fix: throw an error when X and Y columns are present in an sf object (#96)

* fix: throw an error when X and Y columns are present in an sf object

* ...

Author: be-marc

DESCRIPTION

@@ -49,7 +49,7 @@ Config/testthat/parallel: false
 Encoding: UTF-8
 LazyData: true
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.1
+RoxygenNote: 7.3.2
 Collate:
     'DataBackendRaster.R'
     'DataBackendVector.R'

NEWS.md

@@ -1,5 +1,7 @@
 # mlr3spatial (development version)
 
+* fix: Throw an error when `X` and `Y` columns are present in an sf object
+
 # mlr3spatial 0.5.0
 
 * compatibility: Work with new paradox version 1.0.0

R/as_task_classif_st.R

@@ -55,6 +55,11 @@ as_task_classif_st.sf = function(x, target = NULL, id = deparse(substitute(x)),
     stop("Simple feature may not contain geometries of type '%s'", str_collapse(setdiff(geometries, "POINT")))
   }
 
+  if (any(c("X", "Y") %in% colnames(x))) {
+    stopf("Data contains columns named 'X' and 'Y' which are reserved for coordinates. The sf object might contain coordinates in the geometry column and the `X` and `Y` columns. Please remove or rename them before converting to a task.")
+  }
+
+
   # extract spatial meta data
   crs = sf::st_crs(x)$wkt
   coordinates = as.data.frame(sf::st_coordinates(x))

R/as_task_regr_st.R

@@ -55,6 +55,10 @@ as_task_regr_st.sf = function(x, target = NULL, id = deparse(substitute(x)), coo
     stop("Simple feature may not contain geometries of type '%s'", str_collapse(setdiff(geometries, "POINT")))
   }
 
+  if (any(c("X", "Y") %in% colnames(x))) {
+    stopf("Data contains columns named 'X' and 'Y' which are reserved for coordinates. The sf object might contain coordinates in the geometry column and the `X` and `Y` columns. Please remove or rename them before converting to a task.")
+  }
+
   # extract spatial meta data
   crs = sf::st_crs(x)$wkt
   coordinates = as.data.frame(sf::st_coordinates(x))

man-roxygen/param_coords_as_features.R

@@ -1,2 +1,3 @@
 #' @param coords_as_features (`logical(1)`)\cr
-#'   If `TRUE`, coordinates are used as features.
+#' If `TRUE`, coordinates are used as features.
+#' This is a shortcut for `task$set_col_roles(c("x", "y"), role = "feature")` with the assumption that the coordinates in the data are named "x" and "y".