styler and document updates

Updated minor excel output bug, and updated documentation for greater clarity in Mod 3 functions.

R/ATTAINSRefTables.R

@@ -15,32 +15,32 @@ TADA_GetATTAINSOrgIDsRef <- function() {
   if (!is.null(ATTAINSOrgIDsRef_Cached)) {
     return(ATTAINSOrgIDsRef_Cached)
   }
-  
+
   # Try to download up-to-date raw data
-  
+
   raw.data <- tryCatch(
     {
       # get data from ATTAINS
-    rATTAINS::domain_values(domain_name = "OrgName")
+      rATTAINS::domain_values(domain_name = "OrgName")
     },
     error = function(err) {
       NULL
     }
   )
-  
+
   # If the download failed fall back to internal data (and report it)
   if (is.null(raw.data)) {
     message("Downloading latest ATTAINS Organization Reference Table failed!")
     message("Falling back to (possibly outdated) internal file.")
     return(utils::read.csv(system.file("extdata", "ATTAINSOrgIDsRef.csv", package = "EPATADA")))
   }
-  
+
   ATTAINSOrgIDsRef <- raw.data %>%
     dplyr::distinct()
-  
+
   # Save updated table in cache
   ATTAINSOrgIDsRef_Cached <- ATTAINSOrgIDsRef
-  
+
   ATTAINSOrgIDsRef
 }
 
