Fixing issue with 2024 pass completions not having right yardage

R/helper_pbp_add_yardage.R

@@ -86,10 +86,14 @@ add_yardage <- function(play_df) {
           stringi::stri_extract_first_regex(.data$play_text, "(?<= for a loss of)[^,]+"), "\\d+"
         )),
         .data$pass == 1 &
-          stringr::str_detect(.data$play_text, regex("pass complete to", ignore_case = TRUE)) ~
+          stringr::str_detect(.data$play_text, regex("pass complete to", ignore_case = TRUE)) &
+          stringr::str_detect(.data$play_text, regex(" for \\d+ y\\w*ds?", ignore_case = TRUE)) ~
         as.numeric(stringr::str_extract(
           stringi::stri_extract_first_regex(.data$play_text, "(?<= for)[^,]+"), "\\d+"
         )),
+        .data$pass == 1 &
+          stringr::str_detect(.data$play_text, regex("pass complete to", ignore_case = TRUE)) ~
+          yards_gained, # 2024 has games that don't have yards in the PBP text but do have them in the yards_gained field.
         TRUE ~ NA_real_
       )
     )

tests/testthat/test-cfbd_pbp_data.R

@@ -0,0 +1,40 @@
+test_that("2024 pbp handles completions properly", {
+  # skip("working post-fix") # should fail without it
+  p = cfbd_pbp_data(
+    year = 2024,
+    season_type = "regular",
+    week = 1,
+    team = "NC State",
+    play_type = "pass reception",
+    epa_wpa = T
+  )
+
+  completions = p %>%
+    dplyr::filter(game_id == 401634299 & play_type == "Pass Reception" & pos_team == "NC State") %>%
+    dplyr::mutate(
+      same_same = (yards_gained == yds_receiving)
+    ) %>%
+    dplyr::select(yards_gained, yds_receiving, same_same)
+
+  testthat::expect_equal(sum(completions$same_same), nrow(completions))
+})
+
+test_that("base case 2023 pbp are already properly handled", {
+  p = cfbd_pbp_data(
+    year = 2023,
+    season_type = "regular",
+    week = 2,
+    team = "Georgia Tech",
+    play_type = "pass reception",
+    epa_wpa = T
+  )
+
+  completions = p %>%
+    dplyr::filter(game_id == 401525494 & play_type == "Pass Reception" & pos_team == "Georgia Tech") %>%
+    dplyr::mutate(
+      same_same = (yards_gained == yds_receiving)
+    ) %>%
+    dplyr::select(yards_gained, yds_receiving, same_same)
+
+  testthat::expect_equal(sum(completions$same_same), nrow(completions))
+})