Merge pull request #135 from FluxML/type-piracy

Remove optimiser type piracy. Make `optimiser` and `builder` "deep" hyper-parmaters

.github/workflows/ci.yml

@@ -17,8 +17,6 @@ jobs:
       fail-fast: false
       matrix:
         version:
-          - '1.3'
-          - '1.4'
           - '1'
           - 'nightly'
         os:

Project.toml

@@ -1,7 +1,7 @@
 name = "MLJFlux"
 uuid = "094fc8d1-fd35-5302-93ea-dabda2abf845"
 authors = ["Anthony D. Blaom <[email protected]>", "Ayush Shridhar <[email protected]>"]
-version = "0.1.11"
+version = "0.1.12"
 
 [deps]
 CategoricalArrays = "324d7699-5711-5eae-9e2f-1d82baa6b597"
@@ -15,15 +15,15 @@ Statistics = "10745b16-79ce-11e8-11f9-7d13ad32a3b2"
 Tables = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
 
 [compat]
-CategoricalArrays = "^0.10"
-ColorTypes = "^0.10.3, 0.11"
-ComputationalResources = "^0.3.2"
-Flux = "^0.10.4, ^0.11, 0.12"
-LossFunctions = "^0.5, ^0.6"
-MLJModelInterface = "^0.4.1, 1"
-ProgressMeter = "^1.1"
-Tables = "^1.0"
-julia = "^1.3"
+CategoricalArrays = "0.10"
+ColorTypes = "0.10.3, 0.11"
+ComputationalResources = "0.3.2"
+Flux = "0.10.4, 0.11, 0.12"
+LossFunctions = "0.5, 0.6"
+MLJModelInterface = "1.1"
+ProgressMeter = "1.1"
+Tables = "1.0"
+julia = "1.6"
 
 [extras]
 LinearAlgebra = "37e2e46d-f89d-539d-b4ee-838fcccc9c8e"

examples/iris/iris.jl

@@ -4,6 +4,8 @@ using Pkg
 Pkg.activate(@__DIR__)
 Pkg.instantiate()
 
+# **Julia version** is assumed to be 1.6.*
+
 using MLJ
 using Flux
 import RDatasets
@@ -75,5 +77,5 @@ plot(curve.parameter_values,
 savefig("iris_history.png")
 
 using Literate #src
-Literate.markdown(@__FILE__, @__DIR__, execute=true) #src
+Literate.markdown(@__FILE__, @__DIR__, execute=false) #src
 Literate.notebook(@__FILE__, @__DIR__, execute=true) #src

examples/iris/iris.md

@@ -1,14 +1,18 @@
 ```@meta
-EditURL = "<unknown>/iris.jl"
+EditURL = "<unknown>/../../MLJFlux/examples/iris/iris.jl"
 ```
 
 # Using MLJ with Flux to train the iris dataset
 
-```julia
+```@example iris
 using Pkg
 Pkg.activate(@__DIR__)
 Pkg.instantiate()
+```
+
+**Julia version** is assumed to be 1.6.*
 
+```@example iris
 using MLJ
 using Flux
 import RDatasets
@@ -23,11 +27,6 @@ pyplot(size=(600, 300*(sqrt(5)-1)));
 nothing #hide
 ```
 
-```
- Activating environment at `~/Dropbox/Julia7/MLJ/MLJFlux/examples/iris/Project.toml`
-
-```
-
 Following is a very basic introductory example, using a default
 builder and no standardization of input features.
 
@@ -36,91 +35,46 @@ example](https://github.com/FluxML/MLJFlux.jl/blob/dev/examples/mnist).
 
 ## Loading some data and instantiating a model
 
-```julia
+```@example iris
 iris = RDatasets.dataset("datasets", "iris");
 y, X = unpack(iris, ==(:Species), colname -> true, rng=123);
 NeuralNetworkClassifier = @load NeuralNetworkClassifier
 clf = NeuralNetworkClassifier()
 ```
 
-```
-NeuralNetworkClassifier(
-    builder = Short(
-            n_hidden = 0,
-            dropout = 0.5,
-            σ = NNlib.σ),
-    finaliser = NNlib.softmax,
-    optimiser = ADAM(0.001, (0.9, 0.999), IdDict{Any,Any}()),
-    loss = Flux.Losses.crossentropy,
-    epochs = 10,
-    batch_size = 1,
-    lambda = 0.0,
-    alpha = 0.0,
-    optimiser_changes_trigger_retraining = false,
-    acceleration = CPU1{Nothing}(nothing)) @252
-```
-
 ## Incremental training
 
-```julia
+```@example iris
 import Random.seed!; seed!(123)
 mach = machine(clf, X, y)
 fit!(mach)
 
 training_loss = cross_entropy(predict(mach, X), y) |> mean
 ```
 
-```
-0.8993467f0
-```
-
 Increasing learning rate and adding iterations:
 
-```julia
+```@example iris
 clf.optimiser.eta = clf.optimiser.eta * 2
 clf.epochs = clf.epochs + 5
 
 fit!(mach, verbosity=2);
 nothing #hide
 ```
 
-```
-┌ Info: Updating Machine{NeuralNetworkClassifier{Short,…},…} @545.
-└ @ MLJBase /Users/anthony/.julia/packages/MLJBase/4DmTL/src/machines.jl:342
-┌ Info: Loss is 0.853
-└ @ MLJFlux /Users/anthony/.julia/packages/MLJFlux/wj7HX/src/core.jl:122
-┌ Info: Loss is 0.8207
-└ @ MLJFlux /Users/anthony/.julia/packages/MLJFlux/wj7HX/src/core.jl:122
-┌ Info: Loss is 0.8072
-└ @ MLJFlux /Users/anthony/.julia/packages/MLJFlux/wj7HX/src/core.jl:122
-┌ Info: Loss is 0.752
-└ @ MLJFlux /Users/anthony/.julia/packages/MLJFlux/wj7HX/src/core.jl:122
-┌ Info: Loss is 0.7077
-└ @ MLJFlux /Users/anthony/.julia/packages/MLJFlux/wj7HX/src/core.jl:122
-
-```
-
-```julia
+```@example iris
 training_loss = cross_entropy(predict(mach, X), y) |> mean
 ```
 
-```
-0.7076617f0
-```
-
 ## Accessing the Flux chain (model)
 
-```julia
+```@example iris
 chain = fitted_params(mach).chain
 ```
 
-```
-Chain(Chain(Dense(4, 3, σ), Dropout(0.5), Dense(3, 3)), softmax)
-```
-
 ##  Evolution of out-of-sample performance
 
-```julia
+```@example iris
 r = range(clf, :epochs, lower=1, upper=200, scale=:log10)
 curve = learning_curve(clf, X, y,
                        range=r,
@@ -133,9 +87,8 @@ plot(curve.parameter_values,
        xscale=curve.parameter_scale,
        ylab = "Cross Entropy")
 ```
-![](3397330029.png)
 
-```julia
+```@example iris
 savefig("iris_history.png")
 ```