Moved all MLJ interface models to Bmlj module (not yet renamed), colv…

…ed bug in GGImputer and GMMRegressor1

1) All MLJ interface models have been moved to the `Bmlj` module, so they can have the same name of BetaML models,
but the actual renaming has not been performed yet
2) Solved a bug in `GMMImputer` and `GMMRegressor1` that it could not have been initinalised with the `mixtures`
keyword being a type

src/BetaML.jl

@@ -56,11 +56,11 @@ import .Bmlj # some MLJ models have the same name as BetaML models, set them in
 # ------------------------------------------------------------------------------
 #MLJ interface...
 const MLJ_PERCEPTRON_MODELS = (Bmlj.LinearPerceptron, Bmlj.KernelPerceptron, Bmlj.Pegasos)
-const MLJ_TREES_MODELS      = (DecisionTreeClassifier, DecisionTreeRegressor, RandomForestClassifier, RandomForestRegressor)
-const MLJ_CLUSTERING_MODELS = (KMeans, KMedoids, GaussianMixtureClusterer)
-const MLJ_IMPUTERS_MODELS   = (SimpleImputer, GaussianMixtureImputer, RandomForestImputer,GeneralImputer) # these are the name of the MLJ models, not the BetaML ones...
-const MLJ_NN_MODELS         = (NeuralNetworkRegressor,MultitargetNeuralNetworkRegressor, NeuralNetworkClassifier)
-const MLJ_OTHER_MODELS      = (GaussianMixtureRegressor,MultitargetGaussianMixtureRegressor,Bmlj.AutoEncoder)
+const MLJ_TREES_MODELS      = (Bmlj.DecisionTreeClassifier, Bmlj.DecisionTreeRegressor, Bmlj.RandomForestClassifier, Bmlj.RandomForestRegressor)
+const MLJ_CLUSTERING_MODELS = (Bmlj.KMeans, Bmlj.KMedoids, Bmlj.GaussianMixtureClusterer)
+const MLJ_IMPUTERS_MODELS   = (Bmlj.SimpleImputer, Bmlj.GaussianMixtureImputer, Bmlj.RandomForestImputer,Bmlj.GeneralImputer) # these are the name of the MLJ models, not the BetaML ones...
+const MLJ_NN_MODELS         = (Bmlj.NeuralNetworkRegressor,Bmlj.MultitargetNeuralNetworkRegressor, Bmlj.NeuralNetworkClassifier)
+const MLJ_OTHER_MODELS      = (Bmlj.GaussianMixtureRegressor,Bmlj.MultitargetGaussianMixtureRegressor,Bmlj.AutoEncoder)
 const MLJ_INTERFACED_MODELS = (MLJ_PERCEPTRON_MODELS..., MLJ_TREES_MODELS..., MLJ_CLUSTERING_MODELS..., MLJ_IMPUTERS_MODELS..., MLJ_NN_MODELS..., MLJ_OTHER_MODELS...) 
 
 

src/Bmlj/Bmlj.jl

@@ -5,12 +5,15 @@
 # MLJ interface for BetaML models
 
 In this module we define the interface of several BetaML models. They can be used using the [MLJ framework](https://github.com/alan-turing-institute/MLJ.jl).
+
+Note that MLJ models (whose name could be the same as the underlying BetaML model) are not exported. You can access them with `BetaML.Bmlj.ModelXYZ`.
+
 """
 module Bmlj
-mljverbosity_to_betaml_verbosity
 
+using Random, LinearAlgebra, Statistics
 using CategoricalArrays, DocStringExtensions
-using Random
+
 
 import MLJModelInterface       # It seems that having done this in the top module is not enought
 const MMI = MLJModelInterface  # We need to repeat it here
@@ -24,12 +27,11 @@ import ..BetaML
 import ..Utils # can't using it as it exports some same-name models
 import ..Perceptron
 import ..Nn: AbstractLayer, ADAM, SGD, NeuralNetworkEstimator, OptimisationAlgorithm, DenseLayer, NN
-import ..Utils: AbstractRNG, squared_cost, SuccessiveHalvingSearch, mljverbosity_to_betaml_verbosity
+import ..Utils: AbstractRNG, squared_cost, SuccessiveHalvingSearch
 
 
 export mljverbosity_to_betaml_verbosity
 
-
 """
 $(TYPEDSIGNATURES)
 
