Fix #41, add tests around evaluate/tuning in MLJ (#42)

* Fix #41, add tests

* fix formatting

* fix bounds for Test, Statistics

* run formatter

* Change formatting default to new lts, 1.10

* bump lts to 1.10, increase StatisticalMeasures lowerbound

* Revert docs version bump. Leaving it for a different PR

* add arm mac to test matrix

* Fix arch for arm mac tests

* bump Catboost.jl to v0.3.6

* Make sure `y_first` is a CategoricalValue

* Pass the pool object to `UnivariateFinite`

* Fix `MMI.predict`, ensure `fitresult` is a named tuple

* reformat

.github/workflows/CI.yml

@@ -26,7 +26,7 @@ jobs:
       fail-fast: false
       matrix:
         version:
-          - '1.6'
+          - '1.10'
           - '1' 
           - 'nightly'
         os:
@@ -40,6 +40,9 @@ jobs:
           - os: macos-latest
             version: '1'
             arch: x64
+          - os: macos-latest
+            version: '1'
+            arch: arm64
     steps:
       - uses: actions/checkout@v4
         with:

.github/workflows/docs.yml

@@ -22,7 +22,7 @@ jobs:
       - uses: julia-actions/setup-julia@latest
         with:
           version: 1.6 # earliest supported version
-      - uses: julia-actions/cache@v1 # https://github.com/julia-actions/cache
+      - uses: julia-actions/cache@v2 # https://github.com/julia-actions/cache
       - uses: julia-actions/julia-docdeploy@releases/v1
         env:
           GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }} # For authentication with GitHub Actions token

.github/workflows/format_check.yml

@@ -15,7 +15,7 @@ jobs:
     steps:
       - uses: julia-actions/setup-julia@latest
         with:
-          version: 1.6.0
+          version: 1.10.7
       - uses: actions/checkout@v4
       - name: Instantiate `format` environment and format
         run: |

CondaPkg.toml

@@ -1,3 +1,2 @@
 [deps]
-numpy = ">=1,<2"
 catboost = ">=1.1"

Project.toml

@@ -1,32 +1,40 @@
 name = "CatBoost"
 uuid = "e2e10f9a-a85d-4fa9-b6b2-639a32100a12"
 authors = ["Beacon Biosignals, Inc."]
-version = "0.3.5"
+version = "0.3.6"
 
 [deps]
+CategoricalArrays = "324d7699-5711-5eae-9e2f-1d82baa6b597"
 MLJModelInterface = "e80e1ace-859a-464e-9ed9-23947d8ae3ea"
 OrderedCollections = "bac558e1-5e72-5ebc-8fee-abe8a469f55d"
 PythonCall = "6099a3de-0909-46bc-b1f4-468b9a2dfc0d"
 Tables = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
 
 [compat]
 Aqua = "0.8.4"
+CategoricalArrays = "0.10.8"
 DataFrames = "1.6"
 MLJBase = "1"
 MLJModelInterface = "1.7"
 MLJTestInterface = "0.2.6"
+MLJTuning = "0.8"
 OrderedCollections = "1.6"
 PythonCall = "0.9"
+StatisticalMeasures = "0.1.7"
+Statistics = "<0.0.1, 1"
 Tables = "1.10"
-Test = "1.6"
-julia = "1.6"
+Test = "<0.0.1, 1"
+julia = "1.10"
 
 [extras]
 Aqua = "4c88cf16-eb10-579e-8560-4a9242c79595"
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
 MLJBase = "a7f614a8-145f-11e9-1d2a-a57a1082229d"
 MLJTestInterface = "72560011-54dd-4dc2-94f3-c5de45b75ecd"
+MLJTuning = "03970b2e-30c4-11ea-3135-d1576263f10f"
+StatisticalMeasures = "a19d573c-0a75-4610-95b3-7071388c7541"
+Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
 
 [targets]
-test = ["Aqua", "DataFrames", "MLJBase", "MLJTestInterface", "Test"]
+test = ["Aqua", "DataFrames", "MLJBase", "MLJTestInterface", "MLJTuning", "Statistics", "StatisticalMeasures", "Test"]

format/Manifest.toml

@@ -1,196 +1,113 @@
 # This file is machine-generated - editing it directly is not advised
 
