RF: Simplify variable loading and resampling

[adelavega]

Attempt to simplify fitting encoding/decoding models. Since the himalaya API is similar to sklearn, I focused on making loading data from Neuroscout API easier.

• I implemented a helper function in pyNS, to help fetch predictors from the Neuroscout API and resample them to TR. ENH: Add high-level predictor fetching utilities neuroscout/pyNS#112
  The main advantage is that pybids already implements densification/resampling logic, and variable alignment. In addition, users could use pybids Transformations on these variables. The downside is the pybids dependency, but it's optional to use this helper.

• Another nice thing is that this returns a df that also includes indexing info (i.e. subject, run, etc...) which can then be used by whichever downstream CV scheme, etc...

I think my plan with this will be to add this as a pyNS tutorial, but not upstream anything related to himayala/sklearn. Those APIs are already good, so I think as long as we provide the data easily from Neuroscout (both events and preprocessed data), and show a good example, that should be good enough.

Perhaps in the future, I will also work on a full workflow like FitLins (or directly in it!) for encoding/decoding w/ BIDS StatsModels.

[adelavega]

I would recommend merging as is, but I'll take this example and develop three things:

1. Simple data load example
2. regularized banded cv regression example
3. (in the future) specification + reproducible workflow w/ himayala

1-2 will live in neuroscout-docs