Follow-up on feedback from CAA

NAMESPACE

@@ -20,6 +20,9 @@ export(abs_to_rel)
 export(albarede_juteau_1984)
 export(as_ASTR)
 export(at_to_wt)
+export(bdl_strategy_default)
+export(bdl_strategy_negative)
+export(bdl_strategy_none)
 export(copper_alloy_bb)
 export(copper_alloy_pollard)
 export(copper_group_bray)

R/ASTR_basic.R

@@ -12,8 +12,8 @@
 #' \itemize{
 #'   \item **as_ASTR**: Transforms an R `data.frame` to an object of class
 #'   `ASTR`.
-#'   \item **read_ASTR**: Reads data from a file (.csv, .xls, .xlsx) into
-#'   an object of class `ASTR`.
+#'   \item **read_ASTR**: Reads data from a file (.csv, .xls, .xlsx) and
+#'   converts it into an object of class `ASTR`.
 #'   \item **validate**: Performs additional validation on `ASTR` and returns
 #'   a `data.frame` as a workable list of potential issues.
 #'   \item **get_..._columns**: Subsets `ASTR` tables to columns of a certain
@@ -33,10 +33,9 @@
 #' @param id_column name of the ID column. Defaults to "ID"
 #' @param context columns that provide contextual (non-measurement) information;
 #'   may be column names, integer positions, or a logical inclusion vector
-#' @param bdl strings representing “below detection limit” values. By default,
-#'   the following are recognized: "b.d.", "bd", "b.d.l.", "bdl", "<LOD", "<"
-#' @param bdl_strategy function used to replace BDL strings. Defaults to a
-#'   static function returning `NA`
+#' @param bdl_strategy function used to replace "below detection limit" strings.
+#'   See [bdl_strategies] for the different available strategies and on how to implement
+#'   a custom one.
 #' @param guess_context_type should appropriate data types for contextual
 #'   columns be guessed automatically? Defaults to `TRUE`
 #' @param na character vector of strings to be interpret as missing values. By
@@ -66,15 +65,6 @@
 #'   unless `drop_columns = TRUE` (then it will result in warnings for the
 #'   respective columns).
 #'
-#'   Below detection limit notation (i.e. ‘b.d.’, ‘bd’, ‘b.d.l.’, ‘bdl’, ‘<LOD’,
-#'   or ‘<..’) for element and oxide concentrations is specified using the `bdl`
-#'   argument. One or more notations can be used as is appropriate for the
-#'   dataset, and can be notations not included in the list above. The argument
-#'   `bdl_strategy` is used to specify the value for handling detection limits.
-#'   This is to facilitate the different handling needs of the detection limit
-#'   for future statistical applications, as opposed to automatically assigning
-#'   such values as ‘NA’.
-#'
 #'   Missing values are allowed anywhere in the data file body, and will be
 #'   replaced by `NA` automatically.
 #'
@@ -120,12 +110,7 @@
 #' @export
 as_ASTR <- function(
   df, id_column = "ID", context = c(),
-  bdl = c("b.d.", "bd", "b.d.l.", "bdl", "<LOD", "<"),
-  bdl_strategy = function() NA_character_,
-  # this only allows static functions, essentially: bdl_replace = "NA"
-  # in case more sophisticated handling is desired:
-  # bdl_strategy = function(x, colname) { bdl_lookup_table[colname] / sqrt(2) }
-  # bdl_lookup_table = c("Fe_%" = 3)
+  bdl_strategy = bdl_strategy_default,
   guess_context_type = TRUE,
   na = c(
     "", "n/a", "NA", "N.A.", "N/A", "na", "-", "n.d.", "n.a.",
@@ -166,7 +151,7 @@ as_ASTR <- function(
     dplyr::ungroup()
   # determine and apply column types
   column_table <- parse_colnames(df2, context, drop_columns)
-  constructors <- build_constructors(column_table, bdl, bdl_strategy, guess_context_type, na)
+  constructors <- build_constructors(column_table, bdl_strategy, guess_context_type, na)
   col_list <- purrr::map2(df2, constructors, function(col, f) f(col)) %>%
     purrr::discard(is.null)
   df3 <- as.data.frame(col_list, check.names = FALSE)
@@ -222,8 +207,7 @@ read_ASTR <- function(
     "", "n/a", "NA", "N.A.", "N/A", "na", "-", "n.d.", "n.a.",
     "#DIV/0!", "#VALUE!", "#REF!", "#NAME?", "#NUM!", "#N/A", "#NULL!"
   ),
-  bdl = c("b.d.", "bd", "b.d.l.", "bdl", "<LOD", "<"),
-  bdl_strategy = function() NA_character_,
+  bdl_strategy = bdl_strategy_default,
   drop_columns = FALSE,
   validate = TRUE,
   ...
@@ -284,7 +268,7 @@ read_ASTR <- function(
   as_ASTR(
     input_file,
     id_column = id_column, context = context,
-    bdl = bdl, bdl_strategy = bdl_strategy,
+    bdl_strategy = bdl_strategy,
     guess_context_type = guess_context_type, na = na,
     drop_columns = drop_columns,
     validate = validate

