Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Setup sets inputs as env vars with a default #90

Merged
merged 5 commits into from
Mar 7, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 8 additions & 6 deletions .github/workflows/update_data.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@ on:
default: 9999
type: number
full_rebuild:
description: 'Full Rebuild'
description: 'Full Rebuild (overwrites above season)'
required: true
default: false
type: boolean
Expand All @@ -32,19 +32,21 @@ jobs:
name: pbp_setup
env:
GH_TOKEN: ${{ secrets.NFLVERSE_GH_TOKEN }}
FULL_REBUILD: ${{ inputs.full_rebuild || false }}
SEASON_REBUILD: ${{ inputs.season_rebuild || 9999 }}
outputs:
seasons: ${{ steps.query_seasons.outputs.seasons }}
steps:
- id: query_seasons
run: |
if [ ${{ inputs.full_rebuild }} == true ]
if [ $FULL_REBUILD == true ]
then
echo "seasons=$(gh release list -R nflverse/nflverse-pbp --json tagName --jq '[.[].tagName | match("\\d+") | .string ]')" > "$GITHUB_OUTPUT"
elif [ ${{ inputs.season_rebuild }} == 9999 ]
elif [ $SEASON_REBUILD == 9999 ]
then
echo "seasons=$(gh release list -R nflverse/nflverse-pbp --json tagName --jq '[[.[].tagName | match("\\d+") | .string ] | max]')" > "$GITHUB_OUTPUT"
else
echo "seasons=$(gh release list -R nflverse/nflverse-pbp --json tagName --jq '[.[].tagName | select(endswith(${{ inputs.season_rebuild }} | tostring)) | match("\\d+") | .string]')" > "$GITHUB_OUTPUT"
echo "seasons=$(gh release list -R nflverse/nflverse-pbp --json tagName --jq '[.[].tagName | select(endswith(${{ env.SEASON_REBUILD }} | tostring)) | match("\\d+") | .string]')" > "$GITHUB_OUTPUT"
fi

update_pbp:
Expand All @@ -55,7 +57,7 @@ jobs:
fail-fast: false
matrix:
season: ${{ fromJson(needs.pbp_setup.outputs.seasons) }}
type: ["pbp", "pbp_stats", "laterals"]
type: ["pbp", "pbp_stats"]
env:
GITHUB_PAT: ${{ secrets.NFLVERSE_GH_TOKEN }}
NFLVERSE_UPDATE_SEASON: ${{ matrix.season }}
Expand Down Expand Up @@ -110,7 +112,7 @@ jobs:
strategy:
fail-fast: false
matrix:
type: ["ps_off_comb", "ps_def_comb", "ps_kick_comb"]
type: ["ps_off_comb", "ps_def_comb", "ps_kick_comb", "laterals"]
env:
GITHUB_PAT: ${{ secrets.NFLVERSE_GH_TOKEN }}
NFLVERSE_UPDATE_TYPE: ${{ matrix.type }}
Expand Down
111 changes: 32 additions & 79 deletions R/update_multiple_laterals.R
Original file line number Diff line number Diff line change
@@ -1,82 +1,35 @@
release_lateral_yards <- function(s) {
check_lateral_yards <- function(id){
cli::cli_progress_step("Loading {id}")
season <- substr(id, 1, 4)
base_url <- "https://github.com/nflverse/nflfastR-raw/raw/master/raw"
load_url <- file.path(base_url, season, paste0(id, ".rds"))
raw_data <- nflreadr::rds_from_url(load_url)
plays <- janitor::clean_names(raw_data[[1]][[1]]$gameDetail$plays) |>
dplyr::select(play_id, play_stats)
stats <- tidyr::unnest(plays, cols = c("play_stats")) |>
janitor::clean_names() |>
dplyr::filter(stat_id %in% c(12, 13, 23, 24)) |>
dplyr::mutate(
game_id = as.character(id),
type = dplyr::if_else(stat_id %in% 12:13, "lateral_rushing", "lateral_receiving", missing = NA_character_)
) |>
dplyr::select(
"game_id",
"play_id",
"stat_id",
"type",
"yards",
"team_abbr" = "team_abbreviation",
"player_name",
"gsis_player_id"
)

stats
}

games <- nflreadr::load_schedules(s) |>
dplyr::filter(!is.na(result))

if(length(games$game_id) == 0){
cli::cli_alert_info("No games yet, nothing to do")
return(invisible(NULL))
}

cli::cli_alert_info("Load {.val {length(games$game_id)}} game{?s} of {.val {s}}")

load <- furrr::future_map_dfr(games$game_id, check_lateral_yards)

cli::cli_alert_info("Process raw data...")

old <- readr::read_csv("lateral_yards/multiple_lateral_yards.csv", show_col_types = FALSE)

all <-
dplyr::bind_rows(
old,
load |>
nflfastR::decode_player_ids() |>
dplyr::group_by(game_id, play_id) |>
dplyr::filter(dplyr::n() > 1) |>
dplyr::ungroup() |>
suppressMessages()
release_lateral_yards <- function(...){
cli::cli_progress_step("Release multiple lateral yards data...")
all_stat_ids <-
purrr::map(
seq(1999, nflreadr::most_recent_season()),
~ nflreadr::rds_from_url(glue::glue("https://github.com/nflverse/nflverse-pbp/releases/download/playstats/play_stats_{.x}.rds")),
.progress = TRUE
) |>
dplyr::distinct() |>
dplyr::arrange(game_id, play_id)

cli::cli_alert_info("Save multiple lateral plays...")

readr::write_csv(all, "lateral_yards/multiple_lateral_yards.csv")

# check if file has changed to trigger nflverse release
comp <- waldo::compare(old, all)

if (length(comp) != 0){
nflversedata::nflverse_save(
data_frame = all,
file_name = "multiple_lateral_yards",
nflverse_type = "multiple_lateral_yards",
release_tag = "misc",
file_types = c("rds", "csv")
)
} else {
cli::cli_alert_info("Data has not changed.")
}

cli::cli_alert_info("DONE!")

purrr::list_rbind()

multiple_laterals <- all_stat_ids |>
dplyr::filter(stat_id %in% c(12, 13, 23, 24)) |>
dplyr::group_by(game_id, play_id) |>
dplyr::filter(dplyr::n() > 1) |>
dplyr::ungroup() |>
dplyr::mutate(
type = dplyr::if_else(stat_id %in% 12:13, "lateral_rushing", "lateral_receiving", missing = NA_character_)
) |>
dplyr::select(tidyselect::any_of(c(
"game_id", "play_id", "stat_id", "type", "yards",
"team_abbr", "player_name", "gsis_player_id"
)))

nflversedata::nflverse_save(
data_frame = multiple_laterals,
file_name = "multiple_lateral_yards",
nflverse_type = "multiple_lateral_yards",
release_tag = "misc",
file_types = c("rds", "csv")
)

cli::cli_progress_done()
invisible(NULL)

}