From f4b674c2c537134d79d2cce18e8ff34d59d46438 Mon Sep 17 00:00:00 2001
From: Ben Baldwin <1425357+guga31bb@users.noreply.github.com>
Date: Fri, 19 Feb 2021 11:24:13 -0500
Subject: [PATCH] drive fix

---
 DESCRIPTION           |  2 +-
 NEWS.md               |  1 +
 R/helper_scrape_nfl.R | 15 ---------------
 3 files changed, 2 insertions(+), 16 deletions(-)

diff --git a/DESCRIPTION b/DESCRIPTION
index c60181fd..aba237d8 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,7 +1,7 @@
 Type: Package
 Package: nflfastR
 Title: Functions to Efficiently Access NFL Play by Play Data
-Version: 4.0.0.9001
+Version: 4.0.0.9002
 Authors@R: 
     c(person(given = "Sebastian",
              family = "Carl",
diff --git a/NEWS.md b/NEWS.md
index 285be3e7..ff0c21a6 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -3,6 +3,7 @@
 * Added the function `calculate_player_stats()` that aggregates official passing, rushing, and receiving stats either at game level or overall
 * Added the new columns `td_player_name` and `td_player_id` to clearly identify the player who scored a touchdown (this is especially helpful for plays with multiple fumbles or laterals resulting in a touchdown)
 * Added the function `load_player_stats()` that loads weekly player stats from 1999 to the most recent season
+* Fix bug in `drive` that was causing incorrect overtime win probabilities (#194)
 
 # nflfastR 4.0.0
 
diff --git a/R/helper_scrape_nfl.R b/R/helper_scrape_nfl.R
index e1b5185f..74390da8 100644
--- a/R/helper_scrape_nfl.R
+++ b/R/helper_scrape_nfl.R
@@ -273,21 +273,6 @@ get_pbp_nfl <- function(id, dir = NULL, qs = FALSE) {
             .data$season <= 2015 & .data$yardline_side == 'JAX',
             'JAC', .data$yardline_side
           ),
-          #if there's some random missing drive, fill in with previous drive
-          #this fixes a bug with plays appearing out of order after defensive TDs
-          drive = dplyr::if_else(
-            !is.na(dplyr::lag(.data$drive)) & !is.na(dplyr::lead(.data$drive)),
-            dplyr::lag(.data$drive), .data$drive
-          ),
-          #fix for drives being messed up in this game
-          drive = dplyr::case_when(
-            id == '2012_04_NO_GB' & .data$play_id == 1085 ~ 4,
-            id == '2012_16_BUF_MIA' & .data$play_id == 2571 ~ 15,
-            id == '2015_16_CHI_TB' & .data$play_id == 2182 ~ 14,
-            id == '2019_12_IND_HOU' & .data$play_id == 2579 ~ 12,
-            id == '2019_12_IND_HOU' & .data$play_id == 2544 ~ 11,
-            TRUE ~ .data$drive
-          ),
           time = dplyr::case_when(
             id == '2012_04_NO_GB' & .data$play_id == 1085 ~ '3:34',
             id == '2012_16_BUF_MIA' & .data$play_id == 2571 ~ '8:31',