C19 Update with Error

It has been bugging me for a while that my curve fits do not have an associated uncertainty. I am using scipy.optimize.curve_fit and it had to be possible to get uncertainty out of it. As usual, the problem, Horatio, lies not in our software but ourselves. Of course the scipy crew put uncertainty in there. So with the help of some blog posts I figured it out.

This is the first set of plots with error estimates given on the cumulative fit and extrapolation plot (lower left in each). For example, the world fit today reads 'Fit max = 237773 +/- 2523' rather than just 'Fit max = 237773'. May seem a small change, but it is an important one. All future plots will include the estimated error.

Of course it would be nice to show the fit curve with standard deviation bands, but that really only works if we have known error bars on the input data. For C19 data we don't have error bars on the input, but it would save a lot of arguing if we did.