Skip to content

Update column unnesting #285

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.

Sign up for GitHub

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

Merged
pbulsink merged 6 commits into from
Apr 18, 2025
Merged

Update column unnesting #285

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
dca161c
Avoid pick_driver deprecation
pbulsink Apr 14, 2025
d2ccd1a
Update load_sprint to handle Jolpica changes
pbulsink Apr 14, 2025
4f14cde
Update load_sprint testing to check both variations
pbulsink Apr 14, 2025
540aa25
Use `names_sep` in `tidyr::unnest()`
pbulsink Apr 18, 2025
f09f2be
Style & Document code
pbulsink Apr 18, 2025
5bff820
Merge branch 'master' into bugfix
pbulsink Apr 18, 2025
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
1 change: 1 addition & 0 deletions .Rbuildignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,3 +19,4 @@
^CRAN-SUBMISSION$
^\w*.pem$
^revdep$
cobertura.xml
1 change: 1 addition & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,3 +15,4 @@ docs
.RData
/revdep/
Thumbs.db
cobertura.xml
81 changes: 62 additions & 19 deletions R/load_results.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,11 +13,15 @@
#' in seconds.
load_results <- function(season = get_current_season(), round = "last") {
if (season != "current" && (season < 1950 || season > get_current_season())) {
cli::cli_abort('{.var season} must be between 1950 and {get_current_season()} (or use "current")')
cli::cli_abort(
'{.var season} must be between 1950 and {get_current_season()} (or use "current")'
)
}

url <- glue::glue("{season}/{round}/results.json?limit=40",
season = season, round = round
url <- glue::glue(
"{season}/{round}/results.json?limit=40",
season = season,
round = round
)
data <- get_jolpica_content(url)

Expand All @@ -31,10 +35,23 @@ load_results <- function(season = get_current_season(), round = "last") {
# all races from before 2004 will have no 'Fastest Lap' column,
# but also 2021 round 12 (Belgian GP) where no racing laps were run
data %>%
tidyr::unnest(cols = c("Driver", "Time", "Constructor"), names_repair = "universal") %>%
tidyr::unnest(
cols = c("Driver", "Time", "Constructor"),
names_sep = ".",
names_repair = "universal"
) %>%
suppressWarnings() %>%
suppressMessages() %>%
dplyr::select("driverId", "constructorId", "position", "points", "grid":"status", gap = "time") %>%
dplyr::select(
"driverId" = "Driver.driverId",
"constructorId" = "Constructor.constructorId",
"points",
"position",
"grid",
"laps",
"status",
gap = "Time.time"
) %>%
dplyr::mutate(
fastest_rank = NA_integer_,
fastest = NA_character_,
Expand All @@ -45,35 +62,61 @@ load_results <- function(season = get_current_season(), round = "last") {
janitor::clean_names()
} else if (!("AverageSpeed" %in% colnames(data$FastestLap))) {
data %>%
tidyr::unnest(cols = c("Driver", "Constructor", "Time", "FastestLap"), names_repair = "universal") %>%
dplyr::select("driverId", "constructorId", "points", "position", "grid", "laps", "status", "time", "Time", "rank") %>%
tidyr::unnest(cols = "Time", names_repair = "universal") %>%
tidyr::unnest(
cols = c("Driver", "Constructor", "Time", "FastestLap"),
names_sep = ".",
names_repair = "universal"
) %>%
tidyr::unnest(
cols = "FastestLap.Time",
names_sep = ".",
names_repair = "universal"
) %>%
suppressWarnings() %>%
suppressMessages() %>%
dplyr::mutate(top_speed_kph = NA_real_) %>%
dplyr::select("driverId", "constructorId", "points", "position", "grid", "laps", "status", gap = "time...8", fastest_rank = "rank", fastest = "time...9", top_speed_kph) %>%
dplyr::select(
"driverId" = "Driver.driverId",
"constructorId" = "Constructor.constructorId",
"points",
"position",
"grid",
"laps",
"status",
gap = "Time.time",
fastest_rank = "FastestLap.rank",
fastest = "FastestLap.Time.time",
top_speed_kph
) %>%
dplyr::mutate(time_sec = time_to_sec(.data$fastest)) %>%
tibble::as_tibble() %>%
janitor::clean_names()
} else {
data %>%
tidyr::unnest(cols = c("Driver", "Constructor", "Time", "FastestLap"), names_repair = "universal") %>%
dplyr::select("driverId", "points", "position", "grid":"AverageSpeed", "constructorId", "name") %>%
tidyr::unnest(
cols = c("Time", "AverageSpeed"),
cols = c("Driver", "Constructor", "Time", "FastestLap"),
names_sep = ".",
names_repair = "universal"
) %>%
tidyr::unnest(
cols = c("FastestLap.Time", "FastestLap.AverageSpeed"),
names_sep = ".",
names_repair = "universal"
) %>%
suppressWarnings() %>%
suppressMessages() %>%
dplyr::select(
"driverId",
"constructorId",
"points":"status",
gap = "time...8",
fastest_rank = "rank",
"driverId" = "Driver.driverId",
"constructorId" = "Constructor.constructorId",
"points",
"position",
"grid",
"laps",
fastest = "time...11",
top_speed_kph = "speed",
"status",
gap = "Time.time",
fastest_rank = "FastestLap.rank",
fastest = "FastestLap.Time.time",
top_speed_kph = "FastestLap.AverageSpeed.speed",
) %>%
dplyr::mutate(time_sec = time_to_sec(.data$fastest)) %>%
tibble::as_tibble() %>%
Expand Down
63 changes: 21 additions & 42 deletions R/load_sprint.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,50 +46,29 @@ load_sprint <- function(season = get_current_season(), round = "last") {
data <- data %>%
tidyr::unnest(
cols = c("Driver", "Constructor", "Time", "FastestLap"),
names_repair = "universal"
names_repair = "universal",
names_sep = "."
) %>%
tidyr::unnest(
cols = c("Time"),
names_repair = "universal"
)

if ("time...24" %in% names(data)) {
data <- data %>%
suppressWarnings() %>%
suppressMessages() %>%
dplyr::select(
"driverId",
"constructorId",
"points",
"position",
"grid",
"laps",
"status",
"position",
gap = "time...21",
"lap",
fastest = "time...24"
)
} else {
data <- data %>%
suppressWarnings() %>%
suppressMessages() %>%
dplyr::select(
"driverId",
"constructorId",
"points",
"position",
"grid",
"laps",
"status",
"position",
gap = "time...21",
"lap",
fastest = "time...23"
)
}

data %>%
cols = c("FastestLap.Time"),
names_repair = "universal",
names_sep = "."
) %>%
suppressWarnings() %>%
suppressMessages() %>%
dplyr::select(
"driverId" = "Driver.driverId",
"constructorId" = "Constructor.constructorId",
"points",
"position",
"grid",
"laps",
"status",
"position",
"gap" = "Time.time",
"lap" = "FastestLap.lap",
"fastest" = "FastestLap.Time.time"
) %>%
dplyr::mutate(time_sec = time_to_sec(.data$fastest)) %>%
tibble::as_tibble() %>%
janitor::clean_names()
Expand Down