Merge remote-tracking branch 'upstream/develop' into develop

Author: mbrousil

DESCRIPTION

@@ -72,7 +72,8 @@ Imports:
     nhdplusTools,
     arcgislayers,
     httr,
-    jsonlite
+    jsonlite,
+    rATTAINS
 Depends: 
     R (>= 3.5.0)
 Suggests:
@@ -96,6 +97,6 @@ VignetteBuilder: knitr, rmarkdown
 Language: en-US
 Config/testthat/edition: 3
 Config/testthat/load-all: list(export_all = FALSE, helpers = FALSE)
-URL: https://usepa.github.io/EPATADA/, https://github.com/USEPA/EPATADA
+URL: https://usepa.github.io/EPATADA/, https://github.com/USEPA/EPATADA, usepa.github.io/EPATADA
 LazyData: true
 LazyDataCompression: xz

NAMESPACE

@@ -40,18 +40,22 @@ export(TADA_FlagSpeciation)
 export(TADA_FlaggedSitesMap)
 export(TADA_FormatDelimitedString)
 export(TADA_GetATTAINS)
+export(TADA_GetATTAINSAUSiteCrosswalk)
+export(TADA_GetATTAINSOrgIDsRef)
 export(TADA_GetActivityTypeRef)
 export(TADA_GetCharacteristicRef)
 export(TADA_GetDetCondRef)
 export(TADA_GetDetLimitRef)
 export(TADA_GetMeasureQualifierCodeRef)
 export(TADA_GetMeasureUnitRef)
+export(TADA_GetMonLocByOrgId)
 export(TADA_GetMonLocTypeRef)
 export(TADA_GetNutrientSummationRef)
 export(TADA_GetSynonymRef)
 export(TADA_GetTemplate)
 export(TADA_GetUSGSSynonymRef)
 export(TADA_GetUniqueNearbySites)
+export(TADA_GetWQPOrgProviderRef)
 export(TADA_GetWQXCharValRef)
 export(TADA_GroupedScatterplot)
 export(TADA_HarmonizeSynonyms)
@@ -77,6 +81,7 @@ export(TADA_SummarizeColumn)
 export(TADA_TribalOptions)
 export(TADA_TwoCharacteristicScatterplot)
 export(TADA_UniqueCharUnitSpeciation)
+export(TADA_UpdateMonitoringLocationsInATTAINS)
 export(TADA_ViewATTAINS)
 export(TADA_ViewColorPalette)
 export(TADA_addPoints)

R/ATTAINSRefTables.R

@@ -0,0 +1,56 @@
+#' ATTAINS Organization Identifier Reference Table
+#'
+#' Function downloads and returns the newest available crosswalk of state/tribe/territory codes
+#' and their respective organization names and organization identifiers.
+#'
+#' This function caches the table after it has been called once
+#' so subsequent calls will be faster.
+#'
+#' @return Updated sysdata.rda with updated ATTAINSOrgIDsRef object
+#'
+#' @export
+
+TADA_GetATTAINSOrgIDsRef <- function() {
+  # If there is a cached table available return it
+  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")
+    },
+    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
+}
+
+# Update  ATTAINS Organization Identifier Reference Table
+# (for internal use only)
+
+TADA_UpdateATTAINSOrgIDsRef <- function() {
+  utils::write.csv(TADA_GetATTAINSOrgIDsRef(), file = "inst/extdata/ATTAINSOrgIDsRef.csv", row.names = FALSE)
+}
+
+
+# Used to store cached Measure Unit Reference Table
+ATTAINSOrgIDsRef_Cached <- NULL

R/CensoredDataSuite.R

@@ -16,7 +16,7 @@
 #' the ResultMeasureValue field is populated with "ND" (indicating non-detect).
 #' In rare situations, new detection limit types are added to WQX domain tables
 #' (and thus WQP data) that have not yet been classified as over- or
-#' non-detects. When these appear in a data frame, they are categorized as
+#' non-detects. When these appear in a dataframe, they are categorized as
 #' "Detection condition or detection limit is not documented in TADA reference
 #' tables." In these situations, users should contact TADA administrators to
 #' update the package accordingly. This function is used by default in
@@ -165,18 +165,18 @@ TADA_IDCensoredData <- function(.data) {
     rm(nd.rmv.list)
 
