blockCV - Spatial and Environmental Blocking for K-Fold and LOO Cross-Validation
Creating spatially or environmentally separated folds for cross-validation to provide a robust error estimation in spatially structured environments; Investigating and visualising the effective range of spatial autocorrelation in continuous raster covariates and point samples to find an initial realistic distance band to separate training and testing datasets spatially described in Valavi, R. et al. (2019) <doi:10.1111/2041-210X.13107>.
Last updated
cross-validationspatialspatial-cross-validationspatial-modellingspecies-distribution-modellingcpp
11.44 score 120 stars 4 dependents 558 scripts 4.9k downloadsdisdat - Data for Comparing Species Distribution Modeling Methods
Easy access to species distribution data for 6 regions in the world, for a total of 226 anonymised species. These data are described and made available by Elith et al (2020) <doi:10.17161/bi.v15i2.13384> to compare species distribution modelling methods.
Last updated
6.31 score 2 stars 84 scripts 4.0k downloads
curves - Model-Agnostic Response Curves for Fitted Models
Create model-agnostic response-curve diagnostics for fitted prediction models. Supports profile curves, partial dependence, individual conditional expectation, and accumulated local effects; univariate curves, bivariate surfaces, ensemble summaries across multiple models, ALE-based interaction ranking, and optional raster-linked exploration with 'terra' and 'shiny'. Static displays are returned as 'ggplot2' plots. For more details on the methods see Molnar (2025) <https://christophm.github.io/interpretable-ml-book/>.
Last updated
partial-dependence-plotspdpresponse-curvesspatial-modellingspecies-distribution-modelling
4.88 score 3 stars 31 downloads
