USEPA · hillarymarler · Jul 26, 2024 · Jul 19, 2024 · Jul 19, 2024 · Jul 19, 2024
diff --git a/R/CensoredDataSuite.R b/R/CensoredDataSuite.R
@@ -364,7 +364,8 @@ TADA_SimpleCensoredMethods <- function(.data, nd_method = "multiplier", nd_multi
       }
     }
 
-    .data <- plyr::rbind.fill(nd, od, all_others)
+    .data <- plyr::rbind.fill(nd, od, all_others) %>%
+      TADA_CreateComparableID()
   }
   .data <- TADA_OrderCols(.data)
   return(.data)

diff --git a/R/Figures.R b/R/Figures.R
@@ -573,7 +573,7 @@ TADA_OverviewMap <- function(.data) {
 #'    then 3 decimal places.
 #' 2) outside USA - coordinates that fall outside the bounds of the USA. 
 #' 3) near other sites - groups of sites that are spatially located within
-#'    a threshhold distance (defaulting to 100 m) from each other.
+#'    a threshold distance (defaulting to 100 m) from each other.
 #'
 #' @export
 #'
@@ -934,10 +934,8 @@ TADA_Scatterplot <- function(.data, id_cols = c("TADA.ComparableDataIdentifier")
 #'
 #' # Load example dataset:
 #' data(Data_6Tribes_5y_Harmonized)
-#' # Filter the example data so it includes only one TADA.ComparableDataIdentifier
-#' df <- dplyr::filter(Data_6Tribes_5y_Harmonized, TADA.ComparableDataIdentifier == "TOTAL PHOSPHORUS, MIXED FORMS_UNFILTERED_AS P_MG/L")
-#' # Creates a scatterplot including the two specified sites in the same plot:
-#' TADA_TwoCharacteristicScatterplot(df, id_cols = "MonitoringLocationName", groups = c("Upper Red Lake: West", "Upper Red Lake: West-Central"))
+#' # Create a single scatterplot with two specified groups from TADA.ComparableDataIdentifier
+#' TADA_TwoCharacteristicScatterplot(Data_6Tribes_5y_Harmonized, id_cols = "TADA.ComparableDataIdentifier", groups = c("TEMPERATURE_NA_NA_DEG C", "PH_NA_NA_NA"))
 #'
 TADA_TwoCharacteristicScatterplot <- function(.data, id_cols = "TADA.ComparableDataIdentifier", groups) {
   # check .data is data.frame

diff --git a/R/UnitConversions.R b/R/UnitConversions.R
diff --git a/R/Utilities.R b/R/Utilities.R
@@ -85,7 +85,7 @@ utils::globalVariables(c(
   "YAxis.DepthUnit", "TADA.CharacteristicsForDepthProfile", "TADA.ConsolidatedDepth",
   "TADA.ConsolidatedDepth.Bottom", "TADA.ConsolidatedDepth.Unit", "col2rgb",
   "palette.colors", "rect", "rgb", "text", "CodeNoSpeciation", "ResultMeasure.MeasureUnitCode.Upper",
-  "TADA.MonitoringLocationIdentifier", "StringA", "StringB"
+  "TADA.MonitoringLocationIdentifier", "StringA", "StringB", "MeasureUnitCode.match"
 ))
 
 # global variables for tribal feature layers used in TADA_OverviewMap in Utilities.R
@@ -1447,7 +1447,7 @@ TADA_UniqueCharUnitSpeciation <- function(.data) {
   )
 
   # Check to see if TADA_Autoclean has been run
-  if (all(required_cols %in% colnames(.data)) == FALSE) {
+  if (any(required_cols %in% colnames(.data)) == FALSE) {
     print("The dataframe does not contain the required fields. Running TADA_AutoClean to create required columns.")
     .data <- TADA_AutoClean(.data)
   }
@@ -1462,6 +1462,7 @@ TADA_UniqueCharUnitSpeciation <- function(.data) {
       TADA.CharacteristicName, TADA.ResultMeasure.MeasureUnitCode,
       ResultMeasure.MeasureUnitCode, TADA.MethodSpeciationName
     ) %>%
+    dplyr::filter(!is.na(TADA.ResultMeasure.MeasureUnitCode)) %>%
     dplyr::distinct()
 
