Skip to content

Make the composition workflow notebook more robust #316

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
ablaom wants to merge 1 commit into
base: dev
Choose a base branch
from
Open

Make the composition workflow notebook more robust #316

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion docs/Project.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,8 +21,9 @@ ProgressMeter = "92933f4c-e287-5a05-a399-4b506db050ca"
RDatasets = "ce6b1742-4840-55fa-b093-852dadbb1d8b"
Random = "9a3f8284-a2c9-5f02-9a11-845980a1fd5c"
ScientificTypes = "321657f4-b219-11e9-178b-2701a2544e81"
StableRNGs = "860ef19b-820b-49d6-a774-d7a799459cd3"
Tables = "bd369af6-aec1-5ad0-b16a-f7cc5008161c"
WordTokenizers = "796a5d58-b03d-544a-977e-18100b691f6e"

[compat]
Documenter = "1"
Documenter = "1"
34 changes: 19 additions & 15 deletions docs/src/common_workflows/composition/notebook.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,27 +18,33 @@ learning model from MLJFlux.
````@example composition
using MLJ # Has MLJFlux models
using Flux # For more flexibility
import RDatasets # Dataset source
import Random # To create imbalance
import Imbalance # To solve the imbalance
import Optimisers # native Flux.jl optimisers no longer supported
using StableRNGs # for reproducability
using CategoricalArrays
````

### Loading and Splitting the Data

````@example composition
iris = RDatasets.dataset("datasets", "iris");
y, X = unpack(iris, ==(:Species), rng=123);
X = Float32.(X); # To be compatible with type of network network parameters
iris = load_iris() # a named-tuple of vectors
species, X = unpack(iris, ==(:target), rng=StableRNG(123))
X = Flux.fmap(column-> Float32.(column), X) # Flux prefers Float32 data
nothing #hide
````

To simulate an imbalanced dataset, we will take a random sample:
The iris dataset has a target with uniformly distributed values, `"versicolor"`,
`"setosa"`, and `"virginica"`. To manufacture an unbalanced dataset, we'll combine the
first two into a single classs, `"colosa"`:

````@example composition
Random.seed!(803429)
subset_indices = rand(1:size(X, 1), 100)
X, y = X[subset_indices, :], y[subset_indices]
y = coerce(
map(y) do species
species == "virginica" ? unwrap(species) : "colosa"
end,
Multiclass,
)
Imbalance.checkbalance(y)
````

Expand All @@ -61,7 +67,7 @@ clf = NeuralNetworkClassifier(
optimiser=Optimisers.Adam(0.01),
batch_size=8,
epochs=50,
rng=42,
rng=StableRNG(123),
)
````

Expand All @@ -83,20 +89,18 @@ pipeline = standarizer |> balanced_model

By this, any training data will be standardized then oversampled then passed to the
model. Meanwhile, for inference, the standardizer will automatically use the training
set's mean and std and the oversampler will be transparent.
set's mean and std and the oversampler will play no role.

### Training the Composed Model

It's indistinguishable from training a single model.
The pipeline model can be evaluated like any other model:

````@example composition
mach = machine(pipeline, X, y)
fit!(mach)
cv=CV(nfolds=5)
evaluate!(mach, resampling=cv, measure=accuracy)
cv=CV(nfolds=6)
evaluate!(mach, resampling=cv, measure=accuracy, verbosity=0)
````

---

*This page was generated using [Literate.jl](https://github.com/fredrikekre/Literate.jl).*

Loading