Filter sites streamorder meas

2_process/src/sites_along_waterbody.R

@@ -1,13 +1,12 @@
-#' @param sw_sites_sf sf object of sf sites and measurements
+#' @param sites_sf sf object of sf sites and measurements
 #' @param waterbody_sf sf object of water body that will be buffered 
 #' @param lake_waterbody whether water body is lake or not
 
-sites_along_waterbody <- function(sw_sites_sf, waterbody_sf, lake_waterbody = FALSE){
+sites_along_waterbody <- function(sites_sf, waterbody_sf, lake_waterbody = FALSE){
 
 
-  sw_sites <- sw_sites_sf %>% 
-    select(site_no, geometry) %>%
-    sf::st_as_sf()
+  sites_sf <- sites_sf %>% 
+    select(site_no)
 
   ## running st_union for the tributary shp because it smooths the buffer and polygons are overlap less. 
   ## Not feasible for lakes due to specific selection of columns
@@ -19,10 +18,39 @@ sites_along_waterbody <- function(sw_sites_sf, waterbody_sf, lake_waterbody = FA
       summarize(geometry = sf::st_union(geometry)) %>%
       sf::st_buffer(dist = units::set_units(250, m))
   }
-  filtered_sites <- st_join(sw_sites, waterbody_buffered, left = FALSE) %>%
+  filtered_sites <- st_join(sites_sf, waterbody_buffered, left = FALSE) %>%
     pull(site_no) %>%
     unique()
 
   return(filtered_sites)
 
 }
+
+#' @title add_stream_order
+#' @description function that joins nwis site info to nwis sw data and adds stream order col
+#' @param nwis_sw_data nwis sw data pulled from dataRetrieval::readNWISdata() or similar dataRetrieval functions 
+#' @param sites_sf sf object of sf sites and measurements
+#' @param join_site_col col to site col to join sites_sf with nwis_sw_data. defaults is site_no as that is expected to be common between both dfs
+#' @param sites_along_streamorder3 vector of site_no that are along stream order 3 streams. Output of sites_along_waterbody()    
+#' @param sites_along_lake vector of sites that are adjacent to saline lakes. Output of sites_along_waterbody
+
+add_stream_order <- function(nwis_sw_data, sites_sf, join_site_col = 'site_no',  sites_along_streamorder3, sites_along_lake){
+
+  nwis_sw_data %>%
+    left_join(sites_sf, by = join_site_col) %>%
+    ## filtering sites that are surface level stream (all ST), lake (LK), or wetland (WE) sites
+    filter(site_tp_cd %in% c('LK','WE') | grepl('ST',site_tp_cd)) %>% 
+    ## create stream_order_category col depending on site type & match with sites stream order/lake vector targets 
+    mutate(
+      stream_order_category = case_when(
+        grepl('^ST',site_tp_cd) & site_no %in% sites_along_streamorder3 ~ 'along SO 3+',
+        site_tp_cd == 'LK' | site_no %in% sites_along_lake ~ 'along lake',
+        TRUE ~ 'not along SO 3+')) %>% 
+    ## used geometry from sites_in_watersheds_sf to get spatial info
+    st_as_sf() %>% 
+    ## grab coords 
+    mutate(lon = st_coordinates(.)[,1], lat = st_coordinates(.)[,2]) %>% 
+    ## remove geometry col
+    st_drop_geometry()  
+
+}