@@ -53,4 +53,4 @@ TADA_UpdateATTAINSOrgIDsRef <- function() {
 
 
 # Used to store cached Measure Unit Reference Table
-ATTAINSOrgIDsRef_Cached <- NULL
+ATTAINSOrgIDsRef_Cached <- NULL

R/CrosswalksFromATTAINS.R

@@ -2,19 +2,19 @@
 #' Crosswalk from ATTAINS
 #'
 #' Tribes and States who participate in electronic reporting of water quality
-#' conditions through EPA ATTAINS may also submit a crosswalk of WQP 
-#' MonitoringLocationIdentifiers associated with their Assessment Units to 
-#' ATTAINS. If the organization has recorded MonitoringLocationIdentifiers 
+#' conditions through EPA ATTAINS may also submit a crosswalk of WQP
+#' MonitoringLocationIdentifiers associated with their Assessment Units to
+#' ATTAINS. If the organization has recorded MonitoringLocationIdentifiers
 #' associated with their Assessment Units in ATTAINS, this function can be used
 #' to create a crosswalk of known MonitoringLocationIdentifiers and Assessment
-#' Units. All tribal nations record this crosswalk in ATTAINS but only a few 
-#' states. If a state has not supplied Monitoring Location information to 
+#' Units. All tribal nations record this crosswalk in ATTAINS but only a few
+#' states. If a state has not supplied Monitoring Location information to
 #' ATTAINS, the function will not return a data frame.
 #'
-#' @param org_id The ATTAINS organization identifier must be supplied by the 
-#' user. A list of organization identifiers can be found by downloading the 
-#' ATTAINS Domains Excel file: 
-#' https://www.epa.gov/system/files/other-files/2023-09/DOMAINS.xlsx. 
+#' @param org_id The ATTAINS organization identifier must be supplied by the
+#' user. A list of organization identifiers can be found by downloading the
+#' ATTAINS Domains Excel file:
+#' https://www.epa.gov/system/files/other-files/2023-09/DOMAINS.xlsx.
 #' Organization identifiers are listed in the "OrgName" tab. The "code" column
 #' contains the organization identifiers that should be used for this param.
 #'
@@ -32,7 +32,8 @@
 #'
 #' # Pueblo of Tesuque example
 #' PUEBLOOFTESUQUE_crosswalk <- TADA_GetATTAINSAUSiteCrosswalk(
-#' org_id = "PUEBLOOFTESUQUE")
+#'   org_id = "PUEBLOOFTESUQUE"
+#' )
 #'
 #' # Arizona example, returns blank dataframe as of 1/21/25
 #' AZ_crosswalk <- TADA_GetATTAINSAUSiteCrosswalk(org_id = "21ARIZ")
@@ -68,12 +69,13 @@ TADA_GetATTAINSAUSiteCrosswalk <- function(org_id = NULL) {
         MonitoringDataLinkText = monitoring_data_link_text
       ) %>%
       # paste org_id in front of MLs from the specified org if they are missing
-      #from ATTAINS
+      # from ATTAINS
       dplyr::mutate(MonitoringLocationIdentifier = ifelse((
         OrganizationIdentifier == org_id &
-          stringr::str_detect(MonitoringLocationIdentifier, 
-                              org_id, 
-                              negate = TRUE)),
+          stringr::str_detect(MonitoringLocationIdentifier,
+            org_id,
+            negate = TRUE
+          )),
       paste0(org_id, "-", MonitoringLocationIdentifier),
       MonitoringLocationIdentifier
       ))
@@ -108,7 +110,7 @@ TADA_GetATTAINSAUSiteCrosswalk <- function(org_id = NULL) {
 #' This function creates the batch upload files needed to add or update
 #' Monitoring Location Identifiers in ATTAINS Assessment Unit profiles. Users
 #' can specify whether all records should be overwritten (replaced) or if new
-#' Monitoring Location Identifiers should be appended (added) to existing 
+#' Monitoring Location Identifiers should be appended (added) to existing
 #' records.
 #'
 #' @param org_id Character argument. The ATTAINS organization identifier must
@@ -118,39 +120,39 @@ TADA_GetATTAINSAUSiteCrosswalk <- function(org_id = NULL) {
 #' Organization identifiers are listed in the "OrgName" tab. The "code" column
 #' contains the organization identifiers that should be used for this param.
 #'
-#' @param wqp_data_links Character argument. When wqp_data_links is equal to 
-#' "add" or "replace", the function will build the URL for the Water Quality 
-#' Portal Data Site page for each Monitoring Location Identifier in the data 
-#' frame. It will examine the response code of each URL and only retain those 
-#' with a 200 response, which indicates the URL is valid. When 
-#' wqp_data_links = "add", the URL will be added to any existing text in the 
-#' MS_DATA_LINK_TEXT column. When wqp_data_links = "replace", the URL will 
-#' replace any existing text in the MS_DATA_LINK_TEXT column. When 
-#' wqp_data_links = "none", no URLs will be created or added to the returned 
+#' @param wqp_data_links Character argument. When wqp_data_links is equal to
+#' "add" or "replace", the function will build the URL for the Water Quality
+#' Portal Data Site page for each Monitoring Location Identifier in the data
+#' frame. It will examine the response code of each URL and only retain those
+#' with a 200 response, which indicates the URL is valid. When
+#' wqp_data_links = "add", the URL will be added to any existing text in the
+#' MS_DATA_LINK_TEXT column. When wqp_data_links = "replace", the URL will
+#' replace any existing text in the MS_DATA_LINK_TEXT column. When
+#' wqp_data_links = "none", no URLs will be created or added to the returned
 #' data frame. Default is wqp_data_links = "add".
 #'
 #' @param attains_replace Character argument. When attains_replace = FALSE, all
-#' Monitoring Location Identifiers in the user supplied crosswalk will be 
-#' appended to the existing ATTAINS crosswalk. When attains_replace = TRUE, 
-#' Monitoring Location Identifiers will only be retained if they are in the 
+#' Monitoring Location Identifiers in the user supplied crosswalk will be
+#' appended to the existing ATTAINS crosswalk. When attains_replace = TRUE,
+#' Monitoring Location Identifiers will only be retained if they are in the
 #' user supplied crosswalk. Default equals FALSE.
 #'
-#' @param crosswalk A user-supplied dataframe with the columns 
+#' @param crosswalk A user-supplied dataframe with the columns
 #' ASSESSMENT_UNIT_ID, MS_LOCATION_ID, MS_ORG_ID, and MONITORING_DATA_LINK_TEXT
-#' is required. The ASSESSMENT_UNIT_ID and MS_LOCATION_ID must be filled out 
-#' in order to use this function. The additional columns, 
-#' MONITORING_DATA_LINK_TEXT, containing a single URL or "; " separated URLs 
-#' linking to information about the Monitoring Location, and MS_ORG_ID, 
-#' containing the WQP organization identifier for the Monitoring Location can 
-#' be left blank and the function will still run. Data link URLS to WQP site 
-#' pages cannot be automatically generated by this function unless the 
-#' MS_ORG_ID column is populated with the WQP OrganizationIdentifier. When 
+#' is required. The ASSESSMENT_UNIT_ID and MS_LOCATION_ID must be filled out
+#' in order to use this function. The additional columns,
+#' MONITORING_DATA_LINK_TEXT, containing a single URL or "; " separated URLs
+#' linking to information about the Monitoring Location, and MS_ORG_ID,
+#' containing the WQP organization identifier for the Monitoring Location can
+#' be left blank and the function will still run. Data link URLS to WQP site
+#' pages cannot be automatically generated by this function unless the
+#' MS_ORG_ID column is populated with the WQP OrganizationIdentifier. When
 #' crosswalk = NULL, the crosswalk will be downloaded from ATTAINS. This allows
 #' users to add URLs for the Water Quality Portal Data Site pages to the ATTAINS
 #' Assessment Unit profile where possible without updating other information
 #' in ATTAINS.
 #'
-#' @return The csv batch upload files for ATTAINS to add or update 
+#' @return The csv batch upload files for ATTAINS to add or update
 #' Monitoring Locations.
 #'
 #' @export
@@ -165,7 +167,7 @@ TADA_GetATTAINSAUSiteCrosswalk <- function(org_id = NULL) {
 #'   wqp_data_links = "replace"
 #' )
 #'
-#' # Alaska example using a user supplied crosswalk to update entries in 
+#' # Alaska example using a user supplied crosswalk to update entries in
 #' # ATTAINS by appending user supplied information to ATTAINS crosswalk
 #'
 #' # example monitoring location identifiers
@@ -174,40 +176,46 @@ TADA_GetATTAINSAUSiteCrosswalk <- function(org_id = NULL) {
 #'   "AK_M_1021109_013", "AK_M_1021109_013",
 #'   "AK_M_1021109_013"
 #' )
-#' 
+#'
 #' # example organization identifiers
 #' MS_ORG_ID <- c("AKDECWQ", "AKDECWQ", "AKDECWQ", "AKDECWQ", "AKDECWQ")
-#' 
+#'
 #' # example assessment units
-#' MS_LOCATION_ID <- c("ExampleSite1", "ExampleSite2", "ExampleSite3",
-#'                        "ExampleSite4", "ExampleSite5")
+#' MS_LOCATION_ID <- c(
+#'   "ExampleSite1", "ExampleSite2", "ExampleSite3",
+#'   "ExampleSite4", "ExampleSite5"
+#' )
 #' # example urls
 #' MONITORING_DATA_LINK_TEXT <- c(
-#' "https://www.waterqualitydata.us/provider/STORET/AKDECWQ/",
-#' "https://www.waterqualitydata.us/provider/STORET/AKDECWQ/",
-#' "https://www.waterqualitydata.us/provider/STORET/AKDECWQ/",
-#' "https://www.waterqualitydata.us/provider/STORET/AKDECWQ/",
-#' "https://www.waterqualitydata.us/provider/STORET/AKDECWQ/")
+#'   "https://www.waterqualitydata.us/provider/STORET/AKDECWQ/",
+#'   "https://www.waterqualitydata.us/provider/STORET/AKDECWQ/",
+#'   "https://www.waterqualitydata.us/provider/STORET/AKDECWQ/",
+#'   "https://www.waterqualitydata.us/provider/STORET/AKDECWQ/",
+#'   "https://www.waterqualitydata.us/provider/STORET/AKDECWQ/"
+#' )
 #'
 #' # create example crosswalk data frame
-#' ex.user.cw <- data.frame(MS_LOCATION_ID, MS_ORG_ID, ASSESSMENT_UNIT_ID,
-#'                          MONITORING_DATA_LINK_TEXT)
+#' ex.user.cw <- data.frame(
+#'   MS_LOCATION_ID, MS_ORG_ID, ASSESSMENT_UNIT_ID,
+#'   MONITORING_DATA_LINK_TEXT
+#' )
 #'
 #' AK_appenduserdata <- TADA_UpdateMonitoringLocationsInATTAINS(
-#' org_id = "AKDECWQ", 
-#' crosswalk = ex.user.cw, 
-#' attains_replace = FALSE, 
-#' wqp_data_links = "none")
-#'
+#'   org_id = "AKDECWQ",
+#'   crosswalk = ex.user.cw,
+#'   attains_replace = FALSE,
+#'   wqp_data_links = "none"
+#' )
 #' }
 #'
 TADA_UpdateMonitoringLocationsInATTAINS <- function(org_id = NULL,
                                                     crosswalk = NULL,
                                                     attains_replace = FALSE,
                                                     wqp_data_links = "add") {
   # get list of organization identifiers from ATTAINS
-  org.ref <- utils::read.csv(system.file("extdata", "ATTAINSOrgIDsRef.csv", 
-                                         package = "EPATADA"))
+  org.ref <- utils::read.csv(system.file("extdata", "ATTAINSOrgIDsRef.csv",
+    package = "EPATADA"
+  ))
 
