For a 0.2.5 release

Project.toml

@@ -1,7 +1,7 @@
 name = "FeatureSelection"
 uuid = "33837fe5-dbff-4c9e-8c2f-c5612fe2b8b6"
 authors = ["Anthony D. Blaom <anthony.blaom@gmail.com>", "Samuel Okon <okonsamuel50@gmail.com"]
-version = "0.2.4"
+version = "0.2.5"
 
 [deps]
 MLJModelInterface = "e80e1ace-859a-464e-9ed9-23947d8ae3ea"
@@ -11,38 +11,28 @@ Tables = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
 [compat]
 Aqua = "0.8"
 Distributions = "0.25"
-julia = "1.10"
 MLJBase = "1.4"
-MLJTuning = "0.8"
 MLJDecisionTreeInterface = "0.4"
-MLJScikitLearnInterface = "0.6"
 MLJModelInterface = "1.10"
+MLJScikitLearnInterface = "0.6, 0.7"
+MLJTuning = "0.8"
 ScientificTypesBase = "3"
 StableRNGs = "1"
 StatisticalMeasures = "0.1, 0.2, 0.3"
 Tables = "1.2"
 Test = "1.6"
+julia = "1.10"
 
 [extras]
 Aqua = "4c88cf16-eb10-579e-8560-4a9242c79595"
 Distributions = "31c24e10-a181-5473-b8eb-7969acd0382f"
 MLJBase = "a7f614a8-145f-11e9-1d2a-a57a1082229d"
-MLJTuning = "03970b2e-30c4-11ea-3135-d1576263f10f"
 MLJDecisionTreeInterface = "c6f25543-311c-4c74-83dc-3ea6d1015661"
 MLJScikitLearnInterface = "5ae90465-5518-4432-b9d2-8a1def2f0cab"
+MLJTuning = "03970b2e-30c4-11ea-3135-d1576263f10f"
 StableRNGs = "860ef19b-820b-49d6-a774-d7a799459cd3"
 StatisticalMeasures = "a19d573c-0a75-4610-95b3-7071388c7541"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
 
 [targets]
-test = [
-    "Aqua",
-    "Distributions",
-    "MLJBase",
-    "MLJTuning",
-    "MLJDecisionTreeInterface",
-    "MLJScikitLearnInterface",
-    "StableRNGs", 
-    "StatisticalMeasures",
-    "Test"
-]
+test = ["Aqua", "Distributions", "MLJBase", "MLJTuning", "MLJDecisionTreeInterface", "MLJScikitLearnInterface", "StableRNGs", "StatisticalMeasures", "Test"]

src/FeatureSelection.jl

@@ -10,5 +10,6 @@ const MMI = MLJModelInterface
 include("models/featureselector.jl")
 include("models/rfe.jl")
 include("shared.jl")
+include("type_docstrings.jl")
 
 end # module

src/models/featureselector.jl

@@ -87,82 +87,4 @@ MMI.metadata_model(
     load_path = "FeatureSelection.FeatureSelector"
 )
 
-## Docstring
-"""
-$(MMI.doc_header(FeatureSelector))
-
-Use this model to select features (columns) of a table, usually as
-part of a model `Pipeline`.
-
-
-# Training data
-
-In MLJ or MLJBase, bind an instance `model` to data with
-
-    mach = machine(model, X)
-
-where
-
-- `X`: any table of input features, where "table" is in the sense of Tables.jl
-
-Train the machine using `fit!(mach, rows=...)`.
-
-
-# Hyper-parameters
-
-- `features`: one of the following, with the behavior indicated:
-
-  - `[]` (empty, the default): filter out all features (columns) which
-    were not encountered in training
-
-  - non-empty vector of feature names (symbols): keep only the
-    specified features (`ignore=false`) or keep only unspecified
-    features (`ignore=true`)
-
-  - function or other callable: keep a feature if the callable returns
-    `true` on its name. For example, specifying
-    `FeatureSelector(features = name -> name in [:x1, :x3], ignore =
-    true)` has the same effect as `FeatureSelector(features = [:x1,
-    :x3], ignore = true)`, namely to select all features, with the
-    exception of `:x1` and `:x3`.
-
-- `ignore`: whether to ignore or keep specified `features`, as
-  explained above
-
-
-# Operations
-
-- `transform(mach, Xnew)`: select features from the table `Xnew` as
-  specified by the model, taking features seen during training into
-  account, if relevant
-
-
-# Fitted parameters
-
-The fields of `fitted_params(mach)` are:
-
-- `features_to_keep`: the features that will be selected
-
-
-# Example
-
-```
-using MLJ
-
-X = (ordinal1 = [1, 2, 3],
-     ordinal2 = coerce(["x", "y", "x"], OrderedFactor),
-     ordinal3 = [10.0, 20.0, 30.0],
-     ordinal4 = [-20.0, -30.0, -40.0],
-     nominal = coerce(["Your father", "he", "is"], Multiclass));
-
-selector = FeatureSelector(features=[:ordinal3, ], ignore=true);
-
-julia> transform(fit!(machine(selector, X)), X)
-(ordinal1 = [1, 2, 3],
- ordinal2 = CategoricalValue{Symbol,UInt32}["x", "y", "x"],
- ordinal4 = [-20.0, -30.0, -40.0],
- nominal = CategoricalValue{String,UInt32}["Your father", "he", "is"],)
-
-```
-"""
-FeatureSelector
+# docstring is in "src/type_docstrings.jl"

