Skip to content
This repository was archived by the owner on May 4, 2019. It is now read-only.

vcat of PooledDataVector might need to expand the reftype #213

Merged
merged 8 commits into from
Sep 27, 2016
Merged

vcat of PooledDataVector might need to expand the reftype #213

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
cffe69f
vcat of PooledDataVector might need to expand the reftype
Sep 12, 2016
6a7fa47
type-stable vcat of pooled arrays
Sep 12, 2016
41f1040
vcat: test multi-dimensional arrays
Sep 15, 2016
76f749b
vcat: replace dim with ndims
Sep 15, 2016
cd07b87
improved tests
Sep 16, 2016
ece7e37
using simpler functions
Sep 16, 2016
5f43d98
Use platform-default Int instead of Int64
Sep 17, 2016
39fef7e
compact code
Sep 17, 2016
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
25 changes: 16 additions & 9 deletions src/pooleddataarray.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -251,13 +251,15 @@ end
##
##############################################################################

function compact{T,R<:Integer,N}(d::PooledDataArray{T,R,N})
sz = length(d.pool)

function compactreftype(sz)
REFTYPE = sz <= typemax(UInt8) ? UInt8 :
sz <= typemax(UInt16) ? UInt16 :
sz <= typemax(UInt32) ? UInt32 :
UInt64
end

function compact{T,R<:Integer,N}(d::PooledDataArray{T,R,N})
REFTYPE = compactreftype(length(d.pool))

if REFTYPE == R
return d
Expand Down Expand Up @@ -618,12 +620,7 @@ Perm{O<:Base.Sort.Ordering}(o::O, v::PooledDataVector) = FastPerm(o, v)
function PooledDataVecs{S,Q<:Integer,R<:Integer,N}(v1::PooledDataArray{S,Q,N},
v2::PooledDataArray{S,R,N})
pool = sort(unique([v1.pool; v2.pool]))
sz = length(pool)

REFTYPE = sz <= typemax(UInt8) ? UInt8 :
sz <= typemax(UInt16) ? UInt16 :
sz <= typemax(UInt32) ? UInt32 :
UInt64
REFTYPE = compactreftype(length(pool))

tidx1 = convert(Vector{REFTYPE}, findat(pool, v1.pool))
tidx2 = convert(Vector{REFTYPE}, findat(pool, v2.pool))
Expand Down Expand Up @@ -829,3 +826,13 @@ function dropna{T}(pdv::PooledDataVector{T})
resize!(res, total)
return res
end

function Base.vcat{T,R,N}(p1::PooledDataArray{T,R,N}, p2::PooledDataArray...)
pa = (p1, p2...)
pool = unique(T[[p.pool for p in pa]...;])

idx = [indexin(p.pool, pool)[p.refs] for p in pa]

refs = Array{DEFAULT_POOLED_REF_TYPE,N}([idx...;])
PooledDataArray(RefArray(refs), pool)
end
21 changes: 21 additions & 0 deletions test/pooleddataarray.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -109,4 +109,25 @@ module TestPDA
pda = @pdata([NA, "A", "B", "C", "A", "B"])
@test isequal(Base.permute!!(copy(pda), [2, 5, 3, 6, 4, 1]), @pdata(["A", "A", "B", "B", "C", NA]))
@test isequal(Base.ipermute!!(copy(pda), [6, 1, 3, 5, 2, 4]), @pdata(["A", "A", "B", "B", "C", NA]))

a1 = 1:200
a2 = 100:300
pa1 = PooledDataArray(a1)
pa2 = PooledDataArray(a2)
ca1 = compact(pa1)
ca2 = compact(pa2)
r = vcat(ca1, ca2)
@test r == vcat(a1, a2)
@test isa(r, PooledDataArray{Int,DataArrays.DEFAULT_POOLED_REF_TYPE})
@test isa(vcat(ca1, pa2), PooledDataArray{Int,DataArrays.DEFAULT_POOLED_REF_TYPE})

a1 = Array{Int}(2,3,4,5)
a2 = Array{Int}(3,3,4,5)
a1[1:end] = length(a1):-1:1
a2[1:end] = (1:length(a2)) + 10
ca1 = compact(PooledDataArray(a1))
ca2 = compact(PooledDataArray(a2))
r = vcat(ca1, ca2)
@test r == vcat(a1, a2)
@test isa(r, PooledDataArray{Int,DataArrays.DEFAULT_POOLED_REF_TYPE,4})
end