Update watersurfaces 2024 and watersurfaces_hab v6

src/generate_watersurfaces_hab/10_generate_watersurfaces_hab.Rmd

@@ -8,7 +8,7 @@ We will create a map with watersurfaces that contain aquatic habitat and rib. Th
 
 * The water surfaces map of Flanders `watersurfaces`
 
-To be sure we will use the correct version of the data sources (version 2023 for the processed habitatmap and version 1.2 for watersurfaces), we will first derive the md5 file hashes and compare them to the file hashes in the [data source version overview table](https://docs.google.com/spreadsheets/d/1E8ERlfYwP3OjluL8d7_4rR1W34ka4LRCE35JTxf3WMI/edit#gid=2100595853)
+To be sure we will use the correct version of the data sources (version 2023 for the processed habitatmap and version 2024 for watersurfaces), we will first derive the md5 file hashes and compare them to the file hashes in the [data source version overview table](https://docs.google.com/spreadsheets/d/1E8ERlfYwP3OjluL8d7_4rR1W34ka4LRCE35JTxf3WMI/edit#gid=2100595853)
 
 ### Processed habitatmap
 
@@ -29,7 +29,7 @@ hashes <-
            md5 = map(filepath, function(x) {
                            x %>% md5sum() %>% str_c(collapse = '')
                          }) %>% as.character) %>% 
-           mutate(md5_ref = c("5e9a0cb2a53f88001796bd7457a343ac"),
+           mutate(md5_ref = c("5e9a0cb2a53f88001796bd7457a343ac"), # version 2023_v1
            match = md5 == md5_ref) %>%
     select(filename,
            md5,
@@ -70,7 +70,7 @@ hashes <-
            md5 = map(filepath, function(x) {
                            x %>% md5sum() %>% str_c(collapse = '')
                          }) %>% as.character) %>% 
-           mutate(md5_ref = c("72f6575ae7095622cd92eb2be720c7cb"), # version 1.2
+           mutate(md5_ref = c("d862df5b5e9ee8a2de4c333a7dcd7645"), # version 2024
            match = md5 == md5_ref) %>%
     select(filename,
            md5,
@@ -84,6 +84,9 @@ if (!all.equal(hashes$md5, hashes$md5_ref)) {
     stop(cat("The source map is NOT up to date ! Please check the datasource. "))
 }
 
+# Official n2khab not updated yet, I work with an updated dev version installed with
+# remotes::install_github(repo="inbo/n2khab", ref = "bd784a5") #0.11.0.9000
+# and included in renv
 
 # load watersurfaces with corrected geometry 
 # (argument fix_geom available since n2khab 0.9.0) 

src/generate_watersurfaces_hab/20_check_result.Rmd

@@ -1,8 +1,8 @@
 # Check results
 
-## The new version v5
+## The new version v6
 
-Based on habitatmap_stdized_2023_v1 and watersurfaces_v1.2
+Based on habitatmap_stdized_2023_v1 and watersurfaces_2024
 
 Checksums:
 
