Merge pull request #27 from alan-turing-institute/dev

For 0.2.0 release

Author: ablaom

Project.toml

@@ -1,9 +1,10 @@
 name = "MLJModelInterface"
 uuid = "e80e1ace-859a-464e-9ed9-23947d8ae3ea"
 authors = ["Thibaut Lienart and Anthony Blaom"]
-version = "0.1.8"
+version = "0.2.0"
 
 [deps]
+Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
 ScientificTypes = "321657f4-b219-11e9-178b-2701a2544e81"
 
 [compat]

src/MLJModelInterface.jl

@@ -1,8 +1,9 @@
 module MLJModelInterface
 
 # ------------------------------------------------------------------------
-# Dependency (ScientificTypes itself does not have dependencies)
+# Dependencies (ScientificTypes itself does not have dependencies)
 using ScientificTypes
+using Random
 
 # ------------------------------------------------------------------------
 # exports
@@ -36,12 +37,21 @@ export input_scitype, output_scitype, target_scitype,
 export matrix, int, classes, decoder, table,
        nrows, selectrows, selectcols, select
 
+# equality
+export is_same_except
+
 # re-exports from ScientificTypes
 export Scientific, Found, Unknown, Known, Finite, Infinite,
        OrderedFactor, Multiclass, Count, Continuous, Textual,
        Binary, ColorImage, GrayImage, Image, Table
 export scitype, scitype_union, elscitype, nonmissing, trait
 
+# ------------------------------------------------------------------------
+# To be extended
+
+import Base.==
+import Base: in, isequal
+#
 # ------------------------------------------------------------------------
 # Mode trick
 
@@ -79,12 +89,13 @@ abstract type Static <: Unsupervised end
 # includes
 
 include("utils.jl")
-
 include("data_utils.jl")
 include("metadata_utils.jl")
 
 include("model_traits.jl")
 include("model_def.jl")
 include("model_api.jl")
+include("equality.jl")
+
 
 end # module

src/equality.jl

@@ -0,0 +1,63 @@
+"""
+    is_same_except(m1::MLJType, m2::MLJType, exceptions::Symbol...)
+
+Returns `true` only the following conditions all hold:
+
+- `m1` and `m2` have the same type.
+
+- `m1` and `m2` have the same undefined fields.
+
+- Corresponding fields agree, or are listed as `exceptions`, or have
+  `AbstractRNG` as values (one or both)
+
+Here "agree" is in the sense of "==", unless the objects are themselves of
+`MLJType`, in which case agreement is in the sense of `is_same_except` with
+no exceptions allowed.
+
+Note that Base.== is overloaded such that `m1 == m2` if and only if
+`is_same_except(m1, m2)`.
+"""
+is_same_except(x1, x2) = ==(x1, x2)
+function is_same_except(m1::M1, m2::M2,
+            exceptions::Symbol...) where {M1<:MLJType,M2<:MLJType}
+    if typeof(m1) != typeof(m2)
+        return false
+    end
+    defined1 = filter(fieldnames(M1)|>collect) do fld
+        isdefined(m1, fld) && !(fld in exceptions)
+    end
+    defined2 = filter(fieldnames(M1)|>collect) do fld
+        isdefined(m2, fld) && !(fld in exceptions)
+    end
+    if defined1 != defined2
+        return false
+    end
+    same_values = true
+    for fld in defined1
+        same_values = same_values &&
+            (is_same_except(getfield(m1, fld), getfield(m2, fld)) ||
+             getfield(m1, fld) isa AbstractRNG ||
+             getfield(m2, fld) isa AbstractRNG)
+    end
+    return same_values
+end
+
+==(m1::M1, m2::M2) where {M1<:MLJType,M2<:MLJType} = is_same_except(m1, m2)
+
+# for using `replace` or `replace!` on collections of MLJType objects
+# (eg, Model objects in a learning network) we need a stricter
+# equality and a corresponding definition of `in`.
+Base.isequal(m1::MLJType, m2::MLJType) = (m1 === m2)
+
+# Note: To prevent julia crash, it seems we need to annotate the type
+# of itr:
+function special_in(x, itr)::Union{Bool,Missing}
+    for y in itr
+        ismissing(y) && return missing
+        y === x && return true
+    end
+    return false
+end
+Base.in(x::MLJType, itr::Set) = special_in(x, itr)
+Base.in(x::MLJType, itr::AbstractVector) = special_in(x, itr)
+Base.in(x::MLJType, itr::Tuple) = special_in(x, itr)

src/model_api.jl

@@ -31,5 +31,10 @@ function predict_median end
 function transform end
 function inverse_transform end
 