   # stop function if organization identifiers is not found in ATTAINS
   if (!org_id %in% org.ref$code) {
@@ -373,8 +381,10 @@ TADA_UpdateMonitoringLocationsInATTAINS <- function(org_id = NULL,
         dplyr::mutate(
           MONITORING_DATA_LINK_TEXT = ifelse(
             grepl("200", response.code),
-            paste0(MONITORING_DATA_LINK_TEXT, "; ", 
-                   MONITORING_DATA_LINK_TEXT.New),
+            paste0(
+              MONITORING_DATA_LINK_TEXT, "; ",
+              MONITORING_DATA_LINK_TEXT.New
+            ),
             MONITORING_DATA_LINK_TEXT
           ),
           MONITORING_DATA_LINK_TEXT = stringr::str_remove_all(
@@ -384,14 +394,20 @@ TADA_UpdateMonitoringLocationsInATTAINS <- function(org_id = NULL,
         ) %>%
         tidyr::separate_rows(MONITORING_DATA_LINK_TEXT, sep = ", ") %>%
         dplyr::group_by(ASSESSMENT_UNIT_ID, MS_ORG_ID, MS_LOCATION_ID) %>%
-        suppressMessages(dplyr::summarise(MONITORING_DATA_LINK_TEXT = 
-                                            paste(
-                                              unique(
-                                                MONITORING_DATA_LINK_TEXT),
-                                              collapse = ", "))) %>%
-        dplyr::select(ASSESSMENT_UNIT_ID, 
-                      MS_ORG_ID, MS_LOCATION_ID, 
-                      MONITORING_DATA_LINK_TEXT) %>%
+        suppressMessages(dplyr::summarise(
+          MONITORING_DATA_LINK_TEXT =
+            paste(
+              unique(
+                MONITORING_DATA_LINK_TEXT
+              ),
+              collapse = ", "
+            )
+        )) %>%
+        dplyr::select(
+          ASSESSMENT_UNIT_ID,
+          MS_ORG_ID, MS_LOCATION_ID,
+          MONITORING_DATA_LINK_TEXT
+        ) %>%
         dplyr::distinct()
     }
     return(update.crosswalk)

