Merge pull request #40 from Evovest/dev

Dev

Manifest.toml

@@ -44,11 +44,6 @@ git-tree-sha1 = "b7720de347734f4716d1815b00ce5664ed6bbfd4"
 uuid = "864edb3b-99cc-5e75-8d2d-829cb0a9cfe8"
 version = "0.17.9"
 
-[[DataValueInterfaces]]
-git-tree-sha1 = "bfc1187b79289637fa0ef6d4436ebdfe6905cbd6"
-uuid = "e2d170a0-9d28-54be-80f0-106bbe20a464"
-version = "1.0.0"
-
 [[Dates]]
 deps = ["Printf"]
 uuid = "ade2ca70-3891-5945-98fb-dc099432e06a"
@@ -81,11 +76,6 @@ uuid = "9fa8497b-333b-5362-9e8d-4d0656e87820"
 deps = ["Markdown"]
 uuid = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
 
-[[IteratorInterfaceExtensions]]
-git-tree-sha1 = "a3f24677c21f5bbe9d2a714f95dcd58337fb2856"
-uuid = "82899510-4779-5014-852e-03e436cf321d"
-version = "1.0.0"
-
 [[JSON]]
 deps = ["Dates", "Mmap", "Parsers", "Unicode"]
 git-tree-sha1 = "b34d7cef7b337321e97d22242c3c2b91f476748e"
@@ -248,18 +238,6 @@ version = "0.9.4"
 deps = ["Libdl", "LinearAlgebra", "Serialization", "SparseArrays"]
 uuid = "4607b0f0-06f3-5cda-b6b1-a6196a1729e9"
 
-[[TableTraits]]
-deps = ["IteratorInterfaceExtensions"]
-git-tree-sha1 = "b1ad568ba658d8cbb3b892ed5380a6f3e781a81e"
-uuid = "3783bdb8-4a98-5b6b-af9a-565f29a5fe9c"
-version = "1.0.0"
-
-[[Tables]]
-deps = ["DataAPI", "DataValueInterfaces", "IteratorInterfaceExtensions", "LinearAlgebra", "TableTraits", "Test"]
-git-tree-sha1 = "aaed7b3b00248ff6a794375ad6adf30f30ca5591"
-uuid = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
-version = "0.2.11"
-
 [[Test]]
 deps = ["Distributed", "InteractiveUtils", "Logging", "Random"]
 uuid = "8dfed614-e22c-5e08-85e1-65c5234f0b40"

Project.toml

@@ -8,21 +8,16 @@ CategoricalArrays = "324d7699-5711-5eae-9e2f-1d82baa6b597"
 Distributions = "31c24e10-a181-5473-b8eb-7969acd0382f"
 MLJModelInterface = "e80e1ace-859a-464e-9ed9-23947d8ae3ea"
 Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
-SortingAlgorithms = "a2af1166-a08f-5f64-846c-94a0d3cef48c"
 StaticArrays = "90137ffa-7385-5640-81b9-e52037218182"
 Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 StatsBase = "2913bbd2-ae8a-5f71-8c99-4fb6c76f3a91"
-Tables = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
-Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
 
 [compat]
 CategoricalArrays = "0.7"
-Distributions = "0.21, 0.22"
+Distributions = "0.22"
 MLJModelInterface = "0.1"
-SortingAlgorithms = "0.3"
 StaticArrays = "0.12"
 StatsBase = "0.32"
-Tables = "0.2"
 julia = "1"
 
 [extras]

src/EvoTrees.jl

@@ -11,8 +11,9 @@ using Random: seed!
 using StaticArrays
 using Distributions
 using CategoricalArrays
-import MLJModelInterface: predict
 import MLJModelInterface
+import MLJModelInterface: fit, update
+import MLJModelInterface: predict
 
 include("models.jl")
 include("structs.jl")

test/MLJ.jl

@@ -21,19 +21,19 @@ tree_model = EvoTreeRegressor(loss=:logistic, max_depth=5, η=0.05, nrounds=10)
 # quantile regression
 tree_model = EvoTreeRegressor(loss=:quantile, α=0.75, max_depth=5, η=0.05, nrounds=10)
 
-tree = machine(tree_model, X, y)
+mach = machine(tree_model, X, y)
 train, test = partition(eachindex(y), 0.7, shuffle=true); # 70:30 split
-fit!(tree, rows=train, verbosity=1)
+fit!(mach, rows=train, verbosity=1)
 
-tree.model.nrounds += 10
-fit!(tree, rows=train, verbosity=1)
+mach.model.nrounds += 10
+fit!(mach, rows=train, verbosity=1)
 
 # predict on train data
-pred_train = predict(tree, selectrows(X,train))
+pred_train = predict(mach, selectrows(X,train))
 mean(abs.(pred_train - selectrows(Y,train)))
 
