import MLJ:fit!,predict
using CSV,DataFrames,GLMakie,Random
using MLJ
Random.seed!(34343)TaskLocalRNG()3-recognizing-handwriting-digits
info
- ref:scikit-learn-docs/auto_examples/classification/plot_digits_classification.html#sphx-glr-auto-examples-classification-plot-digits-classification-py
- data-processing:load-scikit-digits.jl ->csv
1. load package
2. load data
load_csv(str::AbstractString) =
str |> d -> CSV.File("./data/$str.csv") |> DataFrame |> dropmissing
digits = load_csv("scikit_digits")
digits = coerce(digits, :target => Multiclass)
y, X = unpack(digits, ==(:target); rng = 123);
(Xtrain, Xtest), (ytrain, ytest) = partition((X, y), 0.6, multi=true, rng=123)((1078×64 DataFrame Row │ x1 x2 x3 x4 x5 x6 x7 x8 ⋯ │ Float64 Float64 Float64 Float64 Float64 Float64 Float64 Float64 ⋯ ──────┼───────────────────────────────────────────────────────────────────────── 1 │ 0.0 0.0 10.0 15.0 1.0 0.0 0.0 0.0 ⋯ 2 │ 0.0 0.0 4.0 12.0 16.0 14.0 7.0 0.0 3 │ 0.0 0.0 2.0 10.0 15.0 1.0 0.0 0.0 4 │ 0.0 0.0 11.0 16.0 16.0 12.0 0.0 0.0 5 │ 0.0 0.0 5.0 15.0 12.0 4.0 0.0 0.0 ⋯ 6 │ 0.0 1.0 11.0 15.0 16.0 9.0 0.0 0.0 7 │ 0.0 1.0 10.0 15.0 15.0 3.0 0.0 0.0 8 │ 0.0 0.0 8.0 14.0 1.0 0.0 0.0 0.0 9 │ 0.0 3.0 15.0 16.0 14.0 1.0 0.0 0.0 ⋯ 10 │ 0.0 0.0 2.0 12.0 14.0 4.0 0.0 0.0 11 │ 0.0 0.0 3.0 14.0 9.0 3.0 0.0 0.0 ⋮ │ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋱ 1069 │ 0.0 0.0 7.0 16.0 15.0 4.0 0.0 0.0 1070 │ 0.0 0.0 0.0 9.0 16.0 9.0 0.0 0.0 ⋯ 1071 │ 0.0 0.0 0.0 3.0 16.0 3.0 0.0 0.0 1072 │ 0.0 0.0 5.0 8.0 11.0 5.0 0.0 0.0 1073 │ 0.0 2.0 9.0 15.0 14.0 9.0 3.0 0.0 1074 │ 0.0 1.0 12.0 16.0 13.0 7.0 0.0 0.0 ⋯ 1075 │ 0.0 0.0 0.0 2.0 16.0 3.0 0.0 0.0 1076 │ 0.0 0.0 14.0 16.0 15.0 3.0 0.0 0.0 1077 │ 0.0 0.0 2.0 11.0 15.0 2.0 0.0 0.0 1078 │ 0.0 0.0 0.0 4.0 15.0 6.0 0.0 0.0 ⋯ 56 columns and 1057 rows omitted, 719×64 DataFrame Row │ x1 x2 x3 x4 x5 x6 x7 x8 ⋯ │ Float64 Float64 Float64 Float64 Float64 Float64 Float64 Float64 ⋯ ─────┼────────────────────────────────────────────────────────────────────────── 1 │ 0.0 0.0 3.0 12.0 3.0 0.0 0.0 0.0 ⋯ 2 │ 0.0 0.0 1.0 12.0 14.0 3.0 0.0 0.0 3 │ 0.0 0.0 8.0 13.0 11.0 1.0 0.0 0.0 4 │ 0.0 0.0 2.0 13.0 0.0 0.0 0.0 0.0 5 │ 0.0 1.0 13.0 16.0 16.0 12.0 1.0 0.0 ⋯ 6 │ 0.0 0.0 7.0 16.0 13.0 2.0 0.0 0.0 7 │ 0.0 0.0 11.0 16.0 9.0 8.0 0.0 0.0 8 │ 0.0 0.0 0.0 1.0 9.0 14.0 7.0 0.0 9 │ 0.0 0.0 7.0 15.0 16.0 16.0 1.0 0.0 ⋯ 10 │ 0.0 0.0 5.0 10.0 14.0 16.0 11.0 0.0 11 │ 0.0 0.0 7.0 16.0 16.0 16.0 6.0 0.0 ⋮ │ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋮ ⋱ 710 │ 0.0 1.0 9.0 16.0 16.0 15.0 3.0 0.0 711 │ 0.0 0.0 1.0 15.0 7.0 0.0 0.0 0.0 ⋯ 712 │ 0.0 0.0 6.0 14.0 13.0 4.0 0.0 0.0 713 │ 0.0 0.0 2.0 13.0 14.0 6.0 0.0 0.0 714 │ 0.0 0.0 2.0 12.0 10.0 0.0 0.0 0.0 715 │ 0.0 0.0 2.0 14.0 15.0 4.0 0.0 0.0 ⋯ 716 │ 0.0 0.0 3.0 10.0 14.0 3.0 0.0 0.0 717 │ 0.0 0.0 7.0 16.0 15.0 4.0 0.0 0.0 718 │ 0.0 0.0 6.0 15.0 14.0 2.0 0.0 0.0 719 │ 0.0 0.0 5.0 16.0 12.0 2.0 0.0 0.0 ⋯ 56 columns and 698 rows omitted), (CategoricalArrays.CategoricalValue{Int64, UInt32}[1, 3, 0, 9, 0, 3, 9, 1, 2, 0 … 5, 8, 4, 0, 3, 3, 4, 3, 0, 4], CategoricalArrays.CategoricalValue{Int64, UInt32}[6, 0, 3, 6, 3, 2, 8, 9, 5, 5 … 5, 4, 8, 8, 2, 1, 9, 0, 3, 0]))
3. MLJ workflow
SVC = @load SVC pkg=LIBSVM
model=SVC()
mach = machine(model, Xtrain, ytrain)|>fit!
yhat = predict(mach, Xtest)
@info "accuracy"=>accuracy(ytest,yhat)[ Info: For silent loading, specify `verbosity=0`.
[ Info: Training machine(SVC(kernel = RadialBasis, …), …).
[ Info: "accuracy" => 0.9860917941585535import MLJLIBSVMInterface ✔4. plot results
makie plot image
- reshape to image matrix
img=Xtest[pick,:]|>Vector|>d->reshape(d,8,8) - sometimes need rotl
load(patharr[num])|>rotl90 - sometimes need reverse y axis
local ax = Axis(fig[i, j],yreversed=true)
function plot_res()
fig=Figure()
#rand pick 15 origin picture of digits
picks=rand(1:length(Vector(ytest)),15)
for (idx,pick) in enumerate(picks)
ax=Axis(fig[fldmod1(idx,5)...];title="pred:$(yhat[pick])",yreversed=true)
img=Xtest[pick,:]|>Vector|>d->reshape(d,8,8)
image!(ax,img)
hidedecorations!(ax)
end
fig
end
fig=plot_res()