Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
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
1 change: 1 addition & 0 deletions .JuliaFormatter.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
style = "yas"
1 change: 1 addition & 0 deletions .git-blame-ignore-revs
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
b816a8162b8d602a439da67eacca33e8b3961fdd
10 changes: 10 additions & 0 deletions .github/workflows/Format.yml
Original file line number Diff line number Diff line change
@@ -0,0 +1,10 @@
name: Format suggestions
on:
pull_request:
jobs:
code-style:
runs-on: ubuntu-latest
steps:
- uses: julia-actions/julia-format@v4
with:
version: '2'
44 changes: 20 additions & 24 deletions docs/make.jl
Original file line number Diff line number Diff line change
Expand Up @@ -7,28 +7,24 @@ end

DocMeta.setdocmeta!(StatsBase, :DocTestSetup, :(using StatsBase))

makedocs(
sitename = "StatsBase.jl",
modules = [StatsBase, StatsAPI],
format = Documenter.HTML(assets = ["assets/favicon.ico"]),
pages = ["index.md",
"weights.md",
"scalarstats.md",
"robust.md",
"deviation.md",
"cov.md",
"counts.md",
"ranking.md",
"sampling.md",
"empirical.md",
"signalcorr.md",
"multivariate.md",
"misc.md",
"statmodels.md",
"transformations.md"],
checkdocs=:exports
)
makedocs(; sitename="StatsBase.jl",
modules=[StatsBase, StatsAPI],
format=Documenter.HTML(; assets=["assets/favicon.ico"]),
pages=["index.md",
"weights.md",
"scalarstats.md",
"robust.md",
"deviation.md",
"cov.md",
"counts.md",
"ranking.md",
"sampling.md",
"empirical.md",
"signalcorr.md",
"multivariate.md",
"misc.md",
"statmodels.md",
"transformations.md"],
checkdocs=:exports)

deploydocs(
repo = "github.com/JuliaStats/StatsBase.jl.git"
)
deploydocs(; repo="github.com/JuliaStats/StatsBase.jl.git")
34 changes: 17 additions & 17 deletions perf/sampling.jl
Original file line number Diff line number Diff line change
Expand Up @@ -51,31 +51,31 @@ tsample!(s::Sample_NoRep, a, x) = sample!(a, x; replace=false, ordered=false)
mutable struct Sample_NoRep_Ord <: NoRep end
tsample!(s::Sample_NoRep_Ord, a, x) = sample!(a, x; replace=false, ordered=true)


# config is in the form of (n, k)

Base.string(p::SampleProc{Alg}) where {Alg} = lowercase(string(Alg))

Base.length(p::SampleProc, cfg::Tuple{Int,Int}) = cfg[2]
Base.isvalid(p::SampleProc{<:WithRep}, cfg::Tuple{Int,Int}) = ((n, k) = cfg; n >= 1 && k >= 1)
Base.isvalid(p::SampleProc{<:NoRep}, cfg::Tuple{Int,Int}) = ((n, k) = cfg; n >= k >= 1)
Base.isvalid(p::SampleProc{<:WithRep}, cfg::Tuple{Int,Int}) = ((n, k)=cfg; n >= 1 && k >= 1)
Base.isvalid(p::SampleProc{<:NoRep}, cfg::Tuple{Int,Int}) = ((n, k)=cfg; n >= k >= 1)

Base.start(p::SampleProc, cfg::Tuple{Int,Int}) = Vector{Int}(cfg[2])
Base.run(p::SampleProc{Alg}, cfg::Tuple{Int,Int}, s::Vector{Int}) where {Alg} = tsample!(Alg(), 1:cfg[1], s)
function Base.run(p::SampleProc{Alg}, cfg::Tuple{Int,Int}, s::Vector{Int}) where {Alg}
return tsample!(Alg(), 1:cfg[1], s)
end
Base.done(p::SampleProc, cfg, s) = nothing


### benchmarking

const ns = 5 * (2 .^ [0:9])
const ks = 2 .^ [1:16]

## with replacement

const procs1 = Proc[ SampleProc{Direct}(),
SampleProc{Sample_WRep}(),
SampleProc{Xmultinom}(),
SampleProc{Sample_WRep_Ord}() ]
const procs1 = Proc[SampleProc{Direct}(),
SampleProc{Sample_WRep}(),
SampleProc{Xmultinom}(),
SampleProc{Sample_WRep_Ord}()]

const cfgs1 = vec([(n, k) for k in ks, n in ns])

