For 0.1.1 release

Project.toml

@@ -1,7 +1,7 @@
 name = "MLJTransforms"
 uuid = "23777cdb-d90c-4eb0-a694-7c2b83d5c1d6"
 authors = ["Essam <[email protected]> and contributors"]
-version = "0.1.0"
+version = "0.1.1"
 
 [deps]
 BitBasis = "50ba71b6-fa0f-514d-ae9a-0916efc90dcf"
@@ -14,6 +14,7 @@ MLJModelInterface = "e80e1ace-859a-464e-9ed9-23947d8ae3ea"
 OrderedCollections = "bac558e1-5e72-5ebc-8fee-abe8a469f55d"
 Parameters = "d96e819e-fc66-5662-9728-84c9c7592b0a"
 ScientificTypes = "321657f4-b219-11e9-178b-2701a2544e81"
+ScientificTypesBase = "30f210dd-8aff-4c5f-94ba-8e64358c1161"
 Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
 TableOperations = "ab02a1b2-a7df-11e8-156e-fb1833f50b87"
@@ -22,14 +23,15 @@ Tables = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
 [compat]
 BitBasis = "0.9"
 CategoricalArrays = "0.10"
-MLJModelInterface = "1.11"
 Combinatorics = "1"
 Dates = "1"
 Distributions = "0.25"
 LinearAlgebra = "1"
+MLJModelInterface = "1.11"
 OrderedCollections = "1"
 Parameters = "0.12"
-ScientificTypes = "3.0"
+ScientificTypes = "3.1.0"
+ScientificTypesBase = "3.0.0"
 Statistics = "1"
 StatsBase = "0.34"
 TableOperations = "1.2"
@@ -38,11 +40,11 @@ julia = "1.10"
 
 [extras]
 DataFrames = "a93c6f00-e57d-5684-b7b6-d8193f3e46c0"
-StableRNGs = "860ef19b-820b-49d6-a774-d7a799459cd3"
 MLJBase = "a7f614a8-145f-11e9-1d2a-a57a1082229d"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
-Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
+StableRNGs = "860ef19b-820b-49d6-a774-d7a799459cd3"
 StatsModels = "3eaba693-59b7-5ba5-a881-562e759f1c8d"
+Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
 
 [targets]
 test = ["Test", "DataFrames", "MLJBase", "Random", "StableRNGs", "StatsModels"]

src/MLJTransforms.jl

@@ -1,9 +1,12 @@
 module MLJTransforms
 using Tables
-using ScientificTypes
-using ScientificTypes: scitype
+# Note: The `scitype` in
+# MLJModelInterface clashes with the `scitype` in ScientificTypes. See also
+# https://github.com/JuliaAI/MLJBase.jl/issues/1002
+import ScientificTypes: elscitype, schema, coerce, ScientificTimeType
+using MLJModelInterface # exports `scitype`, which will call `ScientificTypes.scitype`,
+                        # once MLJBase is loaded (but this is not a dependency!)
 using CategoricalArrays
-using MLJModelInterface
 using TableOperations
 using StatsBase
 using LinearAlgebra
@@ -15,7 +18,6 @@ using Parameters
 using Dates
 using OrderedCollections
 
-
 const MMI = MLJModelInterface
 
 # Functions of generic use across transformers

src/transformers/other_transformers/continuous_encoder.jl

@@ -73,7 +73,7 @@ end
 metadata_model(ContinuousEncoder,
     input_scitype   = Table,
     output_scitype = Table(Continuous),
-    load_path    = "MLJModels.ContinuousEncoder")
+    load_path    = "MLJTransforms.ContinuousEncoder")
 
 """
 $(MLJModelInterface.doc_header(ContinuousEncoder))

src/transformers/other_transformers/fill_imputer.jl

@@ -187,12 +187,12 @@ metadata_model(UnivariateFillImputer,
                   AbstractVector{<:Count},
                   AbstractVector{<:Finite}},
     human_name = "single variable fill imputer",
-    load_path  = "MLJModels.UnivariateFillImputer")
+    load_path  = "MLJTransforms.UnivariateFillImputer")
 
 metadata_model(FillImputer,
     input_scitype   = Table,
     output_scitype = Table,
-    load_path    = "MLJModels.FillImputer")
+    load_path = "MLJTransforms.FillImputer")
 
 """
 $(MLJModelInterface.doc_header(UnivariateFillImputer))

src/transformers/other_transformers/interaction_transformer.jl

@@ -38,7 +38,7 @@ metadata_model(InteractionTransformer,
     input_scitype   = Tuple{Table},
     output_scitype = Table,
     human_name = "interaction transformer",
-    load_path    = "MLJModels.InteractionTransformer")
+    load_path = "MLJTransforms.InteractionTransformer")
 
 """
 $(MLJModelInterface.doc_header(InteractionTransformer))

src/transformers/other_transformers/metadata_shared.jl

@@ -13,8 +13,8 @@ metadata_pkg.(
         UnivariateTimeTypeToContinuous,
         InteractionTransformer
     ),
-    package_name       = "MLJModels",
-    package_uuid       = "d491faf4-2d78-11e9-2867-c94bc002c0b7",
-    package_url        = "https://github.com/JuliaAI/MLJModels.jl",
+    package_name       = "MLJTransforms",
+    package_uuid       = "23777cdb-d90c-4eb0-a694-7c2b83d5c1d6",
+    package_url        = "https://github.com/JuliaAI/MLJTransforms.jl",
     is_pure_julia      = true,
     package_license    = "MIT")

src/transformers/other_transformers/one_hot_encoder.jl

@@ -163,7 +163,7 @@ metadata_model(OneHotEncoder,
     input_scitype   = Table,
     output_scitype = Table,
     human_name = "one-hot encoder",
-    load_path    = "MLJModels.OneHotEncoder")
+    load_path = "MLJTransforms.OneHotEncoder")
 
 """
 $(MLJModelInterface.doc_header(OneHotEncoder))

src/transformers/other_transformers/standardizer.jl

@@ -229,12 +229,12 @@ metadata_model(UnivariateStandardizer,
     input_scitype   = AbstractVector{<:Infinite},
     output_scitype = AbstractVector{Continuous},
     human_name = "single variable discretizer",
-    load_path    = "MLJModels.UnivariateStandardizer")
+    load_path    = "MLJTransforms.UnivariateStandardizer")
 
 metadata_model(Standardizer,
     input_scitype   = Union{Table, AbstractVector{<:Continuous}},
     output_scitype = Union{Table, AbstractVector{<:Continuous}},
-    load_path    = "MLJModels.Standardizer")
+    load_path = "MLJTransforms.Standardizer")
 
 """
 $(MLJModelInterface.doc_header(Standardizer))

src/transformers/other_transformers/univariate_boxcox_transformer.jl

@@ -91,7 +91,7 @@ metadata_model(UnivariateBoxCoxTransformer,
     input_scitype   = AbstractVector{Continuous},
     output_scitype = AbstractVector{Continuous},
     human_name = "single variable Box-Cox transformer",
-    load_path    = "MLJModels.UnivariateBoxCoxTransformer")
+    load_path = "MLJTransforms.UnivariateBoxCoxTransformer")
 
 """
 $(MLJModelInterface.doc_header(UnivariateBoxCoxTransformer))

src/transformers/other_transformers/univariate_discretizer.jl

@@ -94,7 +94,7 @@ metadata_model(UnivariateDiscretizer,
     input_scitype   = AbstractVector{<:Continuous},
     output_scitype = AbstractVector{<:OrderedFactor},
     human_name = "single variable discretizer",
-    load_path    = "MLJModels.UnivariateDiscretizer")
+    load_path = "MLJTransforms.UnivariateDiscretizer")
 
 
 """

src/transformers/other_transformers/univariate_time_type_to_continuous.jl

@@ -129,7 +129,7 @@ metadata_model(UnivariateTimeTypeToContinuous,
     output_scitype = AbstractVector{Continuous},
     human_name ="single variable transformer that creates "*
          "continuous representations of temporally typed data",
-    load_path    = "MLJModels.UnivariateTimeTypeToContinuous")
+    load_path = "MLJTransforms.UnivariateTimeTypeToContinuous")
 
 """
 $(MLJModelInterface.doc_header(UnivariateTimeTypeToContinuous))

test/encoders/contrast_encoder.jl

@@ -195,16 +195,16 @@ end
 
     df = DataFrame(X)
 
-    mf = ModelFrame(
-        @formula(age ~ (name + height + favnum)),
+    mf = StatsModels.ModelFrame(
+        StatsModels.@formula(age ~ (name + height + favnum)),
         df,
         contrasts = Dict(
             :name => StatsModels.ContrastsCoding(buildrandomcontrast(nothing, 3)),
             :favnum => StatsModels.ContrastsCoding(buildrandomcontrast(nothing, 4)),
         ),
     )
 
-    X_tr_sm = ModelMatrix(mf).m[:, 2:end]
+    X_tr_sm = StatsModels.ModelMatrix(mf).m[:, 2:end]
 
