Josh Day

Sounds like a good plan to me! FYI you may be able to get away with just OnlineStatsBase as a dependency.

I believe this existed in a very early version of OnlineStats, implemented by @tbreloff, but now it's gone for a reason I don't remember. So there's nothing built-in that does...

Some more ecdf fun: ```julia julia> ecdf([1,2,NaN])(Inf) 0.6666666666666666 ```

+1 from me for: - `ecdf(x)` throwing an error if `any(isnan, x)` - `ecdf(x)(Inf)` == 1 - `ecdf(x)(-Inf)` == 0 - `isnan(ecdf(x)(NaN))` I'll try to make a PR today.

Different issue here but along the same lines. How would folks expect `Inf` to work with `ecdf`? Current behavior (matches R) is: ```julia julia> ecdf([1,2,Inf])(Inf). # Works because Inf ==...

I think that adds confusion. I would like to import Logging into my package OnlineStats.jl, but I don't think I can add a dependency for which I have to warn...

`fit!`-ing is based on iteration: https://joshday.github.io/OnlineStats.jl/latest/howfitworks/ This is a good "OnlineStats 2.0" feature, but probably too much of a breaking change for now.

I think the solution is to change show methods that rely on `printstyled` to use [StyledStrings.jl](https://github.com/JuliaLang/StyledStrings.jl)

Actually this looks to be an upstream issue: https://github.com/ronisbr/PrettyTables.jl/issues/244. Closing here.

@ronisbr Thanks for the details! That helped connect some dots I was missing. Sorry for the noise.