     ## Let user know when detection condition text is missing from one or more results
-    # NOTE that at this point, TADA.Detection_Type may be NA if there are detection conditions in data frame that are not present in domain table
+    # NOTE that at this point, TADA.Detection_Type may be NA if there are detection conditions in dataframe that are not present in domain table
     if (any(cens$TADA.Detection_Type[!is.na(cens$TADA.Detection_Type)] == "ResultDetectionConditionText missing")) {
       missing_detcond <- length(cens$TADA.Detection_Type[cens$TADA.Detection_Type == "ResultDetectionConditionText missing"])
-      print(paste0("TADA_IDCensoredData: There are ", missing_detcond, " results in your data frame that are missing ResultDetectionConditionText. TADA requires BOTH ResultDetectionConditionText and DetectionQuantitationLimitTypeName fields to be populated in order to categorize censored data."))
+      print(paste0("TADA_IDCensoredData: There are ", missing_detcond, " results in your dataframe that are missing ResultDetectionConditionText. TADA requires BOTH ResultDetectionConditionText and DetectionQuantitationLimitTypeName fields to be populated in order to categorize censored data."))
     }
 
     ## Let user know when one or more result detection conditions are not in the ref table
     conds <- unique(cens$ResultDetectionConditionText[!is.na(cens$ResultDetectionConditionText)])
     if (any(!conds %in% cond.ref$ResultDetectionConditionText)) {
       missing_conds <- conds[!conds %in% cond.ref$ResultDetectionConditionText]
       missing_conds <- paste(missing_conds, collapse = ", ")
-      print(paste0("TADA_IDCensoredData: ResultDetectionConditionText column in data frame contains value(s) ", missing_conds, " which is/are not represented in the ResultDetectionConditionText WQX domain table. These data records are placed under the TADA.CensoredData.Flag: Censored but not Categorized, and will not be used in censored data handling methods. Please contact TADA administrators to resolve."))
+      print(paste0("TADA_IDCensoredData: ResultDetectionConditionText column in dataframe contains value(s) ", missing_conds, " which is/are not represented in the ResultDetectionConditionText WQX domain table. These data records are placed under the TADA.CensoredData.Flag: Censored but not Categorized, and will not be used in censored data handling methods. Please contact TADA administrators to resolve."))
     }
 
     ## Bring in det limit type reference table
@@ -191,7 +191,7 @@ TADA_IDCensoredData <- function(.data) {
     if (any(!limits %in% limtype.ref$DetectionQuantitationLimitTypeName)) {
       missing_lims <- limits[!limits %in% limtype.ref$DetectionQuantitationLimitTypeName]
       missing_lims <- paste(missing_lims, collapse = ", ")
-      print(paste0("TADA_IDCensoredData: DetectionQuantitationLimitTypeName column in data frame contains value(s) ", missing_lims, " which is/are not represented in the DetectionQuantitationLimitTypeName WQX domain table. These data records are placed under the TADA.CensoredData.Flag: Censored but not Categorized, and will not be used in censored data handling methods. Please contact TADA administrators to resolve."))
+      print(paste0("TADA_IDCensoredData: DetectionQuantitationLimitTypeName column in dataframe contains value(s) ", missing_lims, " which is/are not represented in the DetectionQuantitationLimitTypeName WQX domain table. These data records are placed under the TADA.CensoredData.Flag: Censored but not Categorized, and will not be used in censored data handling methods. Please contact TADA administrators to resolve."))
     }
 
     ## Create flag for condition and limit type combinations
@@ -236,15 +236,15 @@ TADA_IDCensoredData <- function(.data) {
 
     if ("Detection condition or detection limit is not documented in TADA reference tables." %in% cens$TADA.CensoredData.Flag) {
       num <- length(cens$TADA.CensoredData.Flag[cens$TADA.CensoredData.Flag == "Detection condition or detection limit is not documented in TADA reference tables."])
-      print(paste0("TADA_IDCensoredData: ", num, " records in the supplied data frame have detection conditions and/or limit types that are missing from TADA reference tables. These records will not be included in detection limit handling calculations."))
+      print(paste0("TADA_IDCensoredData: ", num, " records in the supplied dataframe have detection conditions and/or limit types that are missing from TADA reference tables. These records will not be included in detection limit handling calculations."))
     }
 