     @test X_tr_mlj == X_tr_sm
 end
@@ -221,24 +221,24 @@ end
     X_tr_mlj = Tables.matrix(X_tr)[:, 1:end-1]
     df = DataFrame(X)
 
-    mf = ModelFrame(
-        @formula(age ~ (name + height + favnum)),
+    mf = StatsModels.ModelFrame(
+        StatsModels.@formula(age ~ (name + height + favnum)),
         df,
         contrasts = Dict(
-            :name => HypothesisCoding(
+            :name => StatsModels.HypothesisCoding(
                 buildrandomhypothesis(nothing, 3);
                 levels = levels(X.name),
                 labels = [],
             ),
-            :favnum => HypothesisCoding(
+            :favnum => StatsModels.HypothesisCoding(
                 buildrandomhypothesis(nothing, 4);
                 levels = levels(X.favnum),
                 labels = [],
             ),
         ),
     )
 
-    X_tr_sm = ModelMatrix(mf).m[:, 2:end]
+    X_tr_sm = StatsModels.ModelMatrix(mf).m[:, 2:end]
 
     @test X_tr_mlj == X_tr_sm
 end
@@ -257,11 +257,11 @@ end
     for ind in 1:6
         stats_models(k, ind) = [
             StatsModels.ContrastsCoding(buildrandomcontrast(nothing, k)),
-            DummyCoding(; base = (k == 3) ? "Mary" : 10),
-            EffectsCoding(; base = (k == 3) ? "Mary" : 10),
-            SeqDiffCoding(),
-            HelmertCoding(),
-            HypothesisCoding(
+            StatsModels.DummyCoding(; base = (k == 3) ? "Mary" : 10),
+            StatsModels.EffectsCoding(; base = (k == 3) ? "Mary" : 10),
+            StatsModels.SeqDiffCoding(),
+            StatsModels.HelmertCoding(),
+            StatsModels.HypothesisCoding(
                 buildrandomhypothesis(nothing, k);
                 levels = (k == 3) ? levels(X.name) : levels(X.favnum),
                 labels = [],
@@ -277,8 +277,8 @@ end
 
         df = DataFrame(X)
 
-        mf = ModelFrame(
-            @formula(age ~ (name + height + favnum)),
+        mf = StatsModels.ModelFrame(
+            StatsModels.@formula(age ~ (name + height + favnum)),
             df,
             contrasts = Dict(
                 :name => stats_models(3, ind),
@@ -287,7 +287,7 @@ end
         )
 
         X_tr_mlj = Tables.matrix(X_tr)[:, 1:end-1]
-        X_tr_sm = ModelMatrix(mf).m[:, 2:end]
+        X_tr_sm = StatsModels.ModelMatrix(mf).m[:, 2:end]
         @test X_tr_mlj ≈ X_tr_sm
     end
 end
@@ -298,11 +298,11 @@ end
         for ind2 in 2:5
             stats_models(k, ind) = [
                 StatsModels.ContrastsCoding(buildrandomcontrast(nothing, k)),
-                DummyCoding(; base = (k == 3) ? "Mary" : 10),
-                EffectsCoding(; base = (k == 3) ? "Mary" : 10),
-                SeqDiffCoding(),
-                HelmertCoding(),
-                HypothesisCoding(
+                StatsModels.DummyCoding(; base = (k == 3) ? "Mary" : 10),
+                StatsModels.EffectsCoding(; base = (k == 3) ? "Mary" : 10),
+                StatsModels.SeqDiffCoding(),
+                StatsModels.HelmertCoding(),
+                StatsModels.HypothesisCoding(
                     buildrandomhypothesis(nothing, k);
                     levels = (k == 3) ? levels(X.name) : levels(X.favnum),
                     labels = [],
@@ -331,8 +331,8 @@ end
 
             df = DataFrame(X)
 
-            mf = ModelFrame(
-                @formula(age ~ (name + height + favnum)),
+            mf = StatsModels.ModelFrame(
+                StatsModels.@formula(age ~ (name + height + favnum)),
                 df,
                 contrasts = Dict(
                     :name => stats_models(3, ind1),
@@ -341,7 +341,7 @@ end
             )
 
             X_tr_mlj = Tables.matrix(X_tr)[:, 1:end-1]
-            X_tr_sm = ModelMatrix(mf).m[:, 2:end]
+            X_tr_sm = StatsModels.ModelMatrix(mf).m[:, 2:end]
 
