Skip to content
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

Jump to bottom

RFC: Added ref type parameter, compact to PooledDataFrame #227

Closed
wants to merge 2 commits into from
Closed

RFC: Added ref type parameter, compact to PooledDataFrame #227

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
f5690d5
Added ref type parameter, `compact` to PooledDataFrame
kmsquire Apr 1, 2013
2a59eb8
Fix reftype conversion in compact
kmsquire Apr 9, 2013
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
4 changes: 2 additions & 2 deletions src/DataFrames.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,8 +25,7 @@ using Stats
##############################################################################

const DEFAULT_COLUMN_TYPE = Float64
const POOLED_DATA_VEC_REF_TYPE = Uint16
const POOLED_DATA_VEC_REF_CONVERTER = uint16
const DEFAULT_POOLED_REF_TYPE = Uint16

##############################################################################
##
Expand Down Expand Up @@ -73,6 +72,7 @@ export # reconcile_groups,
colvars,
colwise,
combine,
compact,
complete_cases,
complete_cases!,
cut,
Expand Down
4 changes: 2 additions & 2 deletions src/dataframe.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1114,8 +1114,8 @@ nas{T}(dv::DataArray{T}, dims) = # TODO move to datavector.jl?

zeros{T<:ByteString}(::Type{T},args...) = fill("",args...) # needed for string arrays in the `nas` method above

nas{T}(dv::PooledDataVector{T}, dims) =
PooledDataArray(fill(uint16(1), dims), dv.pool)
nas{T,R}(dv::PooledDataVector{T,R}, dims) =
PooledDataArray(RefArray(fill(one(R), dims)), dv.pool)

nas(df::DataFrame, dims) =
DataFrame([nas(x, dims) for x in df.columns], colnames(df))
Expand Down
4 changes: 2 additions & 2 deletions src/extras.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -96,7 +96,7 @@ function cut{S, T}(x::Vector{S}, breaks::Vector{T})
if breaks[end] < max_x
push!(breaks, max_x)
end
refs = fill(POOLED_DATA_VEC_REF_CONVERTER(0), length(x))
refs = fill(zero(DEFAULT_POOLED_REF_TYPE), length(x))
for i in 1:length(x)
if x[i] == min_x
refs[i] = 1
Expand All @@ -116,7 +116,7 @@ function cut{S, T}(x::Vector{S}, breaks::Vector{T})
for i in 2:(n - 1)
pool[i] = string("(", from[i], ",", to[i], "]")
end
PooledDataArray(refs, pool)
PooledDataArray(RefArray(refs), pool)
end
cut(x::Vector, ngroups::Int) = cut(x, quantile(x, [1 : ngroups - 1] / ngroups))

Expand Down
13 changes: 7 additions & 6 deletions src/indexing.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -329,17 +329,17 @@ end
maxShowLength(v::IndexedVector) = length(v) > 0 ? max([length(_string(x)) for x = v.x]) : 0

# Methods to speed up grouping and merging
function PooledDataArray(d::IndexedVector)
refs = zeros(POOLED_DATA_VEC_REF_TYPE, size(d))
oneval = one(POOLED_DATA_VEC_REF_TYPE)
function PooledDataArray{R}(d::IndexedVector, ::Type{R})
refs = zeros(R, size(d))
oneval = one(R)
local idx::Int
## local lastval::T
local poolidx::POOLED_DATA_VEC_REF_TYPE
local poolidx::R
pool = Array(eltype(d), 0)
# skip over NAs
nna = length(d) - length(d.x)
if nna == length(d)
return PooledDataArray(refs, pool)
return PooledDataArray(RefArray(refs), pool)
end
lastval = d.x[d.idx[nna+1]]
push!(pool, d.x[d.idx[nna+1]])
Expand All @@ -354,8 +354,9 @@ function PooledDataArray(d::IndexedVector)
end
refs[idx] = poolidx
end
return PooledDataArray(refs, pool)
return PooledDataArray(RefArray(refs), pool)
end
PooledDataArray(d::IndexedVector) = PooledDataArray(d, DEFAULT_POOLED_REF_TYPE)

DataArray(d::IndexedVector) = DataArray(x.x)

Expand Down
9 changes: 5 additions & 4 deletions src/merge.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -95,10 +95,10 @@ function PooledDataVecs(df1::AbstractDataFrame,
ngroups = ngroups * (length(dv1.pool) + 1)
end
pool = [1:ngroups]
(PooledDataArray(refs1, pool), PooledDataArray(refs2, pool))
(PooledDataArray(RefArray(refs1), pool), PooledDataArray(RefArray(refs2), pool))
end

function PooledDataArray(df::AbstractDataFrame)
function PooledDataArray{R}(df::AbstractDataFrame, ::Type{R})
# This method exists to allow another way for merge to work with
# multiple columns. It takes the columns of the DataFrame and
# returns a DataArray with a merged pool that "keys" the
Expand All @@ -107,7 +107,7 @@ function PooledDataArray(df::AbstractDataFrame)
# - I skipped the sort to make it faster.
# - Converting each individual one-row DataFrame to a Tuple
# might be faster.
refs = zeros(POOLED_DATA_VEC_REF_TYPE, nrow(df))
refs = zeros(R, nrow(df))
poolref = Dict{AbstractDataFrame, Int}()
pool = Array(Uint64, 0)
j = 1
Expand All @@ -122,8 +122,9 @@ function PooledDataArray(df::AbstractDataFrame)
j += 1
end
end
return PooledDataArray(refs, pool)
return PooledDataArray(RefArray(refs), pool)
end
PooledDataArray(df::AbstractDataFrame) = PooledDataArray(df, DEFAULT_POOLED_REF_TYPE)

function merge(df1::AbstractDataFrame, df2::AbstractDataFrame, bycol, jointype)

Expand Down
Loading