NEWS

bayesmove 0.2.4 (2026-01-09)

Now explicitly sets "id" as global variable to mitigate breaking change by {dplyr}

Removed table and inset map from Shiny app
Added dropdown option to color mapped points by a selected variable in Shiny app; not available for mapping lines
Updated speed and efficiency of get_MAP()
Fixed issue with expand_behavior() where wrong sample size was specified for track segments by ID
Updated suggested citations for use of package
Fixed bug with use of assign_behavior(); included dropping of behav.names argument

Fixed bug with Shiny app where it would return error based on number and/or frequency of unique IDs

Greatly improved speed of segmentation model by adding internal function summarize1 in C++ and updated get_summary_stats().
Updated shiny_tracks by improving responsiveness to changes in the time window, adding a data table with options to filter, and the ability to explore the time series and map of multiple IDs at once.
Updated traceplot() to automatically determine the number of MCMC iterations and add a line denoting the burn-in period.
Updated progress bar in segment_behavior() to prevent it from disappearing.

Add cluster_obs() function to make observation-level inference of behavioral states.
Add Shiny app as shiny_tracks() function to dynamically explore telemetry data within and among individuals.
Add insert_NAs() function to insert NAs for creation of regular time series.
Export get_MAP_internal() function for use within workflow for observation-level behavior estimation using cluster_obs().
Update assign_tseg_internal() to account for non-consecutive time1 variable.
Update plot_breakpoints_behav() to account for non-consecutive time variable.
Update some function arguments to be compatible with {furrr} package (>= 0.2.0).
Update API for viewing progress bar in segment_behavior() via {progressr}.
Update prep_data() to also calculate net-squared displacement
Update method by which round_track_time() calculates new date and add argument for units