Merge branch 'modularize_cleanepi' of https://github.com/epiverse-tra…

…ce/cleanepi into modularize_cleanepi

R/clean_data.R

@@ -1,11 +1,58 @@
 #' Clean data
 #'
-#' @description this function cleans up messy data frames by performing several operations. These Include
+#' @description Cleans up messy data frames by performing several operations. These Include
 #'    cleaning of column names, detecting and removing
 #'    duplicates, empty records and columns, constant columns, replacing missing
 #'    values by NA, converting character columns into dates when they contain a
 #'    certain number of date values, and detecting subject IDs with wrong format
 #'
+<<<<<<< HEAD
+#' @param data A data frame
+#' @param params A list of parameters that define what cleaning operations will
+#'    be applied on the input data. Possible parameters are:
+#' \enumerate{
+#'   \item `remove_duplicates`: A logical variable to indicate whether to remove duplicated records or not. If
+#'        set `TRUE`, it calls the `remove_duplicate()` function
+#'        with parameter `remove` set to `NULL` i.e., to keep only the first instance
+#'        of duplicated rows. If you only want to detect duplicated rows in the dataset, use
+#'        the `find_duplicates()` function.
+#'   \item `target_columns`: A vector of columns names or indices to consider
+#'        when looking for duplicates. this
+#'        parameter can be set to `tags`from which duplicates to be removed.
+#'   \item `replace_missing`: A logical variable that indicates whether to replace missing value characters
+#'          with NA or not. The default value is `FALSE`.
+#'   \item `na_comes_as`: A string that represents the missing values in
+#'         the data frame. This only required when `replace_missing=TRUE`.
+#'   \item `check_timeframe`: A logical variable that determines whether to check if the
+#'         dates fall under the given time frame of not. default: `FALSE`.
+#'   \item `timeframe`: A vector of 2 dates that specifies the
+#'         first and last date. If provided, all Dates in the data frame must be
+#'         within this range or set to NA during the cleaning.
+#'   \item `error_tolerance`: A number between 0 and 1 indicating the proportion
+#'         of entries which cannot be identified as dates to be tolerated; if
+#'         this proportion is exceeded, the original vector is returned, and a
+#'         message is issued; defaults to 0.1 (10 percent).
+#'   \item `subject_id_col_name`: A column name of subject IDs
+#'   \item `subject_id_format`: A expected subject format
+#'   \item `prefix`: A prefix used in the subject IDs.
+#'   \item `suffix`: A suffix used in the subject IDs.
+#'   \item `range`: A vector with the range of numbers in the subject IDs.
+#'   \item `dictionary`: A data frame of data
+#'         dictionary that will be used to clean the specified columns. Use
+#'         `?clean_using_dictionary` for more details.
+#'   \item `range`: A vector with the range of numbers in the sample IDs
+#'   \item `keep`: A vector of column names to be kept as they appear
+#'          in the original data. default is `NULL`
+#'   }
+#'
+#' @return a list of the following 2 elements:
+#'  \enumerate{
+#'    \item `data`: A  clean data frame  according to the user-specified
+#'          parameters.
+#'    \item `report`: A list with  details from each
+#'          cleaning operation considered.
+#'  }
+=======
 #' @param data the input data frame
 #' @param params a list of parameters that define what cleaning operations will
 #'    be applied on the input data. Possible values are:
@@ -34,6 +81,7 @@
 #'   }
 #'
 #' @return the cleaned data frame according to the user-specified parameters
+>>>>>>> 66c2fcf5d40a69a7f0be86afa08fa94a89e0dcad
 #' @export
 #'
 #' @examples

R/find_and_remove_duplicates.R

@@ -1,15 +1,15 @@
 #' Remove duplicates and constant rows and columns
 #'
 #' @description
-#' Remove duplicates and noise such as  empty rows and
+#' Removes duplicates and noise such as  empty rows and
 #' columns, and constant columns. These operations are
 #' automatically performed by default unless specified otherwise.
 #' Users can specify a set columns to consider when removing
 #' duplicates with the 'target_columns' argument.
 #'
-#' @param data The input data frame or linelist.
+#' @param data A input data frame or linelist.
 #' @param target_columns A vector of column names to use when looking for
-#'    duplicates. When the input data is a `linelist` object, this
+#'    duplicates. When the input data is a `linelist`, this
 #'    parameter can be set to `tags`from which duplicates to be removed.
 #'    Its default value is `NULL`, which considers duplicates across all columns.
 #' @param remove A vector of duplicate indices to be removed. Duplicate indices
@@ -24,7 +24,7 @@
 #' @param rm_constant_cols A logical variable that is used to specify whether to remove
 #'     constant columns or not. Its Default value is `TRUE`.
 #'
-#' @return The input data without the duplicates values.
+#' @return A  data frame or linelist  without the duplicates values and nor constant columns.
 #' @export
 #'
 #' @examples
@@ -97,7 +97,7 @@ remove_duplicates <- function(data,
 
   # remove duplicates
   if (is.null(remove)) {
-    # remove duplicates by keeping the first instance of the duplicate in each
+    # remove duplicates and keep the first instance of the duplicate in each
     # duplicate group
     dat <- dat %>%
       dplyr::distinct_at({{ target_columns }}, .keep_all = TRUE)
@@ -126,11 +126,11 @@ remove_duplicates <- function(data,
 
 #' Identify and return duplicated rows in a data frame or linelist.
 #'
-#' @param data The input data frame or linelist.
+#' @param data A data frame or linelist.
 #' @param target_columns A vector of columns names or indices to consider when
-#'    looking for duplicates. When the input data is a `linelist` object,
-#'    this parameter can be set to `tags` if you wish to look for
-#'    duplicates across the tagged variables only.
+#'    looking for duplicates. When the input data is a `linelist` object, this
+#'    parameter can be set to `tags`from which duplicates to be removed.
+#'    Its default value is `NULL`, which considers duplicates across all columns.
 #'
 #' @return Data frame or linelist of all duplicated rows with following 2
 #'    additional columns:
@@ -178,11 +178,11 @@ find_duplicates <- function(data, target_columns = NULL) {
 
 #' Get the names of the columns from which duplicates will be found
 #'
-#' @param data the input dataset
-#' @param target_columns the user specified target column name
+#' @param data A dataframe or linelist
+#' @param target_columns A vector of column names
 #' @param cols a vector of empty and constant columns
 #'
-#' @return a `vector` with the target column names or indexes
+#' @return a vector with the target column names or indexes
 #'
 #' @keywords internal
 #'