@@ -51,11 +53,11 @@ function mljverbosity_to_betaml_verbosity(i::Integer)
 end
 
 include("Perceptron_mlj.jl") # Perceptron-like algorithms
-#include("Trees_mlj.jl")           # Decision Trees and ensembles (Random Forests)
-#include("Clustering_mlj.jl") # Clustering (hard) algorithms
-#include("GMM_mlj.jl")               # GMM-based learners (clustering, fitter, regression) 
-#include("Imputation_mlj.jl") 
-#include("Nn_mlj.jl")
-include("Utils_mlj.jl")
+include("Trees_mlj.jl")      # Decision Trees and ensembles (Random Forests)
+include("Clustering_mlj.jl") # Clustering (hard) algorithms
+include("GMM_mlj.jl")        # GMM-based learners (clustering, fitter, regression) 
+include("Imputation_mlj.jl") # Imputation models
+include("Nn_mlj.jl")         # Neural network models
+include("Utils_mlj.jl")      # Various transformers/encorders
 
 end

src/Clustering/Clustering_MLJ.jl → src/Bmlj/Clustering_mlj.jl

@@ -2,9 +2,6 @@
 
 # MLJ interface for hard clustering models
 
-import MLJModelInterface       # It seems that having done this in the top module is not enought
-const MMI = MLJModelInterface  # We need to repeat it here
-
 export KMeans, KMedoids
 
 # ------------------------------------------------------------------------------
@@ -165,11 +162,11 @@ function MMI.fit(m::Union{KMeans,KMedoids}, verbosity, X)
     x  = MMI.matrix(X)                        # convert table to matrix
     # Using low level API here. We could switch to APIV2...
     typeof(verbosity) <: Integer || error("Verbosity must be a integer. Current \"steps\" are 0, 1, 2 and 3.")  
-    verbosity = Utils.mljverbosity_to_betaml_verbosity(verbosity)
+    verbosity = mljverbosity_to_betaml_verbosity(verbosity)
     if typeof(m) == KMeans
-        (assignedClasses,representatives) = kmeans(x,m.n_classes,dist=m.dist,initialisation_strategy=m.initialisation_strategy,initial_representatives=m.initial_representatives,rng=m.rng,verbosity=verbosity)
+        (assignedClasses,representatives) = BetaML.Clustering.kmeans(x,m.n_classes,dist=m.dist,initialisation_strategy=m.initialisation_strategy,initial_representatives=m.initial_representatives,rng=m.rng,verbosity=verbosity)
     else
-        (assignedClasses,representatives) = kmedoids(x,m.n_classes,dist=m.dist,initialisation_strategy=m.initialisation_strategy,initial_representatives=m.initial_representatives,rng=m.rng, verbosity=verbosity)
+        (assignedClasses,representatives) = BetaML.Clustering.kmedoids(x,m.n_classes,dist=m.dist,initialisation_strategy=m.initialisation_strategy,initial_representatives=m.initial_representatives,rng=m.rng, verbosity=verbosity)
     end
     cache=nothing
     report=nothing
@@ -216,13 +213,13 @@ MMI.metadata_model(KMeans,
     output_scitype   = MMI.Table(MMI.Continuous),         # scitype of the output of `transform`
     target_scitype   = AbstractArray{<:MMI.Multiclass},   # scitype of the output of `predict`
     supports_weights = false,                             # does the model support sample weights?
-	load_path        = "BetaML.Clustering.KMeans"
+	load_path        = "BetaML.Bmlj.KMeans"
 )
 
 MMI.metadata_model(KMedoids,
     input_scitype    = MMI.Table(MMI.Continuous),         # scitype of the inputs
     output_scitype   = MMI.Table(MMI.Continuous),         # scitype of the output of `transform`
     target_scitype   = AbstractArray{<:MMI.Multiclass},   # scitype of the output of `predict`
     supports_weights = false,                             # does the model support sample weights?
-	load_path        = "BetaML.Clustering.KMedoids"
+	load_path        = "BetaML.Bmlj.KMedoids"
 )

src/GMM/GMM_MLJ.jl → src/Bmlj/GMM_mlj.jl

@@ -1,9 +1,6 @@
 "Part of [BetaML](https://github.com/sylvaticus/BetaML.jl). Licence is MIT."
 
