Merge branch 'dev' of github.com:alberto-paparella/SoleModels.jl into alberto-paparella-dev

Author: giopaglia

Project.toml

@@ -18,7 +18,6 @@ HTTP = "cd3eb016-35fb-5094-929b-558a96fad6f3"
 Lazy = "50d2b5c4-7a5e-59d5-8109-a42b560f39c0"
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"
 Logging = "56ddb016-857b-54e1-b83d-db4d58db5568"
-MLJModelInterface = "e80e1ace-859a-464e-9ed9-23947d8ae3ea"
 PrettyTables = "08abe8d2-0d0c-5749-adfa-8a2ac140af0d"
 ProgressMeter = "92933f4c-e287-5a05-a399-4b506db050ca"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
@@ -33,6 +32,18 @@ Tables = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
 ThreadSafeDicts = "4239201d-c60e-5e0a-9702-85d713665ba7"
 ZipFile = "a5390f91-8eb1-5f08-bee0-b1d1ffed6cea"
 
+[weakdeps]
+DecisionTree = "7806a523-6efd-50cb-b5f6-3fa6f1930dbb"
+MLJ = "add582a8-e3ab-11e8-2d5e-e98b27df1bc7"
+MLJDecisionTreeInterface = "c6f25543-311c-4c74-83dc-3ea6d1015661"
+MLJModelInterface = "e80e1ace-859a-464e-9ed9-23947d8ae3ea"
+
+[extensions]
+DecisionTreeExt = "DecisionTree"
+MLJExt = "MLJ"
+MLJDecisionTreeInterfaceExt = "MLJDecisionTreeInterface"
+MLJModelInterfaceExt = "MLJModelInterface"
+
 [compat]
 AbstractTrees = "0.4"
 BenchmarkTools = "1"
@@ -63,13 +74,10 @@ julia = "1"
 
 [extras]
 InteractiveUtils = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
-MLJ = "add582a8-e3ab-11e8-2d5e-e98b27df1bc7"
-MLJDecisionTreeInterface = "c6f25543-311c-4c74-83dc-3ea6d1015661"
 Markdown = "d6f4376e-aef5-505a-96c1-9c027394607a"
 MultiData = "8cc5100c-b3d1-4f82-90cb-0ea93d317aba"
 PlutoUI = "7f904dfe-b85e-4ff6-b463-dae2292396a8"
-SoleDecisionTreeInterface = "de8eae22-3630-40e0-868c-abfc4c1bb3da"
 Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
 
 [targets]
-test = ["Test", "Markdown", "InteractiveUtils", "PlutoUI", "MultiData", "MLJ", "MLJDecisionTreeInterface", "SoleDecisionTreeInterface"]
+test = ["Test", "Markdown", "InteractiveUtils", "PlutoUI", "MultiData"]

