Merge pull request #427 from nflverse/posteam-fixes

fix posteam for 2023+

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: nflfastR
 Title: Functions to Efficiently Access NFL Play by Play Data
-Version: 4.5.1.9011
+Version: 4.5.1.9012
 Authors@R: 
     c(person(given = "Sebastian",
              family = "Carl",

NEWS.md

@@ -13,7 +13,7 @@
 - Added the new function `missing_raw_pbp()` that computes a vector of game IDs missing in the local raw play-by-play directory. (#423)
 - Decode player IDs in 2023 pbp. (#425)
 - Drop the pseudo plays TV Timeout and Two-Minute Warning. (#426)
-
+- Fix posteam on kickoffs and PATs following a defensive TD in 2023+ pbp. (#427)
 
 # nflfastR 4.5.1
 

R/helper_scrape_nfl.R

@@ -292,7 +292,8 @@ get_pbp_nfl <- function(id,
     # These mess up some of our logic. Since they are useless, we remove them here
     dplyr::filter(
       !(is.na(.data$timeout_team) & stringr::str_detect(tolower(.data$play_description), "timeout at|two-minute"))
-    )
+    ) %>%
+    fix_posteams()
 
   # fix for games where home_team == away_team and fields are messed up
   if (bad_game == 1) {
@@ -372,5 +373,33 @@ fix_bad_games <- function(pbp) {
 
 }
 
+fix_posteams <- function(pbp){
+  # 2023 pbp introduces two new problems
+  # 1. Definition of posteam on kick offs changed to receiving team. That's our
+  #    definition and we swap teams later.
+  # 2. Posteam doesn't change on the PAT after defensive TD
+  #
+  # We adjust both things here, but only for 2023ff to avoid backwards compatibility problems
+  # We need the variable pre_play_by_play which usually looks like "KC  1-10  NYJ 40"
+  if (any(pbp$season >= 2023) && ("pre_play_by_play" %in% names(pbp))){
+    # Let's be as explicit as possible about what we want to extract from the string
+    # It's really only the first valid team abbreviation followed by a blank space
+    valid_team_abbrs <- paste(nflfastR::teams_colors_logos$team_abbr, collapse = "|")
+    posteam_regex <- paste0("^", valid_team_abbrs, "(?=[:space:])")
+
+    pbp <- pbp %>%
+      dplyr::mutate(
+        parsed_posteam = stringr::str_extract(.data$pre_play_by_play, posteam_regex),
+        posteam = dplyr::case_when(
+          is.na(.data$parsed_posteam) ~ .data$posteam,
+          .data$play_description == "GAME" ~ .data$posteam,
+          TRUE ~ .data$parsed_posteam
+        ),
+        # drop helper
+        parsed_posteam = NULL
+      )
+  }
 
+  pbp
+}