2_process_lakes_tribs.R

@@ -5,7 +5,7 @@ source('2_process/src/scope_lake_tributaries.R')
 ## 1. p2_saline_lakes_sf : final sf object representing our focal saline lakes. Fun process_saline_lakes_sf() is
 ## not generalized, and you will find input-specific commands and processing steps ther
 ##
-## 2. p2_lake_tributaries : polylines object representing all upstream tributaries of the lakes - creating using nhdplusTools Get_UT() function (UT:upstream)
+## 2. p2_lake_tributaries_so3 : polylines object representing all upstream tributaries of the lakes - creating using nhdplusTools Get_UT() function (UT:upstream). Filtered to so3
 ## 3. p2_lake_tributaries_cat: polygon object representing all upstream nhd catchments. Current target is not used downstream
 
 p2_lakes_tribs_targets_list <- list(
@@ -30,7 +30,7 @@ p2_lakes_tribs_targets_list <- list(
   # Basin Flowlines Processing #
   ## Get only tributaries of the Lakes using get_UT function
   tar_target(
-    p2_lake_tributaries, 
+    p2_lake_tributaries_so3, 
     scope_lake_tributaries(fline_network = p1_lake_flowlines_huc8_sf,
                            lakes_sf = p2_saline_lakes_sf,
                            buffer_dist = 10000,

2_process_sw_gw_site_data.R → 2_process_site_data.R

@@ -1,6 +1,6 @@
 source('2_process/src/sites_along_waterbody.R')
 
-p2_sw_gw_site_targets_list <- list(
+p2_site_targets_list <- list(
 
   ## simplified vrn of all site in watersheds(regardless of whether there is relevant data at that site) + all site types
   tar_target(p2_site_in_watersheds_sf,
@@ -23,7 +23,7 @@ p2_sw_gw_site_targets_list <- list(
   ## getting all sites along lake 
   tar_target(p2_sw_streamorder3_sites,
              sites_along_waterbody(p2_site_in_watersheds_sf,
-                                   p2_lake_tributaries,
+                                   p2_lake_tributaries_so3,
                                    lake_waterbody = FALSE)
   ),
 
@@ -35,25 +35,27 @@ p2_sw_gw_site_targets_list <- list(
 
   ),
 
-  ## get just sw sites with outputed data for 2000-2020 (timeframe to change) with stream order category column
+  ## get just sw sites with outputed data for 2000-2022 with stream order category column
   tar_target(p2_nwis_dv_sw_data, 
-             p1_nwis_dv_sw_data %>%
-               left_join(p2_site_in_watersheds_sf, by = 'site_no') %>%
-               filter(site_tp_cd %in% c('LK','WE') | grepl('ST',site_tp_cd)) %>% 
-               mutate(stream_order_category = case_when(
-                 grepl(site_tp_cd,'^ST') & site_no %in% p2_sw_streamorder3_sites ~ 'along SO 3+',
-                 site_tp_cd == 'LK' | site_no %in% p2_sw_in_lake_sites ~ 'along lake',
-                 TRUE ~ 'not along SO 3+'
-                 )) %>% 
-               st_as_sf() %>% 
-               mutate(lon = st_coordinates(.)[,1], lat = st_coordinates(.)[,2]) %>% 
-               st_drop_geometry() %>% 
-               ## quickly re-organizing cols
+             add_stream_order(nwis_sw_data = p1_nwis_dv_sw_data,
+                              sites_sf = p2_site_in_watersheds_sf,
+                              join_site_col = 'site_no',
+                              sites_along_streamorder3 = p2_sw_streamorder3_sites,
+                              sites_along_lake = p2_sw_in_lake_sites) %>% 
+               ## quickly re-organizing cols so that measurements cols come after non-measurement cols
                select(!starts_with('X_'),starts_with('X_'))
 
-  )
+  ),
+
+  ##  add stream order to sw sites
+  tar_target(p2_nwis_meas_sw_data, 
+             add_stream_order(nwis_sw_data = p1_nwis_meas_sw_data,
+                              sites_sf = p2_site_in_watersheds_sf,
+                              join_site_col = 'site_no',
+                              sites_along_streamorder3 = p2_sw_streamorder3_sites,
+                              sites_along_lake = p2_sw_in_lake_sites)
+             )
 
-
 )
 