-[[ArgTools]]
-uuid = "0dad84c5-d112-42e6-8d28-ef12dabb789f"
+julia_version = "1.10.7"
+manifest_format = "2.0"
+project_hash = "30b405be1c677184b7703a9bfb3d2100029ccad0"
 
-[[Artifacts]]
-uuid = "56f22d72-fd6d-98f1-02f0-08ddc0907c33"
-
-[[Base64]]
+[[deps.Base64]]
 uuid = "2a0f44e3-6c83-55bd-87e4-b1978d98bd5f"
 
-[[CSTParser]]
+[[deps.CSTParser]]
 deps = ["Tokenize"]
-git-tree-sha1 = "3ddd48d200eb8ddf9cb3e0189fc059fd49b97c1f"
+git-tree-sha1 = "0157e592151e39fa570645e2b2debcdfb8a0f112"
 uuid = "00ebfdb7-1f24-5e51-bd34-a7502290713f"
-version = "3.3.6"
+version = "3.4.3"
 
-[[CommonMark]]
-deps = ["Crayons", "JSON", "PrecompileTools", "URIs"]
-git-tree-sha1 = "532c4185d3c9037c0237546d817858b23cf9e071"
+[[deps.CommonMark]]
+deps = ["Crayons", "PrecompileTools"]
+git-tree-sha1 = "3faae67b8899797592335832fccf4b3c80bb04fa"
 uuid = "a80b9123-70ca-4bc0-993e-6e3bcb318db6"
-version = "0.8.12"
+version = "0.8.15"
 
-[[Compat]]
-deps = ["Dates", "LinearAlgebra", "UUIDs"]
-git-tree-sha1 = "886826d76ea9e72b35fcd000e535588f7b60f21d"
+[[deps.Compat]]
+deps = ["TOML", "UUIDs"]
+git-tree-sha1 = "8ae8d32e09f0dcf42a36b90d4e17f5dd2e4c4215"
 uuid = "34da2185-b29b-5c13-b0c7-acf172513d20"
-version = "4.10.1"
+version = "4.16.0"
+
+    [deps.Compat.extensions]
+    CompatLinearAlgebraExt = "LinearAlgebra"
 
-[[Crayons]]
+    [deps.Compat.weakdeps]
+    Dates = "ade2ca70-3891-5945-98fb-dc099432e06a"
+    LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
+
+[[deps.Crayons]]
 git-tree-sha1 = "249fe38abf76d48563e2f4556bebd215aa317e15"
 uuid = "a8cc5b0e-0ffa-5ad4-8c14-923d3ee1735f"
 version = "4.1.1"
 
-[[DataStructures]]
+[[deps.DataStructures]]
 deps = ["Compat", "InteractiveUtils", "OrderedCollections"]
-git-tree-sha1 = "ac67408d9ddf207de5cfa9a97e114352430f01ed"
+git-tree-sha1 = "1d0a14036acb104d9e89698bd408f63ab58cdc82"
 uuid = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
-version = "0.18.16"
+version = "0.18.20"
 
-[[Dates]]
+[[deps.Dates]]
 deps = ["Printf"]
 uuid = "ade2ca70-3891-5945-98fb-dc099432e06a"
 
-[[Downloads]]
-deps = ["ArgTools", "LibCURL", "NetworkOptions"]
-uuid = "f43a241f-c20a-4ad4-852c-f6b1247861c6"
-
-[[Glob]]
+[[deps.Glob]]
 git-tree-sha1 = "97285bbd5230dd766e9ef6749b80fc617126d496"
 uuid = "c27321d9-0574-5035-807b-f59d2c89b15c"
 version = "1.3.1"
 
-[[InteractiveUtils]]
+[[deps.InteractiveUtils]]
 deps = ["Markdown"]
 uuid = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
 