-# MLJ interface for clustering models
-
-import MLJModelInterface       # It seems that having done this in the top module is not enought
-const MMI = MLJModelInterface  # We need to repeat it here
+# MLJ interface for GMM based models
 
 export  GaussianMixtureClusterer, GaussianMixtureRegressor, MultitargetGaussianMixtureRegressor
 
@@ -68,7 +65,7 @@ mutable struct GaussianMixtureClusterer <: MMI.Unsupervised
     This parameter can also be given symply in term of a _type_. In this case it is automatically extended to a vector of `n_classes` mixtures of the specified type.
     Note that mixing of different mixture types is not currently supported.
     [def: `[DiagonalGaussian() for i in 1:n_classes]`]"""
-  mixtures::Union{Type,Vector{<: AbstractMixture}}
+  mixtures::Union{Type,Vector{<: BetaML.GMM.AbstractMixture}}
   "Tolerance to stop the algorithm [default: 10^(-6)]"
   tol::Float64
   "Minimum variance for the mixtures [default: 0.05]"
@@ -92,7 +89,7 @@ end
 function GaussianMixtureClusterer(;
     n_classes             = 3,
     initial_probmixtures            = Float64[],
-    mixtures      = [DiagonalGaussian() for i in 1:n_classes],
+    mixtures      = [BetaML.GMM.DiagonalGaussian() for i in 1:n_classes],
     tol           = 10^(-6),
     minimum_variance   = 0.05,
     minimum_covariance = 0.0,
@@ -162,7 +159,7 @@ mutable struct GaussianMixtureRegressor <: MMI.Deterministic
     This parameter can also be given symply in term of a _type_. In this case it is automatically extended to a vector of `n_classes`` mixtures of the specified type.
     Note that mixing of different mixture types is not currently supported.
     [def: `[DiagonalGaussian() for i in 1:n_classes]`]"""
-    mixtures::Union{Type,Vector{<: AbstractMixture}}
+    mixtures::Union{Type,Vector{<: BetaML.GMM.AbstractMixture}}
     "Tolerance to stop the algorithm [default: 10^(-6)]"
     tol::Float64
     "Minimum variance for the mixtures [default: 0.05]"
@@ -186,7 +183,7 @@ end
 function GaussianMixtureRegressor(;
     n_classes      = 3,
     initial_probmixtures  = [],
-    mixtures      = [DiagonalGaussian() for i in 1:n_classes],
+    mixtures      = [BetaML.GMM.DiagonalGaussian() for i in 1:n_classes],
     tol           = 10^(-6),
     minimum_variance   = 0.05,
     minimum_covariance = 0.0,
@@ -195,7 +192,7 @@ function GaussianMixtureRegressor(;
     rng           = Random.GLOBAL_RNG
    )
    if typeof(mixtures) <: UnionAll
-     mixtures = [mixtures() for i in 1:n_classes]
+     mixtures = [BetaML.GMM.mixtures() for i in 1:n_classes]
    end
    return GaussianMixtureRegressor(n_classes,initial_probmixtures,mixtures,tol,minimum_variance,minimum_covariance,initialisation_strategy,maximum_iterations,rng)
 end
@@ -258,7 +255,7 @@ mutable struct MultitargetGaussianMixtureRegressor <: MMI.Deterministic
     This parameter can also be given symply in term of a _type_. In this case it is automatically extended to a vector of `n_classes`` mixtures of the specified type.
     Note that mixing of different mixture types is not currently supported.
     [def: `[DiagonalGaussian() for i in 1:n_classes]`]"""
-    mixtures::Union{Type,Vector{<: AbstractMixture}}
+    mixtures::Union{Type,Vector{<: BetaML.GMM.AbstractMixture}}
     "Tolerance to stop the algorithm [default: 10^(-6)]"
     tol::Float64
     "Minimum variance for the mixtures [default: 0.05]"
@@ -282,7 +279,7 @@ end
 function MultitargetGaussianMixtureRegressor(;
     n_classes      = 3,
     initial_probmixtures  = [],
-    mixtures      = [DiagonalGaussian() for i in 1:n_classes],
+    mixtures      = [BetaML.GMM.DiagonalGaussian() for i in 1:n_classes],
     tol           = 10^(-6),
     minimum_variance   = 0.05,
     minimum_covariance = 0.0,
@@ -314,9 +311,9 @@ function MMI.fit(m::GaussianMixtureClusterer, verbosity, X)
     end
     =#
     typeof(verbosity) <: Integer || error("Verbosity must be a integer. Current \"steps\" are 0, 1, 2 and 3.")  
-    verbosity = Utils.mljverbosity_to_betaml_verbosity(verbosity)
+    verbosity = mljverbosity_to_betaml_verbosity(verbosity)
     mixtures = m.mixtures
