julia - 如何制作更强大的类型压缩/解压缩？

Question

我有一个 Array{Tuple{A, B}} , 我想解压/转置成 Tuple{Array{A}, Array{B}} .

typealias MyIndexType Tuple{Bool, Int}

function test(x::MyIndexType)
    # prepare for test data set.
    myArray = Array{Tuple{MyIndexType, Float64}}(0)
    push!(myArray, (x,1))
    push!(myArray, (x,1))
    push!(myArray, (x,1))

    # transform
    a, b = (zip(myArray...)...)
    [a...]
end

test((true, 1))

>>>
3-element Array{Tuple{Bool,Int64},1}:
(true,1)
(true,1)
(true,1)

但是，使用 @code_warntype , JIT 无法推断 a 的类型, b提前时间。

Variables:
  x::Tuple{Bool,Int64}
  myArray::Array{Tuple{Tuple{Bool,Int64},Float64},1}
  a::ANY
  b::ANY
  #s41::Int64

Body:
  begin  # In[47], line 6:
      myArray = (top(ccall))(:jl_alloc_array_1d,(top(apply_type))(Base.Array,Tuple{Tuple{Bool,Int64},Float64},1)::Type{Array{Tuple{Tuple{Bool,Int64},Float64},1}},(top(svec))(Base.Any,Base.Int)::SimpleVector,Array{Tuple{Tuple{Bool,Int64},Float64},1},0,0,0)::Array{Tuple{Tuple{Bool,Int64},Float64},1} # In[47], line 7:
      (Main.push!)(myArray::Array{Tuple{Tuple{Bool,Int64},Float64},1},(top(tuple))(x::Tuple{Bool,Int64},1)::Tuple{Tuple{Bool,Int64},Int64})::Array{Tuple{Tuple{Bool,Int64},Float64},1} # In[47], line 8:
      (Main.push!)(myArray::Array{Tuple{Tuple{Bool,Int64},Float64},1},(top(tuple))(x::Tuple{Bool,Int64},1)::Tuple{Tuple{Bool,Int64},Int64})::Array{Tuple{Tuple{Bool,Int64},Float64},1} # In[47], line 9:
      (Main.push!)(myArray::Array{Tuple{Tuple{Bool,Int64},Float64},1},(top(tuple))(x::Tuple{Bool,Int64},1)::Tuple{Tuple{Bool,Int64},Int64})::Array{Tuple{Tuple{Bool,Int64},Float64},1} # In[47], line 10:
      GenSym(0) = (top(_apply))((top(getfield))(Main,:call)::F,top(tuple),(top(_apply))((top(getfield))(Main,:call)::F,Main.zip,myArray::Array{Tuple{Tuple{Bool,Int64},Float64},1})::UNION{BASE.ZIP2{TUPLE{TUPLE{BOOL,INT64},FLOAT64},TUPLE{TUPLE{BOOL,INT64},FLOAT64}},TUPLE{TUPLE{BOOL,INT64},FLOAT64},ZIP{I,Z<:BASE.ABSTRACTZIPITERATOR}})::TUPLE
      #s41 = 1
      GenSym(4) = (Base.getfield)(GenSym(0),1)::ANY
      GenSym(5) = (Base.box)(Base.Int,(Base.add_int)(1,1)::ANY)::Int64
      a = GenSym(4)
      #s41 = GenSym(5)
      GenSym(6) = (Base.getfield)(GenSym(0),2)::ANY
      GenSym(7) = (Base.box)(Base.Int,(Base.add_int)(2,1)::ANY)::Int64
      b = GenSym(6)
      #s41 = GenSym(7) # In[47], line 11:
      return (top(_apply))((top(getfield))(Main,:call)::F,top(vect),a)::ANY
  end::ANY

有没有办法让 zip 知道结果类型？

更新

其实有2个问题。

它认为a类型为 a::TUPLE{UNION{FLOAT64,INT64},UNION{FLOAT64,INT64}} ，但它实际上是类型 a::TUPLE{FLOAT64,FLOAT64}

function test{T}(x::T)
    A = Tuple{T, Int}[]

    for i in 1:3
        push!(A, (x, 1))
    end

    d = zip(A[1], A[2])
    a, b = d
    a
end

@code_warntype test(3.0)


Variables:
  x::Float64
  A::Array{Tuple{Float64,Int64},1}
  d::Base.Zip2{Tuple{Float64,Int64},Tuple{Float64,Int64}}
  a::TUPLE{UNION{FLOAT64,INT64},UNION{FLOAT64,INT64}}
  b::TUPLE{UNION{FLOAT64,INT64},UNION{FLOAT64,INT64}}
  #s40::Tuple{Int64,Int64}
  #s41::Int64
  i::Int64

对于 zip采用 2 个以上的参数，注意 d 有一个嵌套的 zip2类型，我觉得这可能会给类型推断带来负担。

function test{T}(x::T)
    A = Tuple{T, Int}[]

    for i in 1:3
        push!(A, (x, 1))
    end

    d = zip(A[1], A[2], A[3])
    a, b = d
    a
end

@code_warntype test(3.0)

Variables:
  x::Float64
  A::Array{Tuple{Float64,Int64},1}


  d::Zip{Tuple{Float64,Int64},Base.Zip2{Tuple{Float64,Int64},Tuple{Float64,Int64}}}
  a::TUPLE{UNION{FLOAT64,INT64},UNION{FLOAT64,INT64},UNION{FLOAT64,INT64}}
  b::TUPLE{UNION{FLOAT64,INT64},UNION{FLOAT64,INT64},UNION{FLOAT64,INT64}}
  #s40::Tuple{Int64,Tuple{Int64,Int64}}
  #s41::Int64
  i::Int64
  ##c#7879::Tuple{Tuple{Float64,Int64}}

我为什么关心类型？

编译下面例子的a,b = zip(A...)需要10+秒，速度好像和A的长度有关。(Julia 0.4)

const A = Tuple{Int, Int}[]

for i = 1:200
    push!(A, (1, 1))
end

a, b = zip(A...)
a

我在这里打开了一个错误报告 https://github.com/JuliaLang/julia/issues/13722

Answer 1

我相信@code_warntype不是问题报告说，如果它最终正确，则无法推断出正确的类型。

尽管如此，我还是想知道这是否是由于您的类型的复杂性。但事实并非如此，如下面的代码所示(使用更简单的类型)。

请注意，您还可以简化您的 zip表达;你可能不需要转换 a到一个数组。

代码:

function test{T}(x::T)
    A = Tuple{T, Int}[]

    for i in 1:3
        push!(A, (x, 1))
    end

    a, b = zip(A...)
    a, b
end

julia> test(3)  # now returns a and b
((3,3,3),(2,2,2))   

julia> @code_warntype test(3)
Variables:
  x::Int64
  A::Array{Tuple{Int64,Int64},1}
  a::ANY
  b::ANY
  #s40::ANY
  #s41::Int64
  i::Int64