 # predict on test data
-pred_test = predict(tree, selectrows(X,test))
+pred_test = predict(mach, selectrows(X,test))
 mean(abs.(pred_test - selectrows(Y,test)))
 
 
@@ -46,23 +46,23 @@ X, y = @load_crabs
 tree_model = EvoTreeClassifier(max_depth=4, η=0.05, λ=0.0, γ=0.0, nrounds=10)
 
 # @load EvoTreeRegressor
-tree = machine(tree_model, X, y)
+mach = machine(tree_model, X, y)
 train, test = partition(eachindex(y), 0.7, shuffle=true); # 70:30 split
-fit!(tree, rows=train, verbosity=1)
+fit!(mach, rows=train, verbosity=1)
 
-tree.model.nrounds += 10
-fit!(tree, rows=train, verbosity=1)
+mach.model.nrounds += 10
+fit!(mach, rows=train, verbosity=1)
 
-pred_train = predict(tree, selectrows(X,train))
-pred_train_mode = predict_mode(tree, selectrows(X,train))
+pred_train = predict(mach, selectrows(X,train))
+pred_train_mode = predict_mode(mach, selectrows(X,train))
 cross_entropy(pred_train, selectrows(y, train)) |> mean
 sum(pred_train_mode .== y[train])
 
-pred_test = predict(tree, selectrows(X,test))
-pred_test_mode = predict_mode(tree, selectrows(X,test))
+pred_test = predict(mach, selectrows(X,test))
+pred_test_mode = predict_mode(mach, selectrows(X,test))
 cross_entropy(pred_test, selectrows(y, test)) |> mean
 sum(pred_test_mode .== y[test])
-pred_test_mode = predict_mode(tree, selectrows(X,test))
+pred_test_mode = predict_mode(mach, selectrows(X,test))
 
 ##################################################
 ### count
@@ -94,19 +94,20 @@ X = MLJBase.table(X)
 X_matrix = MLJBase.matrix(X)
 
 # typeof(X)
-tree = machine(tree_model, X, Y)
+mach = machine(tree_model, X, Y)
 train, test = partition(eachindex(Y), 0.8, shuffle=true); # 70:30 split
-fit!(tree, rows=train, verbosity=1, force=true)
+fit!(mach, rows=train, verbosity=1, force=true)
 
-tree.model.nrounds += 10
-MLJBase.update(tree.model, 0, tree.fitresult, tree.cache, X, Y)
+mach.model.nrounds += 10
+MLJBase.update(mach.model, 0, mach.fitresult, mach.cache, X, Y)
 
-tree.model.nrounds += 10
-fit!(tree, rows=train, verbosity=1)
+mach.model.nrounds += 10
+fit!(mach, rows=train, verbosity=1)
 
-pred = predict(tree, selectrows(X,train))
-pred_mean = predict_mean(tree, selectrows(X,train))
-pred_mode = predict_mode(tree, selectrows(X,train))
+pred = predict(mach, selectrows(X,train))
+pred_mean = predict_mean(mach, selectrows(X,train))
+pred_mode = predict_mode(mach, selectrows(X,train))
+# pred_mode = predict_median(mach, selectrows(X,train))
 
 ##################################################
 ### Gaussian - Larger data
@@ -137,19 +138,17 @@ X = MLJBase.table(X)
 X_matrix = MLJBase.matrix(X)
 
 # typeof(X)
-tree = machine(tree_model, X, Y)
+mach = machine(tree_model, X, Y)
 train, test = partition(eachindex(Y), 0.8, shuffle=true); # 70:30 split
-fit!(tree, rows=train, verbosity=1, force=true)
+fit!(mach, rows=train, verbosity=1, force=true)
 
-tree.model.nrounds += 10
-MLJBase.update(tree.model, 0, tree.fitresult, tree.cache, X, Y)
+mach.model.nrounds += 10
+fit!(mach, rows=train, verbosity=1)
 
-tree.model.nrounds += 10
-fit!(tree, rows=train, verbosity=1)
-
-pred = predict(tree, selectrows(X,train))
-pred_mean = predict_mean(tree, selectrows(X,train))
-pred_mode = predict_mode(tree, selectrows(X,train))
+pred = predict(mach, selectrows(X,train))
+pred_mean = predict_mean(mach, selectrows(X,train))
+pred_mode = predict_mode(mach, selectrows(X,train))
+# pred_mode = predict_median(mach, selectrows(X,train))
 mean(abs.(pred_mean - selectrows(Y,train)))
 
 q_20 = quantile.(pred, 0.20)

test/core.jl

@@ -1,3 +1,4 @@
+using Statistics
 using StatsBase: sample
 using EvoTrees: sigmoid, logit