Merge pull request #469 from JuliaAI/dev

For a 0.15.10 release

.github/workflows/check_registry.yml

@@ -17,7 +17,11 @@ jobs:
         arch:
           - x64
     env:
-      PYTHON: ""
+      PYTHON: Conda
+      # remove next line (and others marked below) when 
+      # JuliaAI/MLJScikitLearnInterface.jl#42 properly resolved
+      LD_LIBRARY_PATH: /home/runner/.julia/conda/3/lib
+
     steps:
       - uses: actions/checkout@v2
       - uses: julia-actions/setup-julia@v1
@@ -34,9 +38,20 @@ jobs:
             ${{ runner.os }}-test-${{ env.cache-name }}-
             ${{ runner.os }}-test-
             ${{ runner.os }}-
+      - uses: julia-actions/julia-buildpkg@v1
       - run: julia -e 'using Pkg; Pkg.Registry.update()'
       - run: julia -e 'using Pkg; Pkg.develop(Pkg.PackageSpec(path = pwd()))'
       - run: julia -e 'using Pkg; Pkg.add("Test")'
+
+       # remove next eight lines (and one other marked above) when 
+       # JuliaAI/MLJScikitLearnInterface.jl#42 gets properly resolved
+      - name: "Install Conda"
+        run: julia -e 'using Pkg; Pkg.add("Conda");'
+      - name: "Install Scikit-learn"
+        run: |
+          julia -e 'using Conda; Conda.add("scikit-learn");'\
+          cd $LD_LIBRARY_PATH #just to check that the path is valid
+        
       - run: julia -e 'using Pkg; Pkg.update()'
       - run: julia -e 'using Pkg; Pkg.precompile()'
       - run: julia -e 'using Pkg; Pkg.status()'

Project.toml

@@ -1,7 +1,7 @@
 name = "MLJModels"
 uuid = "d491faf4-2d78-11e9-2867-c94bc002c0b7"
 authors = ["Anthony D. Blaom <[email protected]>"]
-version = "0.15.9"
+version = "0.15.10"
 
 [deps]
 CategoricalArrays = "324d7699-5711-5eae-9e2f-1d82baa6b597"

README.md

@@ -70,34 +70,7 @@ MLJModels contains:
 
 Generally model registration is performed by administrators. If you
 have an interface you would like registered, open an issue
-[here](https://github.com/alan-turing-institute/MLJ.jl/issues).
+[here](https://github.com/alan-turing-institute/MLJ.jl/issues). 
 
-**Administrator instructions.** To register all the models in
-GreatNewPackage with MLJ:
-
-- In the dev branch of a clone of the dev branch of MLJModels, change
-  to the `/src/registry/` directory and, in the latest version of julia, activate the
-  environment specified by the Project.toml there, after checking the
-  [compat] conditions there are up to date. **Do not use**
-  `Revise`. 
-
-- Add `GreatNewPackage` to the environment.
-
-- In some environment to which your MLJModels clone has been added
-  (using `Pkg.dev`) execute `using MLJModels; MLJModels.@update`. This updates
-  `src/registry/Metadata.toml` and `src/registry/Models.toml` (the
-  latter is generated for convenience and not used by MLJ). 
-
-- Quit your REPL session and make a trivial commit to your MLJModels
-  branch to force pre-compilation in a new julia session when you run
-  `using MLJModels`. (For technical reasons the registry is not loaded
-  in `__init__`()`, so without pre-compiliation the new ]registry is not
-  available.)
-
-- Test that the interfaces load properly with
-  `MLJModels.check_registry()`. (CI will fail on dev -> master if
-  this test fails.)
-
-- Push your changes to an appropriate branch of MLJModels to make
-  the updated metadata available to users of the next MLJModels tagged
-  release.
+**Administrator instructions.** These are given in the
+`MLJModels.@update` document string.

src/MLJModels.jl

@@ -74,14 +74,15 @@ const MODEL_TRAITS_IN_REGISTRY = model_traits_in_registry(INFO_GIVEN_HANDLE)
 # model search and registry code:
 include("model_search.jl")
 include("loading.jl")
-include("registry/src/info_dict.jl")
 include("registry/src/Registry.jl")
-include("registry/src/check_registry.jl")
-import .Registry.@update
+using .Registry
 
 # load built-in models:
 include("builtins/Constant.jl")
 include("builtins/Transformers.jl")
 include("builtins/ThresholdPredictors.jl")
 