             @test X_tr_mlj ≈ X_tr_sm
         end
@@ -358,7 +358,7 @@ end
     encoder = ContrastEncoder(ignore = true, ordered_factor = false)
     mach = machine(encoder, X)
     fit!(mach)
-    Xnew_transf = MMI.transform(mach, X)
+    Xnew_transf = MLJBase.transform(mach, X)
 
     # same output
     @test X_transf == Xnew_transf
@@ -392,7 +392,7 @@ end
             buildmatrix = matrix_func[i],
         )
         mach = fit!(machine(encoder, X))
-        Xnew = MMI.transform(mach, X)
+        Xnew = MLJBase.transform(mach, X)
 
         # Test Consistency with Types
         scs = schema(Xnew).scitypes
@@ -406,4 +406,4 @@ end
         @test last_type <: Integer && isconcretetype(last_type)
         @test last_sctype <: Count
     end
-end
+end

test/encoders/frequency_encoder.jl

@@ -5,7 +5,7 @@ using MLJTransforms: frequency_encoder_fit, frequency_encoder_transform
 
     X = dataset_forms[1]
     normalize = [false, true]
-    A_col, C_col, D_col, F_col = MMI.selectcols(X, [1, 3, 4, 6])
+    A_col, C_col, D_col, F_col = selectcols(X, [1, 3, 4, 6])
     for norm in normalize
         result = frequency_encoder_fit(X; normalize = norm)[:statistic_given_feat_val]
         enc =
@@ -72,7 +72,7 @@ end
         encoder = FrequencyEncoder(ignore = true, ordered_factor = false)
         mach = machine(encoder, X)
         fit!(mach)
-        Xnew_transf = MMI.transform(mach, X)
+        Xnew_transf = MLJBase.transform(mach, X)
 
         # same output
         @test X_transf == Xnew_transf
@@ -111,7 +111,7 @@ end
 
     encoder = FrequencyEncoder(ordered_factor = false, normalize = false)
     mach = fit!(machine(encoder, X))
-    Xnew = MMI.transform(mach, X)
+    Xnew = MLJBase.transform(mach, X)
 
 
     scs = schema(Xnew).scitypes

test/encoders/missingness_encoding.jl

@@ -170,7 +170,7 @@ end
     encoder = MissingnessEncoder(ignore = true, ordered_factor = false)
     mach = machine(encoder, X)
     fit!(mach)
-    Xnew_transf = MMI.transform(mach, X)
+    Xnew_transf =  MLJBase.transform(mach, X)
 
     # same output
     @test isequal(X_transf, Xnew_transf)
@@ -197,7 +197,7 @@ end
 
     encoder = MissingnessEncoder()
     mach = fit!(machine(encoder, Xm))
-    Xnew = MMI.transform(mach, Xm)
+    Xnew = MLJBase.transform(mach, Xm)
 
     schema(Xm)
     schema(Xnew)

test/encoders/ordinal_encoding.jl

@@ -15,7 +15,7 @@ push!(
     @test ordinal_encoder_fit(dataset_forms[1]) == ordinal_encoder_fit(dataset_forms[2])
     X = dataset_forms[1]
     result = ordinal_encoder_fit(X)[:index_given_feat_level]
-    A_col, C_col, D_col, F_col = MMI.selectcols(X, [1, 3, 4, 6])
+    A_col, C_col, D_col, F_col = selectcols(X, [1, 3, 4, 6])
     true_output = Dict{Symbol, Dict{Any, AbstractFloat}}(
         :F => Dict(
             "m" => findfirst(==("m"), levels(F_col)),
@@ -70,7 +70,7 @@ end
         encoder = OrdinalEncoder(ignore = true, ordered_factor = false)
         mach = machine(encoder, X)
         fit!(mach)
-        Xnew_transf = MMI.transform(mach, X)
+        Xnew_transf = MLJBase.transform(mach, X)
 
         # same output
         @test X_transf == Xnew_transf
@@ -108,7 +108,7 @@ end
 
     encoder = OrdinalEncoder(ordered_factor = false)
     mach = fit!(machine(encoder, X))
-    Xnew = MMI.transform(mach, X)
+    Xnew = MLJBase.transform(mach, X)
 
     scs = schema(Xnew).scitypes
     ts  = schema(Xnew).types
@@ -123,7 +123,7 @@ end
     ## Int32 case
     encoder = OrdinalEncoder(ordered_factor = false, output_type = Int32)
     mach = fit!(machine(encoder, X))
-    Xnew = MMI.transform(mach, X)
+    Xnew = MLJBase.transform(mach, X)
     scs = schema(Xnew).scitypes
     ts = schema(Xnew).types
     # Check scitypes for previously categorical features