Version 5.5.3

• Fixed a bug in the way compare_clusterings handled preprocessing of series.
• Internal speed optimizations.
• Added support for interruption of multi-threaded tasks via RcppThread.
• Updated timing experiments.

Version 5.5.2

• Fixed plotting of clusters with labels when a cluster has repeated series.

Version 5.5.1

• Documentation fixes.
• The registration of hclust and proc_time with setOldClass now leaves them as virtual classes.

Version 5.5.0

• Added a standalone function to extract centroids for partition around medoids: pam_cent.
• Fixed the calculation of GAK for non-NULL windows.
• "Fixed" the calculation of internal CVIs for clusterings done with TADPole.
• Vignette updates.

Version 5.4.1

• Fixed the distance calculation done by the dtw2 wrapper.

Version 5.4.0

• Added another helper for compare_clusterings: cvi_evaluators.
• Fixed the calculation of SF and CH CVIs for hierarchical clustering with default centroid extraction.
• The data frames passed to pick.clus in compare_clusterings now also contain the configurations' data instead of just the scores. This will require adjustment of existing pick.clus functions.
• The centroids in the objects returned by tsclust now have an attribute series_id if said centroids were extracted from the provided series without modification. It is an integer vector indicating which series were chosen as centroids.
• Improved warning messages in compare_clusterings.
• Multi-threaded parallelization is now more medium-grained to hopefully balance load a bit better.
• Minor updates to parallelization vignette.

Version 5.3.1

• Added parameter no.expand to compare_clusterings_configs.
• Documentation fixes.
• You should now be able to use this package without attaching it, with some caveats. See documentation for dtwclust-package.

Version 5.3.0

• Added 2 shiny apps, see interactive_clustering and ssdtwclust.
• Added another helper for compare_clusterings: repeat_clustering.
• Added distmat to fuzzy_control for when centroid = "fcmdd".
• Dropped dependency on rngtools. Changing the random number generator after loading dtwclust should not be a problem now.
• Fixed a bug regarding the way tsclust handled the seed when called from compare_clusterings. This will affect compare_clusterings results of hierarchical or TADPole clusterings made therein if a centroid subject to randomness was used (e.g. dba).

Version 5.2.0

• Several functions now use RcppParallel for parallelization, refer to the new parallelization vignette for more information.
• None of the distance/centroid functions expose parameters for helper matrices anymore.
• Added the option to add labels to non-dendrogram plots.
• The ellipsis in sdtw_cent is now actually passed to nloptr.
• Fixed tsclust for dtw_lb distance and pam.precompute = FALSE (it was always using dtw_basic, so the results should not change).
• Updated timing experiments.
• Added soft-DTW information to the PDF vignette.

Version 5.1.0

• Added implementations of soft-DTW distance and centroid.
• Fixed the calculation of the clusinfo slot for TSClusters class for clusterings that ended with empty clusters.
• Fixed logic in partitional/fuzzy clustering, which was preventing the usage of parallel backends when only one value of k and one repetition were made.