Add Target Scaling

[glevv]

I think it will have huge impact on results and on model training. I think pymc-marketing does it too.

Right now you can do standardize(y) in formula, but it does not support inverse transformations, which is inconvenient for result analysis and plotting.

[drbenvincent]

Hi @glevv. Sorry for the delayed response. I think this is a good idea. I assume you're after some kind of kwarg which automatically does this behind the scenes and uses something like https://scikit-learn.org/stable/modules/generated/sklearn.preprocessing.StandardScaler.html#sklearn.preprocessing.StandardScaler ?

Is this something you'd like to take a stab at? Either way, marking this as a feature request