+# models can optionally overload these for enable serialization in a
+# custom format:
+function save end
+function restore end
+
 # operations implemented by some meta-models:
 function evaluate end

src/model_traits.jl

@@ -10,11 +10,6 @@ const MODEL_TRAITS = [
     :prediction_type, :implemented_methods, :hyperparameters,
     :hyperparameter_types, :hyperparameter_ranges]
 
-const SUPERVISED_TRAITS = setdiff(MODEL_TRAITS, [:output_scitype])
-
-const UNSUPERVISED_TRAITS = setdiff(MODEL_TRAITS,
-    [:target_scitype, :prediction_type, :supports_weights])
-
 for trait in MODEL_TRAITS
     ex = quote
         $trait(x) = $trait(typeof(x))

test/equality.jl

@@ -0,0 +1,87 @@
+using Random
+using MLJModelInterface
+using Test
+
+mutable struct Foo <: MLJType
+    rng::AbstractRNG
+    x::Int
+    y::Int
+end
+
+mutable struct Bar <: MLJType
+    rng::AbstractRNG
+    x::Int
+    y::Int
+end
+
+mutable struct Super <: MLJType
+    sub::Foo
+    z::Int
+end
+
+mutable struct Partial <: MLJType
+    x::Int
+    y::Vector{Int}
+    Partial(x) = new(x)
+end
+
+@testset "equality for MLJType" begin
+    f1 = Foo(MersenneTwister(7), 1, 2)
+    f2 = Foo(MersenneTwister(8), 1, 2)
+
+    @test f1.rng != f2.rng
+    @test f1 == f2
+    f1.x = 10
+    @test f1 != f2
+    b = Bar(MersenneTwister(7), 1, 2)
+    @test f2 != b
+
+    @test is_same_except(f1, f2, :x)
+    f1.y = 20
+    @test f1 != f2
+    @test is_same_except(f1, f2, :x, :y)
+
+    f1 = Foo(MersenneTwister(7), 1, 2)
+    f2 = Foo(MersenneTwister(8), 1, 2)
+    s1 = Super(f1, 20)
+    s2 = Super(f2, 20)
+    @test s1 == s2
+    s2.sub.x = 10
+    @test f1 != f2
+
+    @test !(f1 == Super(f1, 4))
+
+    @test !(isequal(Foo(MersenneTwister(1), 1, 2),
+                    Foo(MersenneTwister(1), 1, 2)))
+
+    p1 = Partial(1)
+    p2 = Partial(1)
+    p2.y = [1,2]
+    @test !(p1 == p2)
+
+end
+
+@testset "in(x, collection) for MLJType" begin
+    f1 = Foo(MersenneTwister(7), 1, 2)
+    f2 = Foo(MersenneTwister(7), 1, 2)
+    f3 = Super(f1, 20)
+
+    tv = (f1, f3)
+    tk = (f2, f3)
+    tw = (f3, f3)
+    v = [tv...]
+    k = [tk...]
+    w = [tw...]
+    @test f1 in tv
+    @test !(f1 in tk)
+    @test !(f1 in tw)
+    @test f1 in v
+    @test !(f1 in k)
+    @test !(f1 in w)
+    @test f1 in Set(v)
+    @test !(f1 in Set(k))
+    @test !(f1 in Set(w))
+
+end
+
+true

test/runtests.jl

@@ -18,3 +18,4 @@ include("metadata_utils.jl")
 include("model_def.jl")
 include("model_api.jl")
 include("model_traits.jl")
+include("equality.jl")