   # Create df of unique codes and characteristic names(from TADA.CharacteristicName and TADA.DetectionQuantitationLimitMeasure.MeasureUnitCode) in TADA data frame
@@ -1470,6 +1471,7 @@ TADA_UniqueCharUnitSpeciation <- function(.data) {
       TADA.CharacteristicName, TADA.DetectionQuantitationLimitMeasure.MeasureUnitCode,
       DetectionQuantitationLimitMeasure.MeasureUnitCode, TADA.MethodSpeciationName
     ) %>%
+     dplyr::filter(!is.na(TADA.DetectionQuantitationLimitMeasure.MeasureUnitCode)) %>%
     dplyr::distinct() %>%
     dplyr::rename(
       TADA.ResultMeasure.MeasureUnitCode = TADA.DetectionQuantitationLimitMeasure.MeasureUnitCode,
@@ -1488,6 +1490,8 @@ TADA_UniqueCharUnitSpeciation <- function(.data) {
     dplyr::filter(!is.na(TADA.ResultMeasure.MeasureUnitCode) |
       is.na(TADA.ResultMeasure.MeasureUnitCode) & NCode == 1) %>%
     dplyr::select(-NCode)
+
+  return(data.units)
 }
 
 

diff --git a/data/Data_6Tribes_5y.rda b/data/Data_6Tribes_5y.rda
diff --git a/data/Data_6Tribes_5y_Harmonized.rda b/data/Data_6Tribes_5y_Harmonized.rda
diff --git a/data/Data_NCTCShepherdstown_HUC12.rda b/data/Data_NCTCShepherdstown_HUC12.rda
diff --git a/data/Data_Nutrients_UT.rda b/data/Data_Nutrients_UT.rda
diff --git a/data/Data_R5_TADAPackageDemo.rda b/data/Data_R5_TADAPackageDemo.rda
diff --git a/inst/WORDLIST b/inst/WORDLIST
@@ -152,7 +152,6 @@ ND's
 NHD
 NHDPlus
 NWIS
-NearbySiteGroups
 NoResultValue
 NoTargetUnit
 NonStandardized
@@ -237,6 +236,8 @@ Speciation
 SpeciationAssumptions
 SpeciationUnitConversion
 StateCode
+StringA
+StringB
 SubstituteDeprecatedChars
 SummarizeColumn
 TADA
@@ -366,6 +367,7 @@ isimpaired
 isthreatened
 joinkey
 magrittr
+manys
 mimeType
 mlt
 nd

diff --git a/inst/extdata/AKAllotments.dbf b/inst/extdata/AKAllotments.dbf
diff --git a/inst/extdata/AKVillages.dbf b/inst/extdata/AKVillages.dbf
diff --git a/inst/extdata/AmericanIndian.dbf b/inst/extdata/AmericanIndian.dbf
diff --git a/inst/extdata/OKTribe.dbf b/inst/extdata/OKTribe.dbf
diff --git a/inst/extdata/OffReservation.dbf b/inst/extdata/OffReservation.dbf
diff --git a/inst/extdata/USGS_units_speciation.csv b/inst/extdata/USGS_units_speciation.csv
@@ -1,6 +1,7 @@
 Domain,Unique Identifier,Code,CodeNoSpeciation,Description,Last Change Date,Target Unit,Target Speciation,Conversion Factor
 Measurement Unit(MeasureUnitCode),NA,mg/l SiO2,mg/l,,,ug/L,as SiO2,1000
 Measurement Unit(MeasureUnitCode),NA,mg/l CaCO3,mg/l,,,ug/L,as CaCO3,1000
+Measurement Unit(MeasureUnitCode),NA,mg/l CaCO3**,mg/l,,,ug/l,as CaCO3,1000
 Measurement Unit(MeasureUnitCode),NA,mg/l as N,mg/l,,,ug/L,as N,1000
 Measurement Unit(MeasureUnitCode),NA,mg/kg as N,mg/kg,,,ug/kg,as N,1000
 Measurement Unit(MeasureUnitCode),NA,mg/l asPO4,mg/l,,,ug/L,as PO4,1000

