wimbledon.2013.csv

wimbledon.2013.csv

wimbledon.R

library(rvest)
library(dplyr)
library(stringr)

s = html_session("http://www.atpworldtour.com/en/scores/archive/wimbledon/540/2013/results")
rows = s %>% html_nodes("div#scoresResultsContent tr")

matches = data.frame()
for(row in rows) {  
  players = row %>% html_nodes("td.day-table-name a")
  seedings = row %>% html_nodes("td.day-table-seed")
  score = row %>% html_node("td.day-table-score a")
  
  if(!is.null(score)) {
    player1 = players[1] %>% html_text() %>% str_trim()
    seeding1 = ifelse(!is.na(seedings[1]), seedings[1] %>% html_node("span") %>% html_text() %>% str_trim(), NA)
    
    player2 = players[2] %>% html_text() %>% str_trim()
    seeding2 = ifelse(!is.na(seedings[2]), seedings[2] %>% html_node("span") %>% html_text() %>% str_trim(), NA)
        
    matches = rbind(data.frame(winner = player1, 
                               winner_seeding = seeding1, 
                               loser = player2, 
                               loser_seeding = seeding2,
                               score = score %>% html_text() %>% str_trim(),
                               round = round), matches)
    
  } else {
    round = row %>% html_node("th") %>% html_text()
  }
}

main_matches = matches %>% filter(!grepl("Qualifying", round)) %>% mutate(year = 2013)

write.csv(main_matches, "/tmp/wimbledon.2013.csv", row.names = FALSE)
?write.csv

# have made a mistake further up when there's only one qualifier - it always gets set to be the winner even if it isn't

main_matches$winner_type = NA
main_matches$winner_type[main_matches$winner_seeding == "(WC)"] = "wildcard"
main_matches$winner_type[main_matches$winner_seeding == "(Q)"] = "qualifier"
main_matches$winner_type[main_matches$winner_seeding == "(LL)"] = "lucky loser"

main_matches$loser_type = NA
main_matches$loser_type[main_matches$loser_seeding == "(WC)"] = "wildcard"
main_matches$loser_type[main_matches$loser_seeding == "(Q)"] = "qualifier"
main_matches$loser_type[main_matches$loser_seeding == "(LL)"] = "lucky loser"

tidy_seeding = function(seeding) {
  no_brackets = gsub("\\(|\\)", "", seeding)
  return(gsub("WC|Q|L", NA, no_brackets))
}

main_matches = main_matches %>% mutate(winner_seeding = as.numeric(tidy_seeding(winner_seeding)), loser_seeding = as.numeric(tidy_seeding(loser_seeding)))
main_matches$round = factor(main_matches$round, levels =  c("Round of 128", "Round of 64", "Round of 32", "Round of 16", "Quarter-Finals", "Semi-Finals", "Finals"))

# The underdog won
main_matches %>%  filter((winner_seeding > loser_seeding) | (is.na(winner_seeding) & !is.na(loser_seeding)))

# Seeds who lost in the first round
main_matches %>%  filter(round == "Round of 128" & !is.na(loser_seeding))

# How far did the unseeded players get?
main_matches %>% filter(is.na(loser_seeding)) %>% arrange(desc(round)) %>% head(5)

# How far did the wildcards/qualifier/lucky losers get?
main_matches %>% filter(loser_type == "wildcard") %>% arrange(desc(round)) %>% head(5)
main_matches %>% filter(loser_type == "qualifier") %>% arrange(desc(round)) %>% head(5)
main_matches %>% filter(loser_type == "lucky loser") %>% arrange(desc(round)) %>% head(5)

main_matches$winner = as.character(main_matches$winner)
main_matches$loser = as.character(main_matches$loser)

# How far did a particular player get?
round_reached = function(player, main_matches) {
  furthest_match = main_matches %>% 
    filter(winner == player | loser == player) %>% 
    arrange(desc(round)) %>% 
    head(1)  

    return(ifelse(furthest_match$winner == player, "Winner", as.character(furthest_match$round)))
}

player = c("Rafael Nadal", "Andy Murray")
main_matches %>% 
    filter(winner %in% player | loser %in% player) %>% 
    group_by(winner, loser)
    arrange(desc(round)) %>% 
    head(1)  

round_reached("Novak Djokovic", main_matches)
round_reached("Rafael Nadal", main_matches)
round_reached("Andy Murray", main_matches)

rbind(main_matches %>% filter(winner_seeding %in% 1:8) %>% mutate(name = winner, seeding = winner_seeding), 
      main_matches %>% filter(loser_seeding %in% 1:8) %>% mutate(name = loser, seeding = loser_seeding)) %>%
  select(name, seeding) %>%
  distinct() %>%
  arrange(seeding) %>%
  group_by(name) %>%
  mutate(round_reached = round_reached(name, main_matches))


# Which seeds didn't get as far as they should have?