USEPA · cristinamullin · Jul 10, 2025 · Jul 2, 2025 · Jul 2, 2025 · Jul 2, 2025
diff --git a/R/Utilities.R b/R/Utilities.R
@@ -196,12 +196,19 @@ TADA_CheckColumns <- function(.data, expected_cols) {
 #' converted to an average of the two numbers. Result values
 #' containing any other text or non-numeric characters become NA in
 #' the newly created "TADA.COLUMN NAME" and labeled accordingly in "TADA.COLUMN
-#' NAME DataTypes.Flag".
+#' NAME DataTypes.Flag". When clean = TRUE, rows that cannot be converted to
+#' numeric are removed. When clean = FALSE, no rows are removed. Default is
+#' clean = FALSE. When flaggedonly = TRUE, data frame is filtered to show only
+#' rows with non-numeric result values. Default is flaggedonly = FALSE.
 #'
 #'
 #' @param .data A TADA profile object
 #' @param col A character column to be converted to numeric
-#'
+#' @param clean Boolean argument; removes non-numeric result values from the
+#' data frame when clean = TRUE. Default is clean = FALSE.
+#' @param flaggedonly Boolean argument; filters dataframe to show only
+#' non-numeric result values when flaggedonly = TRUE. Default is flaggedonly
+#' = FALSE.
 #' @param percent.ave Boolean argument; default is percent.ave = TRUE. When
 #' clean = TRUE, any percent range values will be averaged. When
 #' percent.ave = FALSE, percent range values are not averaged, but are flagged.
@@ -229,11 +236,17 @@ TADA_CheckColumns <- function(.data, expected_cols) {
 #'   )
 #' unique(HandleSpecialChars_DetLimMeasureValue$
 #'   TADA.DetectionQuantitationLimitMeasure.MeasureValueDataTypes.Flag)
-TADA_ConvertSpecialChars <- function(.data, col, percent.ave = TRUE) {
+TADA_ConvertSpecialChars <- function(.data, col, percent.ave = TRUE,
+                                     clean = FALSE, flaggedonly = FALSE) {
   if (!col %in% names(.data)) {
     stop("Suspect column name specified for input dataset.")
   }
 
+  # check that clean and flaggedonly are not both TRUE
+  if (clean == TRUE & flaggedonly == TRUE) {
+    stop("Function not executed because clean and flaggedonly cannot both be TRUE")
+  }
+
   # Define new column names
   numcol <- paste0("TADA.", col)
   flagcol <- paste0("TADA.", col, "DataTypes.Flag")
@@ -353,7 +366,23 @@ TADA_ConvertSpecialChars <- function(.data, col, percent.ave = TRUE) {
 
   clean.data <- TADA_OrderCols(clean.data)
 
-  return(clean.data)
+  if (flaggedonly == FALSE) {
+    if (clean == TRUE) {
+      clean.data <- clean.data %>%
+        dplyr::filter(!(!!rlang::sym(flagcol)) %in% c("NA - Not Available", "Text"))
+
+      return(clean.data)
+    }
+
+    if (clean == FALSE) {
+      return(clean.data)
+    }
+  }
+
+  if (flaggedonly == TRUE) {
+    clean.data <- clean.data %>%
+      dplyr::filter(!!rlang::sym(flagcol) %in% c("NA - Not Available", "Text"))
+  }
 }
 
 #' Substitute Preferred Characteristic Name for Deprecated Names

diff --git a/R/autoFilter.R b/R/autoFilter.R
@@ -412,21 +412,14 @@ TADA_AnalysisDataFilter <- function(.data,
 
 #' AutoFilter
 #'
-#' This function removes rows where the result value is not numeric to
-#' prepare a dataframe for quantitative analyses. Ideally, this function should
-#' be run after other data cleaning, QA/QC, and harmonization steps are
-#' completed using other TADA package functions, or manually. Specifically,
-#' this function removes rows with "Text" and "NA - Not Available"
-#' in the TADA.ResultMeasureValueDataTypes.Flag column, or NA in the
-#' TADA.ResultMeasureValue column. In addition, this function removes results
-#' with QA/QC ActivityTypeCode's. This function also removes any columns not
-#' required for TADA workflow where all values are equal to NA. It provides a
-#' warning message identifying any TADA required columns containing only NA
-#' values.
+#' This function also removes any columns not required for the TADA workflow
+#' where all values are equal to NA. It provides a warning message identifying
+#' any TADA required columns containing only NA values.
 #'
 #' @param .data TADA dataframe
 #'
-#' @return .data with rows non-quantitative and QA/QC results removed
+#' @return .data with any non-required columns containing only NA values
+#' removed.
 #'
 #' @export
 #'
@@ -436,41 +429,18 @@ TADA_AutoFilter <- function(.data) {
   # check .data is data.frame
   TADA_CheckType(.data, "data.frame", "Input object")
 
