boost sum_play_stats

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: nflfastR
 Title: Functions to Efficiently Access NFL Play by Play Data
-Version: 4.5.0.9002
+Version: 4.5.0.9003
 Authors@R: 
     c(person(given = "Sebastian",
              family = "Carl",

NEWS.md

@@ -3,6 +3,7 @@
 * New implementation of tests to be able to identify breaking changes in reverse dependencies
 * `calculate_standings()` no more freezes when computing standings from schedules where some games are missing results, i.e. upcoming games. (v4.5.0.9000)
 * Bug fix that caused problems with upcoming dplyr and tidyselect updates that weren't reverse compatible.
+* Significant performance improvements of internal functions. (#402)
 * Wrap examples in `try()` to avoid CRAN problems. (#404)
 * Fixed a bug where `calculate_standings()` wasn't able to handle nflverse pbp data. (#404)
 

R/helper_scrape_gc.R

@@ -128,12 +128,8 @@ get_pbp_gc <- function(gameId, dir = NULL, qs = FALSE, ...) {
           playStatSeq = "sequence"
         )
 
-
-      pbp_stats <- furrr::future_map(unique(stats$playId), function(x, s) {
-        sum_play_stats(x, s)
-      }, stats)
-
-      pbp_stats <- dplyr::bind_rows(pbp_stats)
+      pbp_stats <- lapply(unique(stats$playId), sum_play_stats, stats)
+      pbp_stats <- data.table::rbindlist(pbp_stats) %>% tibble::as_tibble()
 
       # drive info
       d <- tibble::tibble(drives) %>%

R/helper_scrape_nfl.R

@@ -169,13 +169,9 @@ get_pbp_nfl <- function(id, dir = NULL, qs = FALSE, ...) {
 
       # if I don't put this here it breaks
       suppressWarnings(
-        pbp_stats <-
-          furrr::future_map(unique(stats$playId), function(x, s) {
-            sum_play_stats(x, s)
-          }, stats)
+        pbp_stats <- lapply(unique(stats$playId), sum_play_stats, stats)
       )
-
-      pbp_stats <- dplyr::bind_rows(pbp_stats)
+      pbp_stats <- data.table::rbindlist(pbp_stats) %>% tibble::as_tibble()
 
       combined <- game_info %>%
         dplyr::bind_cols(plays %>% dplyr::select(-"playStats", -"game_id")) %>%

R/helper_tidy_play_stats.R

@@ -13,9 +13,9 @@
 # @param stats A dataframe including multiple rows for each play_Id holding
 # gsis stat ids and stats
 sum_play_stats <- function(play_Id, stats) {
-  play_stats <- stats %>% filter(.data$playId == play_Id)
+  play_stats <- stats[stats$playId == play_Id,]
 
-  row <- bind_cols(play_id = as.integer(play_Id), tidy_play_stats_row)
+  row <- c("play_id" = as.integer(play_Id), tidy_play_stats_row)
 
   for (index in seq_along(play_stats$playId)) {
     stat_id <- play_stats$statId[index]