We have been re-working the TStools package over the past couple of weeks. The major changes are:

- The
`es`

function that is an alternative to the`ets`

function from the forecast package has been removed. Now it is published separately in the smooth package, which contains a collection of interesting implementations for exponential smoothing, ARIMA and more novel forecasting algorithms such as the Complex Exponential Smoothing that Ivan Svetunkov (the author of the package) and I have been working on. You can read more about the benefits of`es`

function and the package at his blog. - Re-worked the
`nemenyi`

function to streamline the inputs and outputs, as well as improve the visualisation for the MCB test. Now the figure highlights methods for which there is insufficient evidence of differences. - Inspired by my recent blog post on ABC-XYZ analysis, I re-coded the functions
`abc, xyz and abcxyz.`

They are now much more flexible in terms of plotting, accepting arguments for the plot function. When none are provided the functions revert to default behaviour. Furthermore, I got rid of the colouring using transparencies, which caused a few issues wen exporting figures in specific formats. Finally, the`abcxyz`

function now accepts an additional input argument. Now, you can provide a vector of forecast errors which will be average for each class and reported as an array and in the plot. This is quite handy for easily tracking forecasting performance per class. The following figure provides an example.