USEPA · cristinamullin · Mar 17, 2025 · Mar 17, 2025 · Mar 17, 2025 · Mar 17, 2025
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -96,8 +96,7 @@ Suggests:
     spelling,
     htmltools,
     tigris,
-    yaml, 
-    remotes
+    yaml
 Remotes:
     DOI-USGS/dataRetrieval@develop
 VignetteBuilder: knitr, rmarkdown

diff --git a/R/ATTAINSCrosswalks.R b/R/ATTAINSCrosswalks.R
@@ -554,13 +554,14 @@ TADA_UpdateMonitoringLocationsInATTAINS <- function(org_id = NULL,
 #' # See below for a simple example of this workflow:
 #'
 #' # Manually add ATTAINS parameters to crosswalk using R
-#' paramRef_UT2 <- dplyr::mutate(paramRef_UT, 
-#' ATTAINS.ParameterName = dplyr::case_when(
-#'   grepl("AMMONIA", TADA.ComparableDataIdentifier) ~ "AMMONIA, TOTAL",
-#'   grepl("NITRATE", TADA.ComparableDataIdentifier) ~ "NITRATE",
-#'   grepl("NITROGEN", TADA.ComparableDataIdentifier) ~ 
-#'   "NITRATE/NITRITE (NITRITE + NITRATE AS N)"
-#' ))
+#' paramRef_UT2 <- dplyr::mutate(paramRef_UT,
+#'   ATTAINS.ParameterName = dplyr::case_when(
+#'     grepl("AMMONIA", TADA.ComparableDataIdentifier) ~ "AMMONIA, TOTAL",
+#'     grepl("NITRATE", TADA.ComparableDataIdentifier) ~ "NITRATE",
+#'     grepl("NITROGEN", TADA.ComparableDataIdentifier) ~
+#'       "NITRATE/NITRITE (NITRITE + NITRATE AS N)"
+#'   )
+#' )
 #' # Update the 'ATTAINS.FlagParameterName' values
 #' paramRef_UT3 <- TADA_CreateParamRef(Data_Nutrients_UT,
 #'   paramRef = paramRef_UT2,
@@ -570,8 +571,8 @@ TADA_UpdateMonitoringLocationsInATTAINS <- function(org_id = NULL,
 #' # Example where multiple org_id's are selected
 #' # First, run key flag functions and harmonize synonyms across
 #' # characteristic, fraction, and speciation columns
-#' Data_NCTCShepherdstown <- 
-#' TADA_RunKeyFlagFunctions(Data_NCTCShepherdstown_HUC12)
+#' Data_NCTCShepherdstown <-
+#'   TADA_RunKeyFlagFunctions(Data_NCTCShepherdstown_HUC12)
 #' Data_NCTCShepherdstown2 <- TADA_HarmonizeSynonyms(Data_NCTCShepherdstown)
 #' # Create ATTAINS parameter crosswalk for MD, VA, and PA
 #' paramRef_NCTC <- TADA_CreateParamRef(Data_NCTCShepherdstown2,
@@ -742,7 +743,7 @@ TADA_CreateParamRef <- function(.data, org_id = NULL, paramRef = NULL, excel = T
         )
       ) %>%
       dplyr::select(
-        TADA.ComparableDataIdentifier, organization_identifier, 
+        TADA.ComparableDataIdentifier, organization_identifier,
         EPA304A.PollutantName, ATTAINS.ParameterName
       ) %>%
       dplyr::filter(organization_identifier %in% org_id) %>%
@@ -1338,7 +1339,7 @@ TADA_CreateUseParamRef <- function(.data, org_id = NULL, paramRef = NULL,
       dplyr::filter(organization_identifier %in% org_id)
   }
 
-  # This updates the flagging column. Users who only creates an R dataframe in the R environment will need to 
+  # This updates the flagging column. Users who only creates an R dataframe in the R environment will need to