diff --git a/inst/extdata/VATribe.dbf b/inst/extdata/VATribe.dbf
diff --git a/inst/extdata/WQXMeasureQualifierCodeRef.csv b/inst/extdata/WQXMeasureQualifierCodeRef.csv
@@ -96,7 +96,10 @@
 "Result Measure Qualifier(MeasureQualifierCode)",6,"H","Holding time exceeded: ","4/24/2008 8:28:31 AM","Suspect"
 "Result Measure Qualifier(MeasureQualifierCode)",1002,"H2","Extraction or preparation was conducted outside of the recognized method holding time.","5/23/2023 9:56:04 AM","Suspect"
 "Result Measure Qualifier(MeasureQualifierCode)",1003,"H3","Sample was received or analysis requested beyond the recognized method holding time.","5/23/2023 9:56:04 AM","Suspect"
+"Result Measure Qualifier(MeasureQualifierCode)",1191,"H4","Sample was extracted past required extraction holding time, but analyzed within analysis holding time","7/18/2024 8:49:50 PM","Not Reviewed"
+"Result Measure Qualifier(MeasureQualifierCode)",1192,"H5","Test specified to be performed in the field within 15 minutes of sampling; sample was received and analyzed past the regulatory holding time","7/18/2024 8:49:50 PM","Not Reviewed"
 "Result Measure Qualifier(MeasureQualifierCode)",1164,"HE","value extrapolated at high end","8/16/2021 11:03:38 AM","Suspect"
+"Result Measure Qualifier(MeasureQualifierCode)",1193,"HF","Field parameter with a holding time of 15 minutes; test performed by laboratory at client's request","7/18/2024 8:49:50 PM","Not Reviewed"
 "Result Measure Qualifier(MeasureQualifierCode)",819,"HH","Out High","4/10/2020 6:07:22 PM","Suspect"
 "Result Measure Qualifier(MeasureQualifierCode)",156,"HIB","Likely Biased High","3/16/2016 1:04:25 PM","Suspect"
 "Result Measure Qualifier(MeasureQualifierCode)",113,"HICC","Initial calibration criteria not met – high","4/9/2015 9:10:23 AM","Suspect"
@@ -107,6 +110,7 @@
 "Result Measure Qualifier(MeasureQualifierCode)",25,"HNRO","high native analyte recovery in OPR (or LCS), potential high bias","5/19/2010 11:24:46 AM","Pass"
 "Result Measure Qualifier(MeasureQualifierCode)",827,"HQ","High Quality control measures","4/10/2020 6:07:22 PM","Pass"
 "Result Measure Qualifier(MeasureQualifierCode)",158,"HTH","Hard to Homogenize","3/16/2016 1:04:25 PM","Pass"
+"Result Measure Qualifier(MeasureQualifierCode)",1194,"HTI","Holding time for test is immediate; the laboratory measurement, therefore, cannot be used for compliance purposes","7/18/2024 8:49:50 PM","Not Reviewed"
 "Result Measure Qualifier(MeasureQualifierCode)",27,"HVER","high calibration verification standard recovery, estimated value","5/19/2010 11:24:47 AM","Pass"
 "Result Measure Qualifier(MeasureQualifierCode)",61,"I","Estimated value; compound failed initial calibration value","8/22/2013 1:44:00 PM","Suspect"
 "Result Measure Qualifier(MeasureQualifierCode)",159,"ICA","Incorrect Initial Calibration Associated with Sample","3/16/2016 1:04:25 PM","Suspect"
@@ -152,10 +156,13 @@
 "Result Measure Qualifier(MeasureQualifierCode)",817,"LT","Less Than","4/10/2020 6:07:22 PM","Pass"
 "Result Measure Qualifier(MeasureQualifierCode)",834,"LTGTE","Result is less than the MQL but greater than or equal to the MDL","4/10/2020 6:07:23 PM","Non-Detect"
 "Result Measure Qualifier(MeasureQualifierCode)",33,"LVER","low calibration verification standard recovery, potential low bias","5/19/2010 11:24:47 AM","Pass"
+"Result Measure Qualifier(MeasureQualifierCode)",1188,"M3","Spike recovery value unusable since the analyte concentration in the sample is disproportionate to the spike level","7/18/2024 8:49:50 PM","Not Reviewed"
 "Result Measure Qualifier(MeasureQualifierCode)",168,"M6F","More Than 6 Flags Applied","3/16/2016 1:04:26 PM","Pass"
 "Result Measure Qualifier(MeasureQualifierCode)",813,"MDL","Method Detection Level","4/10/2020 6:07:22 PM","Suspect"
+"Result Measure Qualifier(MeasureQualifierCode)",1189,"MHA","Due to high levels of analyte in the sample, the MS/MSD calculation does not provide useful spike recovery information","7/18/2024 8:49:50 PM","Not Reviewed"
 "Result Measure Qualifier(MeasureQualifierCode)",1040,"MI","Matrix Interference","4/24/2020 8:50:16 PM","Suspect"
 "Result Measure Qualifier(MeasureQualifierCode)",816,"MSD","MS and/or MSD","4/10/2020 6:07:22 PM","Suspect"
+"Result Measure Qualifier(MeasureQualifierCode)",1195,"MSI","Sample matrix interference caused MS and/or MSD to be above acceptance limits","7/18/2024 8:49:50 PM","Not Reviewed"
 "Result Measure Qualifier(MeasureQualifierCode)",119,"MSR","Matrix spike acceptance criteria not met","4/9/2015 9:10:25 AM","Suspect"
 "Result Measure Qualifier(MeasureQualifierCode)",67,"N","Presumptive evidence of a nontarget compound","8/22/2013 1:44:00 PM","Pass"
 "Result Measure Qualifier(MeasureQualifierCode)",290,NA,"Not Applicable","11/14/2016 2:52:56 PM","Pass"
@@ -219,6 +226,7 @@
 "Result Measure Qualifier(MeasureQualifierCode)",1000,"SSRV","Surrogate or spike recovery value associated with sample analyte or analytes","5/23/2022 8:46:36 AM","Suspect"
 "Result Measure Qualifier(MeasureQualifierCode)",221,"SUS","Result value is defined as suspect by data owner. (HV) High variability: questionable precision and accuracy","8/30/2016 4:56:40 PM","Suspect"
 "Result Measure Qualifier(MeasureQualifierCode)",108,"T","Hardness by Calculation Method - Standard Methods 2340B - 19th Ed ","9/3/2014 12:00:00 AM","Pass"
+"Result Measure Qualifier(MeasureQualifierCode)",1187,"T5","Laboratory not licensed for this parameter","7/18/2024 8:49:50 PM","Not Reviewed"
 "Result Measure Qualifier(MeasureQualifierCode)",707,"TMLF","Time missing in logger file.","7/30/2019 7:36:04 AM","Suspect"
 "Result Measure Qualifier(MeasureQualifierCode)",112,"TOC","Temperature outside of criteria","4/9/2015 9:10:23 AM","Suspect"
 "Result Measure Qualifier(MeasureQualifierCode)",839,"TR","Trace","1/8/2024 4:44:57 PM","Pass"
@@ -228,6 +236,7 @@
 "Result Measure Qualifier(MeasureQualifierCode)",832,"UDQ","Lab's detection limit not known/available for comparison to the result; however with parameter specific evaluation determined to be quantified.","4/10/2020 6:07:22 PM","Suspect"
 "Result Measure Qualifier(MeasureQualifierCode)",188,"UNC","Value Not Confirmed","3/16/2016 1:04:27 PM","Suspect"
 "Result Measure Qualifier(MeasureQualifierCode)",749,"V","Surrogate recoveries out of range","12/16/2019 12:53:17 PM","Suspect"
+"Result Measure Qualifier(MeasureQualifierCode)",1190,"V1","Continuing calibration verification (CCV) recovery was above method acceptance limits","7/18/2024 8:49:50 PM","Not Reviewed"
 "Result Measure Qualifier(MeasureQualifierCode)",1167,"VS","compound identified verified by 2nd method","8/16/2021 11:03:38 AM","Pass"
 "Result Measure Qualifier(MeasureQualifierCode)",758,"VVRR","Value verified by rerun","8/18/2020 1:54:00 PM","Pass"
 "Result Measure Qualifier(MeasureQualifierCode)",1172,"VVRR2","value verified by rerun, 2nd method","8/16/2021 11:08:55 AM","Pass"