-[[JSON]]
-deps = ["Dates", "Mmap", "Parsers", "Unicode"]
-git-tree-sha1 = "31e996f0a15c7b280ba9f76636b3ff9e2ae58c9a"
-uuid = "682c06a0-de6a-54ab-a142-c8b1cf79cde6"
-version = "0.21.4"
-
-[[JuliaFormatter]]
-deps = ["CSTParser", "CommonMark", "DataStructures", "Glob", "Pkg", "PrecompileTools", "Tokenize"]
-git-tree-sha1 = "8f5295e46f594ad2d8652f1098488a77460080cd"
+[[deps.JuliaFormatter]]
+deps = ["CSTParser", "CommonMark", "DataStructures", "Glob", "PrecompileTools", "TOML", "Tokenize"]
+git-tree-sha1 = "59cf7ad64f1b0708a4fa4369879d33bad3239b56"
 uuid = "98e50ef6-434e-11e9-1051-2b60c6c9e899"
-version = "1.0.45"
-
-[[LibCURL]]
-deps = ["LibCURL_jll", "MozillaCACerts_jll"]
-uuid = "b27032c2-a3e7-50c8-80cd-2d36dbcbfd21"
-
-[[LibCURL_jll]]
-deps = ["Artifacts", "LibSSH2_jll", "Libdl", "MbedTLS_jll", "Zlib_jll", "nghttp2_jll"]
-uuid = "deac9b47-8bc7-5906-a0fe-35ac56dc84c0"
+version = "1.0.62"
 
-[[LibGit2]]
-deps = ["Base64", "NetworkOptions", "Printf", "SHA"]
-uuid = "76f85450-5226-5b5a-8eaa-529ad045b433"
-
-[[LibSSH2_jll]]
-deps = ["Artifacts", "Libdl", "MbedTLS_jll"]
-uuid = "29816b5a-b9ab-546f-933c-edad1886dfa8"
-
-[[Libdl]]
-uuid = "8f399da3-3557-5675-b5ff-fb832c97cbdb"
-
-[[LinearAlgebra]]
-deps = ["Libdl"]
-uuid = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
-
-[[Logging]]
-uuid = "56ddb016-857b-54e1-b83d-db4d58db5568"
-
-[[Markdown]]
+[[deps.Markdown]]
 deps = ["Base64"]
 uuid = "d6f4376e-aef5-505a-96c1-9c027394607a"
 
-[[MbedTLS_jll]]
-deps = ["Artifacts", "Libdl"]
-uuid = "c8ffd9c3-330d-5841-b78e-0817d7145fa1"
-
-[[Mmap]]
-uuid = "a63ad114-7e13-5084-954f-fe012c677804"
-
-[[MozillaCACerts_jll]]
-uuid = "14a3606d-f60d-562e-9121-12d972cd8159"
-
-[[NetworkOptions]]
-uuid = "ca575930-c2e3-43a9-ace4-1e988b2c1908"
-
-[[OrderedCollections]]
-git-tree-sha1 = "dfdf5519f235516220579f949664f1bf44e741c5"
+[[deps.OrderedCollections]]
+git-tree-sha1 = "12f1439c4f986bb868acda6ea33ebc78e19b95ad"
 uuid = "bac558e1-5e72-5ebc-8fee-abe8a469f55d"
-version = "1.6.3"
-
-[[Parsers]]
-deps = ["Dates", "PrecompileTools", "UUIDs"]
-git-tree-sha1 = "8489905bcdbcfac64d1daa51ca07c0d8f0283821"
-uuid = "69de0a69-1ddd-5017-9359-2bf0b02dc9f0"
-version = "2.8.1"
+version = "1.7.0"
 
-[[Pkg]]
-deps = ["Artifacts", "Dates", "Downloads", "LibGit2", "Libdl", "Logging", "Markdown", "Printf", "REPL", "Random", "SHA", "Serialization", "TOML", "Tar", "UUIDs", "p7zip_jll"]
-uuid = "44cfe95a-1eb2-52ea-b672-e2afdf69b78f"
-
-[[PrecompileTools]]
+[[deps.PrecompileTools]]
 deps = ["Preferences"]
-git-tree-sha1 = "03b4c25b43cb84cee5c90aa9b5ea0a78fd848d2f"
+git-tree-sha1 = "5aa36f7049a63a1528fe8f7c3f2113413ffd4e1f"
 uuid = "aea7be01-6a6a-4083-8856-8a6e6704d82a"
-version = "1.2.0"
+version = "1.2.1"
 
-[[Preferences]]
+[[deps.Preferences]]
 deps = ["TOML"]
-git-tree-sha1 = "00805cd429dcb4870060ff49ef443486c262e38e"
+git-tree-sha1 = "9306f6085165d270f7e3db02af26a400d580f5c6"
 uuid = "21216c6a-2e73-6563-6e65-726566657250"
-version = "1.4.1"
+version = "1.4.3"
 
