Extend StatsAPI.predict

[andreasnoack]

And require Julia 1.3 since that is the oldest version that we test with.

Fixes #57

[codecov-commenter]

Codecov Report

Patch coverage has no change and project coverage change: -0.53 ⚠️

Comparison is base (31d924a) 92.59% compared to head (cc215b6) 92.06%.

Additional details and impacted files

@@            Coverage Diff             @@
##           master      #62      +/-   ##
==========================================
- Coverage   92.59%   92.06%   -0.53%     
==========================================
  Files           2        2              
  Lines         189      189              
==========================================
- Hits          175      174       -1     
- Misses         14       15       +1     

Impacted Files	Coverage Δ
src/Loess.jl	87.37% <ø> (ø)

... and 1 file with indirect coverage changes

Help us with your feedback. Take ten seconds to tell us how you rate us. Have a feature suggestion? Share it here.

☔ View full report in Codecov by Sentry.
📢 Do you have feedback about the report comment? Let us know in this issue.

[bkamins]

By the way do you think we need to require?

predict(model::LoessModel{T}, zs::AbstractVector{T}) where T <: AbstractFloat

Maybe we could do instead?

predict(model::LoessModel{T}, zs::AbstractVector)  where T = predict(model, convert(AbstractVector{T}, zs)

Similar for other methods.

(no need to cover this in this PR)

[andreasnoack]

No I don't think that restriction is required. I'm working on a followup PR with some performance improvements and I'll include the suggested change in that PR.