     cens <- cens %>% dplyr::select(-TADA.Detection_Type, -TADA.Limit_Type, -TADA.MeasureQualifierCode.Flag)
 
     cens.check <- plyr::rbind.fill(cens, not_cens)
   } else {
     cens.check <- not_cens
-    print("TADA_IDCensoredData: No censored data detected in your data frame. Returning input dataframe with new column TADA.CensoredData.Flag set to Uncensored")
+    print("TADA_IDCensoredData: No censored data detected in your dataframe. Returning input dataframe with new column TADA.CensoredData.Flag set to Uncensored")
   }
 
   cens.check <- TADA_OrderCols(cens.check)
@@ -258,7 +258,7 @@ TADA_IDCensoredData <- function(.data) {
 #' before applying simple tools for non-detect and over-detect data handling, including filling
 #' in the values as-is, X times the detection limit, or a random number between 0
 #' and the LOWER detection limit. These methods do NOT depend upon censored data frequency
-#' in the data frame.
+#' in the dataframe.
 #'
 #' This function runs TADA_IDCensoredData within it which adds the column
 #' TADA.CensoredData.Flag. Enter ?TADA_IDCensoredData into the console for more
@@ -281,7 +281,7 @@ TADA_IDCensoredData <- function(.data) {
 #' @export
 #'
 #' @examples
-#' # Load example data frame:
+#' # Load example dataframe:
 #' data(Data_Nutrients_UT)
 #' # Check for agreement between detection condition and detection limit type,
 #' # and in instances where the measurement is non-detect, set the result value
@@ -328,7 +328,7 @@ TADA_SimpleCensoredMethods <- function(.data, nd_method = "multiplier", nd_multi
   }
 
   if (all(cens.data$TADA.CensoredData.Flag == "Uncensored")) {
-    print("Cannot apply simple censored methods to data frame with no censored data results. Returning input data frame.")
+    print("Cannot apply simple censored methods to dataframe with no censored data results. Returning input dataframe.")
     .data <- cens.data
   } else {
     # split out over detects and non detects

R/CriteriaComparison.R

@@ -1,31 +1,31 @@
-#' Create Reference Data Frame to Pair Characteristic Results For Use in Numeric Criteria Equations (UNDER ACTIVE DEVELOPMENT)
+#' Create Reference Dataframe to Pair Characteristic Results For Use in Numeric Criteria Equations (UNDER ACTIVE DEVELOPMENT)
 #'
-#' This function creates a data frame that shows all combinations of TADA.CharacteristicName,
+#' This function creates a dataframe that shows all combinations of TADA.CharacteristicName,
 #' TADA.CharacteristicName, TADA.ResultMeasure.MeasureUnitCode, TADA.MethodSpeciationName,
 #' and TADA.ResultSampleFractionText for commonly paired characteristics (such as pH, temperature,
 #' hardness, salinity, and chloride).
 #'
 #' @param .data TADA dataframe
 #'
-#' @param ph Boolean argument. When ph = TRUE, pH is included in this reference data frame. When
-#' ph = FALSE, pH is not included in the reference data frame.
+#' @param ph Boolean argument. When ph = TRUE, pH is included in this reference dataframe. When
+#' ph = FALSE, pH is not included in the reference dataframe.
 #'
 #' @param hardness Boolean argument. When hardness = TRUE, hardness is included in this reference
-#' data frame. When hardness = FALSE, hardness is not included in the reference data frame.
+#' dataframe. When hardness = FALSE, hardness is not included in the reference dataframe.
 #'
 #' @param temp Boolean argument. When temp = TRUE, water temperature is included in this reference
-#' data frame. When temp = FALSE, water temperature is not included in the reference data frame.
+#' dataframe. When temp = FALSE, water temperature is not included in the reference dataframe.
 #'
 #' @param salinity Boolean argument. When salinity = TRUE, salinity is included in this reference
-#' data frame. When salinity = FALSE, salinity is not included in the reference data frame.
+#' dataframe. When salinity = FALSE, salinity is not included in the reference dataframe.
 #'
 #' @param chloride Boolean argument. When chloride = TRUE, salinity is included in this reference
-#' data frame. When chloride = FALSE, chloride is not included in the reference data frame.
+#' dataframe. When chloride = FALSE, chloride is not included in the reference dataframe.
 #'
-#' @param other_char Character argument. The user provides a data frame TADA.CharacteristicNames and
+#' @param other_char Character argument. The user provides a dataframe TADA.CharacteristicNames and
 #' the pairing group they belong to. #Needs more details.
 #
-#' @return A data frame with six columns, TADA.CharacteristicName, TADA.ResultMeasure.MeasureUnitCode,
+#' @return A dataframe with six columns, TADA.CharacteristicName, TADA.ResultMeasure.MeasureUnitCode,
 #' TADA.MethodSpeciationName, TADA.ResultSampleFractionText, TADA.PairingGroup, and
 #' TADA.PairingGroupRank.
 #'
@@ -40,7 +40,7 @@
 #'
 TADA_CreatePairRef <- function(.data, ph = TRUE, hardness = TRUE, temp = TRUE,
                                chloride = TRUE, salinity = TRUE, other_char = "null") {
-  # create data frame to store pair refs
+  # create dataframe to store pair refs
   pair.ref <- data.frame(matrix(ncol = 6, nrow = 0))
 
