rename classes_seen field of Obs subtypes to levels_seen

Author: ablaom

src/backends.jl

@@ -31,7 +31,7 @@ If [`Sage`](@ref)`(multitarget=..., code_type=...)` has been implemented, then
 `observations.target` has an integer element type controlled by `code_type`, and we
 additionally have:
 
-- `observations.classes`: A categorical vector of the ordered target levels, as actually
+- `observations.levels`: A categorical vector of the ordered target levels, as actually
   seen in the user-supplied target, with the full pool of levels available by applying
   `Categorical.levels` to the result. The corresponding integer codes will be
   `sort(unique(observations.target))`.
@@ -111,7 +111,7 @@ struct SageObs{F,T,E,D} <: Obs
     features::F  # p x n
     names::Vector{Symbol}
     target::T
-    classes_seen::CategoricalArrays.CategoricalVector{E}
+    levels_seen::CategoricalArrays.CategoricalVector{E}
     decoder::D
 end
 
@@ -122,8 +122,8 @@ function Base.show(io::IO, ::MIME"text/plain", observations::SageObs)
     println(io, "  features :: $(typeof(A))($(size(A)))")
     println(io, "  names: $(observations.names)")
     println(io, "  target :: $(typeof(y))($(size(y)))")
-    println(io, "  classes_seen: "*
-        "$(CategoricalArrays.unwrap.(observations.classes_seen)) "*
+    println(io, "  levels_seen: "*
+        "$(CategoricalArrays.unwrap.(observations.levels_seen)) "*
         "(categorical vector with complete pool)")
     print(io, "  decoder: <callable>")
 end
@@ -133,7 +133,7 @@ Base.getindex(observations::SageObs, idx) =
         MLCore.getobs(observations.features, idx),
         observations.names,
         MLCore.getobs(observations.target, idx),
-        observations.classes_seen,
+        observations.levels_seen,
         observations.decoder,
     )
 

src/saffron.jl

@@ -153,10 +153,10 @@ function finalize(x, names, y, int)  # here `int` is `levelcode` or `refcode` fu
     l = CategoricalArrays.levels(y)
     u = unique(y)
     mask = map(in(u), l)
-    _classes_seen = l[mask]
+    _levels_seen = l[mask]
     _decoder = LearnDataFrontEnds.decoder(l)
 
-    return SageObs(x, names, int.(y), _classes_seen, _decoder)
+    return SageObs(x, names, int.(y), _levels_seen, _decoder)
 end
 
 # for input `(x::AbstractMatrix, y::MatrixOrVector)`:

src/sage.jl

@@ -104,12 +104,12 @@ function LearnAPI.fit(
     X = observations.features # p x n matrix
     y = observations.target   # n-vector or q x n matrix
     decoder = observations.decoder
-    classes_seen = observations.classes_seen
+    levels_seen = observations.levels_seen
     feature_names = observations.names
 
     # do stuff with `X`, `y` and `feature_names`:
     # return a `model` object which also stores the `decoder` and/or
-    # `classes_seen` to make them available to `predict`.
+    # `levels_seen` to make them available to `predict`.
     ...
 
 end
@@ -127,10 +127,10 @@ function LearnAPI.predict(model::MyModel, :K, observations::Obs)
 
     # Do stuff with `X` and `model` to obtain raw `predictions` (a vector of integer
     # codes for `K = Point`, or an `n x c` matrix of probabilities for `K = Distribution`).
-    # Extract `decoder` or `classes_seen` from `model`.
+    # Extract `decoder` or `levels_seen` from `model`.
     # For `K = Point`, return `decoder.(predictions)`.
     # For `K = Distribution`, return, say,
-    # `CategoricalDistributions.Univariate(classes_seen, predictions)`.
+    # `CategoricalDistributions.Univariate(levels_seen, predictions)`.
     ...
 end
 LearnAPI.predict(model::MyModel, kind_of_proxy, X) = LearnAPI.predict(model,

src/tools.jl

@@ -113,7 +113,7 @@ function decompose(X, v, _targets::NTuple)
 end
 
 struct CategoricalDecoder{V,R}
-    classes::CategoricalArrays.CategoricalVector{
+    levels::CategoricalArrays.CategoricalVector{
         V,
         R,
         V,
@@ -146,4 +146,4 @@ pool as `x`.
 decoder(x) = CategoricalDecoder(CategoricalArrays.levels(x))
 
