Merge pull request #22 from gbganalyst/input-checking

Input checking

DESCRIPTION

@@ -55,4 +55,4 @@ VignetteBuilder:
 Config/testthat/edition: 3
 Encoding: UTF-8
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.1

R/fill_missing_values.R

@@ -16,12 +16,13 @@
 #'   which missing values should be imputed. If `NULL` (default), imputation is
 #'   applied to all variables in the data frame.
 #'
-#' @param method A character string specifying the imputation method for continuous
-#'   variables. Supported methods are "min", "max", "mean", "median", "harmonic",
-#'   and "geometric". The default method is "mean". For categorical variables, the
-#'   mode is always used.
+#' @param method A character string specifying the imputation method for
+#' continuous variables. Supported methods are "min", "max", "mean", "median",
+#' "harmonic", and "geometric". The default method is "mean". For categorical
+#' variables, the mode is always used.
 #'
-#' @return  A data frame with missing values imputed according to the specified `method`.
+#' @return  A data frame with missing values imputed according to the specified
+#'  `method`.
 #'
 #' @export
 #'
@@ -71,17 +72,21 @@
 #' map_df(fill_missing_values, method = "median")
 #'
 #'
-fill_missing_values <- function(df, selected_variables = NULL, method = "mean") {
+fill_missing_values <- function(df, selected_variables = NULL, method = c("mean", "min", "max", "median", "harmonic", "geometric")) {
+
+  # Check if df is a dataframe
+
+  if (!is.data.frame(df)) {
+    stop("fill_missing_values() is designed to operate exclusively on objects of the class 'dataframe'")
+  }
 
   if (missing(df)) {
     stop("argument 'df' is missing, with no default")
   }
 
   # Validate method input for continuous variables
-  valid_methods <- c("min", "max", "mean", "median", "harmonic", "geometric")
-  if (!(method %in% valid_methods)) {
-    stop("Invalid method. Choose from 'min', 'max', 'mean', 'median', 'harmonic', 'geometric'")
-  }
+
+  method <- rlang::arg_match(method)
 
   # Calculate the replacement value based on the specified method
 
@@ -91,13 +96,13 @@ fill_missing_values <- function(df, selected_variables = NULL, method = "mean")
     } # Skip non-numeric columns
 
     replacement_value <- switch(method,
-      min = min(x, na.rm = TRUE),
-      max = max(x, na.rm = TRUE),
-      mean = mean(x, na.rm = TRUE),
-      median = median(x, na.rm = TRUE),
-      harmonic = harmonic_mean(x),
-      geometric = geometric_mean(x),
-      x
+                                min = min(x, na.rm = TRUE),
+                                max = max(x, na.rm = TRUE),
+                                mean = mean(x, na.rm = TRUE),
+                                median = median(x, na.rm = TRUE),
+                                harmonic = harmonic_mean(x),
+                                geometric = geometric_mean(x),
+                                x
     ) # Default to return x as is
 
 

R/utils-pipe.R

@@ -1,12 +1,14 @@
 #' Pipe operator
 #'
-#' See \code{magrittr::\link[magrittr]{\%>\%}} for details.
+#' See \code{magrittr::\link[magrittr:pipe]{\%>\%}} for details.
 #'
 #' @name %>%
 #' @rdname pipe
 #' @keywords internal
-#' @return No return value
 #' @export
 #' @importFrom magrittr %>%
 #' @usage lhs \%>\% rhs
+#' @param lhs A value or the magrittr placeholder.
+#' @param rhs A function call using the magrittr semantics.
+#' @return The result of calling `rhs(lhs)`.
 NULL

vignettes/other-functions.Rmd

@@ -94,7 +94,7 @@ airquality %>%
 
 ## fill_missing_values() 
 
-`fill_missing_values()` is an efficient function that addresses missing values in a data frame. It uses imputation by function, also known as column-based imputation, to impute the missing values. It supports various imputation methods for continuous variables, including minimum, maximum, mean, median, harmonic mean, and geometric mean. For categorical variables, missing values are replaced with the mode of the column. This approach ensures accurate and consistent replacements derived from individual columns, resulting in a complete and reliable dataset for improved analysis and decision-making.
+`fill_missing_values()` is an efficient function that addresses missing values in a data frame. It uses imputation by function, also known as column-based imputation, to impute the missing values. It supports various imputation methods for continuous variables, including `minimum`, `maximum`, `mean`, `median`, `harmonic mean`, and `geometric mean`. For categorical variables, missing values are replaced with the `mode` of the column. This approach ensures accurate and consistent replacements derived from individual columns, resulting in a complete and reliable dataset for improved analysis and decision-making.
 
 
 ```{r example 6}