Open
Description
Since {dplyr} 1.1.0 there is the (experimental) .by argument in some verbs as a group-by-alternative. I tripped over an unexpected interaction with summarise()and sf objects.
library(dplyr)
#>
#> Attaching package: 'dplyr'
#> The following objects are masked from 'package:stats':
#>
#> filter, lag
#> The following objects are masked from 'package:base':
#>
#> intersect, setdiff, setequal, union
library(sf)
#> Linking to GEOS 3.9.3, GDAL 3.5.2, PROJ 8.2.1; sf_use_s2() is TRUE
nc <- read_sf(system.file("shape/nc.shp", package = "sf"))
nc$area_cl <- cut(nc$AREA, c(0, .1, .12, .15, .25))
nc |>
group_by(area_cl) |>
summarise(mean(AREA))
#> Simple feature collection with 4 features and 2 fields
#> Geometry type: MULTIPOLYGON
#> Dimension: XY
#> Bounding box: xmin: -84.32385 ymin: 33.88199 xmax: -75.45698 ymax: 36.58965
#> Geodetic CRS: NAD27
#> # A tibble: 4 × 3
#> area_cl `mean(AREA)` geometry
#> <fct> <dbl> <MULTIPOLYGON [°]>
#> 1 (0,0.1] 0.0760 (((-76.68874 36.29452, -76.72651 36.15682, -76.69016…
#> 2 (0.1,0.12] 0.112 (((-80.93127 35.61959, -81.00358 35.69706, -81.05478…
#> 3 (0.12,0.15] 0.134 (((-76.46926 34.69328, -76.2877 34.87701, -76.37468 …
#> 4 (0.15,0.25] 0.190 (((-80.76612 35.68204, -80.70597 35.85166, -80.68958…
# geometries are all the same
nc |>
summarise(mean(AREA), .by = area_cl)
#> Simple feature collection with 4 features and 2 fields
#> Geometry type: MULTIPOLYGON
#> Dimension: XY
#> Bounding box: xmin: -84.32385 ymin: 33.88199 xmax: -75.45698 ymax: 36.58965
#> Geodetic CRS: NAD27
#> # A tibble: 4 × 3
#> area_cl `mean(AREA)` geometry
#> <fct> <dbl> <MULTIPOLYGON [°]>
#> 1 (0.1,0.12] 0.112 (((-75.97629 36.51793, -75.97728 36.47802, -75.9248 …
#> 2 (0,0.1] 0.0760 (((-75.97629 36.51793, -75.97728 36.47802, -75.9248 …
#> 3 (0.12,0.15] 0.134 (((-75.97629 36.51793, -75.97728 36.47802, -75.9248 …
#> 4 (0.15,0.25] 0.190 (((-75.97629 36.51793, -75.97728 36.47802, -75.9248 …
# this ist the expected result
nc |>
summarise(mean(AREA), across(geometry, st_union), .by = area_cl)
#> Simple feature collection with 4 features and 2 fields
#> Geometry type: MULTIPOLYGON
#> Dimension: XY
#> Bounding box: xmin: -84.32385 ymin: 33.88199 xmax: -75.45698 ymax: 36.58965
#> Geodetic CRS: NAD27
#> # A tibble: 4 × 3
#> area_cl `mean(AREA)` geometry
#> <fct> <dbl> <MULTIPOLYGON [°]>
#> 1 (0.1,0.12] 0.112 (((-80.93127 35.61959, -81.00358 35.69706, -81.05478…
#> 2 (0,0.1] 0.0760 (((-76.68874 36.29452, -76.72651 36.15682, -76.69016…
#> 3 (0.12,0.15] 0.134 (((-76.46926 34.69328, -76.2877 34.87701, -76.37468 …
#> 4 (0.15,0.25] 0.190 (((-80.76612 35.68204, -80.70597 35.85166, -80.68958…
sf_extSoftVersion()
#> GEOS GDAL proj.4 GDAL_with_GEOS USE_PROJ_H
#> "3.9.3" "3.5.2" "8.2.1" "true" "true"
#> PROJ
#> "8.2.1"Created on 2023-08-02 with reprex v2.0.2
Session info
sessioninfo::session_info()
#> ─ Session info ───────────────────────────────────────────────────────────────
#> setting value
#> version R version 4.2.3 (2023-03-15 ucrt)
#> os Windows 10 x64 (build 19045)
#> system x86_64, mingw32
#> ui RTerm
#> language (EN)
#> collate German_Germany.utf8
#> ctype German_Germany.utf8
#> tz Europe/Berlin
#> date 2023-08-02
#> pandoc 3.1.1 @ C:/Program Files/RStudio/resources/app/bin/quarto/bin/tools/ (via rmarkdown)
#>
#> ─ Packages ───────────────────────────────────────────────────────────────────
#> package * version date (UTC) lib source
#> class 7.3-22 2023-05-03 [2] CRAN (R 4.2.3)
#> classInt 0.4-9 2023-02-28 [1] CRAN (R 4.2.2)
#> cli 3.6.1 2023-03-23 [1] CRAN (R 4.2.3)
#> DBI 1.1.3 2022-06-18 [1] CRAN (R 4.2.0)
#> digest 0.6.33 2023-07-07 [1] CRAN (R 4.2.3)
#> dplyr * 1.1.2 2023-04-20 [1] CRAN (R 4.2.3)
#> e1071 1.7-13 2023-02-01 [1] CRAN (R 4.2.2)
#> evaluate 0.21 2023-05-05 [1] CRAN (R 4.2.3)
#> fansi 1.0.4 2023-01-22 [1] CRAN (R 4.2.2)
#> fastmap 1.1.1 2023-02-24 [1] CRAN (R 4.2.2)
#> fs 1.6.3 2023-07-20 [1] CRAN (R 4.2.3)
#> generics 0.1.3 2022-07-05 [1] CRAN (R 4.2.1)
#> glue 1.6.2 2022-02-24 [1] CRAN (R 4.2.0)
#> htmltools 0.5.5 2023-03-23 [1] CRAN (R 4.2.3)
#> KernSmooth 2.23-22 2023-07-10 [2] CRAN (R 4.2.3)
#> knitr 1.43 2023-05-25 [1] CRAN (R 4.2.3)
#> lifecycle 1.0.3 2022-10-07 [1] CRAN (R 4.2.1)
#> magrittr 2.0.3 2022-03-30 [1] CRAN (R 4.2.0)
#> pillar 1.9.0 2023-03-22 [1] CRAN (R 4.2.3)
#> pkgconfig 2.0.3 2019-09-22 [1] CRAN (R 4.2.0)
#> proxy 0.4-27 2022-06-09 [1] CRAN (R 4.2.0)
#> purrr 1.0.1 2023-01-10 [1] CRAN (R 4.2.2)
#> R.cache 0.16.0 2022-07-21 [1] CRAN (R 4.2.1)
#> R.methodsS3 1.8.2 2022-06-13 [1] CRAN (R 4.2.0)
#> R.oo 1.25.0 2022-06-12 [1] CRAN (R 4.2.0)
#> R.utils 2.12.2 2022-11-11 [1] CRAN (R 4.2.2)
#> R6 2.5.1 2021-08-19 [1] CRAN (R 4.2.0)
#> Rcpp 1.0.11 2023-07-06 [1] CRAN (R 4.2.3)
#> reprex 2.0.2 2022-08-17 [1] CRAN (R 4.2.1)
#> rlang 1.1.1 2023-04-28 [1] CRAN (R 4.2.3)
#> rmarkdown 2.23 2023-07-01 [1] CRAN (R 4.2.3)
#> rstudioapi 0.15.0 2023-07-07 [1] CRAN (R 4.2.3)
#> s2 1.1.4 2023-05-17 [1] CRAN (R 4.2.3)
#> sessioninfo 1.2.2 2021-12-06 [1] CRAN (R 4.2.0)
#> sf * 1.0-14 2023-07-11 [1] CRAN (R 4.2.3)
#> styler 1.10.1 2023-06-05 [1] CRAN (R 4.2.3)
#> tibble 3.2.1 2023-03-20 [1] CRAN (R 4.2.3)
#> tidyselect 1.2.0 2022-10-10 [1] CRAN (R 4.2.1)
#> units 0.8-2 2023-04-27 [1] CRAN (R 4.2.3)
#> utf8 1.2.3 2023-01-31 [1] CRAN (R 4.2.2)
#> vctrs 0.6.3 2023-06-14 [1] CRAN (R 4.2.3)
#> withr 2.5.0 2022-03-03 [1] CRAN (R 4.2.0)
#> wk 0.7.3 2023-05-06 [1] CRAN (R 4.2.3)
#> xfun 0.39 2023-04-20 [1] CRAN (R 4.2.3)
#> yaml 2.3.7 2023-01-23 [1] CRAN (R 4.2.2)
#>
#> [1] C:/Users/philipp_h/AppData/Local/R/win-library/4.2
#> [2] C:/Program Files/R/R-4.2.3/library
#>
#> ──────────────────────────────────────────────────────────────────────────────Metadata
Metadata
Assignees
Labels
No labels