-  TADA_CheckColumns(.data, c(
-    "ActivityTypeCode", "MeasureQualifierCode",
-    "TADA.ResultMeasureValueDataTypes.Flag",
-    "TADA.ResultMeasureValue", "TADA.ActivityMediaName",
-    "ActivityTypeCode"
-  ))
-
-  # keep track of starting and ending number of rows
-  start <- dim(.data)[1]
-
-  # run TADA_FindQCActivities if needed
-  if (("TADA.ActivityType.Flag" %in% colnames(.data)) == TRUE) {
-    .data <- .data
-  }
-
-  if (("TADA.ActivityType.Flag" %in% colnames(.data)) == FALSE) {
-    .data <- TADA_FindQCActivities(.data, clean = FALSE, flaggedonly = FALSE)
-  }
-
-  # remove text, NAs and QC results
-  .data <- dplyr::filter(.data, TADA.ResultMeasureValueDataTypes.Flag != "Text" &
-    TADA.ResultMeasureValueDataTypes.Flag != "NA - Not Available" &
-    TADA.ActivityType.Flag == "Non_QC" & # filter out QA/QC ActivityTypeCode's
-    !is.na(TADA.ResultMeasureValue))
-
   # remove columns that are not required for TADA workflow
-  print("TADA_Autofilter: removing columns not required for TADA workflow if they contain only NAs.")
+  print("TADA_AutoFilter: removing columns not required for TADA workflow if they contain only NAs.")
 
   # create list of columns containing all NA values.
   na.cols <- .data %>%
     purrr::keep(~ all(is.na(.x))) %>%
     names()
 
-  # create list of columns to be removed by comparing columns containing all NA values to required columns.
-  # any required columns with all NA values will be excluded from the list of columns to remove.
+  # create list of columns to be removed by comparing columns containing all NA
+  # values to required columns.
+  # any required columns with all NA values will be excluded from the list of
+  # columns to remove.
   remove.cols <- setdiff(na.cols, require.cols)
 
   # remove not required columns containing all NA values from dataframe.
@@ -489,33 +459,27 @@ TADA_AutoFilter <- function(.data) {
   # create character string for list of removed columns
   remove.paste <- stringi::stri_replace_last_fixed(paste(as.character(remove.cols), collapse = ", ", sep = ""), ", ", " and ")
 
-  # print list of columns removed from dataframe
+  # print list of columns removed from data frame
   if (length(remove.cols) > 0) {
-    print(paste0("The following column(s) were removed as they contained only NAs: ", remove.paste, "."))
+    print(paste0("The following column(s) were removed as they contained only NAs ",
+                 "and are not required for the TADA workflow: ", remove.paste, "."))
   } else {
     print("All columns contained some non-NA values and were retained in the dataframe.")
   }
 
   # remove columns that are not required for TADA workflow
-  print("TADA_Autofilter: checking required columns for non-NA values.")
+  print("TADA_AutoFilter: checking required columns for non-NA values.")
 
   # if some required columns contain only NA values print a warning message.
   if (length(req.check) > 0) {
-    print(paste0("TADA Required column(s) ", req.paste, " contain only NA values. This may impact other TADA functions."))
+    print(paste0("TADA_AutoFilter: TADA Required column(s) ", req.paste,
+                 " contain only NA values. This may impact other TADA functions."))
   } else {
-    print("All TADA Required columns contain some non-NA values.")
+    print("TADA_AutoFilter: All TADA Required columns contain some non-NA values.")
   }
 
   # remove intermediate objects
   rm(req.paste, remove.cols, remove.paste, req.check)
 
-  end <- dim(.data)[1]
-
-  # print number of results removed
-  if (!start == end) {
-    net <- start - end
-    print(paste0("Function removed ", net, " results. These results are either text or NA and cannot be plotted or represent quality control activities (not routine samples or measurements)."))
-  }
-
   return(.data)
 }
diff --git a/man/TADA_AutoFilter.Rd b/man/TADA_AutoFilter.Rd
diff --git a/man/TADA_ConvertSpecialChars.Rd b/man/TADA_ConvertSpecialChars.Rd