src/models/rfe.jl

@@ -22,7 +22,7 @@ const ERR_FEATURES_SEEN = ArgumentError(
 const MODEL_TYPES = [
     :ProbabilisticRecursiveFeatureElimination, :DeterministicRecursiveFeatureElimination
 ]
-const SUPER_TYPES = [:Deterministic, :Probabilistic]
+const SUPER_TYPES = [:Probabilistic, :Deterministic]
 const MODELTYPE_GIVEN_SUPERTYPES = zip(MODEL_TYPES, SUPER_TYPES)
 
 for (ModelType, ModelSuperType) in  MODELTYPE_GIVEN_SUPERTYPES
@@ -181,6 +181,7 @@ function RecursiveFeatureElimination(
         # which is rare.
         throw(ERR_MODEL_TYPE)
     end
+
     message = MMI.clean!(selector)
     isempty(message) || @warn(message)
     return selector

src/type_docstrings.jl

@@ -0,0 +1,81 @@
+# This file cannot be include before types and all metadata is defined
+
+## Docstring
+"""
+$(MMI.doc_header(FeatureSelector))
+
+Use this model to select features (columns) of a table, usually as
+part of a model `Pipeline`.
+
+
+# Training data
+
+In MLJ or MLJBase, bind an instance `model` to data with
+
+    mach = machine(model, X)
+
+where
+
+- `X`: any table of input features, where "table" is in the sense of Tables.jl
+
+Train the machine using `fit!(mach, rows=...)`.
+
+
+# Hyper-parameters
+
+- `features`: one of the following, with the behavior indicated:
+
+  - `[]` (empty, the default): filter out all features (columns) which
+    were not encountered in training
+
+  - non-empty vector of feature names (symbols): keep only the
+    specified features (`ignore=false`) or keep only unspecified
+    features (`ignore=true`)
+
+  - function or other callable: keep a feature if the callable returns
+    `true` on its name. For example, specifying
+    `FeatureSelector(features = name -> name in [:x1, :x3], ignore =
+    true)` has the same effect as `FeatureSelector(features = [:x1,
+    :x3], ignore = true)`, namely to select all features, with the
+    exception of `:x1` and `:x3`.
+
+- `ignore`: whether to ignore or keep specified `features`, as
+  explained above
+
+
+# Operations
+
+- `transform(mach, Xnew)`: select features from the table `Xnew` as
+  specified by the model, taking features seen during training into
+  account, if relevant
+
+
+# Fitted parameters
+
+The fields of `fitted_params(mach)` are:
+
+- `features_to_keep`: the features that will be selected
+
+
+# Example
+
+```
+using MLJ
+
+X = (ordinal1 = [1, 2, 3],
+     ordinal2 = coerce(["x", "y", "x"], OrderedFactor),
+     ordinal3 = [10.0, 20.0, 30.0],
+     ordinal4 = [-20.0, -30.0, -40.0],
+     nominal = coerce(["Your father", "he", "is"], Multiclass));
+
+selector = FeatureSelector(features=[:ordinal3, ], ignore=true);
+
+julia> transform(fit!(machine(selector, X)), X)
+(ordinal1 = [1, 2, 3],
+ ordinal2 = CategoricalValue{Symbol,UInt32}["x", "y", "x"],
+ ordinal4 = [-20.0, -30.0, -40.0],
+ nominal = CategoricalValue{String,UInt32}["Your father", "he", "is"],)
+
+```
+"""
+FeatureSelector

test/models/featureselector.jl

@@ -62,6 +62,7 @@
     # Test model Metadata
     @test MLJBase.input_scitype(selector) == MLJBase.Table
     @test MLJBase.output_scitype(selector) == MLJBase.Table
+    @test MLJBase.package_name(selector) == "FeatureSelection"
 end
 
 #  To be added with FeatureSelectorRule X = (n1=["a", "b", "a"], n2=["g", "g", "g"], n3=[7, 8, 9],

test/models/rfe.jl

@@ -51,7 +51,9 @@ const DTM = DummyTestModels
     selector = RecursiveFeatureElimination(model=rf)
     selector2 = RecursiveFeatureElimination(model=rf2)
     @test selector isa FeatureSelection.DeterministicRecursiveFeatureElimination
+    @test selector isa MLJBase.Deterministic
     @test selector2 isa FeatureSelection.ProbabilisticRecursiveFeatureElimination
+    @test selector2 isa MLJBase.Probabilistic
     @test MLJBase.constructor(selector) == RecursiveFeatureElimination
 
     # Fit models
@@ -104,8 +106,10 @@ const DTM = DummyTestModels
     # Traits
     @test MLJBase.package_name(selector) == "FeatureSelection"
     @test MLJBase.load_path(selector) == "FeatureSelection.RecursiveFeatureElimination"
-    @test MLJBase.iteration_parameter(selector) == FeatureSelection.prepend(:model, MLJBase.iteration_parameter(selector.model))
-    @test MLJBase.training_losses(selector, rpt) == MLJBase.training_losses(selector.model, rpt.model_report)
+    @test MLJBase.iteration_parameter(selector) ==
+        FeatureSelection.prepend(:model, MLJBase.iteration_parameter(selector.model))
+    @test MLJBase.training_losses(selector, rpt) ==
+        MLJBase.training_losses(selector.model, rpt.model_report)
 end
 
 @testset "Compare results for RFE with scikit-learn" begin