README.md

@@ -85,7 +85,7 @@ end
 
 Then, port it to Sole and play with it:
 ```julia
-Pkg.add("SoleDecisionTreeInterface"); using SoleDecisionTreeInterface
+Pkg.add("DecisionTree"); import DecisionTree as DT
 
 # Convert to 🌞-compliant model
 🌲 = solemodel(🌱);

ext/DecisionTreeExt.jl

@@ -0,0 +1,81 @@
+module DecisionTreeExt
+
+using SoleModels
+
+import DecisionTree as DT
+
+function SoleModels.solemodel(model::DT.Ensemble, args...; kwargs...)
+    return SoleModels.DecisionForest(map(t -> SoleModels.DecisionTree(SoleModels.solemodel(t, args...; kwargs...)), model.trees))
+end
+
+function SoleModels.solemodel(tree::DT.InfoNode, keep_condensed = false; use_featurenames = true, kwargs...)
+    # @show fieldnames(typeof(tree))
+    use_featurenames = use_featurenames ? tree.info.featurenames : false
+    root, info = begin
+        if keep_condensed
+            root = SoleModels.solemodel(tree.node; use_featurenames = use_featurenames, kwargs...)
+            info = (;
+                apply_preprocess=(y -> UInt32(findfirst(x -> x == y, tree.info.classlabels))),
+                apply_postprocess=(y -> tree.info.classlabels[y]),
+            )
+            root, info
+        else
+            root = SoleModels.solemodel(tree.node; replace_classlabels = tree.info.classlabels, use_featurenames = use_featurenames, kwargs...)
+            info = (;)
+            root, info
+        end
+    end
+
+    info = merge(info, (;
+            featurenames=tree.info.featurenames,
+            # 
+            supporting_predictions=root.info[:supporting_predictions],
+            supporting_labels=root.info[:supporting_labels],
+        )
+    )
+    return DecisionTree(root, info)
+end
+
+# function SoleModels.solemodel(tree::DT.Root)
+#     root = SoleModels.solemodel(tree.node)
+#     # @show fieldnames(typeof(tree))
+#     info = (;
+#         n_feat = tree.n_feat,
+#         featim = tree.featim,
+#         supporting_predictions = root.info[:supporting_predictions],
+#         supporting_labels = root.info[:supporting_labels],
+#     )
+#     return DecisionTree(root, info)
+# end
+
+function SoleModels.solemodel(tree::DT.Node; replace_classlabels = nothing, use_featurenames = false)
+    test_operator = (<)
+    # @show fieldnames(typeof(tree))
+    feature = (use_featurenames != false) ? VariableValue(use_featurenames[tree.featid]) : VariableValue(tree.featid)
+    cond = ScalarCondition(feature, test_operator, tree.featval)
+    antecedent = Atom(cond)
+    lefttree = SoleModels.solemodel(tree.left; replace_classlabels = replace_classlabels, use_featurenames = use_featurenames)
+    righttree = SoleModels.solemodel(tree.right; replace_classlabels = replace_classlabels, use_featurenames = use_featurenames)
+    info = (;
+        supporting_predictions = [lefttree.info[:supporting_predictions]..., righttree.info[:supporting_predictions]...],
+        supporting_labels = [lefttree.info[:supporting_labels]..., righttree.info[:supporting_labels]...],
+    )
+    return Branch(antecedent, lefttree, righttree, info)
+end
+
+function SoleModels.solemodel(tree::DT.Leaf; replace_classlabels = nothing, use_featurenames = false)
+    # @show fieldnames(typeof(tree))
+    prediction = tree.majority
+    labels = tree.values
+    if !isnothing(replace_classlabels)
+        prediction = replace_classlabels[prediction]
+        labels = replace_classlabels[labels]
+    end
+    info = (;
+        supporting_predictions = fill(prediction, length(labels)),
+        supporting_labels = labels,
+    )
+    return SoleModels.ConstantModel(prediction, info)
+end
+
+end

ext/MLJDecisionTreeInterfaceExt.jl

@@ -0,0 +1,5 @@
+module MLJDecisionTreeInterfaceExt
+
+using SoleModels, MLJDecisionTreeInterface
+
+end

ext/MLJExt.jl

@@ -0,0 +1,5 @@
+module MLJExt
+
+using SoleModels, MLJ
+
+end

ext/MLJModelInterfaceExt.jl

@@ -0,0 +1,5 @@
+module MLJModelInterfaceExt
+
+using SoleModels, MLJModelInterface
+
+end

test/DecisionTreeExt/forest.jl

@@ -0,0 +1,56 @@
+using Test
+
+using MLJ
+using MLJBase
+using DataFrames
+
+using MLJDecisionTreeInterface
+using BenchmarkTools
+using Sole
+
+import DecisionTree as DT
+
+X, y = @load_iris
+X = DataFrame(X)
+
+train_ratio = 0.8
+
+train, test = partition(eachindex(y), train_ratio, shuffle=true)