   # name columns in pair.ref df
@@ -155,7 +155,7 @@ TADA_CreatePairRef <- function(.data, ph = TRUE, hardness = TRUE, temp = TRUE,
   }
 
   if (!is.data.frame(other_char) & other_char != "null") {
-    stop("TADA_CreatePairRef: 'other_char' must be a data frame with three columns. The first column
+    stop("TADA_CreatePairRef: 'other_char' must be a dataframe with three columns. The first column
            contains TADA.CharacteristicName, the second column contains TADA.PairingGroup, and the
            third column contains TADA.PairingGroup.Rank")
   }
@@ -172,7 +172,7 @@ TADA_CreatePairRef <- function(.data, ph = TRUE, hardness = TRUE, temp = TRUE,
   # check to see if there are any rows in pair.ref
 
   if (nrow(pair.ref) == 0) {
-    stop("None of the specified pairing characteristics were found in the TADA data frame.")
+    stop("None of the specified pairing characteristics were found in the TADA dataframe.")
   }
 
   return(pair.ref)
@@ -183,7 +183,7 @@ TADA_CreatePairRef <- function(.data, ph = TRUE, hardness = TRUE, temp = TRUE,
 #' This function pairs TADA results with results from specified characteristics from the same
 #' 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.
+#' present in the dataframe, 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,
@@ -198,7 +198,7 @@ TADA_CreatePairRef <- function(.data, ph = TRUE, hardness = TRUE, temp = TRUE,
 #' @param hours_range Numeric argument. The time difference allowed between the paired characteristic
 #' and the result.
 #
-#' @return A TADA data frame with six additional columns added for each pairing group specified
+#' @return A TADA dataframe with six additional columns added for each pairing group specified
 #' in the pairing ref.
 #' @export
 #'
@@ -217,7 +217,7 @@ TADA_PairForCriteriaCalc <- function(.data, ref = "null", hours_range = 4) {
   # check to see if user-supplied ref is a df
   if (!is.character(ref)) {
     if (!is.data.frame(ref)) {
-      stop("TADA_PairForCriteriaCalc: 'ref' must be a data frame with six columns: TADA.CharacteristicName,
+      stop("TADA_PairForCriteriaCalc: 'ref' must be a dataframe with six columns: TADA.CharacteristicName,
          TADA.ResultMeasure.MeasureUnitCode, TADA.MethodSpeciationName, TADA.ResultSampleFractionText,
          TADA.PairingGroup.Rank, and TADA.PairingGroup.")
     }
@@ -232,7 +232,7 @@ TADA_PairForCriteriaCalc <- function(.data, ref = "null", hours_range = 4) {
       ref.names <- names(ref)
 
       if (length(setdiff(col.names, ref.names)) > 0) {
-        stop("TADA_PairForCriteriaCalc: 'ref' must be a data frame with six columns: TADA.CharacteristicName,
+        stop("TADA_PairForCriteriaCalc: 'ref' must be a dataframe with six columns: TADA.CharacteristicName,
          TADA.ResultMeasure.MeasureUnitCode, TADA.MethodSpeciationName, TADA.ResultSampleFractionText,
          TADA.PairingGroup.Rank, and TADA.PairingGroup.")
       }