👨‍🔧 Fix types for features

EssamWisam · EssamWisam · commit 194c53e113de · 2025-05-25T17:54:59.000+03:00
diff --git a/src/encoders/contrast_encoder/contrast_encoder.jl b/src/encoders/contrast_encoder/contrast_encoder.jl
@@ -79,7 +79,7 @@ Fit a contrast encoing scheme on given data in `X`.
 """
 function contrast_encoder_fit(
     X,
-    features::AbstractVector{Symbol} = Symbol[];
+    features = Symbol[];
     mode::Union{Symbol, AbstractVector{Symbol}} = :dummy,
     buildmatrix = nothing,
     ignore::Bool = true,
diff --git a/src/encoders/contrast_encoder/interface_mlj.jl b/src/encoders/contrast_encoder/interface_mlj.jl
@@ -1,11 +1,11 @@
 ### ContrastEncoding with MLJ Interface
 
 # 1. Interface Struct
-mutable struct ContrastEncoder{AS <: AbstractVector{Symbol}} <: Unsupervised
-    features::AS
+mutable struct ContrastEncoder{ASS <: Union{Symbol, AbstractVector{Symbol}}, A1 <: Any, A2 <: Any} <: Unsupervised
+    features::A1
     ignore::Bool
-    mode::Union{Symbol, AS}
-    buildmatrix::Any
+    mode:: ASS
+    buildmatrix::A2
     ordered_factor::Bool
 end;
 
diff --git a/src/encoders/frequency_encoding/frequency_encoding.jl b/src/encoders/frequency_encoding/frequency_encoding.jl
@@ -20,7 +20,7 @@ categorical features with their (normalized or raw) frequencies of occurrence in
 """
 function frequency_encoder_fit(
     X,
-    features::AbstractVector{Symbol} = Symbol[];
+    features = Symbol[];
     ignore::Bool = true,
     ordered_factor::Bool = false,
     normalize::Bool = false,
diff --git a/src/encoders/frequency_encoding/interface_mlj.jl b/src/encoders/frequency_encoding/interface_mlj.jl
@@ -1,8 +1,8 @@
 ### FrequencyEncoding with MLJ Interface
 
 # 1. Interface Struct
-mutable struct FrequencyEncoder{AS <: AbstractVector{Symbol}} <: Unsupervised
-    features::AS
+mutable struct FrequencyEncoder{A <: Any} <: Unsupervised
+    features::A
     ignore::Bool
     ordered_factor::Bool
     normalize::Bool
diff --git a/src/encoders/missingness_encoding/interface_mlj.jl b/src/encoders/missingness_encoding/interface_mlj.jl
@@ -2,11 +2,10 @@
 
 # 1. Interface Struct
 mutable struct MissingnessEncoder{
-    AS <: AbstractVector{Symbol},
     T <: Type,
     A <: Any,
 } <: Unsupervised
-    features::AS
+    features::A
     ignore::Bool
     ordered_factor::Bool
     label_for_missing::Dict{T, A}
diff --git a/src/encoders/missingness_encoding/missingness_encoding.jl b/src/encoders/missingness_encoding/missingness_encoding.jl
@@ -27,7 +27,7 @@ types that are in `Char`, `AbstractString`, and `Number`.
 """
 function missingness_encoder_fit(
     X,
-    features::AbstractVector{Symbol} = Symbol[];
+    features = Symbol[];
     ignore::Bool = true,
     ordered_factor::Bool = false,
     label_for_missing::Dict{<:Type, <:Any} = Dict(    
diff --git a/src/encoders/ordinal_encoding/interface_mlj.jl b/src/encoders/ordinal_encoding/interface_mlj.jl
@@ -1,8 +1,8 @@
 ### OrdinalEncoding with MLJ Interface
 
 # 1. Interface Struct
-mutable struct OrdinalEncoder{AS <: AbstractVector{Symbol}} <: Unsupervised
-    features::AS
+mutable struct OrdinalEncoder{A <: Any} <: Unsupervised
+    features::A
     ignore::Bool
     ordered_factor::Bool
 end;
diff --git a/src/encoders/ordinal_encoding/ordinal_encoding.jl b/src/encoders/ordinal_encoding/ordinal_encoding.jl
@@ -18,7 +18,7 @@ Fit an encoder to encode the levels of categorical variables in a given table as
 """
 function ordinal_encoder_fit(
     X,
-    features::AbstractVector{Symbol} = Symbol[];
+    features = Symbol[];
     ignore::Bool = true,
     ordered_factor::Bool = false,
 )
diff --git a/src/encoders/target_encoding/interface_mlj.jl b/src/encoders/target_encoding/interface_mlj.jl
@@ -1,9 +1,9 @@
 ### TargetEncoding with MLJ Interface
 