   # # SW data -----------------------------------------------------------------

3_viz_prep.R

@@ -32,7 +32,7 @@ p3_prep_viz_targets_list <- list(
   ## This takes a long time because rmapshaper::ms_simplify() is very slow for me when simplifying flowlines
   tar_target(
     p3_lake_tributaries,
-    p2_lake_tributaries %>%
+    p2_lake_tributaries_so3 %>%
       rmapshaper::ms_simplify() %>%
       mutate(label = paste0("Stream: ",
                             ifelse(gnis_name == " ", "No GNIS name/ID",

4_export.R

@@ -4,34 +4,34 @@ p4_export_csv_targets_list <- list(
 
 # exports dfs -------------------------------------------------------------------
 
-## writing daily sw values to a single csv 
+## writing daily sw values to a single rds 
 tar_target(
   p4_nwis_dv_sw_data_rds,
   write_rds(p2_nwis_dv_sw_data,
             "4_reports/out/p1_nwis_dv_sw_data.rds"),
   format = "file"
   ),
 
-## writing daily gw values to a single csv
+## writing daily gw values to a single rds
 tar_target(
   p4_nwis_dv_gw_data_rds, 
   write_rds(p2_nwis_dv_gw_data,
             "4_reports/out/p1_nwis_dv_gw_data.rds"),
   format = "file"
   ),
 
-## writing field measurement sw values to a single csv 
+## writing field measurement sw values to a single rds 
 tar_target(
   p4_nwis_meas_sw_data_rds,
   readr::write_csv(p1_nwis_meas_sw_data,
-                   '4_reports/out/p1_nwis_meas_sw_data.csv')
+                   '4_reports/out/p1_nwis_meas_sw_data.rds')
 ),
 
-## writing field measurement gw values to a single csv 
+## writing field measurement gw values to a single rds
 tar_target(
   p4_nwis_meas_gw_data_rds,
   readr::write_csv(p1_nwis_meas_gw_data,
-                   '4_reports/out/p1_nwis_meas_gw_data.csv')
+                   '4_reports/out/p1_nwis_meas_gw_data.rds')
 ),
 
 ## writing iv data to lake specific csvs
@@ -53,18 +53,22 @@ tar_target(
 
 # export shapefiles -------------------------------------------------------
 
+# exporting saline lakes shp 
 tar_target(p4_saline_lakes_shp,
            write_shp(p2_saline_lakes_sf,
                     'out_shp/saline_lakes.shp'),
            format = 'file'
            ),
+
+## exporting flines shp 
 ## Commenting out because taking too long 
 # tar_target(p4_lake_tributaries_shp,
-#            write_shp(p2_lake_tributaries,
+#            write_shp(p2_lake_tributaries_so3,
 #                     'out_shp/p2_lake_tributaries.shp'),
 #            format = 'file'
 #            ),
 
+# exporting saline lakes shp 
 tar_target(p4_lake_watersheds_shp,
            write_shp(p2_lake_watersheds_dissolved,
                     'out_shp/p2_lake_watersheds.shp'),

_targets.R

@@ -13,7 +13,7 @@ source("1_fetch_nwis.R")
 
 source("2_process_lakes_tribs.R")
 source("2_process_watershed_boundary.R")
-source('2_process_sw_gw_site_data.R')
+source('2_process_site_data.R')
 
 source("3_viz_prep.R")
 source("3_visualize.R")
@@ -28,6 +28,6 @@ dir.create('1_fetch/in/states_shp', showWarnings = FALSE)
 # Return the complete list of targets
 c(p0_targets_list,
   p1_sp_targets_list, p1_feeback_xlsx_targets_list, p1_nw_targets_list,
-  p2_watershed_boundary_targets_list, p2_lakes_tribs_targets_list, p2_sw_gw_site_targets_list,
+  p2_watershed_boundary_targets_list, p2_lakes_tribs_targets_list, p2_site_targets_list,
   p3_prep_viz_targets_list, p3_viz_targets_list,
   p4_export_csv_targets_list, p4_reports_targets_list)