Replace entire strings based on partial match

Question

New to R. Looking to replace the entire string if there is a partial match.

d = c(\"SDS0G2 Blue\", \"Blue SSC2CWA3\", \"Blue SA2M1GC\", \"SA5 Blue CSQ5\")
         


        

Answer 1

If you did want to keep the variable as a factor and replace multiple partial matches at once, the following function will work (example from another question).

clrs <- c("blue", "light blue", "red", "rose", "ruby", "yellow", "green", "black", "brown", "royal blue")
dfx <- data.frame(colors1=clrs, colors2 = clrs, Amount=sample(100,10))

# Function to replace levels with regex matching
make_levels <- function(.f, patterns, replacement = NULL, ignore.case = FALSE) {

  lvls <- levels(.f)

  # Replacements can be listed in the replacement argument, taken as names in patterns, or the patterns themselves.
  if(is.null(replacement)) {
    if(is.null(names(patterns)))
      replacement <- patterns
    else
      replacement <- names(patterns)
  }

  # Find matching levels
  lvl_match <- setNames(vector("list", length = length(patterns)), replacement)
  for(i in seq_along(patterns))
    lvl_match[[replacement[i]]] <- grep(patterns[i], lvls, ignore.case = ignore.case, value = TRUE)

  # Append other non-matching levels
  lvl_other <- setdiff(lvls, unlist(lvl_match))
  lvl_all <- append(
    lvl_match, 
    setNames(as.list(lvl_other), lvl_other)
  )

  return(lvl_all)

}

# Replace levels
levels(dfx$colors2) <- make_levels(.f = dfx$colors2, patterns = c(Blue = "blue", Red = "red|rose|ruby"))

dfx
#>       colors1 colors2 Amount
#> 1        blue    Blue     75
#> 2  light blue    Blue     55
#> 3         red     Red     47
#> 4        rose     Red     83
#> 5        ruby     Red     56
#> 6      yellow  yellow     10
#> 7       green   green     25
#> 8       black   black     29
#> 9       brown   brown     23
#> 10 royal blue    Blue     24

^{Created on 2020-04-18 by the reprex package (v0.3.0)}

Answer 2

I'd suggest using grepl to find the indices and replace those indices with "Red":

d = c("SDS0G2 Blue", "Blue SSC2CWA3", "Blue SA2M1GC", "SA5 Blue CSQ5", "ABCDE")
d[grepl("Blue", d, ignore.case=FALSE)] <- "Red"
d
# [1] "Red"   "Red"   "Red"   "Red"   "ABCDE"