The hardware and bandwidth for this mirror is donated by dogado GmbH, the Webhosting and Full Service-Cloud Provider. Check out our Wordpress Tutorial.
If you wish to report a bug, or if you are interested in having us mirror your free-software or open-source project, please feel free to contact us at mirror[@]dogado.de.
Bug Fixes
- Updated Readme file
- Fixes to new maxent interface
New features
- Updated the entire package to use terra instead of raster
- Numerous other bug fixes and behind-the-scenes improvements
Bug Fixes
- Fixed issues with background buffer when mask and points didn’t overlap
- Added citation for breadth measurements
Bug Fixes
- Permutations for background tests were selecting presences from both species’ ranges, leading to incorrect values for hypothesis tests.
Bug Fixes
- Raes and ter Steege-style tests were returning incorrect evaluate objects, although plots and p values were correct
- test.prop = “block” wasn’t working correctly
Enhancements
- Suppressing maxent startup messages by default
- Added support for bias layers to modeling functions
- Added check.env function to homogenize raster stacks so NAs propagate across layers
Enhancements
- Brought up to date for new spatstat changes
- Removed ppmlasso until it is brought back on CRAN
Enhancements
- Added a new general-purpose function for making background layers from point data. It can do both circular buffers and buffered convex hulls, and can return points, a polygon, or a raster. Converted the existing background buffer functions to just call this one, and will eventually deprecate the single-application functions.
- Added ability to select which corner you want for “block” validation.
- Added a function called multi.variogram which takes a raster stack, builds a variogram for each layer, and then plots the gamma for each variable as a function of distance, scaled by the maximum gama for that variable. This allows users to get some idea of the level of spatial autocorrelation in each predictor variable.
Bug fixes
- Minor update to fix an rgdal import that was making CRAN angry
Bug fixes
- Minor update to fix an rgdal import that was making CRAN angry
Enhancements
- Added variable importance tests via interface with the vip package
- Added clamping for the predict functions, including plots of where clamping is happening
- Added clamping for model construction functions, with a TRUE/FALSE switch defaulting to TRUE
- Changed naming conventions for predict functions so that the suitability raster is in the $suitability slot, just as with modeling functions
- Added progress bars for a lot of tests
- Added “verbose” option for a lot of functions, defaulting to FALSE
Bug fixes
- Fixed interactive.plot generic and moved the function to its own file to make it easier to extend
- Temporarily suppressing some warnings coming out of leaflet that are being produced by the recent rgdal changes
- Fixed background sampling code to resample when necessary
- Changed enmtools.ranger demo code to actually use ranger instead of rf
- Fixed code for calculating p values for some of the hypothesis tests, the old code was getting wrong answers when there were repeated values
These binaries (installable software) and packages are in development.
They may not be fully stable and should be used with caution. We make no claims about them.
Health stats visible at Monitor.