+X_train, y_train = X[train, :], y[train]
+X_test, y_test = X[test, :], y[test]
+
+println("Training set size: ", size(X_train), " - ", size(y_train))
+println("Test set size: ", size(X_test), " - ", size(y_test))
+println("Training set type: ", typeof(X_train), " - ", typeof(y_train))
+println("Test set type: ", typeof(X_test), " - ", typeof(y_test))
+
+Forest = MLJ.@load RandomForestClassifier pkg=DecisionTree
+
+model = Forest(
+  max_depth=3,
+  min_samples_leaf=1,
+  min_samples_split=2,
+  n_trees = 10,
+)
+
+# Bind the model and data into a machine
+mach = machine(model, X_train, y_train)
+# Fit the model
+fit!(mach)
+
+
+sole_forest = solemodel(fitted_params(mach).forest)
+
+@test SoleData.scalarlogiset(X_test; allow_propositional = true) isa PropositionalLogiset
+
+# Make test instances flow into the model
+apply!(sole_forest, X_test, y_test)
+
+# apply!(sole_forest, X_test, y_test, mode = :append)
+
+sole_forest = @test_nowarn @btime solemodel(fitted_params(mach).forest, true)
+sole_forest = @test_nowarn @btime solemodel(fitted_params(mach).forest, false)
+
+printmodel(sole_forest; max_depth = 7, show_intermediate_finals = true, show_metrics = true)
+
+printmodel.(listrules(sole_forest, min_lift = 1.0, min_ninstances = 0); show_metrics = true);

test/DecisionTreeExt/tree.jl

@@ -0,0 +1,69 @@
+using Test
+
+using MLJ
+using MLJBase
+using DataFrames
+
+using MLJDecisionTreeInterface
+using BenchmarkTools
+using Sole
+
+import DecisionTree as DT
+
+X, y = @load_iris
+X = DataFrame(X)
+
+train_ratio = 0.8
+
+train, test = partition(eachindex(y), train_ratio, shuffle=true)
+X_train, y_train = X[train, :], y[train]
+X_test, y_test = X[test, :], y[test]
+
+println("Training set size: ", size(X_train), " - ", size(y_train))
+println("Test set size: ", size(X_test), " - ", size(y_test))
+println("Training set type: ", typeof(X_train), " - ", typeof(y_train))
+println("Test set type: ", typeof(X_test), " - ", typeof(y_test))
+
+Tree = MLJ.@load DecisionTreeClassifier pkg=DecisionTree
+
+model = Tree(
+  max_depth=-1,
+  min_samples_leaf=1,
+  min_samples_split=2,
+)
+
+# Bind the model and data into a machine
+mach = machine(model, X_train, y_train)
+# Fit the model
+fit!(mach)
+
+
+sole_dt = solemodel(fitted_params(mach).tree)
+
+@test SoleData.scalarlogiset(X_test; allow_propositional = true) isa PropositionalLogiset
+
+# Make test instances flow into the model
+apply!(sole_dt, X_test, y_test)
+
+# apply!(sole_dt, X_test, y_test, mode = :append)
+
+sole_dt = @test_nowarn @btime solemodel(fitted_params(mach).tree, true)
+sole_dt = @test_nowarn @btime solemodel(fitted_params(mach).tree, false)
+
+printmodel(sole_dt; max_depth = 7, show_intermediate_finals = true, show_metrics = true)
+
+printmodel.(listrules(sole_dt, min_lift = 1.0, min_ninstances = 0); show_metrics = true);
+
+printmodel.(listrules(sole_dt, min_lift = 1.0, min_ninstances = 0); show_metrics = true, show_subtree_metrics = true);
+
+printmodel.(listrules(sole_dt, min_lift = 1.0, min_ninstances = 0); show_metrics = true, show_subtree_metrics= true, tree_mode=true);
+
+readmetrics.(listrules(sole_dt; min_lift=1.0, min_ninstances = 0))
+
+printmodel.(listrules(sole_dt, min_lift = 1.0, min_ninstances = 0); show_metrics = true);
+
+interesting_rules = listrules(sole_dt; min_lift=1.0, min_ninstances = 0, custom_thresholding_callback = (ms)->ms.coverage*ms.ninstances >= 4)
+# printmodel.(sort(interesting_rules, by = readmetrics); show_metrics = (; round_digits = nothing, ));
+printmodel.(sort(interesting_rules, by = readmetrics); show_metrics = (; round_digits = nothing, additional_metrics = (; length = r->natoms(antecedent(r)))));
+
+@test_broken joinrules(interesting_rules) == "Check this result."

test/juliacon2024.jl

@@ -34,7 +34,7 @@ end
 🌱 = fitted_params(mach).tree
 
 # Convert to 🌞-compliant model
-using SoleDecisionTreeInterface
+import DecisionTree as DT
 🌲 = solemodel(🌱);
 
 # Print model

test/runtests.jl

@@ -21,6 +21,7 @@ test_suites = [
     ("Rules", ["juliacon2024.jl", ]),
     ("Linear forms", ["linear-form-utilities.jl", ]),
     ("Pluto Demo", ["$(dirname(dirname(pathof(SoleModels))))/pluto-demo.jl", ]),
+    ("DecisionTreeExt", ["DecisionTreeExt/tree.jl"]) #, "DecisionTreeExt/forest.jl"])
 ]
 
 @testset "SoleModels.jl" begin