Expand All @@ -84,14 +84,14 @@ println()

## without replacement

const procs2 = Proc[ SampleProc{Knuths}(),
SampleProc{Fisher_Yates}(),
SampleProc{Self_Avoid}(),
SampleProc{Sample_NoRep}(),
SampleProc{Seq_A}(),
SampleProc{Seq_C}(),
SampleProc{Seq_D}(),
SampleProc{Sample_NoRep_Ord}() ]
const procs2 = Proc[SampleProc{Knuths}(),
SampleProc{Fisher_Yates}(),
SampleProc{Self_Avoid}(),
SampleProc{Sample_NoRep}(),
SampleProc{Seq_A}(),
SampleProc{Seq_C}(),
SampleProc{Seq_D}(),
SampleProc{Sample_NoRep_Ord}()]

const cfgs2 = (Int, Int)[]
for n in 5 * (2 .^ [0:11]), k in 2 .^ [1:16]
Expand Down
29 changes: 14 additions & 15 deletions perf/wsampling.jl
Original file line number Diff line number Diff line change
Expand Up @@ -33,14 +33,15 @@ tsample!(s::Sample_WRep, wv, x) = sample!(1:length(wv), wv, x; ordered=false)
mutable struct Sample_WRep_Ord <: WithRep end
tsample!(s::Sample_WRep_Ord, wv, x) = sample!(1:length(wv), wv, x; ordered=true)


# config is in the form of (n, k)

Base.string(p::WSampleProc{Alg}) where {Alg} = lowercase(string(Alg))

Base.length(p::WSampleProc, cfg::Tuple{Int,Int}) = cfg[2]
Base.isvalid(p::WSampleProc{<:WithRep}, cfg::Tuple{Int,Int}) = ((n, k) = cfg; n >= 1 && k >= 1)
Base.isvalid(p::WSampleProc{<:NoRep}, cfg::Tuple{Int,Int}) = ((n, k) = cfg; n >= k >= 1)
function Base.isvalid(p::WSampleProc{<:WithRep}, cfg::Tuple{Int,Int})
return ((n, k)=cfg; n >= 1 && k >= 1)
end
Base.isvalid(p::WSampleProc{<:NoRep}, cfg::Tuple{Int,Int}) = ((n, k)=cfg; n >= k >= 1)

function Base.start(p::WSampleProc, cfg::Tuple{Int,Int})
n, k = cfg
Expand All @@ -49,36 +50,34 @@ function Base.start(p::WSampleProc, cfg::Tuple{Int,Int})
return (w, x)
end

Base.run(p::WSampleProc{Alg}, cfg::Tuple{Int,Int}, s) where {Alg} = tsample!(Alg(), s[1], s[2])
function Base.run(p::WSampleProc{Alg}, cfg::Tuple{Int,Int}, s) where {Alg}
return tsample!(Alg(), s[1], s[2])
end
Base.done(p::WSampleProc, cfg, s) = nothing


### benchmarking

const ns = 5 * (2 .^ [0:9])
const ks = 2 .^ [1:16]

## with replacement

const procs1 = Proc[ WSampleProc{Direct}(),
WSampleProc{Alias}(),
WSampleProc{Xmultinom_S}(),
WSampleProc{Sample_WRep}(),
WSampleProc{Xmultinom}(),
WSampleProc{Direct_S}(),
WSampleProc{Sample_WRep_Ord}() ]
const procs1 = Proc[WSampleProc{Direct}(),
WSampleProc{Alias}(),
WSampleProc{Xmultinom_S}(),
WSampleProc{Sample_WRep}(),
WSampleProc{Xmultinom}(),
WSampleProc{Direct_S}(),
WSampleProc{Sample_WRep_Ord}()]

const cfgs1 = vec([(n, k) for k in ks, n in ns])

rtable1 = run(procs1, cfgs1; duration=0.2)
println()


## show results

println("Sampling With Replacement")
println("===================================")
show(rtable1; unit=:mps, cfghead="(n, k)")
println()


Loading
Loading