Skip to contents

This function builds Expected Fantasy Points predictions by downloading the xgboost models and play-by-play data, applying the model, and summarizing to player level.

Usage

ep_build(season = nflreadr:::most_recent_season(), version = "latest")

Arguments

season

a numeric vector of seasons that defaults to most recent season. Must be later than 2006.

version

an EP model version - one of "latest" (default) or "v1.0.0" (these are currently identical)

Value

a list containing three dataframes: ep_weekly provides a game-level summary by player, ep_pbp_pass provides EP data on pass plays, and ep_pbp_rush provides EP data on rush plays.

See also

Other main: ep_load()

Examples

# \donttest{
try({ # prevents cran-related errors
  ep_build(season = 2021)
})
#> ── Starting ep build for 2021 season(s)! 2022-05-12 00:48:27 ───────────────────
#> → Downloading EP models, if required 2022-05-12 00:48:27
#>  Could not find ep model version "latest" in cache directory: 
#> ~/.cache/ffopportunity 
#>  Attempting download
#>  Successfully downloaded ep model version "latest" to cache!
#> → Loading pbp 2022-05-12 00:48:29
#> → Preprocessing pbp 2022-05-12 00:48:31
#> → Generating predictions 2022-05-12 00:48:44
#> → Summarizing data 2022-05-12 00:50:02
#> ── Finished building ep for 2021 season(s)! 2022-05-12 00:50:02 ────────────────
#> → <ffopportunity predictions>
#> → Generated 2022-05-12 00:50:02 with model version latest
#> List of 5
#>  $ ep_weekly  : tibble [6,018 × 159] (S3: tbl_df/tbl/data.frame)
#>  $ ep_pbp_pass: nflverse_data [19,689 × 57] (S3: nflverse_data/tbl_df/tbl/data.table/data.frame)
#>  $ ep_pbp_rush: nflverse_data [14,649 × 47] (S3: nflverse_data/tbl_df/tbl/data.table/data.frame)
#>  $ ep_version : chr "latest"
#>  $ timestamp  : POSIXct[1:1], format: "2022-05-12 00:50:02"
# }