st_sf() drops any sub classes of input data.frame whereas st_as_sf() respects it

[JosiahParry]

When using st_sf() with an input data.frame with any sub class, that class is dropped. However, this is not the case when using st_as_sf() all the time. It would be quite nice of st_sf() did not strip the subclasses so that we do not need to cast to data.frame and then back to sf.

For example, you can see that both st_sf() and st_as_sf() ignores the printing from tbl class. However, it respects it when the object has the tbl_df (tibble)class. In this case,st_sf()drops the class whereasst_as_sf()` keeps it but ignores it for printing purposes.

library(sf)
#> Linking to GEOS 3.11.0, GDAL 3.5.3, PROJ 9.1.0; sf_use_s2() is TRUE
library(pillar)

nc <- st_read(system.file("shape/nc.shp", package = "sf"))
#> Reading layer `nc' from data source 
#>   `/Library/Frameworks/R.framework/Versions/4.4-arm64/Resources/library/sf/shape/nc.shp' 
#>   using driver `ESRI Shapefile'
#> Simple feature collection with 100 features and 14 fields
#> Geometry type: MULTIPOLYGON
#> Dimension:     XY
#> Bounding box:  xmin: -84.32385 ymin: 33.88199 xmax: -75.45698 ymax: 36.58965
#> Geodetic CRS:  NAD27

# extract geometry and data.frame
geoms <- st_geometry(nc)
data <- st_drop_geometry(nc)


# create a tbl for formatting from pillar
tbl <- structure(data, class = c("tbl", "data.frame"))
tbl
#> # A data frame: 100 × 14
#>     AREA PERIMETER CNTY_ CNTY_ID NAME  FIPS  FIPSNO CRESS_ID BIR74 SID74 NWBIR74
#>  * <dbl>     <dbl> <dbl>   <dbl> <chr> <chr>  <dbl>    <int> <dbl> <dbl>   <dbl>
#>  1 0.114      1.44  1825    1825 Ashe  37009  37009        5  1091     1      10
#>  2 0.061      1.23  1827    1827 Alle… 37005  37005        3   487     0      10
#>  3 0.143      1.63  1828    1828 Surry 37171  37171       86  3188     5     208
#>  4 0.07       2.97  1831    1831 Curr… 37053  37053       27   508     1     123
#>  5 0.153      2.21  1832    1832 Nort… 37131  37131       66  1421     9    1066
#>  6 0.097      1.67  1833    1833 Hert… 37091  37091       46  1452     7     954
#>  7 0.062      1.55  1834    1834 Camd… 37029  37029       15   286     0     115
#>  8 0.091      1.28  1835    1835 Gates 37073  37073       37   420     0     254
#>  9 0.118      1.42  1836    1836 Warr… 37185  37185       93   968     4     748
#> 10 0.124      1.43  1837    1837 Stok… 37169  37169       85  1612     1     160
#> # ℹ 90 more rows
#> # ℹ 3 more variables: BIR79 <dbl>, SID79 <dbl>, NWBIR79 <dbl>


