For a 0.6.7 release

Project.toml

@@ -1,7 +1,7 @@
 name = "MLJFlux"
 uuid = "094fc8d1-fd35-5302-93ea-dabda2abf845"
 authors = ["Anthony D. Blaom <anthony.blaom@gmail.com>", "Ayush Shridhar <ayush.shridhar1999@gmail.com>"]
-version = "0.6.6"
+version = "0.6.7"
 
 [deps]
 CategoricalArrays = "324d7699-5711-5eae-9e2f-1d82baa6b597"
@@ -17,15 +17,15 @@ Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 Tables = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
 
 [compat]
-CategoricalArrays = "0.10"
+CategoricalArrays = "1"
 ColorTypes = "0.10.3, 0.11, 0.12"
 ComputationalResources = "0.3.2"
 Flux = "0.14, 0.15, 0.16"
 MLJModelInterface = "1.11"
 Metalhead = "0.9.3"
 Optimisers = "0.3.2, 0.4"
 ProgressMeter = "1.7.1"
-StatisticalMeasures = "0.1"
+StatisticalMeasures = "0.3"
 Statistics = "<0.0.1, 1"
 Tables = "1.0"
 julia = "1.10"

src/classifier.jl

@@ -8,7 +8,7 @@ data `X` and `y`.
 """
 function MLJFlux.shape(model::NeuralNetworkClassifier, X, y)
     X = X isa Matrix ? Tables.table(X) : X
-    levels = MLJModelInterface.classes(y[1])
+    levels = CategoricalArrays.levels(y[1])
     n_output = length(levels)
     n_input = Tables.schema(X).names |> length
     return (n_input, n_output)
@@ -31,7 +31,7 @@ MLJFlux.fitresult(
     y,
     ordinal_mappings = nothing,
     embedding_matrices = nothing,
-) = (chain, MLJModelInterface.classes(y[1]), ordinal_mappings, embedding_matrices)
+) = (chain, levels(y[1]), ordinal_mappings, embedding_matrices)
 
 function MLJModelInterface.predict(
     model::NeuralNetworkClassifier,

src/core.jl

@@ -253,7 +253,7 @@ tomat(y::Vector) = reshape(y, size(y, 1), 1)
 reformat(y, ::Type{<:AbstractVector{<:Union{Continuous,Count}}}) =
     reshape(y, 1, length(y))
 function reformat(y, ::Type{<:AbstractVector{<:Finite}})
-    levels = y |> first |> MLJModelInterface.classes
+    levels = y |> first |> CategoricalArrays.levels
     return Flux.onehotbatch(y, levels)
 end
 
@@ -285,7 +285,7 @@ end
 function collate(model::NeuralNetworkBinaryClassifier, X, y, verbosity)
     row_batches = Base.Iterators.partition(1:nrows(y), model.batch_size)
     Xmatrix = _f32(reformat(X), verbosity)
-    yvec = (y .== classes(y)[2])' # convert to boolean
+    yvec = (y .== levels(y)[2])' # convert to boolean
     return [_get(Xmatrix, b) for b in row_batches], [_get(yvec, b) for b in row_batches]
 end
 
@@ -294,4 +294,3 @@ function _f32(x::AbstractArray, verbosity)
     verbosity > 0 && @info "MLJFlux: converting input data to Float32"
     return Float32.(x)
 end
-

src/encoders.jl

@@ -17,7 +17,7 @@ function ordinal_encoder_fit(X; featinds)
     # 2. Use feature mapper to compute the mapping of each level in each column
     for i in featinds
         feat_col = Tables.getcolumn(Tables.columns(X), i)
-        feat_levels = levels(feat_col)
+        feat_levels = CategoricalArrays.unwrap.(levels(feat_col))
         # Check if feat levels is already ordinal encoded in which case we skip
         (Set([Float32(i) for i in 1:length(feat_levels)]) == Set(feat_levels)) && continue
         # Compute the dict using the given feature_mapper function
@@ -64,10 +64,10 @@ function ordinal_encoder_transform(X, mapping_matrix)
         # Create the transformation function for each column
         if ind in keys(mapping_matrix)
             train_levels = keys(mapping_matrix[ind])
-            test_levels = levels(col)
+            test_levels = CategoricalArrays.unwrap.(levels(col))
             check_unkown_levels(train_levels, test_levels)
             level2scalar = mapping_matrix[ind]
-            new_col = unwrap.(recode(col, level2scalar...))
+            new_col = CategoricalArrays.unwrap.(recode(col, level2scalar...))
             push!(new_feats, new_col)
         else
             push!(new_feats, col)