@@ -66,59 +66,59 @@ sum(!validities | is.na(validities)) == 0
 
 ## Compare with the previous version 
 
-We load the previous version of watersurfaces_hab (version 4 based on watersurfaces_v1.1 and habitatmap_stdized_2020_v1)
+We load the previous version of watersurfaces_hab (version 5 based on watersurfaces_v1.2 and habitatmap_stdized_2023_v1)
 
 ```{r paged.print=FALSE, warning=FALSE}
 
-filepath_v4 <- file.path(path,"20_processed/_versions/watersurfaces_hab/watersurfaces_hab_v4/watersurfaces_hab.gpkg")
+filepath_v5 <- file.path(path,"20_processed/_versions/watersurfaces_hab/watersurfaces_hab_v5/watersurfaces_hab.gpkg")
 
 hashes <-
-    tibble(filepath_v4) %>%
-    mutate(filename = basename(filepath_v4),
-           md5 = map(filepath_v4, function(x) {
+    tibble(filepath_v5) %>%
+    mutate(filename = basename(filepath_v5),
+           md5 = map(filepath_v5, function(x) {
                            x %>% md5sum() %>% str_c(collapse = '')
                          }) %>% as.character) %>% 
-           mutate(md5_ref = c("96b6a7abc3d637d71052900970e70904"),
+           mutate(md5_ref = c("e7d9930938f5111de33de6ecaec31a66"),
            match = md5 == md5_ref) %>%
     select(filename,
            md5,
            md5_ref,
            match)
 
 if (!all.equal(hashes$md5, hashes$md5_ref)) {
-    stop(cat("The source map is NOT v4 ! Please check the datasource. "))
+    stop(cat("The source map is NOT v5 ! Please check the datasource. "))
 }
 
-(pol_v4 <- read_sf(filepath_v4, 
+(pol_v5 <- read_sf(filepath_v5, 
                 layer = "watersurfaces_hab_polygons"))
-(types_v4 <- read_sf(filepath_v4, 
+(types_v5 <- read_sf(filepath_v5, 
                 layer = "watersurfaces_hab_types"))
 ```
 
-- Are there differences between version v4 and version v5 and where are they located?
+- Are there differences between version v5 and version v6 and where are they located?
 
 In the table below we check the differences between both versions.
 Note that for a large number of records only polygon_habitatmap_id changes, but the geometry and the type description remain the same.
 
 ```{r}
-# polygons with polygon_id in v5 but not in version v4
-check_polygon_id_v5_v4 <- pol %>%
-  anti_join(pol_v4 %>%
+# polygons with polygon_id in v6 but not in version v5
+check_polygon_id_v6_v5 <- pol %>%
+  anti_join(pol_v5 %>%
               st_drop_geometry(), 
             by = c("polygon_id_habitatmap", "polygon_id_ws")) %>%
-  left_join(pol_v4 %>%
-              mutate(geom_text_v4 = st_as_text(geom)) %>%
+  left_join(pol_v5 %>%
+              mutate(geom_text_v5 = st_as_text(geom)) %>%
               st_drop_geometry() %>%
-              select(polygon_id, description_orig_v4 = description_orig, geom_text_v4), 
+              select(polygon_id, description_orig_v5 = description_orig, geom_text_v5), 
             by = c("polygon_id")) %>%
-  mutate(new_polygon_id = !(polygon_id %in% pol_v4$polygon_id),
-         new_polygon_id_ws = !(polygon_id_ws %in% pol_v4$polygon_id_ws),
-         new_polygon_id_habitatmap = !(polygon_id_habitatmap %in% pol_v4$polygon_id_habitatmap),
-         description_orig_update = description_orig != description_orig_v4,
-         geom_text_v5 = st_as_text(geom),  
-         geom_update = geom_text_v5 != geom_text_v4)
-
-check_polygon_id_v5_v4 %>%
+  mutate(new_polygon_id = !(polygon_id %in% pol_v5$polygon_id),
+         new_polygon_id_ws = !(polygon_id_ws %in% pol_v5$polygon_id_ws),
+         new_polygon_id_habitatmap = !(polygon_id_habitatmap %in% pol_v5$polygon_id_habitatmap),
+         description_orig_update = description_orig != description_orig_v5,
+         geom_text_v6 = st_as_text(geom),  
+         geom_update = geom_text_v6 != geom_text_v5)
+
+check_polygon_id_v6_v5 %>%
   st_drop_geometry() %>%
   group_by(new_polygon_id, new_polygon_id_ws, new_polygon_id_habitatmap, geom_update, description_orig_update) %>%
   summarise(n_records = n()) %>%
@@ -128,26 +128,28 @@ check_polygon_id_v5_v4 %>%
 