-    res        = gmm(x,m.n_classes,initial_probmixtures=deepcopy(m.initial_probmixtures),mixtures=mixtures, minimum_variance=m.minimum_variance, minimum_covariance=m.minimum_covariance,initialisation_strategy=m.initialisation_strategy,verbosity=verbosity,maximum_iterations=m.maximum_iterations,rng=m.rng)
+    res        = BetaML.GMM.gmm(x,m.n_classes,initial_probmixtures=deepcopy(m.initial_probmixtures),mixtures=mixtures, minimum_variance=m.minimum_variance, minimum_covariance=m.minimum_covariance,initialisation_strategy=m.initialisation_strategy,verbosity=verbosity,maximum_iterations=m.maximum_iterations,rng=m.rng)
     fitResults = (pₖ=res.pₖ,mixtures=res.mixtures) # res.pₙₖ
     cache      = nothing
     report     = (res.ϵ,res.lL,res.BIC,res.AIC)
@@ -327,7 +324,7 @@ MMI.fitted_params(model::GaussianMixtureClusterer, fitresult) = (weights=fitresu
 function MMI.fit(m::GaussianMixtureRegressor, verbosity, X, y)
     x  = MMI.matrix(X) # convert table to matrix
     typeof(verbosity) <: Integer || error("Verbosity must be a integer. Current \"steps\" are 0, 1, 2 and 3.")  
-    verbosity = Utils.mljverbosity_to_betaml_verbosity(verbosity)
+    verbosity = mljverbosity_to_betaml_verbosity(verbosity)
     ndims(y) < 2 || error("Trying to fit `GaussianMixtureRegressor` with a multidimensional target. Use `MultitargetGaussianMixtureRegressor` instead.")
     #=
     if typeof(y) <: AbstractMatrix
@@ -345,7 +342,7 @@ function MMI.fit(m::GaussianMixtureRegressor, verbosity, X, y)
     end
     =#
     mixtures = m.mixtures
-    betamod = GMMRegressor2(
+    betamod = BetaML.GMM.GMMRegressor2(
         n_classes     = m.n_classes,
         initial_probmixtures = m.initial_probmixtures,
         mixtures     = mixtures,
@@ -363,7 +360,7 @@ end
 function MMI.fit(m::MultitargetGaussianMixtureRegressor, verbosity, X, y)
     x  = MMI.matrix(X) # convert table to matrix
     typeof(verbosity) <: Integer || error("Verbosity must be a integer. Current \"steps\" are 0, 1, 2 and 3.")  
-    verbosity = Utils.mljverbosity_to_betaml_verbosity(verbosity)
+    verbosity = mljverbosity_to_betaml_verbosity(verbosity)
     ndims(y) >= 2 || @warn "Trying to fit `MultitargetGaussianMixtureRegressor` with a single-dimensional target. You may want to consider `GaussianMixtureRegressor` instead."
     #=
     if typeof(y) <: AbstractMatrix
@@ -381,7 +378,7 @@ function MMI.fit(m::MultitargetGaussianMixtureRegressor, verbosity, X, y)
     end
     =#
     mixtures = m.mixtures
-    betamod = GMMRegressor2(
+    betamod = BetaML.GMM.GMMRegressor2(
         n_classes     = m.n_classes,
         initial_probmixtures = m.initial_probmixtures,
         mixtures     = mixtures,
@@ -407,7 +404,7 @@ function MMI.predict(m::GaussianMixtureClusterer, fitResults, X)
     (pₖ,mixtures)   = (fitResults.pₖ, fitResults.mixtures)
     nCl             = length(pₖ)
     # Compute the probabilities that maximise the likelihood given existing mistures and a single iteration (i.e. doesn't update the mixtures)
-    thisOut         = gmm(x,nCl,initial_probmixtures=pₖ,mixtures=mixtures,tol=m.tol,verbosity=NONE,minimum_variance=m.minimum_variance,minimum_covariance=m.minimum_covariance,initialisation_strategy="given",maximum_iterations=1,rng=m.rng)
+    thisOut         = BetaML.GMM.gmm(x,nCl,initial_probmixtures=pₖ,mixtures=mixtures,tol=m.tol,verbosity=NONE,minimum_variance=m.minimum_variance,minimum_covariance=m.minimum_covariance,initialisation_strategy="given",maximum_iterations=1,rng=m.rng)
     classes         = CategoricalArray(1:nCl)
     predictions     = MMI.UnivariateFinite(classes, thisOut.pₙₖ)
     return predictions
@@ -416,12 +413,12 @@ end
 function MMI.predict(m::GaussianMixtureRegressor, fitResults, X)
     x               = MMI.matrix(X) # convert table to matrix
     betamod         = fitResults
-    return dropdims(predict(betamod,x),dims=2)
+    return dropdims(BetaML.Api.predict(betamod,x),dims=2)
 end
 function MMI.predict(m::MultitargetGaussianMixtureRegressor, fitResults, X)
     x               = MMI.matrix(X) # convert table to matrix
     betamod         = fitResults
-    return predict(betamod,x)
+    return BetaML.Api.predict(betamod,x)
 end
 
