fix cran submission issues

Author: Karim-Mane

CRAN-SUBMISSION

@@ -1,3 +1,3 @@
-Version: 1.0.0
-Date: 2024-06-13 15:49:31 UTC
-SHA: 347316e702882365c29a470fb39578875a2b7dbb
+Version: 1.0.1
+Date: 2024-06-13 19:21:41 UTC
+SHA: a28e97c0cd96fb15e85b41e487485c089edebf95

DESCRIPTION

@@ -5,33 +5,36 @@ Authors@R: c(
     person("Karim", "Mané", , "[email protected]", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0002-9892-2999")),
     person("Thibaut", "Jombart", , "[email protected]", role = "cph",
-           comment = c("Thibault is the owner of the code in guess_dates.R file.")),
+           comment = "Thibault is the owner of the code in guess_dates.R file."),
     person("Bubacarr", "Bah", , "[email protected]", role = "aut",
            comment = c(ORCID = "0000-0003-3318-6668")),
     person("Bankolé", "Ahadzie", , "[email protected]", role = "aut"),
     person("Nuredin", "Mohammed", , "[email protected]", role = "aut"),
-    person("Abdoelnaser", "Degoot", , "[email protected]", role = "aut", 
-          comment = c(ORCID = "0000-0001-8788-2496")),
-    person("Hugo", "Gruson", , "[email protected]", role = "rev", 
-          comment = c(ORCID = "0000-0002-4094-1476")),
-    person("Pratik R.", "Gupte", , "[email protected]", role ="rev",
+    person("Abdoelnaser", "Degoot", , "[email protected]", role = "aut",
+           comment = c(ORCID = "0000-0001-8788-2496")),
+    person("Hugo", "Gruson", , "[email protected]", role = "rev",
+           comment = c(ORCID = "0000-0002-4094-1476")),
+    person("Pratik R.", "Gupte", , "[email protected]", role = "rev",
            comment = c(ORCID = "0000-0001-5294-7819")),
     person("James M.", "Azam", , "[email protected]", role = "rev",
-           comment = c(ORCID = "0000-0001-5782-7330")),  
+           comment = c(ORCID = "0000-0001-5782-7330")),
     person("Joshua W.", "Lambert", , "[email protected]", role = "rev",
            comment = c(ORCID = "0000-0001-5218-3046")),
     person("Chris", "Hartgerink", , "[email protected]", role = "rev",
            comment = c(ORCID = "0000-0003-1050-6809")),
     person("London School of Hygiene and Tropical Medicine, LSHTM", role = "cph"),
     person("data.org", role = "fnd")
   )
-Description: cleanepi provides functions for cleaning and standardizing tabular data,
-    tailored specifically for curating epidemiological data.
+Description: Cleaning and standardizing tabular data package, tailored
+    specifically for curating epidemiological data. It streamlines various data
+    cleaning tasks that are typically expected when working with datasets in
+    epidemiology. It returns the processed data in the same format, ensuring
+    seamless integration into existing workflows. Additionally, it generates a
+    comprehensive report detailing the outcomes of each cleaning task.
 License: MIT + file LICENSE
 URL: https://epiverse-trace.github.io/cleanepi/,
     https://github.com/epiverse-trace/cleanepi
 BugReports: https://github.com/epiverse-trace/cleanepi/issues
-Language: en-US
 Imports:
     arsenal,
     checkmate,
@@ -62,6 +65,7 @@ VignetteBuilder:
 Config/Needs/website: epiverse-trace/epiversetheme
 Config/testthat/edition: 3
 Encoding: UTF-8
+Language: en-US
 LazyData: true
 Roxygen: list(markdown = TRUE)
 RoxygenNote: 7.3.1

