search

rvalavi / blockCV

The blockCV package creates spatially or environmentally separated training and testing folds for cross-validation to provide a robust error estimation in spatially structured environments. See
https://doi.org/10.1111/2041-210X.13107
GNU General Public License v3.0
106 stars 22 forks source link

Fix missing sf to SpatialPointsDataFrame conversion and crs check #4

Closed be-marc closed 4 years ago

be-marc commented 4 years ago

We are currently implementing your package into mlr-org/mlr3spatiotemporal.

I got an error with the buffering function. It seems that you missed the conversion to SpatialPointsDataFrame if the speciesData is an sf object. I also removed a part of the crs check. Maybe the bug you mentioned in the comments is fixed and the new check is sufficient.

rvalavi commented 4 years ago

@be-marc thanks for mentioning this.

I'm going to update blockCV and release it on CRAN soon. I will check for this issue and any other possible one.