ENMeval 2.0.4 =========== * This update makes a bunch of bug fixes and enhancements brought to me by the user community. Thank you for helping me improve the software!* o Added documentation on the columns of the e@results table to ?ENMevaluation. o Fixed the variable importance slot in ENMevaluation objects. This slot will only be populated for maxent.jar models because maxnet (or BIOCLIM) lack a native function for this. Might add some external function to do this for these models in the future. o Simplified the predict method for maxnet ENMdetails objects and provided an example in ?ENMevaluate. o Added the ability to turn clamping on or off for maxnet models by specifying doClamp in other.settings, and added a doClamp slot for ENMnull objects. o Fixed a bug that prevented clamping even when doClamp was TRUE for models specified without raster environmental predictor data (species-with-data format). Now models specified without raster data also clamp as expected. o Added a switch that turns on or off ecospat functionality depending on whether it is installed into ENMnulls. This was already present in ENMevaluate. o Added documentation on the other.args option for the other.settings argument in ENMevaluate. o Added a warning message when AIC is unable to be calculated because the number of model non-zero coefficients exceeds the number of occurrence records input. Previously, this resulted in the silent attribution of NAs to the results table without explanation. o Fixed a bug that caused an error when other.settings was specified in ENMevaluate instead of left at the default NULL. Now this list is populated with default fields whether it is left NULL or specified as a list with elements by the user. ENMeval 2.0.3 =========== o Updated to be compatible with ecospat 3.2.1. ENMeval 2.0.2 =========== o Fixed a bug that caused an error in the clamp.vars() function when more than one categorical variable was specified for tabular data inputs (which ENMevaluate() uses internally). o Added new unit tests for functionality with multiple categorical variables and clamping, and also fixed some bugs with the tests. o Small changes to the print methods for classes. o Fixed a bug that made ENMnulls() error when the model included user-specified evaluation metrics. o Fixed a warning for clamp.vars() that printed when a data frame with multiple categorical variables was input instead of a raster. ENMeval 2.0.1 =========== o Fixed the DESCRIPTION file to ensure that all necessary packages are installed with the installation of ENMeval. o Addition of ENMevaluation_convert() function to convert old ENMevaluation objects (<=0.3.1) into new (>=2.0.0) ones. ENMeval 2.0.0 =========== o Complete redesign of nearly all functionality. Code is now much tidier and readable thanks to dplyr and tidyr, and commented documentation is more prevalent throughout. o New object-oriented algorithm specification for using any algorithm with ENMeval. Implementations of the new ENMdetails object exist for maxent.jar, maxnet, and BIOCLIM as examples of what is possible. o Automated output metadata for tuning analyses which uses the Range Model Metadata Standards (R package rangeModelMetadata). o New function for running null ENM simulations and calculating significance and effect sizes for empirical model performance metrics (Bohl et al. 2019 -- check ?ENMnulls). o New partition schema for fully withheld testing data and evaluation without partitions. Also includes a new option for spatial block partitions to customize the spatial orientation of the blocks. o Now implements continuous Boyce Index for training, validation, and full withheld testing data (via R package ecospat), and allows use of custom evaluation functions with the user.eval argument (see ?ENMevaluate). o A suite of new visualization functions using ggplot2 that map partition groups, plot environmental similarity histograms for partition groups, map environmental similarity for partition groups, and plot histograms or violins for null ENM results. The original evaluation plots were also redone and now use ggplot. o New analysis options for more flexibility (see ?ENMevaluate). o Fully updated and extensive vignette (https://jamiemkass.github.io/ENMeval/articles/ENMeval-2.0-vignette.html) that walks through a full analysis while describing all the new functionality. o Now supports doSNOW parallelization as well as doParallel. The doSNOW option has a functioning progress bar for parallel processes. ENMeval 0.3.1 =========== o Vignette no longer uses spocc to download occurrences due to intermittent problems downloading from GBIF. This data is now loaded from a RDS file. o Various URL changes in vignette. ======= ENMeval 0.3.0 =========== o Changed the default behavior to use the 'maxnet' function of the 'maxnet' package instead of the 'maxent.jar' program, and removed the dependency on the 'rJava' package by default, among others. o Added an algorithm slot to the ENMevaluation object. o Added information on the aggregation factor(s) or number of k folds to the ENMevaluation object when relevant. o Corrected use of 'corrected.var' in the 'tuning' function. o Changed some column names in the @results table to be more intuitive and compatable with the R package, Wallace. ENMeval 0.2.2 =========== o Added a vignette. Type: vignette('ENMeval-vignette', package='ENMeval') o Added an option to pass additional arguments to maxent (e.g., prevalence) o Added a function to extract variable importance for maxent models o Fixed an inconsistency with the AICc columns of the results table when rasterPreds=F o Fixed potential errors in the partitioning methods functions when used independently o Added some progress bar options to increase compatibility with Wallace ENMeval 0.2.1 =========== o Fixed an error in the organization of results table when bin.output=T ENMeval 0.2.0 =========== o Fixed a bug that allowed only a single categorical variable; now multiple categorical variables work. o Added an option to run the tuning function in parallel. o Added a slot in ENMevaluation object class to hold Maxent model objects. This allows the user to access the lambda values and original results table generated by Maxent. o Added arguments in ENMevaluate function to turn off raster prediction generation to save time. ENMeval 0.1.1 =========== o This version corrects the calc.aicc function that, in version 0.1.0, could give erroneous results when used with multiple models simultaneously. AICc, delta.AICc, and w.AIC values calculated in v.0.1.0 are potentially flawed! ENMeval 0.1.0 =========== o This is the initial version of ENMeval. The main function is ENMeval::ENMevaluate().