update standings -> 2025-02-25 10:00:00

02-SCRIPTS/clean_data.R

@@ -74,14 +74,104 @@ all_data <- all_data |>
 
 # Export the dataset
 
-write_csv(x = all_data, file = "03-DATA_PROCESSED/standings_to_20250114060000.csv")
+write_csv(x = all_data, file = "03-DATA_PROCESSED/standings_to_20250224_220000.csv")
 
-# ⬇️ Get and clean data since Dalin's arrival -------------------------
+# ⬇️ Get and clean data from Dalin's arrival to 2025-02-24 ----------------
 
-# Richomme : 2025_01_15 07:21:02
+
+
+# Dalin : 2025_01_14 08:24:49 (paths[1] -> paths[383])
+# Richomme : 2025_01_15 07:21:02 (paths[384] -> )
+# 2025-02-24 : paths[626]
+
+
+paths <- list.files(path = "01-DATA_RAW/", full.names = T, pattern = "*.xlsx")
+paths <- paths[384:626]
+
+all_files <- tibble(path = paths) |> 
+  separate(col = path, into = c("dir", "file"), sep = "/", remove = FALSE) |> 
+  select(-dir) |> 
+  mutate(date_time = str_remove_all(string = file, pattern = "vendeeglobe_leaderboard_"),
+         date_time = str_remove_all(string = date_time, pattern = ".xlsx")) |> 
+  separate(col = date_time, into = c("date", "time"), sep = "_") |> 
+  select(-file) |> 
+  arrange(date, time)
+
+# all_files |> 
+#   mutate(datetime = as_datetime(date, time))
+#   mutate(sheet_range = case_when(date <= 20250113 ~ "B6:U45",
+#                                  .default = NA))
+
+all_data <- list()
+
+ok_val <- c(1:40, "RET")
+
+for (i in 1:nrow(all_files)) {
+
+  df <- readxl::read_xlsx(all_files$path[i], 
+                          range = "B6:U47", col_names = FALSE) |> 
+    filter(...1 %in% ok_val)
+
+  names(df) <- c("rank", "nat_sail", "skipper_boat", "hour_FR", "lat_deg", "lon_deg",
+                 "last30min_heading_deg", "last30min_speed_kts", "last30min_VMG_kts", "last30min_distance_nm",
+                 "since_last_standings_heading_deg", "since_last_standings_speed_kts", "since_last_standings_VMG_kts",
+                 "since_last_standings_distance_nm", "last24hrs_heading_deg", "last24hrs_speed_kts", 
+                 "last24hrs_VMG_kts", "last24hrs_distance_nm", "distance_to_finish_nm", "distance_to_leader_nm")
+
+  all_data[[i]] <- df |> 
+    mutate(nat = str_extract(string = nat_sail, pattern = "^.{3}"),
+           sail = str_remove(string = nat_sail, pattern = "^.{3}"),
+           .after = nat_sail) |> 
+    left_join(skippers) |> 
+    select(rank, nat, sail, surname, name, hour_FR:distance_to_leader_nm) |> 
+    mutate(date = all_files$date[i],
+           time = all_files$time[i],
+           .before = rank)
+
+}
+
+all_data <- bind_rows(all_data)
+
+all_data <- all_data |> 
+  mutate(datetime = as_datetime(paste0(date, time)),
+         .before = date, .keep = "unused") |> 
+  select(-hour_FR) |> 
+  mutate(sail = case_when(sail == "FRA85" ~ "FRA 85",
+                          .default = sail)) |> 
+  mutate(across(.cols = ends_with("heading_deg"),
+                .fns = ~ str_remove_all(string = .x, pattern = "°")),
+         across(.cols = ends_with(c("speed_kts", "VMG_kts")),
+                .fns = ~ str_remove_all(string = .x, pattern = " kts")),
+         across(.cols = contains("distance_"),
+                .fns = ~ str_remove_all(string = .x, pattern = " nm")),
+         across(.cols = last30min_heading_deg:distance_to_leader_nm,
+                .fns = ~ as.numeric(.x)),
+         across(.cols = c(rank:sail),
+                .fns = ~ as_factor(.x))) |> 
+  mutate(lat = parzer::parse_lat(lat_deg), .after = lat_deg) |>
+  mutate(lon = parzer::parse_lon(lon_deg), .after = lon_deg) |> 
+  mutate(lat = case_when(is.na(lat_deg) ~ NA,
+                         .default = lat)) |> 
+  mutate(lon = case_when(is.na(lon_deg) ~ NA,
+                         .default = lon))
+
+# Read first dataset
+d1 <- read_csv("03-DATA_PROCESSED/standings_to_20250114060000.csv")
+
+# Combine both datasets
+full_data <- bind_rows(d1, all_data)
+
+# Export the dataset
+
+write_csv(x = full_data, file = "03-DATA_PROCESSED/standings_to_20250224_220000.csv")
+
+# ⬇️ Add latest standings -------------------------------------------------
 
