Skip to content

Join reftype #890

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

Closed
wants to merge 2 commits into from
Closed

Join reftype #890

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
1d35279
join: let the user specify a larger reftype if DEFAULT_POOLED_REF_TYP…
Nov 22, 2015
259005d
use test_throws
Nov 22, 2015
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
22 changes: 12 additions & 10 deletions src/abstractdataframe/join.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -76,13 +76,14 @@ function join_idx(left, right, max_groups)
right_sorter[right_indexer], right_sorter[rightonly_indexer])
end

function DataArrays.PooledDataVecs(df1::AbstractDataFrame,
df2::AbstractDataFrame)
function DataArrays.PooledDataVecs{R<:Integer}(df1::AbstractDataFrame,
df2::AbstractDataFrame,
::Type{R})
# This method exists to allow merge to work with multiple columns.
# It takes the columns of each DataFrame and returns a DataArray
# with a merged pool that "keys" the combination of column values.
# The pools of the result don't really mean anything.
dv1, dv2 = PooledDataVecs(df1[1], df2[1])
dv1, dv2 = PooledDataVecs(df1[1], df2[1], R)
refs1 = dv1.refs .+ 1 # the + 1 handles NA's
refs2 = dv2.refs .+ 1
ngroups = length(dv1.pool) + 1
Expand Down Expand Up @@ -129,7 +130,7 @@ function DataArrays.PooledDataArray{R}(df::AbstractDataFrame, ::Type{R})
return PooledDataArray(DataArrays.RefArray(refs), pool)
end

DataArrays.PooledDataArray(df::AbstractDataFrame) = PooledDataArray(df, DEFAULT_POOLED_REF_TYPE)
DataArrays.PooledDataArray{R<:Integer}(df::AbstractDataFrame, r::Type{R} = DataArrays.DEFAULT_POOLED_REF_TYPE) = PooledDataArray(df, r)



Expand Down Expand Up @@ -168,7 +169,7 @@ join(df1::AbstractDataFrame,

### Result

* `::DataFrame` : the joined DataFrame
* `::DataFrame` : the joined DataFrame

### Examples

Expand All @@ -189,10 +190,11 @@ join(name, job, kind = :cross)
:join


function Base.join(df1::AbstractDataFrame,
df2::AbstractDataFrame;
on::@compat(Union{Symbol, Vector{Symbol}}) = Symbol[],
kind::Symbol = :inner)
function Base.join{R<:Integer}(df1::AbstractDataFrame,
df2::AbstractDataFrame;
on::@compat(Union{Symbol, Vector{Symbol}}) = Symbol[],
kind::Symbol = :inner,
reftype::Type{R} = DataArrays.DEFAULT_POOLED_REF_TYPE)
if kind == :cross
if on != Symbol[]
throw(ArgumentError("Cross joins don't use argument 'on'."))
Expand All @@ -202,7 +204,7 @@ function Base.join(df1::AbstractDataFrame,
throw(ArgumentError("Missing join argument 'on'."))
end

dv1, dv2 = PooledDataVecs(df1[on], df2[on])
dv1, dv2 = PooledDataVecs(df1[on], df2[on], reftype)

left_idx, leftonly_idx, right_idx, rightonly_idx =
join_idx(dv1.refs, dv2.refs, length(dv1.pool))
Expand Down
8 changes: 8 additions & 0 deletions test/join.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,4 +66,12 @@ module TestJoin

# Cross joins don't take keys
@test_throws ArgumentError join(df1, df2, on = :A, kind = :cross)

# Reftype is needed for joins on several columns and several rows
N = 10000
dfc1 = DataFrame(A = 1:N, B=1:N, C=1:N, dfc1=ones(N))
dfc2 = DataFrame(A = 1:N, B=1:N, C=1:N, dfc2=2*ones(N))

@test_throws InexactError join(dfc1, dfc2, on=[:A,:B,:C])
join(dfc1, dfc2, on=[:A,:B,:C], reftype=BigInt)
end