Merge branch 'Contrast-Encoding' of https://github.com/JuliaAI/MLJTransforms.jl into Contrast-Encoding

Author: EssamWisam

src/encoders/contrast_encoder/contrast_encoder.jl

@@ -2,6 +2,7 @@ include("errors.jl")
 
 """
 ** Private Method **
+
 This and the following four methods implement the contrast matrix for dummy coding, sum coding, 
     backaward/forward difference coding and helmert coding.
 Where `k` is the number of levels in the feature and the returned contrast matrix has dimensions (k,k-1).

src/encoders/contrast_encoder/errors.jl

@@ -1,5 +1,5 @@
-MATRIX_SIZE_ERROR(k, matrix_size, feat_name)= "In ContrastEncoder, a categorical variable with $k levels should have a contrast matrix of size ($k, $k-1). However, the given contrast matrix by `buildmatrix` is $matrix_size for feature $feat_name."
-MATRIX_SIZE_ERROR_HYP(k, matrix_size, feat_name)= "In ContrastEncoder, a categorical variable with $k levels should have a hypothesis matrix of size ($k-1, $k). However, the given hypothesis matrix by `buildmatrix` is $matrix_size for feature $feat_name."
+MATRIX_SIZE_ERROR(k, matrix_size, feat_name)= "In ContrastEncoder, a categorical variable with $k levels should have a contrast matrix of size ($k, $k-1). However, the contrast matrix returned by `buildmatrix` is $matrix_size for feature $feat_name."
+MATRIX_SIZE_ERROR_HYP(k, matrix_size, feat_name)= "In ContrastEncoder, a categorical variable with $k levels should have a hypothesis matrix of size ($k-1, $k). However, the given hypothesis matrix returned by `buildmatrix` is $matrix_size for feature $feat_name."
 IGNORE_MUST_FALSE_VEC_MODE = "In ContrastEncoder with mode given as a vector of symbols, the ignore argument must be set to false and features must be explictly specified in features."
 BUILDFUNC_MUST_BE_SPECIFIED = "In ContrastEncoder with mode=:contrast or mode=:hypothesis, the `buildmatrix` argument must be specified."
 LENGTH_MISMATCH_VEC_MODE(len_mode, len_feat) = "In ContrastEncoder with mode given as a vector of symbols, the length of the features argument must match the number of specified modes. However, the method received $(len_mode) modes and $(len_feat) features."

src/encoders/contrast_encoder/interface_mlj.jl

@@ -126,15 +126,21 @@ The fields of `report(mach)` are:
 using MLJ
 
 # Define categorical dataset
-X = (name   = categorical(["Ben", "John", "Mary", "John"]),
-height = [1.85, 1.67, 1.5, 1.67],
-favnum = categorical([7, 5, 10, 1]),
-age    = [23, 23, 14, 23])
+X = (
+    name   = categorical(["Ben", "John", "Mary", "John"]),
+    height = [1.85, 1.67, 1.5, 1.67],
+    favnum = categorical([7, 5, 10, 1]),
+    age    = [23, 23, 14, 23],
+)
 
 # Check scitype coercions:
 schema(X)
 
-encoder =  ContrastEncoder(features=[:name, :favnum]; ignore=false, mode = [:dummy, :helmert])
+encoder =  ContrastEncoder(
+    features = [:name, :favnum],
+    ignore = false, 
+    mode = [:dummy, :helmert],
+)
 mach = fit!(machine(encoder, X))
 Xnew = transform(mach, X)