R/GeospatialFunctions.R

@@ -479,10 +479,12 @@ fetchATTAINS <- function(.data, catchments_only = FALSE) {
 #'   applyautoclean = TRUE
 #' )
 #'
-#' nhd_data <- fetchNHD(.data = tada_data, resolution = "Hi", 
-#' features = c("catchments", "waterbodies", "flowlines"))
+#' nhd_data <- fetchNHD(
+#'   .data = tada_data, resolution = "Hi",
+#'   features = c("catchments", "waterbodies", "flowlines")
+#' )
 #' }
-#' 
+#'
 fetchNHD <- function(.data, resolution = "Hi", features = "catchments") {
   suppressMessages(suppressWarnings({
     # sf::sf_use_s2(TRUE)
@@ -925,13 +927,13 @@ fetchNHD <- function(.data, resolution = "Hi", features = "catchments") {
 #'
 #' Link catchment-based ATTAINS assessment unit data (EPA snapshot of NHDPlus HR catchments associated with entity submitted assessment unit features - points, lines, and polygons) to Water Quality Portal observations, often imported via `TADA_DataRetrieval()`. This function returns the objects that can be mapped in `TADA_ViewATTAINS()`. Check out the
 #' TADAModule2.Rmd for an example workflow. Note that approximately 80% of state submitted assessment units in ATTAINS were developed based on high res NHDPlus, so we are using that as the default.
-#' 
+#'
 #' The ATTAINS snapshot of NHDPlus HR catchments is not available for areas that do not have existing Assessment Units in ATTAINS. For these areas where there are WQP sites, but no existing ATTAINS assessment units, a user can choose to associate the WQP sites with NHDPlus catchments available from the USGS nhdplusTools package (USGS snapshot) using the optional function param 'fill_catchments'. In theory, if desired by the user, these high res catchments could be created as new assessment unit polygons in ATTAINS (that process is outside of TADA).
 #'
 #' Adds one new column to input dataframe, 'index', which identifies rows that are the same observation but are linked to multiple ATTAINS assessment units. It is possible for a single TADA WQP observation to have multiple ATTAINS assessment units linked to it and subsequently more than one row of data.
 #'
-#' If TADA_MakeSpatial has not yet been run, this function runs it which also adds another new column to the input dataframe, 'geometry', which allows for mapping and additional geospatial capabilities. 
-#' 
+#' If TADA_MakeSpatial has not yet been run, this function runs it which also adds another new column to the input dataframe, 'geometry', which allows for mapping and additional geospatial capabilities.
+#'
 #' Please review the output of this function carefully, especially waterbody intersections and lake/ocean coasts where imprecise WQP monitoring location coordinates can be problematic. Note that many WQP locations will not fall within the bounds of NHDPlus (estuaries, oceans). Manual adjustments and quality control checks are strongly encouraged. WQP monitoring location metadata may also be helpful for matching waterbody names with ATTAINS waterbody names instead of relying solely on the geospatial location (lat/long).
 #'
 #' @param .data A dataframe created by `TADA_DataRetrieval()` or the sf equivalent made by `TADA_MakeSpatial()`.