R/ASTR_bdl_strategies.R

@@ -0,0 +1,39 @@
+#' @name bdl_strategies
+#'
+#' @title Strategies to replace "below detection limit" values
+#'
+#' @description ...
+#'
+#' @param x a vector, derived from a data.frame column
+#' @param colname name of the respective data.frame column
+#' @param ... further arguments passed to or from other methods
+#'
+#' @rdname bdl_strategies
+#'
+#' @examples
+#' plot(1,1)
+#'
+NULL
+
+#' @rdname bdl_strategies
+#' @export
+bdl_strategy_default <- function(x, colname, ...) {
+  bdl_strings <- c("b.d.", "bd", "b.d.l.", "bdl", "<LOD", "<")
+  bdl_indices <- which(grepl(paste(bdl_strings, collapse = "|"), x, perl = FALSE))
+  x[bdl_indices] <- NA_character_
+  return(x)
+}
+
+#' @rdname bdl_strategies
+#' @export
+bdl_strategy_none <- function(x, colname, ...) {
+  return(x)
+}
+
+#' @rdname bdl_strategies
+#' @export
+bdl_strategy_negative <- function(x, colname, ...) {
+  bdl_indices <- which(grepl("^-\\d*\\.?\\d*\\*?\\d*\\^?\\-?\\d*$", x))
+  x[bdl_indices] <- NA_character_
+  return(x)
+}

R/ASTR_colname_parser.R

@@ -206,7 +206,7 @@ parse_colnames <- function(x, context, drop_columns) {
 # 2. build constructor functions
 build_constructors <- function(
   column_table,
-  bdl, bdl_strategy,
+  bdl_strategy,
   guess_context_type, na
 ) {
   purrr::pmap(
@@ -224,7 +224,7 @@ build_constructors <- function(
         function(x) {
           # bdl
           if (consider_bdl) {
-            x <- apply_bdl_strategy(x, colname, bdl, bdl_strategy)
+            x <- bdl_strategy(x = x, colname = colname)
           }
           # type
           if (type == "numeric") {
@@ -268,14 +268,6 @@ as_numeric_info <- function(x, colname) {
   return(y)
 }
 
-# colname only an argument in case we want to implement more specific handling
-# eventually
-apply_bdl_strategy <- function(x, colname, bdl, bdl_strategy) {
-  bdl_values <- which(grepl(paste(bdl, collapse = "|"), x, perl = FALSE))
-  x[bdl_values] <- bdl_strategy()
-  return(x)
-}
-
 #### regex validators ####
 
 is_err_percent <- function(colname) {

vignettes/ASTR.showcase.Rmd

@@ -57,7 +57,7 @@ data
 
 Note how the column headers are organised according to the ASTR conventions. This allows the package to _understand_ some of the semantics of the dataset in the `read_ASTR()` process, and correctly represent them in the resulting `ASTR` object. A closer look at the mock-up data also reveals (common) problems with the copper isotope data: it seems that some Excel formulas did not work as intended and left `#REF!` entries. `read_ASTR()` will read these as `NA` values. Finally, every `ASTR` object requires one column that acts as a unique row identifier. In this dataset there is no such column, though, only a `Group` identifier. `read_ASTR()` can automatically turn such a column to a unique identifier.
 
-We can now perform the reading process. As we are working with mock-up data in an R vignette, we do not read from the file system. We only need to call an essential internal function of `read_ASTR()`: `as_ASTR()`. It turns R data.frames to `ASTR` objects. If we would start from an Excel file we would call `read_ASTR()` instead.
+We can now perform the reading process. As we are working with mock-up data in an R vignette, we do not read from the file system. We only need to call an essential internal function of `read_ASTR()`: `as_ASTR()`. It turns R data.frames to `ASTR` objects. If we would start from an Excel file we would call `read_ASTR()` instead, which internally calls `as_ASTR()` to convert the data into an ASTR object after reading the file.
 
 To do this in practice, we not only have to submit our `data` to `as_ASTR()`, but also set two other arguments: 1. We have to define one of the columns as the ID column with `id_column`, and 2. we explicitly have to mark any column providing contextual information with `context` (i.e. no analytical values, cf. [ASTR schema: Implementation](VG.ASTR.Schema.Implementation.html)).