   # ensure they re-run the function with their completed paramRef as an input to reflect this column accurately.
   Flag1 <- CreateParamUseRef %>%
     dplyr::anti_join(
@@ -1431,18 +1432,18 @@ TADA_CreateUseParamRef <- function(.data, org_id = NULL, paramRef = NULL,
     # set zoom size
     set_zoom <- function(x) gsub('(?<=zoomScale=")[0-9]+', x, sV, perl = TRUE)
     n_sheets <- length(wb$worksheets)
-    for(i in 1:n_sheets){
+    for (i in 1:n_sheets) {
       sV <- wb$worksheets[[i]]$sheetViews
       wb$worksheets[[i]]$sheetViews <- set_zoom(90)
     }
-      
+
     # sV <- wb$worksheets[[2]]$sheetViews
     # wb$worksheets[[2]]$sheetViews <- set_zoom(90)
     # sV <- wb$worksheets[[3]]$sheetViews
     # wb$worksheets[[3]]$sheetViews <- set_zoom(90)
     # sV <- wb$worksheets[[4]]$sheetViews
     # wb$worksheets[[4]]$sheetViews <- set_zoom(90)
-    
+
     # Format column header
     header_st <- openxlsx::createStyle(textDecoration = "Bold")
     # Format Column widths
@@ -1539,4 +1540,3 @@ TADA_CreateUseParamRef <- function(.data, org_id = NULL, paramRef = NULL,
   }
   return(CreateParamUseRef)
 }
-
diff --git a/R/CensoredDataSuite.R b/R/CensoredDataSuite.R
@@ -288,21 +288,23 @@ TADA_IDCensoredData <- function(.data) {
 #' # and in instances where the measurement is non-detect, set the result value
 #' # to half of the detection limit value. For over-detect measurements, retain
 #' # the detection limit value as the result value as-is.
-#' Data_Nutrients_UT_CensoredFlag <- 
-#' TADA_SimpleCensoredMethods(Data_Nutrients_UT, nd_method = "multiplier", 
-#' nd_multiplier = 0.5, od_method = "as-is", od_multiplier = "null")
+#' Data_Nutrients_UT_CensoredFlag <-
+#'   TADA_SimpleCensoredMethods(Data_Nutrients_UT,
+#'     nd_method = "multiplier",
+#'     nd_multiplier = 0.5, od_method = "as-is", od_multiplier = "null"
+#'   )
 #'
-#' # Check for agreement between detection condition and detection limit type, 
+#' # Check for agreement between detection condition and detection limit type,
 #' # and in instances where the measurement is non-detect, set the result value
 #' # to a random value between 0 and the detection limit value. For over-detect
 #' # measurements, retain the detection limit value as the result value as-is.
-#' Data_Nutrients_UT_CensoredFlag <- 
-#' TADA_SimpleCensoredMethods(Data_Nutrients_UT, 
-#' nd_method = "randombelowlimit", nd_multiplier = "null",
-#' od_method = "as-is", od_multiplier = "null")
+#' Data_Nutrients_UT_CensoredFlag <-
+#'   TADA_SimpleCensoredMethods(Data_Nutrients_UT,
+#'     nd_method = "randombelowlimit", nd_multiplier = "null",
+#'     od_method = "as-is", od_multiplier = "null"
+#'   )
 #' }
-#' 
-
+#'
 TADA_SimpleCensoredMethods <- function(.data, nd_method = "multiplier", nd_multiplier = 0.5, od_method = "as-is", od_multiplier = "null") {
   # check .data has all of the required columns
   expected_cols <- c(

diff --git a/R/CriteriaComparison.R b/R/CriteriaComparison.R
@@ -181,14 +181,14 @@ TADA_CreatePairRef <- function(.data, ph = TRUE, hardness = TRUE, temp = TRUE,
 #' Pair Results for Numeric Criteria Calculation (UNDER ACTIVE DEVELOPMENT)
 #'
 #' This function pairs TADA results with results from specified characteristics from the same
-#' TADA.MonitoringLocation within a user-specified time window to facilitate the calculation of 
-#' numeric criteria. The columns created by TADA_AutoClean are required to run this function. If 
+#' TADA.MonitoringLocation within a user-specified time window to facilitate the calculation of
+#' numeric criteria. The columns created by TADA_AutoClean are required to run this function. If
 #' they are not present in the data frame, the function will stop and print an error message.
