USEPA · jakegreif · Mar 21, 2022 · Mar 18, 2022
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -13,7 +13,6 @@ Encoding: UTF-8
 LazyData: true
 RoxygenNote: 7.1.2
 Imports:
-    ape,
     dataRetrieval,
     dplyr,
     magrittr,

diff --git a/NAMESPACE b/NAMESPACE
@@ -9,6 +9,8 @@ export(InvalidResultUnit)
 export(InvalidSpeciation)
 export(MediaNotWater)
 export(PotentialDuplicateRowID)
+export(QAPPDocAvailable)
+export(QAPPapproved)
 export(ResultValueSpecialCharacters)
 export(UncommonAnalyticalMethodID)
 export(readWQPdataTADA)
diff --git a/R/ResultFlagsIndependent.R b/R/ResultFlagsIndependent.R
@@ -374,4 +374,162 @@ AboveNationalWQXUpperThreshold <- function(.data, clean = FALSE){
       stop("clean argument must be Boolean (TRUE or FALSE)")
     }
   }
-}
+}
+
+
+#' Flag or remove result without an approved QAPP
+#' 
+#' Organizations that submit data to the Water Quality Portal (WQP) sometimes 
+#' include metadata with their results to indicate if the data produced has an
+#' approved Quality Assurance Project Plan (QAPP). This check reviews data
+#' submitted under the column "QAPPApprovedIndicator". When clean=false, 
+#' a column will be appended to flag results that do not have an approved QAPP.
+#' When clean = TRUE, rows with values that do not have an approved QAPP are 
+#' removed from the dataset and no column will be appended.This function should
+#' only be used to remove data if an approved QAPP is required to use data in 
+#' water quality assessments
+#'
+#' @param .data TADA dataset
+#' @param clean Boolean argument; removes data without an Approved QAPP from 
+#' the dataset when clean = TRUE. Default is clean = FALSE.
+#'
+#' @return When clean = FALSE, a column is appended to the input data set that
+#' flags rows without an Approved QAPP. When clean = TRUE, data without an  
+#' Approved QAPP is removed from the dataset.
+#' 
+#' @export
+
+QAPPapproved <- function(.data, clean = FALSE){
+
+  # check that .data object is compatible with TADA
+  # check .data is of class data.frame
+  if(("data.frame" %in% class(.data)) == FALSE) {
+    stop("Input object must be of class 'data.frame'")
+  }
+  # check .data has required columns
+  if(all(c("QAPPApprovedIndicator") %in% colnames(.data)) == FALSE) {
+    stop("The dataframe does not contain the required fields to use TADA. 
+         Use either the full physical/chemical profile downloaded from WQP or 
+         download the TADA profile template available on the EPA TADA webpage.")
+  }
+  # execute function after checks are passed
+  if(all(c("QAPPApprovedIndicator") %in% colnames(.data)) == TRUE) {
+
+    # flag data where QAPP was not approved
+    # make QAPPapproved.data data frame
+    QAPPapproved.data <- dplyr::filter(.data, 
+                              QAPPApprovedIndicator == "N")
+
+    # if there is data without an approved QAPP in the data set
+    if(nrow(QAPPapproved.data) != 0){
+      # append flag column
+      QAPPapproved.data$QAPPapproved <- "N"
+      # join QAPPapproved.data to flag.data
+      flag.data <- merge(.data, QAPPapproved.data, all.x = TRUE)
+
+      # flagged output
+      if(clean == FALSE) {
+        return(flag.data)
+      }
+
+      # clean output
+      if(clean == TRUE) {
+        # remove data without an approved QAPP
+        clean.data <- dplyr::filter(flag.data, !(QAPPapproved %in% "N"))
+
+        # remove QAPPapproved column
+        clean.data <- dplyr::select(clean.data, -QAPPapproved)
+
+        return(clean.data)
+      } else {
+        stop("clean argument must be Boolean (TRUE or FALSE)")
+      }
+    }  
+
+    # if no QAPP approved indicator data is in the data set
+    if(nrow(QAPPapproved.data) == 0){
+      warning("The dataset does not contain QAPP approval indicator data.")
+
+      return(.data)
+    }   
+  }
+}
+
+
+#' Flag or remove result without an approved QAPP
+#' 
+#' Organizations that submit data to the Water Quality Portal (WQP) sometimes 
