Tidy Tuesday Week 37

This notebook uses #TidyTuesday week 37 Formula 1 Races data from ergast.com/mrd/db, and the new {gtExtras} package from Thomas Mock.

# Load Libraries 
library(tidyverse)
library(gt)
#remotes::install_github("jthomasmock/gtExtras")
library(gtExtras)

# Suppress summarise info
options(dplyr.summarise.inform = FALSE)

# Import data
races <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-09-07/races.csv',show_col_types = FALSE)
driver_standings <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-09-07/driver_standings.csv',show_col_types = FALSE)
drivers <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-09-07/drivers.csv',show_col_types = FALSE)
results <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2021/2021-09-07/results.csv',show_col_types = FALSE)

# Dataset of results by race, driver and season from https://github.com/rfordatascience/tidytuesday/blob/master/data/2021/2021-09-07/readme.md

driver_results_df <- driver_standings %>% 
  left_join(races, by = "raceId") %>% 
  rename(driver_url = url) %>% 
  left_join(drivers, by = "driverId") 

# get top 10 drivers with most wins (position==1)
wins10 = drivers %>% 
  left_join(results, by = "driverId") %>% 
  left_join(races, by = "raceId") %>% 
  filter(position == "1") %>%
  mutate(Driver = paste(forename, surname)) %>%
  count(Driver, sort=T) %>% slice(1:10)

# Data preparation
d1 = driver_results_df %>% 
  mutate(Driver = paste(forename, surname)) %>%
  select(Driver, year, wins, position, points) %>%
  group_by(Driver,year) %>%
  summarise(wins = sum(wins), points=sum(points)) %>%
  filter(Driver %in% wins10$Driver) %>%
  ungroup() %>%
  mutate(wins_1 = ifelse(wins==0,0,1)) %>%
  group_by(Driver) %>%
  summarise(
    Wins = length(wins_1[wins_1==1]),
    Losses = length(wins_1[wins_1==0]),
    Outcomes = list(wins_1), .groups = "drop",
    Points= sum(points),
    Spark = list(points),
    ) %>%
  arrange(desc(Points))

d2 = d1 %>% left_join(wins10, by="Driver")
d3 = d2 %>% select(Driver,"Wins"=n, "Years with Wins" = Wins, "Years with Losses"=Losses,
                   Outcomes, Points, "Sparkline" = Spark) %>% arrange(desc(Wins))

d3

d3 %>%
  gt() %>%
  gt_plt_winloss(Outcomes) %>%
  gt_kable_sparkline(Sparkline, height=45) %>%
  gt_theme_espn() %>%
  tab_header(title="Top 10 Formula 1 Drivers with the most wins") %>%
  tab_source_note(source_note = "Data source: ergast.com/mrd/db") %>%
  cols_align(
  align = "center",
  columns = c(Wins,`Years with Wins`,`Years with Losses`)) %>%
  cols_width(`Years with Wins` ~px(90),
             `Years with Losses` ~px(90),)

Top 10 Formula 1 Drivers with the most wins
Driver	Wins	Years with Wins	Years with Losses	Outcomes	Points	Sparkline
Lewis Hamilton	99	15	0		40351.0
Michael Schumacher	91	15	4		14514.0
Sebastian Vettel	53	10	5		31307.0
Alain Prost	51	11	2		6829.5
Ayrton Senna	41	9	2		5531.0
Fernando Alonso	32	9	9		19231.0
Nigel Mansell	31	8	7		3928.0
Jackie Stewart	27	8	1		2574.0
Niki Lauda	25	8	5		3768.5
Jim Clark	25	7	2		1516.0
Data source: ergast.com/mrd/db