+# finalize:
+include("init.jl")
+
 end # module

src/builtins/Transformers.jl

@@ -860,7 +860,7 @@ function MMI.fit(transformer::OneHotEncoder, verbosity::Int, X)
         if T <: allowed_scitypes && ftr in specified_features
             ref_name_pairs_given_feature[ftr] = Pair{<:Unsigned,Symbol}[]
             shift = transformer.drop_last ? 1 : 0
-            levels = classes(first(col))
+            levels = classes(col)
             fitted_levels_given_feature[ftr] = levels
             if verbosity > 0
                 @info "Spawning $(length(levels)-shift) sub-features "*

src/init.jl

@@ -0,0 +1,6 @@
+function __init__()
+    project = open(joinpath(@__DIR__, "registry", "Project.toml")) do io
+        readlines(io)
+    end
+    global REGISTRY_PROJECT = Ref{Vector{String}}(project)
+end 

src/loading.jl

@@ -15,25 +15,9 @@ function _append!(program, ex, doprint::Bool, tick_early::Bool)
 end
 
 function _import(modl, api_pkg, pkg, doprint)
-    # can be removed once MLJModel #331 is resolved:
-    if pkg == :NearestNeighbors
-        doprint && print("import NearestNeighbors")
-        try
-            modl.eval(:(import MLJModels))
-        catch
-            try
-                modl.eval(:(import MLJ.MLJModels))
-            catch
-                error("Problem putting MLJModels into scope. ")
-            end
-        end
-        modl.eval(:(import NearestNeighbors))
-        doprint && println(" \u2714")
-    else
-        doprint && print("import $api_pkg")
-        modl.eval(:(import $api_pkg))
-        doprint && println(" \u2714")
-    end
+    doprint && print("import $api_pkg")
+    modl.eval(:(import $api_pkg))
+    doprint && println(" \u2714")
 end
 
 function _eval(modl, path::Union{Expr,Symbol})
@@ -44,19 +28,26 @@ end
 ## OVERLOADING load_path
 
 """
-    load_path(model::String, pkg=nothing)
+    load_path(model_name::String, pkg=nothing)
+
+Return the load path for model type with name `model_name`, specifying
+the algorithm=providing package name `pkg` to resolve name conflicts,
+if necessary.
+
+    load_path(proxy::NamedTuple)
 
-Return the load path for model type with name `model`, specifying the
-package name `pkg` to resolve name conflicts if necessary.
+Return the load path for the model whose name is `proxy.name` and whose
+algorithm-providing package has name `proxy.package_name`. For example,
+`proxy` could be any element of the vector returned by `models()`.
 
     load_path(model)
 
 Return the load path of a `model` instance or type. Usually requires
-necessary model code to have been separately loaded. Supply a string
+necessary model code to have been separately loaded. Supply strings
 as above if code is not loaded.
 
 """
-function MLJModelInterface.load_path(proxy::ModelProxy)
+function MLJModelInterface.load_path(proxy::NamedTuple)
     handle = (name=proxy.name, pkg=proxy.package_name)
     return INFO_GIVEN_HANDLE[handle][:load_path]
 end
@@ -213,15 +204,30 @@ function _load(modl, name_ex, kw_exs...; interactive=false)
 end
 
 
-## NO LONGER SUPPORTED
+"""
+    MLJModels.load(name; pkg=nothing, add=false, verbosity=0, mod=Main)
+
+Experimental method.
+Currently private.
+
+Loads model code into specified module `mod` at run time, as opposed
+to `@load` which loads coad into calling module at time of invokation.
+
+"""
+function load(
+    name::String;
+    pkg::Union{String,Nothing}=nothing,
+    add::Bool=false,
+    verbosity::Integer=0,
+    mod=Main
+)
+    ex = if isnothing(pkg)
+        :(@load $name add=$add verbosity=$verbosity)
+    else
+        :(@load $name pkg=$pkg add=$add verbosity=$verbosity)
+    end
+    mod.eval(ex)
+end
 
-_deperror() = error(
-    "The `load` function is no longer supported. "*
-    "Use the `@load` macro instead, as in "*
-    "`@load RandomForestRegressor pkg = DecisionTree`.\n"*
-    "For explicit importing, you can discover a model's "*
-    "full load path with the `load_path` function, as in "*
-    "`load_path(\"RandomForestRegressor\", pkg=\"DecisionTree\")`. )")
 
-load(proxy::ModelProxy; kwargs...) = _deperror()
-load(name::String; kwargs...) = _deperror()
+#load(proxy, ...) = ...