 #'
 #' Users can provide a pairing reference file (can be created using TADA_CreatePairRef) to specify
 #' which combinations of TADA.CharacteristicName, TADA.ResultMeasure.MeasureUnit,
 #' TADA.MethodSpeciationName, and TADA.ResultSampleFractionText should be used for hardness, pH,
-#' temperature, salinity, chloride or other user-defined groups. If no ref is specified, all 
+#' temperature, salinity, chloride or other user-defined groups. If no ref is specified, all
 #' possible combinations for hardness, pH, temperature, salinity and chloride will be used. It is
 #' highly recommended that users perform all unit conversion and synonym harmonization before using
 #' TADA_PairForCriteriaCalc.
@@ -204,7 +204,7 @@ TADA_CreatePairRef <- function(.data, ph = TRUE, hardness = TRUE, temp = TRUE,
 #' in the pairing ref.
 #' @export
 #'
-#' @examples 
+#' @examples
 #' \dontrun{
 #' AL_df <- TADA_DataRetrieval(
 #'   startDate = "2010-11-30",
@@ -215,7 +215,7 @@ TADA_CreatePairRef <- function(.data, ph = TRUE, hardness = TRUE, temp = TRUE,
 #'
 #' AL_PairRef <- TADA_PairForCriteriaCalc(AL_df)
 #' }
-#' 
+#'
 TADA_PairForCriteriaCalc <- function(.data, ref = "null", hours_range = 4) {
   # check to see if user-supplied ref is a df
   if (!is.character(ref)) {

diff --git a/R/DataDiscoveryRetrieval.R b/R/DataDiscoveryRetrieval.R
@@ -23,8 +23,8 @@
 #' aoi_sf cannot be used with tribal_area_type. If countrycode, countycode, huc,
 #' siteid, or statecode are used with aoi_sf or tribal_area_type they will be ignored
 #' under the assumption that the sf object or tribal location are the intended
-#' area of interest. 
-#' 
+#' area of interest.
+#'
 #' aoi_sf is only designed to work with polygon shapefiles.
 #'
 #' Users can reference the \href{https://www.epa.gov/waterdata/storage-and-retrieval-and-water-quality-exchange-domain-services-and-downloads}{WQX domain tables}
@@ -44,7 +44,7 @@
 #' @param startDate Start Date string in the format YYYY-MM-DD, for example, "2020-01-01"
 #' @param endDate End Date string in the format YYYY-MM-DD, for example, "2020-01-01"
 #' @param aoi_sf An sf object to use for a query area of interest. If using a local shapefile,
-#'        sf::read_sf can be used to read in a user provided shapefile. This will only 
+#'        sf::read_sf can be used to read in a user provided shapefile. This will only
 #'        work for polygons.
 #' @param countrycode Code that identifies a country or ocean (e.g. countrycode = "CA" for Canada,
 #'        countrycode = "OA" for Atlantic Ocean).
@@ -1381,7 +1381,7 @@ make_groups <- function(x, maxrecs) {
 #' @param time_col time column
 #' @param tz_col time zone column
 #' @param tz time zone
-#' 
+#'
 #' @examples
 #' \dontrun{
 #' # Find web service URLs for each Profile using WQP User Interface (https://www.waterqualitydata.us/)
@@ -1410,44 +1410,46 @@ make_groups <- function(x, maxrecs) {
 #'   tz_col = "ActivityStartTime.TimeZoneCode",
 #'   tz = "UTC"
 #' )
-#' 
+#'
 #' # Re-run TADA_CheckRequiredFields, no longer returns error message
 #' TADA_CheckRequiredFields(TADAProfile1)
 #' }
-#' 
-TADA_CreateDateTime <- function(.data, date_col, time_col, tz_col, tz){
+#'
+TADA_CreateDateTime <- function(.data, date_col, time_col, tz_col, tz) {
   offsetLibrary <- data.frame(
     offset = c(5, 4, 6, 5, 7, 6, 8, 7, 9, 8, 10, 10, 0, 0, 0, 0),
-    code = c("EST", "EDT", "CST", "CDT", "MST", "MDT", "PST", "PDT",
-             "AKST", "AKDT", "HAST", "HST", "UTC", "", NA, "GMT")
+    code = c(
+      "EST", "EDT", "CST", "CDT", "MST", "MDT", "PST", "PDT",
+      "AKST", "AKDT", "HAST", "HST", "UTC", "", NA, "GMT"
+    )
   )
-  
+
   # Difference in behavior between NWIS and WQP
   offsetLibrary$offset[is.na(offsetLibrary$code)] <- NA
   original_order <- names(.data)
-  
+
   .data <- merge(
     x = .data,
     y = offsetLibrary,
     by.x = tz_col,
     by.y = "code",
     all.x = TRUE
   )
-  
+
   .data$dateTime <- paste(.data[[date_col]], .data[[time_col]])
   .data$dateTime <- lubridate::fast_strptime(
     .data$dateTime,
     "%Y-%m-%d %H:%M:%S"
   ) + 60 * 60 * .data$offset
-  
+
   attr(.data$dateTime, "tzone") <- tz
-  
+
   .data[[date_col]] <- suppressWarnings(as.Date(lubridate::parse_date_time(.data[[date_col]], c("Ymd", "mdY"))))
-  
+
   .data <- .data[, c(original_order, "offset", "dateTime")]
-  
+
   names(.data)[names(.data) == "offset"] <- paste0(tz_col, "_offset")
   names(.data)[names(.data) == "dateTime"] <- paste0(date_col, "Time")
-  
+
   return(.data)
 }
diff --git a/R/DepthProfile.R b/R/DepthProfile.R
@@ -28,7 +28,7 @@
 #' TADA.MonitoringLocation, ActivityDate, Organization ID, and TADA.CharacteristicName combination.
