[FEAT] Sliding predictions for an arbitrary DF

[howarth]

I want to be able to run something similar to predict_insample but with an arbitrary df instead of the training data. I didn't see anywhere else where I could run sliding window predictions. I moved the bulk of predict_insample to _predict_sliding and then I have predict_insample call _predict_sliding. Similarly, predict_sliding(df, ..) calls _predict_sliding

This is not complete, I don't think it will work with exogenous variables, and it definitely will not work with static variables. I will figure that out. I wanted to first get feedback on if anything I'm doing here is incorrect.

I think this is the type of predictions we will want to do for many of the medical projects at Auton

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.

---

Dan Howarth seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[CLAassistant]

Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.

---

Dan Howarth seems not to be a GitHub user. You need a GitHub account to be able to sign the CLA. If you have already a GitHub account, please add the email address used for this commit to your account.
_{You have signed the CLA already but the status is still pending? Let us recheck it.}

[elephaint]

Thanks for submitting a PR!

What is the use case for this?

[marcopeix]

Reopening. I think we get the point of this, but we need to think about the best way of doing it.