# create an sf with a tbl object
st_sf(
  structure(data, class = c("tbl", "data.frame")),
  geometry = geoms
)
#> Simple feature collection with 100 features and 14 fields
#> Geometry type: MULTIPOLYGON
#> Dimension:     XY
#> Bounding box:  xmin: -84.32385 ymin: 33.88199 xmax: -75.45698 ymax: 36.58965
#> Geodetic CRS:  NAD27
#> First 10 features:
#>     AREA PERIMETER CNTY_ CNTY_ID        NAME  FIPS FIPSNO CRESS_ID BIR74 SID74
#> 1  0.114     1.442  1825    1825        Ashe 37009  37009        5  1091     1
#> 2  0.061     1.231  1827    1827   Alleghany 37005  37005        3   487     0
#> 3  0.143     1.630  1828    1828       Surry 37171  37171       86  3188     5
#> 4  0.070     2.968  1831    1831   Currituck 37053  37053       27   508     1
#> 5  0.153     2.206  1832    1832 Northampton 37131  37131       66  1421     9
#> 6  0.097     1.670  1833    1833    Hertford 37091  37091       46  1452     7
#> 7  0.062     1.547  1834    1834      Camden 37029  37029       15   286     0
#> 8  0.091     1.284  1835    1835       Gates 37073  37073       37   420     0
#> 9  0.118     1.421  1836    1836      Warren 37185  37185       93   968     4
#> 10 0.124     1.428  1837    1837      Stokes 37169  37169       85  1612     1
#>    NWBIR74 BIR79 SID79 NWBIR79                       geometry
#> 1       10  1364     0      19 MULTIPOLYGON (((-81.47276 3...
#> 2       10   542     3      12 MULTIPOLYGON (((-81.23989 3...
#> 3      208  3616     6     260 MULTIPOLYGON (((-80.45634 3...
#> 4      123   830     2     145 MULTIPOLYGON (((-76.00897 3...
#> 5     1066  1606     3    1197 MULTIPOLYGON (((-77.21767 3...
#> 6      954  1838     5    1237 MULTIPOLYGON (((-76.74506 3...
#> 7      115   350     2     139 MULTIPOLYGON (((-76.00897 3...
#> 8      254   594     2     371 MULTIPOLYGON (((-76.56251 3...
#> 9      748  1190     2     844 MULTIPOLYGON (((-78.30876 3...
#> 10     160  2038     5     176 MULTIPOLYGON (((-80.02567 3...

# create the sf object, cast back to df, cast back to sf
st_sf(
  tbl, geometry = geoms
) |> 
  as.data.frame() |> 
  structure(class = c("tbl", "data.frame")) |> 
  st_as_sf()
#> Simple feature collection with 100 features and 14 fields
#> Geometry type: MULTIPOLYGON
#> Dimension:     XY
#> Bounding box:  xmin: -84.32385 ymin: 33.88199 xmax: -75.45698 ymax: 36.58965
#> Geodetic CRS:  NAD27
#> First 10 features:
#>     AREA PERIMETER CNTY_ CNTY_ID        NAME  FIPS FIPSNO CRESS_ID BIR74 SID74
#> 1  0.114     1.442  1825    1825        Ashe 37009  37009        5  1091     1
#> 2  0.061     1.231  1827    1827   Alleghany 37005  37005        3   487     0
#> 3  0.143     1.630  1828    1828       Surry 37171  37171       86  3188     5
#> 4  0.070     2.968  1831    1831   Currituck 37053  37053       27   508     1
#> 5  0.153     2.206  1832    1832 Northampton 37131  37131       66  1421     9
#> 6  0.097     1.670  1833    1833    Hertford 37091  37091       46  1452     7
#> 7  0.062     1.547  1834    1834      Camden 37029  37029       15   286     0
#> 8  0.091     1.284  1835    1835       Gates 37073  37073       37   420     0
#> 9  0.118     1.421  1836    1836      Warren 37185  37185       93   968     4
#> 10 0.124     1.428  1837    1837      Stokes 37169  37169       85  1612     1
#>    NWBIR74 BIR79 SID79 NWBIR79                       geometry
#> 1       10  1364     0      19 MULTIPOLYGON (((-81.47276 3...
#> 2       10   542     3      12 MULTIPOLYGON (((-81.23989 3...
#> 3      208  3616     6     260 MULTIPOLYGON (((-80.45634 3...
#> 4      123   830     2     145 MULTIPOLYGON (((-76.00897 3...
#> 5     1066  1606     3    1197 MULTIPOLYGON (((-77.21767 3...
#> 6      954  1838     5    1237 MULTIPOLYGON (((-76.74506 3...
#> 7      115   350     2     139 MULTIPOLYGON (((-76.00897 3...
#> 8      254   594     2     371 MULTIPOLYGON (((-76.56251 3...
#> 9      748  1190     2     844 MULTIPOLYGON (((-78.30876 3...
#> 10     160  2038     5     176 MULTIPOLYGON (((-80.02567 3...