 #' When dailyagg == "min" or when dailyagg == "max", the min or max
 #' value in each group of results (as determined by the depth category) will
-#' be identified or calculated for each TADA.MonitoringLocation, ActivityDate, and 
+#' be identified or calculated for each TADA.MonitoringLocation, ActivityDate, and
 #' TADA.CharacteristicName combination. An additional column, TADA.DepthProfileAggregation.Flag will
 #' be added to describe aggregation.
 #'
@@ -89,7 +89,7 @@
 #'   bycategory = "all", dailyagg = "avg", aggregatedonly = FALSE
 #' )
 #'
-TADA_FlagDepthCategory <- function(.data, bycategory = "no", bottomvalue = 2, surfacevalue = 2, 
+TADA_FlagDepthCategory <- function(.data, bycategory = "no", bottomvalue = 2, surfacevalue = 2,
                                    dailyagg = "none", aggregatedonly = FALSE, clean = FALSE) {
   # check .data is data.frame
   TADA_CheckType(.data, "data.frame", "Input object")
@@ -690,7 +690,7 @@ TADA_IDDepthProfiles <- function(.data, nresults = TRUE, nvalue = 2, aggregates
 #'   depthcat = FALSE
 #' )
 #' }
-#' 
+#'
 TADA_DepthProfilePlot <- function(.data,
                                   groups = NULL,
                                   location = NULL,

diff --git a/R/Figures.R b/R/Figures.R
@@ -37,8 +37,10 @@
 #' # Create multiple boxplots with additional grouping columns and view the first
 #' # plot in list. In this example, we will group data in the input dataframe
 #' # by both the TADA.ComparableDataIdentifier and the OrganizationIdentifier
-#' Boxplots_TPbyOrg <- TADA_Boxplot(df, id_cols = 
-#' c("TADA.ComparableDataIdentifier", "OrganizationIdentifier"))
+#' Boxplots_TPbyOrg <- TADA_Boxplot(df,
+#'   id_cols =
+#'     c("TADA.ComparableDataIdentifier", "OrganizationIdentifier")
+#' )
 #' # This example generates 2 box plots.
 #' Boxplots_TPbyOrg[[1]]
 #' Boxplots_TPbyOrg[[2]]
@@ -49,8 +51,9 @@
 #' # (e.g. stream, reservoir, canal, etc.)
 #' # Load example dataframe:
 #' data(Data_Nutrients_UT)
-#' Boxplot_output <- TADA_Boxplot(Data_Nutrients_UT, 
-#' id_cols = c("TADA.ComparableDataIdentifier", "MonitoringLocationTypeName"))
+#' Boxplot_output <- TADA_Boxplot(Data_Nutrients_UT,
+#'   id_cols = c("TADA.ComparableDataIdentifier", "MonitoringLocationTypeName")
+#' )
 #' # This example generates 32 box plots.
 #' Boxplot_output[[2]]
 #' Boxplot_output[[25]]
@@ -229,9 +232,12 @@ TADA_Boxplot <- function(.data, id_cols = c("TADA.ComparableDataIdentifier")) {
 #' # and MonitoringLocationTypeName (e.g. stream, reservoir, canal, etc.)