 (d::CategoricalDecoder{V,R})(i::Integer) where {V,R} =
-    CategoricalArrays.CategoricalValue{V,R}(d.classes[i])
+    CategoricalArrays.CategoricalValue{V,R}(d.levels[i])

test/backends.jl

@@ -18,7 +18,7 @@ import CategoricalArrays
         "[:x1, :x2]\n  target :: Vector{Int64}((3,))"
     @test sprint(show, mime, LearnDataFrontEnds.SageObs(x, names, y, c, d)) ==
         "SageObs\n  features :: Matrix{Int64}((2, 3))\n  names: "*
-        "[:x1, :x2]\n  target :: Vector{Int64}((3,))\n  classes_seen: "*
+        "[:x1, :x2]\n  target :: Vector{Int64}((3,))\n  levels_seen: "*
         "[1, 2, 3] (categorical vector with complete pool)\n  decoder: <callable>"
 end
 

test/sage.jl

@@ -62,8 +62,8 @@ f = @formula(t ~ c + a)
     @test o.names == [:x1, :x2]
     @test o.target == repeat([1, 2, 1], n)
     @test eltype(o.target) == Int
-    @test o.classes_seen == CA.levels(y)[1:2]
-    @test o.classes_seen isa CA.CategoricalArray
+    @test o.levels_seen == CA.levels(y)[1:2]
+    @test o.levels_seen isa CA.CategoricalArray
     yy = o.decoder.(o.target)
     @test  yy == y
     @test yy isa CA.CategoricalVector
@@ -87,8 +87,8 @@ end
     @test o.names == [:c, :a]
     @test o.target == repeat([1, 2, 1], n)
     @test eltype(o.target) == Int
-    @test o.classes_seen == CA.levels(y)[1:2]
-    @test o.classes_seen isa CA.CategoricalArray
+    @test o.levels_seen == CA.levels(y)[1:2]
+    @test o.levels_seen isa CA.CategoricalArray
     yy = o.decoder.(o.target)
     @test  yy == y
     @test yy isa CA.CategoricalVector
@@ -112,8 +112,8 @@ end
     @test o.features == x
     @test o.target == repeat([1, 2, 1], n)
     @test eltype(o.target) == Int
-    @test o.classes_seen == CA.levels(y)[1:2]
-    @test o.classes_seen isa CA.CategoricalArray
+    @test o.levels_seen == CA.levels(y)[1:2]
+    @test o.levels_seen isa CA.CategoricalArray
     yy = o.decoder.(o.target)
     @test  yy == y
     @test yy isa CA.CategoricalVector
@@ -138,8 +138,8 @@ end
     @test o.names == [:c, :a]
     @test o.target == repeat([1, 2, 1], n)
     @test eltype(o.target) == Int
-    @test o.classes_seen == CA.levels(y)[1:2]
-    @test o.classes_seen isa CA.CategoricalArray
+    @test o.levels_seen == CA.levels(y)[1:2]
+    @test o.levels_seen isa CA.CategoricalArray
     yy = o.decoder.(o.target)
     @test  yy == y
     @test yy isa CA.CategoricalVector
@@ -163,8 +163,8 @@ end
     @test o.names == [:c, :a]
     @test o.target == repeat([1, 2, 1], n)
     @test eltype(o.target) == Int
-    @test o.classes_seen == CA.levels(y)[1:2]
-    @test o.classes_seen isa CA.CategoricalArray
+    @test o.levels_seen == CA.levels(y)[1:2]
+    @test o.levels_seen isa CA.CategoricalArray
     yy = o.decoder.(o.target)
     @test  yy == y
     @test yy isa CA.CategoricalVector
@@ -223,7 +223,7 @@ struct ConstantClassifierFitted
     learner::ConstantClassifier
     probabilities
     names::Vector{Symbol}
-    classes_seen
+    levels_seen
     codes_seen
     decoder
 end
@@ -256,7 +256,7 @@ function LearnAPI.fit(learner::ConstantClassifier, observations::Obs; verbosity=
 
     y = observations.target # integer "codes"
     names = observations.names
-    classes_seen = observations.classes_seen
+    levels_seen = observations.levels_seen
     codes_seen = sort(unique(y))
     decoder = observations.decoder
 
@@ -268,7 +268,7 @@ function LearnAPI.fit(learner::ConstantClassifier, observations::Obs; verbosity=
         learner,
         probabilities,
         names,
-        classes_seen,
+        levels_seen,
         codes_seen,
         decoder,
     )
@@ -290,7 +290,7 @@ function LearnAPI.predict(model::ConstantClassifierFitted, ::Distribution, obser
     probs = model.probabilities
     # repeat vertically to get rows of a matrix:
     probs_matrix = reshape(repeat(probs, n), (length(probs), n))'
-    return CategoricalDistributions.UnivariateFinite(model.classes_seen, probs_matrix)
+    return CategoricalDistributions.UnivariateFinite(model.levels_seen, probs_matrix)
 end
 LearnAPI.predict(model::ConstantClassifierFitted, ::Distribution, Xnew) =
         predict(model, Distribution(), obs(model, Xnew))