 # 1. Interface Struct
-mutable struct TargetEncoder{R1 <: Real, R2 <: Real, AS <: AbstractVector{Symbol}} <:
+mutable struct TargetEncoder{R1 <: Real, R2 <: Real, A <: Any} <:
                Unsupervised
-    features::AS
+    features::A
     ignore::Bool
     ordered_factor::Bool
     lambda::R1
@@ -45,7 +45,7 @@ end
 struct TargetEncoderResult{
     I <: Integer,
     S <: AbstractString,
-    A <: Any            # Useless but likely can't do much better
+    A <: Any,            # Useless but likely can't do much better
 } <: MMI.MLJType
     # target statistic for each level of each categorical feature
     y_stat_given_feat_level::Dict{A, A}
diff --git a/src/encoders/target_encoding/target_encoding.jl b/src/encoders/target_encoding/target_encoding.jl
@@ -132,7 +132,7 @@ Fit a target encoder on table X with target y by computing the necessary statist
 function target_encoder_fit(
     X,
     y::AbstractVector,
-    features::AbstractVector{Symbol} = Symbol[];
+    features = Symbol[];
     ignore::Bool = true,
     ordered_factor::Bool = false,
     lambda::Real = 1.0,
diff --git a/src/generic.jl b/src/generic.jl
@@ -29,7 +29,7 @@ logic?"
     - encoded_features: The subset of the categorical features of X that were encoded
 """
 function generic_fit(X,
-    features::Union{AbstractVector{Symbol}, Function} = Symbol[],
+    features = Symbol[],
     args...;
     ignore::Bool = true,
     ordered_factor::Bool = false,
@@ -49,7 +49,8 @@ function generic_fit(X,
         end
     else
         # Original behavior for vector of symbols
-        feat_names = (ignore) ? setdiff(feat_names, features) : intersect(feat_names, features)
+        feat_names =
+            (ignore) ? setdiff(feat_names, features) : intersect(feat_names, features)
     end
 
     # 3. Define mapping per column per level dictionary
@@ -61,11 +62,13 @@ function generic_fit(X,
         feat_col = Tables.getcolumn(X, feat_name)
         feat_type = elscitype(feat_col)
         feat_has_allowed_type =
-            feat_type <: Union{Missing, Multiclass} || (ordered_factor && feat_type <: Union{Missing, OrderedFactor})
+            feat_type <: Union{Missing, Multiclass} ||
+            (ordered_factor && feat_type <: Union{Missing, OrderedFactor})
         if feat_has_allowed_type  # then should be encoded
             push!(encoded_features, feat_name)
             # Compute the dict using the given feature_mapper function
-            mapping_per_feat_level[feat_name] = feature_mapper(feat_col, feat_name, args...; kwargs...)
+            mapping_per_feat_level[feat_name] =
+                feature_mapper(feat_col, feat_name, args...; kwargs...)
         end
     end
     return mapping_per_feat_level, encoded_features
@@ -84,7 +87,7 @@ function generate_new_feat_names(feat_name, num_inds, existing_names)
 
     new_column_names = []
     while conflict
-        suffix = repeat("_", count)  
+        suffix = repeat("_", count)
         new_column_names = [Symbol("$(feat_name)$(suffix)$i") for i in 1:num_inds]
         conflict = any(name -> name in existing_names, new_column_names)
         count += 1
@@ -97,22 +100,27 @@ end
 """
 **Private method.**
 
-Given a table `X` and a dictionary `mapping_per_feat_level` which maps each level for each column in 
+Given a table `X` and a dictionary `mapping_per_feat_level` which maps each level for each column in
 a subset of categorical features of X into a scalar or a vector (as specified in single_feat)
 
-  - transforms each value (some level) in each column in `X` using the function in `mapping_per_feat_level` 
-  into a scalar (single_feat=true)
+  - transforms each value (some level) in each column in `X` using the function in `mapping_per_feat_level`
+    into a scalar (single_feat=true)
 
