Merge pull request #121 from davnn/patch-2

Supervised fit should work for all unsupervised annotators

Author: ablaom

src/model_api.jl

@@ -15,12 +15,11 @@ fit(::Static, ::Integer, data...) = (nothing, nothing, nothing)
 # fallbacks for supervised models that don't support sample weights:
 fit(m::Supervised, verbosity, X, y, w) = fit(m, verbosity, X, y)
 
-# fallback for unsupervised detectors when no "evaluation" labels appear:
-fit(m::Union{ProbabilisticUnsupervisedDetector,
-             DeterministicUnsupervisedDetector},
-             verbosity,
-             X,
-             y) =  fit(m, verbosity, X)
+# fallback for unsupervised annotators when labels or weights appear:
+# this is useful for evaluation and mixed composite models that combine
+# both supervised and unsupervised annotators
+fit(m::UnsupervisedAnnotator, verbosity, X, y) =  fit(m, verbosity, X)
+fit(m::UnsupervisedAnnotator, verbosity, X, y, w) =  fit(m, verbosity, X)
 
 """
     MLJModelInterface.update(model, verbosity, fitresult, cache, data...)

src/model_traits.jl

@@ -41,10 +41,8 @@ for M in ABSTRACT_MODEL_SUBTYPES
     @eval(StatTraits.abstract_type(::Type{<:$M}) = $M)
 end
 
-StatTraits.fit_data_scitype(M::Type{<:Unsupervised}) =
-    Tuple{input_scitype(M)}
-StatTraits.fit_data_scitype(::Type{<:Static}) = Tuple{}
-function StatTraits.fit_data_scitype(M::Type{<:Supervised})
+# helper to determine the scitype of supervised models
+function supervised_fit_data_scitype(M)
     I = input_scitype(M)
     T = target_scitype(M)
     ret = Tuple{I,T}
@@ -57,21 +55,21 @@ function StatTraits.fit_data_scitype(M::Type{<:Supervised})
     end
     return ret
 end
-StatTraits.fit_data_scitype(M::Type{<:UnsupervisedAnnotator}) =
+
+StatTraits.fit_data_scitype(M::Type{<:Unsupervised}) =
     Tuple{input_scitype(M)}
+StatTraits.fit_data_scitype(::Type{<:Static}) = Tuple{}
+StatTraits.fit_data_scitype(M::Type{<:Supervised}) =
+    supervised_fit_data_scitype(M)
+
+# In special case of `UnsupervisedAnnotator`, we allow the target 
+# as an optional argument to `fit` (that is ignored) so that the
+# `machine` constructor will accept it as a valid argument, which
+# then enables *evaluation* of the detector with labeled data:
+StatTraits.fit_data_scitype(M::Type{<:UnsupervisedAnnotator}) =
+    Union{Tuple{input_scitype(M)}, supervised_fit_data_scitype(M)}
 StatTraits.fit_data_scitype(M::Type{<:SupervisedAnnotator}) =
-    Tuple{input_scitype(M),target_scitype(M)}
-
-# In special case of `UnsupervisedProbabilisticDetector`, and
-# `UnsupervsedDeterministicDetector` we allow the target as an
-# optional argument to `fit` (that is ignored) so that the `machine`
-# constructor will accept it as a valid argument, which then enables
-# *evaluation* of the detector with labeled data:
-StatTraits.fit_data_scitype(M::Type{<:Union{
-    ProbabilisticUnsupervisedDetector,
-    DeterministicUnsupervisedDetector}}) =
-        Union{Tuple{input_scitype(M)},
-              Tuple{input_scitype(M),target_scitype(M)}}
+    supervised_fit_data_scitype(M)
 
 StatTraits.transform_scitype(M::Type{<:Unsupervised}) =
     output_scitype(M)
@@ -82,7 +80,6 @@ StatTraits.inverse_transform_scitype(M::Type{<:Unsupervised}) =
 StatTraits.predict_scitype(M::Type{<:Union{
     Deterministic,DeterministicDetector}}) = target_scitype(M)
 
-
 ## FALLBACKS FOR `predict_scitype` FOR `Probabilistic` and
 ## `ProbabilisticDetector` MODELS