Merge pull request #4 from mrcaseb/ben

Add series and series_success

DESCRIPTION

@@ -2,7 +2,7 @@ Type: Package
 Package: nflfastR
 Title: Functions to Efficiently Scrape NFL Play by Play and
     Roster Data
-Version: 1.0.3
+Version: 1.1.0
 Authors@R: 
     c(person(given = "Sebastian",
              family = "Carl",

R/helper_add_series_data.R

@@ -0,0 +1,65 @@
+################################################################################
+# Author: Sebastian Carl
+# Purpose: Function to add series variables analogue Lee Sharpe's Version
+# Code Style Guide: styler::tidyverse_style()
+################################################################################
+
+## series =
+##  starts at 1, each new first down increments, numbers shared across both teams
+##  NA: kickoffs, extra point/two point conversion attempts, non-plays, no posteam
+## series_success =
+##  1: scored touchdown, gained enough yards for first down
+##  0: punt, interception, fumble lost, turnover on downs, 4th down FG attempt
+##  NA: series is NA, series contains QB spike/kneel, half ended with none of above
+
+add_series_data <- function(pbp) {
+  out <-
+    pbp %>%
+    dplyr::group_by(game_id) %>%
+    dplyr::mutate(
+      # make down numeric
+      down = as.numeric(down),
+      # create a first down indicator which marks first down for the offense
+      # AND first down after change of possesion (-> drivenumber increases)
+      # we don't want a first down being indicated for XP, 2P, KO
+      first_down = dplyr::if_else(
+        (first_down_rush == 1 | first_down_pass == 1 |
+           first_down_penalty == 1 | drive < dplyr::lead(drive)) &
+          (extra_point_attempt == 0 & two_point_attempt == 0 & kickoff_attempt == 0),
+        1, 0
+      ),
+      # after setting the first down indicator we modificate it for the end of a half
+      first_down = dplyr::if_else(game_half != dplyr::lead(game_half), 1, first_down),
+      # the 'trigger' is being used for calculatung cumsum because we don't want the
+      # series number to increase in the play the first down occured but in the next play
+      trigger = dplyr::lag(first_down, 1, 0)
+    ) %>%
+    # now compute series number with cumsum (for the calculation NA are being relaced with 0)
+    dplyr::mutate(series = cumsum(tidyr::replace_na(trigger, 0)) + 1) %>%
+    dplyr::mutate(
+      # now modificated series number for special cases
+      series = dplyr::if_else(
+        kickoff_attempt == 1 | extra_point_attempt == 1 |
+          two_point_attempt == 1 | is.na(down) |
+          is.na(posteam),
+        NA_real_,
+        series
+      ),
+      series_success = dplyr::case_when(
+        is.na(series) | qb_kneel == 1 | qb_spike == 1 ~ NA_real_,
+        touchdown == 1 | first_down_rush == 1 | first_down_pass == 1 |
+          first_down_penalty == 1 ~ 1,
+        punt_attempt == 1 | interception == 1 | fumble_lost == 1 |
+          fourth_down_failed == 1 | field_goal_attempt == 1 ~ 0,
+        TRUE ~ 0
+      )
+    ) %>%
+    dplyr::group_by(game_id, series) %>%
+    # set series_success value for the whole series
+    dplyr::mutate(series_success = last(series_success)) %>%
+    dplyr::ungroup() %>%
+    dplyr::select(-first_down, -trigger)
+
+  message("added series variables")
+  return(out)
+}

R/helper_variable_selector.R

@@ -119,6 +119,6 @@ rs_cols <- c(
   "drive_time_of_possession", "drive_inside20", "drive_first_downs",
   "drive_possession_team_abbr", "scoring_team_abbr", "scoring_type",
   "alert_play_type", "play_type_nfl", "time_of_day",
-  "yards", "end_yardline_side", "end_yardline_number"
+  "yards", "end_yardline_side", "end_yardline_number", "series", "series_success"
 )
 

R/top-level_scraper.R

@@ -317,6 +317,8 @@
 #' \item{yards} - Analogue yards_gained but with the kicking team being the possession team (which means that there are many yards gained through kickoffs and punts).
 #' \item{end_yardline_side} - String indicating the side of the field at the end of the given play.
 #' \item{end_yardline_number} - Yardline number within the above given side at the end of the given play.
+#' \item{series} - Starts at 1, each new first down increments, numbers shared across both teams. Is NA for: kickoffs, extra point/two point conversion attempts, no posteam.
+#' \item{series_success} - 1 when scored touchdown, gained enough yards for first down. 0 when punt, interception, fumble lost, turnover on downs, 4th down FG attempt. NA when series is NA, series contains QB spike/kneel.
 #' }
 #' @export
 #' @examples
@@ -352,6 +354,7 @@ fast_scraper <- function(game_ids, source = "rs", pp = FALSE) {
           add_wp() %>%
           add_air_yac_wp() %>%
           add_cp() %>%
+          add_series_data() %>%
           select_variables()
       }
     })
@@ -379,6 +382,7 @@ fast_scraper <- function(game_ids, source = "rs", pp = FALSE) {
           add_wp() %>%
           add_air_yac_wp() %>%
           add_cp() %>%
+          add_series_data() %>%
           select_variables()
       }
     })