✨ Add support of output type to frequency encoder

Based on normalize, we may want integers or floats so let's give this flexibility

Author: EssamWisam

src/encoders/frequency_encoding/frequency_encoding.jl

@@ -24,12 +24,13 @@ function frequency_encoder_fit(
     ignore::Bool = true,
     ordered_factor::Bool = false,
     normalize::Bool = false,
+    output_type::Type = Float32,
 )
     # 1. Define feature mapper
     function feature_mapper(col, name)
         frequency_map = (!normalize) ? countmap(col) : proportionmap(col)
         feat_levels = levels(col)
-        statistic_given_feat_val = Dict{eltype(feat_levels), Float32}(
+        statistic_given_feat_val = Dict{eltype(feat_levels), output_type}(
             level => frequency_map[level] for level in feat_levels
         )
         return statistic_given_feat_val

src/encoders/frequency_encoding/interface_mlj.jl

@@ -6,6 +6,7 @@ mutable struct FrequencyEncoder{AS <: AbstractVector{Symbol}} <: Unsupervised
     ignore::Bool
     ordered_factor::Bool
     normalize::Bool
+    output_type::Type
 end;
 
 # 2. Constructor
@@ -14,8 +15,9 @@ function FrequencyEncoder(;
     ignore = true,
     ordered_factor = false,
     normalize = false,
+    output_type = Float32,
 )
-    return FrequencyEncoder(features, ignore, ordered_factor, normalize)
+    return FrequencyEncoder(features, ignore, ordered_factor, normalize, output_type)
 end;
 
 
@@ -32,6 +34,7 @@ function MMI.fit(transformer::FrequencyEncoder, verbosity::Int, X)
         ignore = transformer.ignore,
         ordered_factor = transformer.ordered_factor,
         normalize = transformer.normalize,
+        output_type = transformer.output_type,
     )
     fitresult = generic_cache[:statistic_given_feat_val]
 
@@ -96,6 +99,7 @@ Train the machine using `fit!(mach, rows=...)`.
 - `ignore=true`: Whether to exclude or include the features given in `features`
 - `ordered_factor=false`: Whether to encode `OrderedFactor` or ignore them
 - `normalize=false`: Whether to use normalized frequencies that sum to 1 over category values or to use raw counts.
+- `output_type=Float32`: The type of the output values. The default is `Float32`, but you can set it to `Float64` or any other type that can hold the frequency values.
 
 # Operations
 

src/encoders/ordinal_encoding/interface_mlj.jl

@@ -5,17 +5,17 @@ mutable struct OrdinalEncoder{AS <: AbstractVector{Symbol}} <: Unsupervised
     features::AS
     ignore::Bool
     ordered_factor::Bool
-    op_dtype::Type
+    output_type::Type
 end;
 
 # 2. Constructor
 function OrdinalEncoder(;
     features = Symbol[],
     ignore = true,
     ordered_factor = false,
-    op_dtype = Float32,
+    output_type = Float32,
 )
-    return OrdinalEncoder(features, ignore, ordered_factor, op_dtype)
+    return OrdinalEncoder(features, ignore, ordered_factor, output_type)
 end;
 
 
@@ -31,7 +31,7 @@ function MMI.fit(transformer::OrdinalEncoder, verbosity::Int, X)
         transformer.features;
         ignore = transformer.ignore,
         ordered_factor = transformer.ordered_factor,
-        op_dtype = transformer.op_dtype,
+        output_type = transformer.output_type,
     )
     fitresult =
         generic_cache[:index_given_feat_level]
@@ -95,7 +95,7 @@ Train the machine using `fit!(mach, rows=...)`.
 - `features=[]`: A list of names of categorical features given as symbols to exclude or include from encoding
 - `ignore=true`: Whether to exclude or includes the features given in `features`
 - `ordered_factor=false`: Whether to encode `OrderedFactor` or ignore them
-- `op_dtype`: The numerical concrete type of the encoded features. Default is `Float32`.
+- `output_type`: The numerical concrete type of the encoded features. Default is `Float32`.
 
 # Operations
 

src/encoders/ordinal_encoding/ordinal_encoding.jl

@@ -21,13 +21,13 @@ function ordinal_encoder_fit(
     features::AbstractVector{Symbol} = Symbol[];
     ignore::Bool = true,
     ordered_factor::Bool = false,
-    op_dtype::Type = Float32,
+    output_type::Type = Float32,
 )
     # 1. Define feature mapper
     function feature_mapper(col, name)
         feat_levels = levels(col)
         index_given_feat_val =
-            Dict{eltype(feat_levels), op_dtype}(value => index for (index, value) in enumerate(feat_levels))
+            Dict{eltype(feat_levels), output_type}(value => index for (index, value) in enumerate(feat_levels))
         return index_given_feat_val
     end
 

test/encoders/ordinal_encoding.jl

@@ -121,7 +121,7 @@ end
     schema(X).scitypes[end]
 
     ## Int32 case
-    encoder = OrdinalEncoder(ordered_factor = false, op_dtype = Int32)
+    encoder = OrdinalEncoder(ordered_factor = false, output_type = Int32)
     mach = fit!(machine(encoder, X))
     Xnew = MMI.transform(mach, X)
     scs = schema(Xnew).scitypes