Update penalty_type parser

also update the description of penalty_type

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: nflfastR
 Title: Functions to Efficiently Access NFL Play by Play Data
-Version: 4.0.0.9014
+Version: 4.0.0.9015
 Authors@R: 
     c(person(given = "Sebastian",
              family = "Carl",

NEWS.md

@@ -27,6 +27,7 @@
 * `fixed_drive` now increments properly on onside kick recoveries (#215)
 * `fixed_drive` no longer counts a muffed kickoff as a one-play drive on its own (#217)
 * `fixed_drive` now properly increments after a safety (#219)
+* Improved parser for `penalty_type` and updated the description of the variable to make more clear it's the first penalty that happened on a play. (#223)
 
 # nflfastR 4.0.0
 

R/helper_add_nflscrapr_mutations.R

@@ -80,10 +80,11 @@ add_nflscrapr_mutations <- function(pbp) {
       penalty_type = dplyr::if_else(
         .data$penalty == 1,
         .data$play_description %>%
-          stringr::str_extract("PENALTY on (.){2,35},.+, [0-9]{1,2} yard(s),") %>%
-          stringr::str_extract(", (([:alpha:])+([:space:])?)+,") %>%
-          stringr::str_remove_all(",") %>%
-          stringr::str_trim(), NA_character_
+          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("\\(.+\\)") %>%
+          stringr::str_squish(), NA_character_
       ),
       # Make plays marked with down == 0 as NA:
       down = dplyr::if_else(

R/top-level_scraper.R

@@ -319,7 +319,7 @@
 #' \item{penalty_yards}{Yards gained (or lost) by the posteam from the penalty.}
 #' \item{replay_or_challenge}{Binary indicator for whether or not a replay or challenge.}
 #' \item{replay_or_challenge_result}{String indicating the result of the replay or challenge.}
-#' \item{penalty_type}{String indicating the penalty type.}
+#' \item{penalty_type}{String indicating the penalty type of the first penalty in the given play. Will be `NA` if `desc` is missing the type.}
 #' \item{defensive_two_point_attempt}{Binary indicator whether or not the defense was able to have an attempt on a two point conversion, this results following a turnover.}
 #' \item{defensive_two_point_conv}{Binary indicator whether or not the defense successfully scored on the two point conversion.}
 #' \item{defensive_extra_point_attempt}{Binary indicator whether or not the defense was able to have an attempt on an extra point attempt, this results following a blocked attempt that the defense recovers the ball.}

data-raw/variable_list.txt

@@ -276,7 +276,7 @@
 #' \item{penalty_yards}{Yards gained (or lost) by the posteam from the penalty.}
 #' \item{replay_or_challenge}{Binary indicator for whether or not a replay or challenge.}
 #' \item{replay_or_challenge_result}{String indicating the result of the replay or challenge.}
-#' \item{penalty_type}{String indicating the penalty type.}
+#' \item{penalty_type}{String indicating the penalty type of the first penalty in the given play. Will be `NA` if `desc` is missing the type.}
 #' \item{defensive_two_point_attempt}{Binary indicator whether or not the defense was able to have an attempt on a two point conversion, this results following a turnover.}
 #' \item{defensive_two_point_conv}{Binary indicator whether or not the defense successfully scored on the two point conversion.}
 #' \item{defensive_extra_point_attempt}{Binary indicator whether or not the defense was able to have an attempt on an extra point attempt, this results following a blocked attempt that the defense recovers the ball.}