 
@@ -434,19 +431,19 @@ MMI.metadata_model(GaussianMixtureClusterer,
     target_scitype   = AbstractArray{<:MMI.Multiclass},       # scitype of the output of `predict`
     #prediction_type  = :probabilistic,  # option not added to metadata_model function, need to do it separately
     supports_weights = false,                                 # does the model support sample weights?
-	load_path        = "BetaML.GMM.GaussianMixtureClusterer"
+	load_path        = "BetaML.Bmlj.GaussianMixtureClusterer"
 )
 MMI.prediction_type(::Type{<:GaussianMixtureClusterer}) = :probabilistic
 
 MMI.metadata_model(GaussianMixtureRegressor,
     input_scitype    = MMI.Table(Union{MMI.Missing, MMI.Infinite}),
     target_scitype   = AbstractVector{<: MMI.Continuous},           # for a supervised model, what target?
     supports_weights = false,                                       # does the model support sample weights?
-	load_path        = "BetaML.GMM.GaussianMixtureRegressor"
+	load_path        = "BetaML.Bmlj.GaussianMixtureRegressor"
 )
 MMI.metadata_model(MultitargetGaussianMixtureRegressor,
     input_scitype    = MMI.Table(Union{MMI.Missing, MMI.Infinite}),
     target_scitype   = AbstractMatrix{<: MMI.Continuous},           # for a supervised model, what target?
     supports_weights = false,                                       # does the model support sample weights?
-	load_path        = "BetaML.GMM.MultitargetGaussianMixtureRegressor"
+	load_path        = "BetaML.Bmlj.MultitargetGaussianMixtureRegressor"
 )