rerun doco

R/utils.R

@@ -73,3 +73,75 @@ pretty_count <- function(x) {
   x <- prettyNum(x, big.mark = ",")
   return(x)
 }
+
+
+
+#' Unsuppress data using sampling
+#'
+#' @param x
+#' @param replace_char the character you want to replace in the vector
+#' @param zeros the number of zeroes to oversample when replacing replace_char
+#' @param max_value the numeric maximum value the replacement for the "*" can be
+#' @return a numeric vector with no characters representing suppressed values
+#' @export
+#'
+#' @examples
+#' suppr_data <- c("2", "8", "*", "*", "7", "9", "100")
+#' star_subs(suppr_data, zeros = 1, max_value = 10)
+#' star_subs(suppr_data, zeros = 1, max_value = 200)
+star_subs <- function(x, replace_char = "*",
+                      zeros = 15, max_value = 20) {
+  x[x == "*"] <- sample(c(rep("0", zeros), as.character(0:max_value)),
+                        sum(x==replace_char), replace = TRUE)
+  x <- as.numeric(x)
+  return(x)
+}
+
+
+
+#' Recode grade level from character to numeric
+#'
+#' @param x character description of grade levels from NCES style data
+#'
+#' @return
+#' @export
+#'
+#' @examples
+grade_level_to_num <- function(x) {
+  # Cannot generate new levels if it is a factor so we coerce to character first
+  x <- as.character(x)
+  x[x %in% c("KG", "Kindergarten")] <- "0"
+  x[x %in% c("Pre-K", "Pre-k", "Preschool", "Pre-Kindergarten")] <- "-1"
+  x[x %in% c("Adult", "Adult Education")] <- "13"
+  y <- as.numeric(x)
+  return(y)
+}
+
+
+#' Recode NCES race categories to shorter names
+#'
+#' @param x a character vector with NCES race codes, often from Urban Institute
+#'
+#' @return
+#' @export
+#'
+#' @examples
+race_short_names <- function(x) {
+  x <- as.character(x)
+  x[x %in% c("Black", "Black Or African American", "Black or African American",
+             "African American")] <- "black"
+  x[x %in% c("Hispanic", "Hispanic Or Latino", "Hispanic or Latino")] <-
+    "hisp_lat"
+  x[x %in% c("White", "white", "White and Not Hispanic")] <- "white"
+  x[x %in% c("Asian", "Asian American")] <- "asian"
+  x[x %in% c("Two Or More Races", "Two or More Races")] <- "two_or_more"
+  x[x %in% c("Native Hawaiian Or Other Pacific Islander",
+             "Native Hawaiian or Other Pacific Islander",
+             "Native Hawaiian Pacific Islander")] <- "native_haw"
+  x[x %in% c("American Indian", "American Indian Or Alaska Native",
+             "American Indian or Alaska Native", "American Indian or Native Alaskan")] <- "amind"
+  x[x %in% c("Not Reported")] <- "other"
+  return(x)
+}
+
+