 ```
 
-We check some of the polygons for which the geometry has changed.
-Changes are minor.
+We check some of the polygons for which the geometry has changed. 
+
+In this case there are only 2 polygons with modified geometry
+Changes are minor for Stappersven, and bigger extent for Houtsaegerduinen.
 
 ```{r}
-check_geom <- check_polygon_id_v5_v4 %>%
+check_geom <- check_polygon_id_v6_v5 %>%
   filter(geom_update & !is.na(geom_update)) %>%
   slice_head(n = 5) %>%
   st_transform(4326)
 
-check_geom_v4 <- pol_v4 %>%
+check_geom_v5 <- pol_v5 %>%
   filter(polygon_id %in% check_geom$polygon_id) %>%
   st_transform(4326)
 
 check_geom %>%
   leaflet() %>%
   addTiles() %>%
-  addPolygons(group = "v5") %>%
-  addPolygons(data = check_geom_v4, color = "yellow", group = "v4") %>%
+  addPolygons(group = "v6") %>%
+  addPolygons(data = check_geom_v5, color = "red", group = "v5") %>%
    addLayersControl(
-   overlayGroups = c("v5", "v4"),
+   overlayGroups = c("v6 (blue)", "v5 (red)"),
     options = layersControlOptions(collapsed = FALSE)
   )
 ```
@@ -156,43 +158,43 @@ check_geom %>%
 
 
 ```{r}
-check_polygon_id_v4_v5 <- pol_v4 %>%
+check_polygon_id_v5_v6 <- pol_v5 %>%
   anti_join(pol %>%
               st_drop_geometry(), 
             by = c("polygon_id_habitatmap", "polygon_id_ws")) %>%
   mutate(ws_removed = !(polygon_id_ws %in% pol$polygon_id_ws))
 
-nrow(check_polygon_id_v4_v5) 
+nrow(check_polygon_id_v5_v6) 
 ```
 
 Here we show:
 
-+ new polygons from the watersurfaces layer that are included in `watersurfaces_hab_v5` (blue polygons)
-+ polygons from the watersurfaces layer that are removed in `watersurfaces_hab_v5` compared to `watersurfaces_hab_v4` (black polygons)
++ new polygons from the watersurfaces layer that are included in `watersurfaces_hab_v6` (blue polygons)
++ polygons from the watersurfaces layer that are removed in `watersurfaces_hab_v6` compared to `watersurfaces_hab_v5` (black polygons)
 
 
 ```{r}
 
-ws_new <- check_polygon_id_v5_v4 %>%
+ws_new <- check_polygon_id_v6_v5 %>%
   filter(new_polygon_id_ws) %>%
   st_transform(crs = 4326)
 
-ws_removed <- check_polygon_id_v4_v5 %>%
+ws_removed <- check_polygon_id_v5_v6 %>%
   filter(ws_removed) %>%
   st_transform(crs = 4326)
 
 leaflet() %>%
   addTiles(group = "OSM (default)") %>%
   addPolygons(data = ws_new, 
-            group = "in v5 and not v4 (blue)",
+            group = "in v6 and not v5 (blue)",
             popup = paste("polygon_id_habitatmap:", ws_new$polygon_id_habitatmap, "<br>",
                            "polygon_id_ws:", ws_new$polygon_id_ws)) %>%
   addPolygons(data = ws_removed, 
-            color = "black", group = "in v4 and not v5 (black)",
+            color = "black", group = "in v5 and not v6 (black)",
             popup = paste("polygon_id_habitatmap:", ws_removed$polygon_id_habitatmap, "<br>",
                            "polygon_id_ws:", ws_removed$polygon_id_ws)) %>% 
   addLayersControl(
-    overlayGroups = c("in v5 and not v4 (blue)", "in v4 and not v5 (black)"),
+    overlayGroups = c("in v6 and not v5 (blue)", "in v5 and not v6 (black)"),
     options = layersControlOptions(collapsed = FALSE)
   )
 ```

src/generate_watersurfaces_hab/index.Rmd

@@ -50,7 +50,7 @@ library(leaflet)
 
 # ISO8601 timestamp to set as fixed value in the GeoPackage 
 # (to be UPDATED to the actual creation date; at least update for each version):
-Sys.setenv(OGR_CURRENT_DATE = "2024-05-15T00:00:00.000Z")
+Sys.setenv(OGR_CURRENT_DATE = "2025-01-08T00:00:00.000Z")
 # This is used to keep results reproducible, as the timestamp is otherwise
 # updated each time.
 # Above environment variable OGR_CURRENT_DATE is used by the GDAL driver.