[DOC] ESAD example from documentation failing

[leona]

Describe the bug

When running the ESADDetector example from the documentation here https://outlierdetectionjl.github.io/OutlierDetection.jl/dev/API/detectors/#esaddetector

Specifically

using OutlierDetection: ESADDetector, fit, score
detector = ESADDetector()
X = rand(10, 100)
y = rand([-1,1], 100)
model = fit(detector, X, y)
train_scores, test_scores = score(detector, model, X)

I receive multiple errors. First, that score does not exist in OutlierDetection, then verbosity is not set on fit. I can resolve those errors, but I'm unable to resolve this

ERROR: DomainError with Supervised detectors can only be fitted with array
inputs with one observation per last dimension, found X=Matrix{Float64}, y=Vector{Int64}:

Stacktrace:
 [1] fit(::DSADDetector, X::Matrix{Float64}, y::Vector{Int64}; verbosity::Int64)
   @ OutlierDetectionInterface ~/.julia/packages/OutlierDetectionInterface/8U8oT/src/base.jl:137
 [2] top-level scope
   @ REPL[34]:1
 [3] top-level scope
   @ ~/.julia/packages/CUDA/DfvRa/src/initialization.jl:52

Versions

[v0.3.2](https://github.com/OutlierDetectionJL/OutlierDetection.jl/releases/tag/v0.3.2)

[davnn]

Hey, it appears that you have discovered some (very) outdated docs. Have a look at the following code snippet

using OutlierDetection: fit, transform, to_categorical
using OutlierDetectionNetworks: AEDetector, ESADDetector
using OutlierDetectionNetworks.Templates: MLPAutoEncoder

n_samples, n_features = 100, 10
encoder, decoder = MLPAutoEncoder(n_features, 5, [50, 20]; bias=false);
detector = ESADDetector(encoder=encoder, decoder=decoder)
X = rand(n_features, n_samples)
y = to_categorical(rand(["normal", "outlier"], n_samples))
model, scores_train = fit(detector, X, y; verbosity=0)
scores_test = transform(detector, model, X)

Would be happy to accept a pull request fixing the docs.