R/clean_data.R

@@ -124,7 +124,7 @@ clean_data <- function(data, params = NULL) {
   ## | Column names in 'keep' will not be modified.
   ## -----
   if (!is.null(params[["standardize_column_names"]])) {
-    base::cat("\ncleaning column names\n")
+    message("\ncleaning column names\n")
     data <- standardize_column_names(
       data   = data,
       keep   = params[["standardize_column_names"]][["keep"]],
@@ -139,7 +139,7 @@ clean_data <- function(data, params = NULL) {
   ## | user if known, or inferred internally otherwise.
   ## -----
   if (!is.null(params[["replace_missing_values"]])) {
-    base::cat("replacing missing values with NA\n")
+    message("replacing missing values with NA\n")
     data <- replace_missing_values(
       data           = data,
       target_columns = params[["replace_missing_values"]][["target_columns"]],
@@ -151,7 +151,7 @@ clean_data <- function(data, params = NULL) {
   ## | we can choose to remove the constant columns, the empty rows and columns
   ## -----
   if (!is.null(params[["remove_constants"]])) {
-    base::cat("removing the constant columns, empty rows and columns\n")
+    message("removing the constant columns, empty rows and columns\n")
     data <- remove_constants(
       data   = data,
       cutoff = params[["remove_constants"]][["cutoff"]]
@@ -166,7 +166,7 @@ clean_data <- function(data, params = NULL) {
   ## | duplicates will only be considered from the specified columns.
   ## -----
   if (!is.null(params[["remove_duplicates"]])) {
-    base::cat("removing duplicated rows\n")
+    message("removing duplicated rows\n")
     data <- remove_duplicates(
       data,
       target_columns = params[["remove_duplicates"]][["target_columns"]]
@@ -179,7 +179,7 @@ clean_data <- function(data, params = NULL) {
   ## | easy to apply the functions that operate on variables of type Date.
   ## -----
   if (!is.null(params[["standardize_dates"]])) {
-    base::cat("standardising date columns\n")
+    message("standardising date columns\n")
     data <- standardize_dates(
       data            = data,
       target_columns  = params[["standardize_dates"]][["target_columns"]],
@@ -199,7 +199,7 @@ clean_data <- function(data, params = NULL) {
   ## | redundant subject ID.
   ## -----
   if (!is.null(params[["standardize_subject_ids"]])) {
-    base::cat("checking subject IDs format\n")
+    message("checking subject IDs format\n")
     stopifnot(
       "'target_columns' must be provided." =
         !is.null(params[["standardize_subject_ids"]][["target_columns"]])
@@ -220,7 +220,7 @@ clean_data <- function(data, params = NULL) {
   ## | homogeneous.
   ## -----
   if (!is.null(params[["to_numeric"]])) {
-    base::cat(
+    message(
       "converting",
       paste(params[["to_numeric"]], sep = ", "),
       "into numeric\n"
@@ -238,7 +238,7 @@ clean_data <- function(data, params = NULL) {
   ## replace these coded values with the exact values from the data dictionary.
   ## -----
   if (!is.null(params[["dictionary"]])) {
-    base::cat("performing dictionary-based cleaning\n")
+    message("performing dictionary-based cleaning\n")
     data <- clean_using_dictionary(data, params[["dictionary"]])
   }
 
@@ -248,7 +248,7 @@ clean_data <- function(data, params = NULL) {
   ## will be flagged out.
   ## -----
   if (!is.null(params[["check_date_sequence"]])) {
-    base::cat("checking whether date the sequences are respected\n")
+    message("checking whether date the sequences are respected\n")
     data <- check_date_sequence(
       data           = data,
       target_columns = params[["check_date_sequence"]][["target_columns"]]

R/guess_dates.R

@@ -24,48 +24,6 @@
 #'    than one format. If all values comply with only one format, the later
 #'    element will be NULL.
 #'
-#' @examples
-#' \dontrun{
-#' # Mixed format date -----------------------------------------
-#'
-#' guess_dates(c("03 Jan 2018", "07/03/1982", "08/20/85")) # default
-#'
-#' # Prioritizing specific date formats ------------------------
-#' #
-#' # The default orders prioritize world date ordering over American-style.
-#' orders <- list(
-#'   world_named_months = c("Ybd", "dby"),
-#'   world_digit_months = c("dmy", "Ymd"),
-#'   US_formats         = c("Omdy", "YOmd")
-#' )
-#'
-#' # if you want to prioritize American-style dates with numeric months, you
-#' # can switch the second and third elements of the default orders
-#'
-#' print(us_ord <- orders[c(1, 3, 2)])
-#' date_guess(c("03 Jan 2018", "07/03/1982", "08/20/85"), orders = us_ord)
-#'
-#' # Handling dates with time formats --------------------------
-#' #
-#' # If you have a format with hours, minutes and seconds, you can also add that
-#' # to the list of formats. Note, however, that this function will drop levels
-#' # below day.
-#'
-#' print(orders$ymdhms <- c("Ymdhms", "Ymdhm"))
-#'
-#' date_guess(c("2014_04_05_23:15:43", "03 Jan 2018",
-#' "07/03/1982", "08/20/85"), orders = orders)
-#'
-#' # Handling  missing and nonsense data -----------------------
-#' #
-#' # date_guess can handle messy dates and tolerate missing data
-#'
-#' x <- c("01-12-2001", "male", "female", "2018-10-18", NA, NA, "2018_10_17",
-#'        "43391", "2018 10 19", "// 24/12/1989", "this is 24/12/1989!",
-#'        "RECON NGO: 19 Sep 2018 :)", "6/9/11", "10/10/10")
-#'
-#' date_guess(x)
-#' }
 #' @keywords internal
 #'
 date_guess <- function(x,

R/print_report.R

@@ -13,7 +13,7 @@
 #'
 #' @returns A string containing the name and path of the saved report
 #' @examples
-#' \dontrun{
+#' \donttest{
 #' data <- readRDS(system.file("extdata", "test_df.RDS", package = "cleanepi"))
 #' test_dictionary <- readRDS(system.file("extdata", "test_dictionary.RDS",
 #'                                        package = "cleanepi"))

cran-comments.md

@@ -7,3 +7,13 @@
 ## revdepcheck results
 
 * There are currently no downstream dependencies for this package.
+
+## Resubmission
+
+This is a resubmission. In this version I have fixed the NOTE raised during the
+previous submission. The changes include:
+
+* Updating inst/WORDLIST with the new words that were missing.
+* Adding a '/' to the package Github link in the DESCRIPTION file.
+* Removing "Type: Package" from the DESCRIPTION file.
+* Update package description from the DESCRIPTION file.