regression

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)))

Currently, when data::Split is called on a dataset in which data and labels have different sizes, then the result is undefined. Sometimes, it splits while sometimes it gives segmentation fault while sometimes it throws an out of bound error. Ideally, it should always throw an exception clearly saying that the sizes do not match.

I encountered this while writing a test where I accidentally for

What's wrong?

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

Is your feature request related to a problem? Please describe.
While sales forecasting, it is necessary that the model is given the input about the promotions, special events that are taken care of in the prophet model as the holiday effect. Does orbit support this feature?