# create an sf with a tibble object
st_sf(
  structure(data, class = c("tbl_df", "tbl", "data.frame")),
  geometry = geoms
)
#> Simple feature collection with 100 features and 14 fields
#> Geometry type: MULTIPOLYGON
#> Dimension:     XY
#> Bounding box:  xmin: -84.32385 ymin: 33.88199 xmax: -75.45698 ymax: 36.58965
#> Geodetic CRS:  NAD27
#> First 10 features:
#>     AREA PERIMETER CNTY_ CNTY_ID        NAME  FIPS FIPSNO CRESS_ID BIR74 SID74
#> 1  0.114     1.442  1825    1825        Ashe 37009  37009        5  1091     1
#> 2  0.061     1.231  1827    1827   Alleghany 37005  37005        3   487     0
#> 3  0.143     1.630  1828    1828       Surry 37171  37171       86  3188     5
#> 4  0.070     2.968  1831    1831   Currituck 37053  37053       27   508     1
#> 5  0.153     2.206  1832    1832 Northampton 37131  37131       66  1421     9
#> 6  0.097     1.670  1833    1833    Hertford 37091  37091       46  1452     7
#> 7  0.062     1.547  1834    1834      Camden 37029  37029       15   286     0
#> 8  0.091     1.284  1835    1835       Gates 37073  37073       37   420     0
#> 9  0.118     1.421  1836    1836      Warren 37185  37185       93   968     4
#> 10 0.124     1.428  1837    1837      Stokes 37169  37169       85  1612     1
#>    NWBIR74 BIR79 SID79 NWBIR79                       geometry
#> 1       10  1364     0      19 MULTIPOLYGON (((-81.47276 3...
#> 2       10   542     3      12 MULTIPOLYGON (((-81.23989 3...
#> 3      208  3616     6     260 MULTIPOLYGON (((-80.45634 3...
#> 4      123   830     2     145 MULTIPOLYGON (((-76.00897 3...
#> 5     1066  1606     3    1197 MULTIPOLYGON (((-77.21767 3...
#> 6      954  1838     5    1237 MULTIPOLYGON (((-76.74506 3...
#> 7      115   350     2     139 MULTIPOLYGON (((-76.00897 3...
#> 8      254   594     2     371 MULTIPOLYGON (((-76.56251 3...
#> 9      748  1190     2     844 MULTIPOLYGON (((-78.30876 3...
#> 10     160  2038     5     176 MULTIPOLYGON (((-80.02567 3...

# create the sf object, cast back to df, cast back to sf
st_sf(
  tbl, geometry = geoms
) |> 
  as.data.frame() |> 
  structure(class = c("tbl_df", "tbl", "data.frame")) |> 
  st_as_sf()
#> Simple feature collection with 100 features and 14 fields
#> Geometry type: MULTIPOLYGON
#> Dimension:     XY
#> Bounding box:  xmin: -84.32385 ymin: 33.88199 xmax: -75.45698 ymax: 36.58965
#> Geodetic CRS:  NAD27
#> # A data frame: 100 × 15
#>     AREA PERIMETER CNTY_ CNTY_ID NAME  FIPS  FIPSNO CRESS_ID BIR74 SID74 NWBIR74
#>  * <dbl>     <dbl> <dbl>   <dbl> <chr> <chr>  <dbl>    <int> <dbl> <dbl>   <dbl>
#>  1 0.114      1.44  1825    1825 Ashe  37009  37009        5  1091     1      10
#>  2 0.061      1.23  1827    1827 Alle… 37005  37005        3   487     0      10
#>  3 0.143      1.63  1828    1828 Surry 37171  37171       86  3188     5     208
#>  4 0.07       2.97  1831    1831 Curr… 37053  37053       27   508     1     123
#>  5 0.153      2.21  1832    1832 Nort… 37131  37131       66  1421     9    1066
#>  6 0.097      1.67  1833    1833 Hert… 37091  37091       46  1452     7     954
#>  7 0.062      1.55  1834    1834 Camd… 37029  37029       15   286     0     115
#>  8 0.091      1.28  1835    1835 Gates 37073  37073       37   420     0     254
#>  9 0.118      1.42  1836    1836 Warr… 37185  37185       93   968     4     748
#> 10 0.124      1.43  1837    1837 Stok… 37169  37169       85  1612     1     160
#> # ℹ 90 more rows
#> # ℹ 4 more variables: BIR79 <dbl>, SID79 <dbl>, NWBIR79 <dbl>,
#> #   geometry <MULTIPOLYGON [°]>

[edzer]

Thanks, @JosiahParry !