Hi I would like to propose a better implementation for 'test_indices':

We can remove the unneeded np.array casting:

Cleaner/New:
test_indices = list(set(range(len(texts))) - set(train_indices))

Old:
test_indices = np.array(list(set(range(len(texts))) - set(train_indices)))

What is the desired addition or change?

It would be nice to have some time series methods. Like

1. naive
2. seasonal naive
3. seasonal trend loess decomposition.
4. Holt Winters
5. Exponential smoothing
6. Arima

Since many time series come in groups it may be useful to think about how the data should be organized to take in many time series and account for seasonality. Also prob

• What's wrong?

String representations of dataset objects are used for previewing their contents from the terminal. When converting a Dataset object to a string, we build a table using ascii characters. The current table has fixed width columns that do not take full advantage of the terminal real estate if the dataset only contains a few columns.

echo $dataset;

<img width="574" alt="Annotation

The PR JuliaData/CategoricalArrays.jl#310 means that an array with elements of type Symbol can no longer be wrapped as a CategoricalArray.

This means all MLJ documentation and test code that uses symbols in categorical data must be refactored to use strings instead.

These repos, at least, need checking/refactoring, in order of priority:

• MLJ

• [ ]

Hi @JavierAntoran @stratisMarkou,

First of all, thanks for making all of this code available - it's been great to look through!

Im currently spending some time trying to work through the Weight Uncertainty in Neural Networks in order to implement Bayes-by-Backprop. I was struggling to understand the difference between your implementation of `Bayes-by-Bac