 paths <- list.files(path = "01-DATA_RAW/", full.names = T, pattern = "*.xlsx")
-paths <- paths[384:length(paths)]
+
+# 2025-02-24 : paths[626]
+
+paths <- paths[627:length(paths)]
 
 all_files <- tibble(path = paths) |> 
   separate(col = path, into = c("dir", "file"), sep = "/", remove = FALSE) |> 
@@ -150,6 +240,12 @@ all_data <- all_data |>
   mutate(lon = case_when(is.na(lon_deg) ~ NA,
                          .default = lon))
 
+# Read existing standings dataset
+d1 <- read_csv("03-DATA_PROCESSED/standings_to_20250224_220000.csv")
+
+# Combine both datasets
+full_data <- bind_rows(d1, all_data)
+
 # Export the dataset
 
-write_csv(x = all_data, file = "03-DATA_PROCESSED/standings_since_20250114100000.csv")
+write_csv(x = full_data, file = "03-DATA_PROCESSED/standings_to_20250225_100000.csv")

02-SCRIPTS/get_standings.R

@@ -50,12 +50,12 @@ get_standings <- function(date = NULL, time = NULL, from = NULL, to = NULL, dir)
   }
 }
 
-get_standings(date = "20250224", time = "020000", dir = "01-DATA_RAW/")
-get_standings(date = "20250224", time = "060000", dir = "01-DATA_RAW/")
-get_standings(date = "20250224", time = "100000", dir = "01-DATA_RAW/")
-get_standings(date = "20250224", time = "140000", dir = "01-DATA_RAW/")
-get_standings(date = "20250224", time = "180000", dir = "01-DATA_RAW/")
-get_standings(date = "20250224", time = "220000", dir = "01-DATA_RAW/")
+get_standings(date = "20250225", time = "020000", dir = "01-DATA_RAW/")
+get_standings(date = "20250225", time = "060000", dir = "01-DATA_RAW/")
+get_standings(date = "20250225", time = "100000", dir = "01-DATA_RAW/")
+get_standings(date = "20250225", time = "140000", dir = "01-DATA_RAW/")
+get_standings(date = "20250225", time = "180000", dir = "01-DATA_RAW/")
+get_standings(date = "20250225", time = "220000", dir = "01-DATA_RAW/")
 
 get_standings(from = "20250221", to = "20250223", dir = "01-DATA_RAW/")
 

02-SCRIPTS/gt_standings.R

@@ -0,0 +1,31 @@
+# 📦 Load packages --------------------------------------------------------
+
+library(tidyverse)
+library(glue)
+library(gt)
+
+# ⬇️ Import the data ------------------------------------------------------
+
+
+standings <- read_csv("03-DATA_PROCESSED/standings_to_20250225_100000.csv")
+
+arrivals <- read_csv("04-RESULTS/arrivals.csv")
+
+withdrawals <- read_csv("04-RESULTS/withdrawals.csv")
+
+# 🧹 Clean the data -------------------------------------------------------
+
+arrivals |> 
+  separate(col = duration,
+           into = c("days", "hours", "minutes", "seconds"),
+           remove = FALSE) |> 
+  mutate(across(.cols = days:seconds,
+                .fns = ~parse_number(.x))) |> 
+  mutate(duration = duration(duration),
+         race_time = glue("{days} days {hours} hours {minutes} minutes {seconds} seconds")) |>
+  select(surname, race_time) |> 
+  gt()
+
+standings |> 
+  filter(datetime >= "2025-02-25 10:00:00") |> 
+  drop_na() |> select(surname, name, distance_to_finish_nm)

02-SCRIPTS/passage_caps.R

@@ -276,7 +276,7 @@ write_csv(x = arrivals, file = "04-RESULTS/arrivals.csv")
 
 # Abandons
 
-retired <- tribble(
+withdrawals <- tribble(
   ~surname, ~datetime,
   "Sorel", "2024-11-15 13:25:00",
   "Burton", "2024-12-05 05:00:00",
@@ -287,4 +287,4 @@ retired <- tribble(
   "Boissieres", "2025-02-02 14:00:00"
 )
 
-write_csv(x = retired, file = "04-RESULTS/retired.csv")
+write_csv(x = withdrawals, file = "04-RESULTS/withdrawals.csv")