+#' include metadata with their results to indicate if the data produced has an
+#' associated Quality Assurance Project Plan (QAPP). This check reviews data
+#' submitted under the column "ProjectFileUrl" to determine if
+#' a QAPP document is available to review. When clean=false, 
+#' a column will be appended to flag results that do not have an associated 
+#' QAPP document url provided. When clean = TRUE, rows with values that do not
+#' have an associated QAPP document are removed from the dataset and no column
+#' will be appended. This function should only be used to remove data if an 
+#' accompanying QAPP document is required to use data in assessments
+#'
+#' @param .data TADA dataset
+#' @param clean Boolean argument; removes data without an associated QAPP
+#' document from the dataset when clean = TRUE. Default is clean = FALSE.
+#'
+#' @return When clean = FALSE, a column is appended to the input data set that
+#' flags rows without an associated QAPP document. When clean = TRUE, 
+#' data without an associated QAPP document is removed from the dataset.
+#' 
+#' @export
+#' 
+QAPPDocAvailable <- function(.data, clean = FALSE){
+
+  # check that .data object is compatible with TADA
+  # check .data is of class data.frame
+  if(("data.frame" %in% class(.data)) == FALSE) {
+    stop("Input object must be of class 'data.frame'")
+  }
+  # check .data has required columns
+  if(all(c("ProjectFileUrl") %in% colnames(.data)) == FALSE) {
+    stop("The dataframe does not contain the required fields to use TADA. 
+         Use either the full physical/chemical profile downloaded from WQP or 
+         download the TADA profile template available on the EPA TADA webpage.")
+  }
+  # execute function after checks are passed
+  if(all(c("ProjectFileUrl") %in% colnames(.data)) == TRUE) {
+
+    # flag data where QAPP document url is not provided
+    # make QAPPdoc.data data frame
+    QAPPdoc.data <- dplyr::filter(.data, ProjectFileUrl == c("null", "NA"))
+
+    # if there is data without an associated QAPP url in the data set
+    if(nrow(QAPPdoc.data) != 0){
+      # append flag column
+      QAPPdoc.data$QAPPDocAvailable <- "N"
+      # join QAPPdoc.data to flag.data
+      flag.data <- merge(.data, QAPPdoc.data, all.x = TRUE)
+
+      # flagged output
+      if(clean == FALSE) {
+        return(flag.data)
+      }
+
+      # clean output
+      if(clean == TRUE) {
+        # remove data without an associated QAPP url
+        clean.data <- dplyr::filter(flag.data, !(QAPPDocAvailable %in% "N"))
+
+        # remove QAPPDocAvailable column
+        clean.data <- dplyr::select(clean.data, -QAPPDocAvailable)
+
+        return(clean.data)
+      } else {
+        stop("clean argument must be Boolean (TRUE or FALSE)")
+      }
+    }  
+
+    # if no associated QAPP url data is in the data set
+    if(nrow(QAPPdoc.data) == 0){
+      warning("The dataset does not contain QAPP document url data.")
+
+      return(.data)
+    }   
+  }
+}
diff --git a/man/QAPPDocAvailable.Rd b/man/QAPPDocAvailable.Rd
diff --git a/man/QAPPapproved.Rd b/man/QAPPapproved.Rd
diff --git a/test_data/test_data.R b/test_data/test_data.R
@@ -2,6 +2,9 @@ library(dataRetrieval)
 library(dplyr)
 library(stringr)
 
+#WQP URL
+#https://www.waterqualitydata.us/data/Project/search?statecode=US%3A24&siteType=Lake%2C%20Reservoir%2C%20Impoundment&siteType=Stream&sampleMedia=water&sampleMedia=Water&startDateLo=01-01-2019&startDateHi=01-01-2022&mimeType=csv&zip=yes&providers=NWIS&providers=STEWARDS&providers=STORET
+
 # Set query parameters ####
 WQPquery <- list(statecode = "US:24", Sitetype = c(
   "Lake, Reservoir, Impoundment", "Stream"), Samplemedia = c("water", "Water"),
@@ -15,6 +18,8 @@ narrow.DR <- readWQPdata(WQPquery, dataProfile = "narrowResult")
 
 sites.DR <- whatWQPsites(WQPquery)
 
+projects.DR <- readWQPdata(WQPquery, service = "Project")
+
 # Join station data to full phys/chem (results.DR) ####
 
 join1 <- results.DR %>%