 #' # Load example dataframe:
 #' data(Data_Nutrients_UT)
-#' Histogram_output <- TADA_Histogram(Data_Nutrients_UT, 
-#' id_cols = c("TADA.ComparableDataIdentifier", 
-#' "MonitoringLocationTypeName"))
+#' Histogram_output <- TADA_Histogram(Data_Nutrients_UT,
+#'   id_cols = c(
+#'     "TADA.ComparableDataIdentifier",
+#'     "MonitoringLocationTypeName"
+#'   )
+#' )
 #' # This example generates 32 histograms
 #' Histogram_output[[10]]
 #' Histogram_output[[25]]
@@ -679,11 +685,13 @@ TADA_FlaggedSitesMap <- function(.data) {
 #' # Create a list of parameters in the dataset and the number of records of
 #' # each parameter:
 #' TADA_FieldValuesPie(Data_Nutrients_UT, field = "TADA.CharacteristicName")
-#' # If there are more than 12 categories to display, any remaining categories, 
+#' # If there are more than 12 categories to display, any remaining categories,
 #' # the ones that have the smallest number of results,
 #' # are combined into an "ALL OTHERS" category.
-#' TADA_FieldValuesPie(Data_Nutrients_UT, field = 
-#' "TADA.ComparableDataIdentifier")
+#' TADA_FieldValuesPie(Data_Nutrients_UT,
+#'   field =
+#'     "TADA.ComparableDataIdentifier"
+#' )
 #'
 TADA_FieldValuesPie <- function(.data, field = "null", characteristicName = "null") {
   dat <- utils::head(TADA_FieldValuesTable(.data = .data, field = field, characteristicName = characteristicName), 12)
@@ -1207,26 +1215,35 @@ TADA_TwoCharacteristicScatterplot <- function(.data, id_cols = "TADA.ComparableD
 #' df2 <- TADA_SimpleCensoredMethods(Data_Nutrients_UT)
 #' # create scatterplots for selected counties
 #' UT_Nutrients_by_CountyCode <- TADA_GroupedScatterplot(
-#' df2, group_col = "CountyCode", groups = c("057", "011", "003", "037"))
+#'   df2,
+#'   group_col = "CountyCode", groups = c("057", "011", "003", "037")
+#' )
 #' # view the 3rd and 4th plots
 #' UT_Nutrients_by_CountyCode[[3]]
 #' UT_Nutrients_by_CountyCode[[4]]
 #'
 #' # Load example dataset:
 #' data(Data_6Tribes_5y_Harmonized)
 #'
-#' # Filter the example data so it includes only one 
+#' # Filter the example data so it includes only one
 #' # TADA.ComparableDataIdentifier
-#' df <- dplyr::filter(Data_6Tribes_5y_Harmonized, 
-#' TADA.ComparableDataIdentifier %in% c(
-#' "TOTAL PHOSPHORUS, MIXED FORMS_UNFILTERED_AS P_UG/L"))
-#' # Creates a scatterplot of the three specified sites of interest in the 
+#' df <- dplyr::filter(
+#'   Data_6Tribes_5y_Harmonized,
+#'   TADA.ComparableDataIdentifier %in% c(
+#'     "TOTAL PHOSPHORUS, MIXED FORMS_UNFILTERED_AS P_UG/L"
+#'   )
+#' )
+#' # Creates a scatterplot of the three specified sites of interest in the
 #' # same plot.
-#' TADA_GroupedScatterplot(df, group_col = "MonitoringLocationName", 
-#' groups = c("Upper Red Lake: West", "Upper Red Lake: West-Central", 
-#' "Upper Red Lake: East Central"))
+#' TADA_GroupedScatterplot(df,
+#'   group_col = "MonitoringLocationName",
+#'   groups = c(
+#'     "Upper Red Lake: West", "Upper Red Lake: West-Central",
+#'     "Upper Red Lake: East Central"
+#'   )
+#' )
 #'
-#' # If no groups are selected, return the 4 groups 
+#' # If no groups are selected, return the 4 groups
 #' # (by MonitoringLocationName) with the greatest number of results
 #' TADA_GroupedScatterplot(df, group_col = "MonitoringLocationName")
 #'