diff --git a/man/TADA_FlaggedSitesMap.Rd b/man/TADA_FlaggedSitesMap.Rd
diff --git a/man/TADA_TwoCharacteristicScatterplot.Rd b/man/TADA_TwoCharacteristicScatterplot.Rd
diff --git a/tests/testthat/test-Utilities.R b/tests/testthat/test-Utilities.R
@@ -7,3 +7,4 @@ test_that("TADA_AutoClean function does not grow dataset", {
   testautoclean2 <- TADA_AutoClean(testautoclean1)
   expect_true(dim(testautoclean1)[1] == dim(testautoclean2)[1])
 })
+
diff --git a/vignettes/TADAModule1.Rmd b/vignettes/TADAModule1.Rmd
@@ -71,7 +71,7 @@ GitHub (un-comment).
 
 ```{r install_TADA, eval = F, results = 'hide'}
 remotes::install_github("USEPA/EPATADA",
-  ref = "develop",
+  ref = "502-tadacomparabledataidentifier-column-showing-na-for-the-tadaresultmeasuremeasureunitcode-portion-of-its-string-pasting",
   dependencies = TRUE
 )
 # remotes::install_github("USGS-R/dataRetrieval", dependencies=TRUE)

diff --git a/vignettes/TADAModule1_AdvancedTraining.Rmd b/vignettes/TADAModule1_AdvancedTraining.Rmd
@@ -101,7 +101,7 @@ them (enter 1 into the console).
 
