Carlos Parada
Carlos Parada
Is there an easy way to plot density intervals when using `density`? If not, should one be added? Example: 
When `Zeros` or `Ones` gets an empty tuple as its only argument, perhaps we should return `zero` or `one`? This way functions that can be called on both arrays and...
``` julia> import Pkg; Pkg.precompile() Precompiling project... ✗ ProfileView 0 dependencies successfully precompiled in 7 seconds (168 already precompiled) ERROR: The following 1 direct dependency failed to precompile: ProfileView [c46f51b8-102a-5cf2-8d2c-8597cb0e0da7]...
ATM, the state dataset from Datasets is missing.
Maximizing the expected log posterior density (ELPD) is a common objective function in Bayesian inference and Bayesian neural networks, and I'd be interested in having it as a loss function...
Looking at the tutorials, the ordering looks a bit random. Perhaps we should reorder the tutorials, roughly in order from least to most advanced, to make it easier to understand...
Leaving this here for someone to do in the future if they want/can -- we should probably have a tutorial for ordered logistic regressions. They're probably the most criminally underused...
The big block of data-cleaning operations at the start of the tutorials kind of breaks up the flow, and IMO makes the tutorials seem more confusing. Maybe we should pre-clean...
Similarly to `lag`, it's very common to use differenced time series in analysis. Would a differencing function be a good addition to the package? Where I think it could be...
Mentioned [here](https://github.com/mcabbott/Tullio.jl/issues/125); should be a quick fix+would let AxisKeys be compatible with ArrayInterface.