Want to share your content on R-bloggers? click here if you have a blog, or here if you don't.

It is a while since I last updated the CRAN version of the forecast package, so I uploaded the latest version (6.2) today. The github version remains the most up-to-date version and is already two commits ahead of the CRAN version.

This update is mostly bug fixes and additional error traps. The full ChangeLog is listed below.

• Many unit tests added using testthat.

• Fixed bug in ets() when very short seasonal series were passed in a data frame.

• Fixed bug in nnetar() where the initial predictor vector was reversed.

• Corrected model name returned in nnetar().

• Fixed bug in accuracy() when non-integer seasonality used.

• Made auto.arima() robust to non-integer seasonality.

• Fixed bug in auto.arima() where allowmean was ignored when stepwise=FALSE.

• Improved robustness of forecast.ets() for explosive models with multiplicative trends.

• Exogenous variables now passed to VAR forecasts

• Increased maximum nmse in ets() to 30.

• Made tsoutliers() more robust to weak seasonality

• Changed tsoutliers() to use supsmu on non-seasonal and seasonally adjusted data.

• Fixed bug in tbats() when seasonal period 1 is a small multiple of seasonal period 2.

• Other bug fixes

Thanks to David Shaub for contributing most of the unit tests.

Please submit bug reports and feature requests to the github page. Don’t forget to provide a minimal reproducible example for any bug reports.