keep yardage string for 5 yard Face Mask penalties

nflverse · Mar 22, 2021 · ab0b289 · ab0b289
1 parent d564c06
commit ab0b289
Showing 1 changed file with 4 additions and 3 deletions.
diff --git a/R/helper_add_nflscrapr_mutations.R b/R/helper_add_nflscrapr_mutations.R
@@ -81,9 +81,10 @@ add_nflscrapr_mutations <- function(pbp) {
         .data$penalty == 1,
         .data$play_description %>%
           stringr::str_extract("(?<=PENALTY on .{1,50}, ).{1,50}(?=, [0-9]{1,2} yard)") %>%
-          # For some reason Face Mask penalties include the string (15 Yards)
-          # Seb thought it's ok to drop that with the next two lines
-          stringr::str_remove("\\(.+\\)") %>%
+          # Face Mask penalties include the yardage as string (either 5 Yards or 15 Yards)
+          # We remove the 15 Yards part and just keep the additional info if it's a
+          # 5 yard Face Mask penalty
+          stringr::str_remove("\\([0-9]{2}+ Yards\\)") %>%
           stringr::str_squish(), NA_character_
       ),
       # Make plays marked with down == 0 as NA: