join.jl

using DataTables, StatsBase

function random_frame(nrow::Int, col_values::Dict{Symbol, Any})
  DataTable(Any[isa(col_values[key], CategoricalArray) ?
                categorical(sample(col_values[key], nrow)) :
                NullableArray(sample(col_values[key], nrow)) for key in keys(col_values)],
            keys(col_values) |> collect)
end

function random_join(kind::Symbol, nrow_left::Int, nrow_right::Int,
                     on_col_values::Dict{Symbol, Any},
                     left_col_values::Dict{Symbol, Any},
                     right_col_values::Dict{Symbol, Any})
  dfl = random_frame(nrow_left, merge(on_col_values, left_col_values))
  dfr = random_frame(nrow_right, merge(on_col_values, right_col_values))
  join(dfl, dfr, on = keys(on_col_values) |> collect, kind = kind)
end

function f(n::Int)
  for i in 1:n
    r = random_join(:outer, 1000, 2000,
                Dict{Symbol,Any}(:A => 1:10, :B => NullableArray([:A, :B, :C, :D]),
                                 :C => 1:10, :D => 1:10),
                Dict{Symbol,Any}(:E => 1:10, :F => NullableArray([:A, :B, :C, :D])),
                Dict{Symbol,Any}(:G => 1:10, :H => NullableArray([:A, :B, :C, :D])))
  end
end

f(1)

@time f(100)