-[[Printf]]
+[[deps.Printf]]
 deps = ["Unicode"]
 uuid = "de0858da-6303-5e67-8744-51eddeeeb8d7"
 
-[[REPL]]
-deps = ["InteractiveUtils", "Markdown", "Sockets", "Unicode"]
-uuid = "3fa0cd96-eef1-5676-8a61-b3b8758bbffb"
-
-[[Random]]
-deps = ["Serialization"]
+[[deps.Random]]
+deps = ["SHA"]
 uuid = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 
-[[SHA]]
+[[deps.SHA]]
 uuid = "ea8e919c-243c-51af-8825-aaa63cd721ce"
+version = "0.7.0"
 
-[[Serialization]]
-uuid = "9e88b42a-f829-5b0c-bbe9-9e923198166b"
-
-[[Sockets]]
-uuid = "6462fe0b-24de-5631-8697-dd941f90decc"
-
-[[TOML]]
+[[deps.TOML]]
 deps = ["Dates"]
 uuid = "fa267f1f-6049-4f14-aa54-33bafae1ed76"
+version = "1.0.3"
 
-[[Tar]]
-deps = ["ArgTools", "SHA"]
-uuid = "a4e569a6-e804-4fa4-b0f3-eef7a1d5b13e"
-
-[[Tokenize]]
-git-tree-sha1 = "3ac1ac11b09e8033ec93a7993acdb9b68252be6d"
+[[deps.Tokenize]]
+git-tree-sha1 = "468b4685af4abe0e9fd4d7bf495a6554a6276e75"
 uuid = "0796e94c-ce3b-5d07-9a54-7f471281c624"
-version = "0.5.27"
-
-[[URIs]]
-git-tree-sha1 = "67db6cc7b3821e19ebe75791a9dd19c9b1188f2b"
-uuid = "5c2747f8-b7ea-4ff2-ba2e-563bfd36b1d4"
-version = "1.5.1"
+version = "0.5.29"
 
-[[UUIDs]]
+[[deps.UUIDs]]
 deps = ["Random", "SHA"]
 uuid = "cf7118a7-6976-5b1a-9a39-7adc72f591a4"
 
-[[Unicode]]
+[[deps.Unicode]]
 uuid = "4ec0a83e-493e-50e2-b9ac-8f72acf5a8f5"
-
-[[Zlib_jll]]
-deps = ["Libdl"]
-uuid = "83775a58-1f1d-513f-b197-d71354ab007a"
-
-[[nghttp2_jll]]
-deps = ["Artifacts", "Libdl"]
-uuid = "8e850ede-7688-5339-a07c-302acd2aaf8d"
-
-[[p7zip_jll]]
-deps = ["Artifacts", "Libdl"]
-uuid = "3f19e933-33d8-53b3-aaab-bd5110c3b7a0"

format/README.md

@@ -1,6 +1,6 @@
 # format
 
-Run `julia --project=format format/run.jl` with Julia 1.6 to run JuliaFormatter.
+Run `julia --project=format format/run.jl` with Julia 1.10 to run JuliaFormatter.
 
 If you update the version of Julia used to generate the `Manifest.toml` make sure to also
-update the version in `.github/workflows/format_check.yml` to match.
+update the version in `.github/workflows/format_check.yml` to match.

src/MLJCatBoostInterface.jl

@@ -9,6 +9,7 @@ using Tables
 using MLJModelInterface: MLJModelInterface
 const MMI = MLJModelInterface
 using MLJModelInterface: Table, Continuous, Count, Finite, OrderedFactor, Multiclass
+using CategoricalArrays: CategoricalArray, CategoricalValue
 const PKG = "CatBoost"
 
 """
@@ -150,7 +151,7 @@ function MMI.update(mlj_model::CatBoostModels, verbosity::Integer, fitresult, ca
         report = (feature_importances=feature_importance(new_model),)
         cache = (; mlj_model=mlj_model)
     else
-        new_model, cache, report = fit(mlj_model, verbosity, data_pool)
+        new_model, cache, report = MMI.fit(mlj_model, verbosity, data_pool)
     end
 
     return new_model, cache, report