g=[1,1,1,2,2], x_y_identity=ByRow(identity)((x=1:5, y=6:10)))
+    @test combine(gdf, AsTable([:x, :y]) => ByRow(x -> df[1, :])) ==
+          DataFrame(g=[1,1,1,2,2], x_y_function=fill(df[1, :], 5))
 end
 
 @testset "test correctness of ungrouping" begin
@@ -2710,12 +2712,8 @@ end
     @test isequal_typed(combine(df, :x => (x -> 1:2) => :y), DataFrame(y=1:2))
     @test isequal_typed(combine(df, :x => (x -> x isa Vector{Int} ? "a" : 'a') => :y),
                         DataFrame(y="a"))
-
-    # in the future this should be DataFrame(nrow=0)
-    @test_throws ArgumentError combine(nrow, df)
-
-    # in the future this should be DataFrame(a=1,b=2)
-    @test_throws ArgumentError combine(sdf -> DataFrame(a=1,b=2), df)
+    @test combine(nrow, df) == DataFrame(nrow=0)
+    @test combine(sdf -> DataFrame(a=1,b=2), df) == DataFrame(a=1,b=2)
 end
 
 @testset "disallowed tuple column selector" begin