Use the viewhint option in Sample (#238)

* Use the 'viewhint' option in 'Sample' * Update tests * Update tests
JuliaML · Nov 28, 2023 · 709a2f5 · 709a2f5
1 parent a5394d0
commit 709a2f5
Show file tree

Hide file tree

Showing 5 changed files with 18 additions and 7 deletions.
diff --git a/src/transforms/sample.jl b/src/transforms/sample.jl
@@ -12,14 +12,14 @@ the same order of the original table.
 # Examples
 
 ```julia
-Sample(1_000)
-Sample(1_000, replace=false)
-Sample(1_000, replace=false, ordered=true)
+Sample(1000)
+Sample(1000, replace=false)
+Sample(1000, replace=false, ordered=true)
 
 # with rng
 using Random
 rng = MersenneTwister(2)
-Sample(1_000, rng=rng)
+Sample(1000, rng=rng)
 
 # with weights
 Sample(10, rand(100))
@@ -68,8 +68,8 @@ function applyfeat(::Sample, feat, prep)
   sinds, rinds = prep
 
   # selected and removed rows
-  srows = Tables.subset(feat, sinds)
-  rrows = Tables.subset(feat, rinds)
+  srows = Tables.subset(feat, sinds, viewhint=true)
+  rrows = Tables.subset(feat, rinds, viewhint=true)
 
   newfeat = srows |> Tables.materializer(feat)
   newfeat, (sinds, rinds, rrows)

diff --git a/src/transforms/satisfies.jl b/src/transforms/satisfies.jl
@@ -62,7 +62,7 @@ Selects the columns that don't have scientific type `S`.
 
 ```julia
 import DataScienceTraits as DST
-Except(DST.Continuous)
+Except(DST.Categorical)
 ```
 """
 Except(S::Type{<:SciType}) = Satisfies(x -> !(elscitype(x) <: S))
diff --git a/test/Project.toml b/test/Project.toml
@@ -1,6 +1,7 @@
 [deps]
 CairoMakie = "13f3f980-e62b-5c42-98c6-ff1f3baf88f0"
 CategoricalArrays = "324d7699-5711-5eae-9e2f-1d82baa6b597"
+CoDa = "5900dafe-f573-5c72-b367-76665857777b"
 ColumnSelectors = "9cc86067-7e36-4c61-b350-1ac9833d277f"
 DataScienceTraits = "6cb2f572-2d2b-4ba6-bdb3-e710fa044d6c"
 Distributions = "31c24e10-a181-5473-b8eb-7969acd0382f"

diff --git a/test/runtests.jl b/test/runtests.jl
@@ -1,4 +1,5 @@
 using TableTransforms
+using CoDa
 using Tables
 using Unitful
 using TypedTables

diff --git a/test/transforms/sample.jl b/test/transforms/sample.jl
@@ -60,4 +60,13 @@
   @test isapprox(count(==(trows[4]), nrows) / 10_000, 4 / 21, atol=0.01)
   @test isapprox(count(==(trows[5]), nrows) / 10_000, 5 / 21, atol=0.01)
   @test isapprox(count(==(trows[6]), nrows) / 10_000, 6 / 21, atol=0.01)
+
+  # performance tests
+  x = rand(100_000)
+  y = rand(100_000)
+  c = CoDaArray((a = rand(100_000), b = rand(100_000), c = rand(100_000)))
+  t = Table(; x, y, c)
+
+  T = Sample(10_000)
+  @test @elapsed(apply(T, t)) < 0.5
 end