initial files

.github/workflows/TagBot.yml

@@ -0,0 +1,11 @@
+name: TagBot
+on:
+  schedule:
+    - cron: 0 0 * * *
+jobs:
+  TagBot:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: JuliaRegistries/TagBot@v1
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}

.gitignore

@@ -0,0 +1,2 @@
+Manifest.toml
+*DS_Store

.travis.yml

@@ -0,0 +1,16 @@
+### Documentation: http://docs.travis-ci.com/user/languages/julia/
+language: julia
+os:
+  - linux
+env:
+  global:
+    - PYTHON=Conda
+julia:
+  - 1.0
+  - 1.4
+  - nightly
+notifications:
+  email: false
+
+after_success:
+ - julia -e 'import Pkg; Pkg.add("Coverage"); using Coverage; Coveralls.submit(process_folder())'

LICENSE.md

@@ -0,0 +1,24 @@
+The MLJ.jl package is licensed under the MIT "Expat" License:
+
+> Copyright (c) 2020: Thibaut Lienart, Anthony Blaom and collaborators
+
+> 
+> Permission is hereby granted, free of charge, to any person obtaining a copy
+> of this software and associated documentation files (the "Software"), to deal
+> in the Software without restriction, including without limitation the rights
+> to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+> copies of the Software, and to permit persons to whom the Software is
+> furnished to do so, subject to the following conditions:
+> 
+> The above copyright notice and this permission notice shall be included in all
+> copies or substantial portions of the Software.
+> 
+> THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+> IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+> FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+> AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+> LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+> OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+> SOFTWARE.
+> 
+

Project.toml

@@ -0,0 +1,23 @@
+name = "MLJScikitLearnInterface"
+uuid = "5ae90465-5518-4432-b9d2-8a1def2f0cab"
+authors = ["Thibaut Lienart, Anthony Blaom"]
+version = "0.1.0"
+
+[deps]
+MLJModelInterface = "e80e1ace-859a-464e-9ed9-23947d8ae3ea"
+PyCall = "438e738f-606a-5dbb-bf0a-cddfbfd45ab0"
+ScikitLearn = "3646fa90-6ef7-5e7e-9f22-8aca16db6324"
+
+[compat]
+MLJModelInterface = "0.2"
+PyCall = "1"
+ScikitLearn = "0.5,0.6"
+julia = "1"
+
+[extras]
+MLJBase = "a7f614a8-145f-11e9-1d2a-a57a1082229d"
+StableRNGs = "860ef19b-820b-49d6-a774-d7a799459cd3"
+Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
+
+[targets]
+test = ["StableRNGs", "Test", "MLJBase"]

README.md

@@ -0,0 +1,10 @@
+# MLJ <> ScikitLearn.jl
+
+**Note**: for errors with MKL on Mac, please refer to [ScikitLearn.jl](https://github.com/cstjean/ScikitLearn.jl) as it's a known issue.
+
+## Todo
+
+**June 2020**
+
+* Tests for clustering (port from MLJModels)
+* Maybe more integration tests

src/MLJScikitLearnInterface.jl

@@ -0,0 +1,74 @@
+module MLJScikitLearnInterface
+
+import MLJModelInterface
+import MLJModelInterface:
+        @mlj_model, _process_model_def, _model_constructor, _model_cleaner,
+        Table, Continuous, Count, Finite, OrderedFactor, Multiclass, Unknown
+const MMI = MLJModelInterface
+
+import ScikitLearn
+function __init__()
+    ScikitLearn.Skcore.import_sklearn()
+end
+const SK = ScikitLearn
+
+# Note: PyCall is already imported as part of ScikitLearn so this is cheap
+import PyCall: ispynull, PyNULL, pyimport
+
+# ------------------------------------------------------------------------
+# NOTE: the next few lines of wizardry and their call should not be
+# modified carelessly. In particular do consider the recommendations at
+# JuliaPy/PyCall.jl#using-pycall-from-julia-modules
+# from which much of this stems.
+
+# supervised
+const SKLM = PyNULL()
+const SKGP = PyNULL()
+const SKEN = PyNULL()
+const SKDU = PyNULL()
+const SKNB = PyNULL()
+const SKNE = PyNULL()
+const SKDA = PyNULL()
+const SKSV = PyNULL()
+sklm(m) = (:SKLM, :linear_model, m)
+skgp(m) = (:SKGP, :gaussian_process, m)
+sken(m) = (:SKEN, :ensemble, m)
+skdu(m) = (:SKDU, :dummy, m)
+sknb(m) = (:SKNB, :naive_bayes, m)
+skne(m) = (:SKNE, :neighbors, m)
+skda(m) = (:SKDA, :discriminant_analysis, m)
+sksv(m) = (:SKSV, :svm, m)
+
+# unsupervised
+const SKCL = PyNULL()
+skcl(m) = (:SKCL, :cluster, m)
+
+# Generic loader (see _skmodel_fit_* in macros)
+ski!(sks, mdl) = copy!(sks, pyimport("sklearn.$mdl"))
+# ------------------------------------------------------------------------
+
+const Option{T} = Union{Nothing,T}
+
+# recurrent information for traits
+const SK_NAME = "ScikitLearn"
+const SK_UUID = "3646fa90-6ef7-5e7e-9f22-8aca16db6324"
+const SK_URL  = "https://github.com/cstjean/ScikitLearn.jl"
+const SK_LIC  = "BSD"
+
+const CV = "with built-in cross-validation"
+
+include("macros.jl")
+include("meta.jl")
+
+include("models/linear-regressors.jl")
+include("models/linear-regressors-multi.jl")
+include("models/linear-classifiers.jl")
+include("models/gaussian-process.jl")
+include("models/ensemble.jl")
+include("models/discriminant-analysis.jl")
+include("models/svm.jl")
+include("models/misc.jl")
+
+include("models/clustering.jl")
+
+end