ConvergenceWarning: Optimization failed to converge. Check mle_retvals. about darts

[robomotic]

Thanks for the pointers, yes this is right the convergence warning comes from the optimizer. I guess by setting the error target value to a higher value that will disappear. For now I will just ignore them as you show in your examples.
Feel free to close once the autocorr documentation is removed.
Cheers.

[pennfranc]

Thanks for getting in touch! TimeSeries.autocorr is indeed out-of-date and should be updated or removed, good catch!
However, as far as I can tell this is unrelated to the fact that you get a convergence warning. Despite the warning, you should still get a fairly good forecast as can be seen here: https://github.com/unit8co/darts/blob/master/examples/darts-intro.ipynb
(we simply suppress the warning in that notebook).
For the ExponentialSmoothing model we simply wrap the statsmodels.tsa.holtwinters.ExponentialSmoothing model, which is responsible for the warning.