Merge pull request #423 from nflverse/utils-performance

Utils performance & raw pbp functions

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: nflfastR
 Title: Functions to Efficiently Access NFL Play by Play Data
-Version: 4.5.1.9008
+Version: 4.5.1.9009
 Authors@R: 
     c(person(given = "Sebastian",
              family = "Carl",

NAMESPACE

@@ -18,8 +18,10 @@ export(fast_scraper_roster)
 export(fast_scraper_schedules)
 export(load_pbp)
 export(load_player_stats)
+export(missing_raw_pbp)
 export(nflverse_sitrep)
 export(report)
+export(save_raw_pbp)
 export(update_db)
 import(dplyr)
 import(fastrmodels)

NEWS.md

@@ -8,6 +8,9 @@
 - `fixed_drive` now correctly increments on plays where posteam lost a fumble but remains posteam because defteam also lost a fumble during the same play. (#419)
 - nflfastR now fixes missing drive number counts in raw pbp data in order to provide accurate drive information. (#420)
 - nflfastR now returns correct `kick_distance` on all punts and kickoffs. (#422)
+- nflfastR now fully supports loading raw pbp data from local file system. The best way to use this feature is to set `options("nflfastR.raw_directory" = {"your/local/directory"})`. Alternatively, both `build_nflfastR_pbp()` and `fast_scraper()` support the argument `dir` which defaults to the above option. (#423)
+- Added the new function `save_raw_pbp()` which efficiently downloads raw play-by-play data and saves it to the local file system. This serves as a helper to setup the system for faster play-by-play parsing via the above functionality. (#423)
+- Added the new function `missing_raw_pbp()` that computes a vector of game IDs missing in the local raw play-by-play directory. (#423)
 
 
 # nflfastR 4.5.1

R/build_nflfastR_pbp.R

@@ -55,30 +55,27 @@
 #' }
 #' }
 build_nflfastR_pbp <- function(game_ids,
+                               dir = getOption("nflfastR.raw_directory", default = NULL),
                                ...,
                                decode = TRUE,
                                rules = TRUE) {
 
   if (!is.vector(game_ids) && is.data.frame(game_ids)) game_ids <- game_ids$game_id
 
-  if (!is.vector(game_ids)) cli::cli_abort("Param {.code game_ids} is not a valid vector!")
+  if (!is.vector(game_ids)) cli::cli_abort("Param {.arg game_ids} is not a valid vector!")
 
   if (isTRUE(decode) && !is_installed("gsisdecoder")) {
-    cli::cli_abort("Package {.val gsisdecoder} required for decoding. Please install it with {.code install.packages(\"gsisdecoder\")}.")
+    cli::cli_abort("Package {.pkg gsisdecoder} required for decoding. Please install it with {.code install.packages(\"gsisdecoder\")}.")
   }
 
   if (isTRUE(rules)) rule_header("Build nflfastR Play-by-Play Data")
 
   game_count <- ifelse(is.vector(game_ids), length(game_ids), nrow(game_ids))
   builder <- TRUE
 
-  if (game_count > 1) {
-    cli::cli_ul("{my_time()} | Start download of {game_count} games...")
-  } else {
-    cli::cli_ul("{my_time()} | Start download of {game_count} game...")
-  }
+  cli::cli_ul("{my_time()} | Start download of {game_count} game{?s}...")
 
-  ret <- fast_scraper(game_ids = game_ids, ..., in_builder = builder) %>%
+  ret <- fast_scraper(game_ids = game_ids, dir = dir, ..., in_builder = builder) %>%
     clean_pbp(in_builder = builder) %>%
     add_qb_epa(in_builder = builder) %>%
     add_xyac(in_builder = builder) %>%