minor tings

.JuliaFormatter.toml

@@ -0,0 +1,2 @@
+# See https://domluna.github.io/JuliaFormatter.jl/stable/ for a list of options
+style = "blue"

.github/workflows/CI.yml

@@ -20,7 +20,7 @@ jobs:
       matrix:
         version:
           - '1.10'
-          - 'pre'
+          - '1'
         os:
           - ubuntu-latest
         arch:

.github/workflows/FormatCheck.yml

@@ -0,0 +1,37 @@
+name: Format Check
+
+on:
+  push:
+    branches:
+      - 'main'
+      - 'release-'
+    tags: '*'
+  pull_request:
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: julia-actions/setup-julia@latest
+        with:
+          version: 1
+      - uses: actions/checkout@v1
+      - name: Install JuliaFormatter
+        run: |
+          using Pkg
+          Pkg.add("JuliaFormatter")
+        shell: julia --color=yes {0}
+      - name: Format code
+        run: |
+          using JuliaFormatter
+          format("."; verbose=true)
+        shell: julia --color=yes {0}
+      - name: Check for formatting errors
+        shell: bash
+        run: |
+          output=$(git diff --name-only)
+          if [ "$output" != "" ]; then
+              >&2 echo "Some files have not been formatted !!!"
+              echo "$output"
+              exit 1
+          fi

docs/make.jl

@@ -14,12 +14,7 @@ makedocs(;
         edit_link="master",
         assets=String[],
     ),
-    pages=[
-        "Home" => "index.md",
-    ],
+    pages=["Home" => "index.md"],
 )
 
-deploydocs(;
-    repo="github.com/JuliaTrustworthyAI/TaijaData.jl",
-    devbranch="master",
-)
+deploydocs(; repo="github.com/JuliaTrustworthyAI/TaijaData.jl", devbranch="master")

src/synthetic/blobs.jl

@@ -11,6 +11,6 @@ function load_blobs(n=250; seed=data_seed, k=2, centers=2, kwrgs...)
     X, y = MLJBase.make_blobs(n, k; centers=centers, rng=seed, kwrgs...)
     X = permutedims(MLJBase.matrix(X))
     y = DataAPI.unwrap.(y)
-    
+
     return (X, y)
 end

src/tabular/california_housing.jl

@@ -26,6 +26,6 @@ function load_california_housing(n::Union{Nothing,Int}=5000)
     if !isnothing(n)
         X, y = subsample(X, y, n)
     end
-    
+
     return (X, y)
 end

src/tabular/credit_default.jl

@@ -12,7 +12,7 @@ function load_credit_default(n::Union{Nothing,Int}=5000)
     df.SEX = MLJBase.categorical(df.SEX)
     df.EDUCATION = MLJBase.categorical(df.EDUCATION)
     df.MARRIAGE = MLJBase.categorical(df.MARRIAGE)
-    transformer = MLJModels.Standardizer(; count=true) |> MLJModels.ContinuousEncoder()
+    transformer = MLJModels.ContinuousEncoder()(MLJModels.Standardizer(; count=true))
     mach = MLJBase.fit!(MLJBase.machine(transformer, df[:, DataFrames.Not(:target)]))
     X = MLJBase.transform(mach, df[:, DataFrames.Not(:target)])
     X = permutedims(Matrix(X))

src/tabular/german_credit.jl

@@ -25,7 +25,7 @@ function load_german_credit(n::Union{Nothing,Int}=nothing)
     X = permutedims(X)
 
     # Counterfactual data:
-    y = convert(Vector,df.target)
+    y = convert(Vector, df.target)
 
     # Undersample:
     if !isnothing(n)

src/utils.jl

@@ -24,5 +24,4 @@ function subsample(X::AbstractMatrix, y::AbstractVector, n::Int)
     y = y[idx]
 
     return (X, y)
-
 end

src/vision/cifar_10.jl

@@ -17,7 +17,7 @@ function load_cifar_10(n::Union{Nothing,Int}=nothing)
     if !isnothing(n)
         X, y = subsample(X, y, n)
     end
-    
+
     return (X, y)
 end
 

test/data.jl

@@ -26,17 +26,16 @@ end
             @test size(dataset[1])[2] == 1000  # replace ... with actual size of your data
         end
     end
-    
+
     @testset "load_synthetic_data tests" begin
-            # Test dropping a specific dataset
-            data = TaijaData.load_synthetic_data(; drop=:linearly_separable)
-            @test !haskey(data, :linearly_separable)
-
-            # Test loading with specified number of samples
-            data = TaijaData.load_synthetic_data(500)
-            for dataset in values(data)
-                @test size(dataset[1])[2] == 500  # replace ... with actual size of your data
-            end
+        # Test dropping a specific dataset
+        data = TaijaData.load_synthetic_data(; drop=:linearly_separable)
+        @test !haskey(data, :linearly_separable)
+
+        # Test loading with specified number of samples
+        data = TaijaData.load_synthetic_data(500)
+        for dataset in values(data)
+            @test size(dataset[1])[2] == 500  # replace ... with actual size of your data
         end
+    end
 end
-

test/tabular.jl

@@ -7,7 +7,7 @@ using TaijaData
         @testset "Check output types and sizes" begin
             result = load_california_housing(100)
 
-            @test isa(result, Tuple{Matrix, Vector})
+            @test isa(result, Tuple{Matrix,Vector})
 
             @test size(result[1], 2) == 100  # there should be 100 observations