src/image.jl

@@ -1,5 +1,5 @@
 function shape(model::ImageClassifier, X, y)
-    levels = MLJModelInterface.classes(y[1])
+    levels = CategoricalArrays.levels(y)
     n_output = length(levels)
     n_input = size(X[1])
 
@@ -18,7 +18,7 @@ build(model::ImageClassifier, rng, shape) =
                model.finaliser)
 
 fitresult(model::ImageClassifier, chain, y, ::Any, ::Any) =
-    (chain, MLJModelInterface.classes(y[1]))
+    (chain, levels(y))
 
 function MLJModelInterface.predict(model::ImageClassifier, fitresult, Xnew)
     chain, levels = fitresult

src/mlj_embedder_interface.jl

@@ -110,6 +110,7 @@ In the following example we wrap a `NeuralNetworkClassifier` as an `EntityEmbedd
 that it can be used to supply continuously encoded features to a nearest neighbor model,
 which does not support categorical features.
 
+## Simple Example
 ```julia
 using MLJ
 
@@ -129,21 +130,46 @@ EntityEmbedder = @load EntityEmbedder pkg=MLJFlux
 # Flux model to do learn the entity embeddings:
 NeuralNetworkClassifier = @load NeuralNetworkClassifier pkg=MLJFlux
 
-# Other supervised model type, requiring `Continuous` features:
-KNNClassifier = @load KNNClassifier pkg=NearestNeighborModels
-
 # Instantiate the models:
 clf = NeuralNetworkClassifier(embedding_dims=Dict(:b => 2, :c => 3))
 emb = EntityEmbedder(clf)
 
-# For illustrative purposes, train the embedder on its own:
+# Train and transform the data using the embedder:
 mach = machine(emb, X, y)
 fit!(mach)
 Xnew = transform(mach, X)
 
-# And compare feature scitypes:
+# Compare schemas before and after transformation
 schema(X)
 schema(Xnew)
+```
+
+## Using with Downstream Models (Pipeline)
+```julia
+using MLJ
+
+# Setup some data
+N = 400
+X = (
+  a = rand(Float32, N),
+  b = categorical(rand("abcde", N)),
+  c = categorical(rand("ABCDEFGHIJ", N), ordered = true),
+)
+
+y = categorical(rand("YN", N));
+
+# Initiate model
+EntityEmbedder = @load EntityEmbedder pkg=MLJFlux
+
+# Flux model to do learn the entity embeddings:
+NeuralNetworkClassifier = @load NeuralNetworkClassifier pkg=MLJFlux
+
+# Other supervised model type, requiring `Continuous` features:
+KNNClassifier = @load KNNClassifier pkg=NearestNeighborModels
+
+# Instantiate the models:
+clf = NeuralNetworkClassifier(embedding_dims=Dict(:b => 2, :c => 3))
+emb = EntityEmbedder(clf)
 
 # Now construct the pipeline:
 pipe = emb |> KNNClassifier()

test/entity_embedding.jl

@@ -36,7 +36,7 @@ entityprops = [
     EE1 = Flux.trainables(embedder.embedders[2])[1]         # (newdim, levels) = (5, 10)
     EE2 = Flux.trainables(embedder.embedders[4])[1]         # (newdim, levels) = (2, 2)
 
-    ## One-hot encoding 
+    ## One-hot encoding
     z2_hot = Flux.onehotbatch(z2, levels(z2))
     z4_hot = Flux.onehotbatch(z4, levels(z4))