✨ Contrast encoding should use level names as it generates columns

Author: EssamWisam

src/MLJTransforms.jl

@@ -7,7 +7,7 @@ using MLJModelInterface
 using TableOperations
 using StatsBase
 using LinearAlgebra
-
+using OrderedCollections: OrderedDict
 # Other transformers
 using Combinatorics
 import Distributions

src/encoders/contrast_encoder/contrast_encoder.jl

@@ -125,7 +125,7 @@ function contrast_encoder_fit(
             throw(ArgumentError("Mode $feat_mode is not supported."))
         end
 
-        vector_given_value_given_feature = Dict(level=>contrastmatrix[l, :] for (l, level) in enumerate(feat_levels))
+        vector_given_value_given_feature = OrderedDict(level=>contrastmatrix[l, :] for (l, level) in enumerate(feat_levels))
         return vector_given_value_given_feature
     end
 
@@ -159,5 +159,5 @@ Use a fitted contrast encoder to encode the levels of selected categorical varia
 """
 function contrast_encoder_transform(X, cache::Dict)
     vector_given_value_given_feature = cache[:vector_given_value_given_feature]
-    return generic_transform(X, vector_given_value_given_feature, single_feat = false)
+    return generic_transform(X, vector_given_value_given_feature, single_feat = false; use_levelnames = true)
 end

src/encoders/contrast_encoder/interface_mlj.jl

@@ -148,12 +148,12 @@ mach = fit!(machine(encoder, X))
 Xnew = transform(mach, X)
 
 julia > Xnew
-    (name_1 = [1.0, 0.0, 0.0, 0.0],
-    name_2 = [0.0, 1.0, 0.0, 1.0],
+    (name_John = [1.0, 0.0, 0.0, 0.0],
+    name_Mary = [0.0, 1.0, 0.0, 1.0],
     height = [1.85, 1.67, 1.5, 1.67],
-    favnum_1 = [0.0, 1.0, 0.0, -1.0],
-    favnum_2 = [2.0, -1.0, 0.0, -1.0],
-    favnum_3 = [-1.0, -1.0, 3.0, -1.0],
+    favnum_5 = [0.0, 1.0, 0.0, -1.0],
+    favnum_7 = [2.0, -1.0, 0.0, -1.0],
+    favnum_10 = [-1.0, -1.0, 3.0, -1.0],
     age = [23, 23, 14, 23],)
 ```