-  - transforms each value (some level) in each column in `X` using the function in `mapping_per_feat_level` 
-  into a set of k features where k is the length of the vector (single_feat=false)
+  - transforms each value (some level) in each column in `X` using the function in `mapping_per_feat_level`
+    into a set of k features where k is the length of the vector (single_feat=false)
   - In both cases it attempts to preserve the type of the table.
   - In the latter case, it assumes that all levels under the same category are mapped to vectors of the same length. Such
-    assumption is necessary because any column in X must correspond to a constant number of features 
+    assumption is necessary because any column in X must correspond to a constant number of features
     in the output table (which is equal to k).
   - Features not in the dictionary are mapped to themselves (i.e., not changed).
   - Levels not in the nested dictionary are mapped to themselves if `identity_map_unknown` is true else raise an error.
 """
-function generic_transform(X, mapping_per_feat_level; single_feat = true, ignore_unknown = false)
+function generic_transform(
+    X,
+    mapping_per_feat_level;
+    single_feat = true,
+    ignore_unknown = false,
+)
     feat_names = Tables.schema(X).names
     new_feat_names = Symbol[]
     new_cols = []
@@ -127,18 +135,20 @@ function generic_transform(X, mapping_per_feat_level; single_feat = true, ignore
                 if !issubset(test_levels, train_levels)
                     # get the levels in test that are not in train
                     lost_levels = setdiff(test_levels, train_levels)
-                    error("While transforming, found novel levels for the column $(feat_name): $(lost_levels) that were not seen while training.")
+                    error(
+                        "While transforming, found novel levels for the column $(feat_name): $(lost_levels) that were not seen while training.",
+                    )
                 end
             end
-            
+
             if single_feat
                 level2scalar = mapping_per_feat_level[feat_name]
                 new_col = !isempty(level2scalar) ? recode(col, level2scalar...) : col
                 push!(new_cols, new_col)
                 push!(new_feat_names, feat_name)
             else
                 level2vector = mapping_per_feat_level[feat_name]
-                new_multi_col = map(x->get(level2vector, x, x), col)
+                new_multi_col = map(x -> get(level2vector, x, x), col)
                 new_multi_col = [col for col in eachrow(hcat(new_multi_col...))]
                 push!(new_cols, new_multi_col...)
 
@@ -156,8 +166,8 @@ function generic_transform(X, mapping_per_feat_level; single_feat = true, ignore
         end
     end
 
-    transformed_X= NamedTuple{tuple(new_feat_names...)}(tuple(new_cols)...)
+    transformed_X = NamedTuple{tuple(new_feat_names...)}(tuple(new_cols)...)
     # Attempt to preserve table type
     transformed_X = Tables.materializer(X)(transformed_X)
     return transformed_X
-end
+end
diff --git a/src/transformers/cardinality_reducer/cardinality_reducer.jl b/src/transformers/cardinality_reducer/cardinality_reducer.jl
@@ -32,7 +32,7 @@ types that are in `Char`, `AbstractString`, and `Number`.
 """
 function cardinality_reducer_fit(
     X,
-    features::AbstractVector{Symbol} = Symbol[];
+    features = Symbol[];
     ignore::Bool = true,
     ordered_factor::Bool = false,
     min_frequency::Real = 3,                        
diff --git a/src/transformers/cardinality_reducer/interface_mlj.jl b/src/transformers/cardinality_reducer/interface_mlj.jl
@@ -2,12 +2,11 @@
 
 # 1. Interface Struct
 mutable struct CardinalityReducer{
-    AS <: AbstractVector{Symbol},
     R <: Real,
     T <: Type,
     A <: Any,
 } <: Unsupervised
-    features::AS
+    features::A
     ignore::Bool
     ordered_factor::Bool
     min_frequency::R
diff --git a/test/encoders/contrast_encoder.jl b/test/encoders/contrast_encoder.jl
diff --git a/test/runtests.jl b/test/runtests.jl

Original file line number	Diff line number	Diff line change
`@@ -18,7 +18,7 @@ Fit an encoder to encode the levels of categorical variables in a given table as`
`18`	`18`	`"""`
`19`	`19`	`function ordinal_encoder_fit(`
`20`	`20`	`X,`
`21`		`- features::AbstractVector{Symbol} = Symbol[];`
	`21`	`+ features = Symbol[];`
`22`	`22`	`ignore::Bool = true,`
`23`	`23`	`ordered_factor::Bool = false,`
`24`	`24`	`)`