 ```{r install_TADA, eval = F, results = 'hide'}
 remotes::install_github("USEPA/EPATADA",
-  ref = "develop",
+  ref = "502-tadacomparabledataidentifier-column-showing-na-for-the-tadaresultmeasuremeasureunitcode-portion-of-its-string-pasting",
   dependencies = TRUE
 )
 ```

diff --git a/vignettes/TADAModule1_BeginnerTraining.Rmd b/vignettes/TADAModule1_BeginnerTraining.Rmd
@@ -83,7 +83,7 @@ console).
 
 ```{r install_TADA, eval = F, results = 'hide'}
 remotes::install_github("USEPA/EPATADA",
-  ref = "develop",
+  ref = "502-tadacomparabledataidentifier-column-showing-na-for-the-tadaresultmeasuremeasureunitcode-portion-of-its-string-pasting",
   dependencies = TRUE
 )
 

diff --git a/vignettes/TADAModule2.Rmd b/vignettes/TADAModule2.Rmd
@@ -73,7 +73,7 @@ console).
 
 ```{r install_TADA, eval = F, results = 'hide'}
 remotes::install_github("USEPA/EPATADA",
-  ref = "develop",
+  ref = "502-tadacomparabledataidentifier-column-showing-na-for-the-tadaresultmeasuremeasureunitcode-portion-of-its-string-pasting",
   dependencies = TRUE
 )
 ```
Original file line number	Diff line number	Diff line change
Expand Up		@@ -7,3 +7,4 @@ test_that("TADA_AutoClean function does not grow dataset", {
		testautoclean2 <- TADA_AutoClean(testautoclean1)
		expect_true(dim(testautoclean1)[1] == dim(testautoclean2)[1])
		})