```{r, message=FALSE} library(tidyverse) library(dplyr) library(ggplot2) ``` # 1. Data Import ```{r} url<-url("https://github.com/pjournal/mef03-demirefe91/blob/master/atp_tennis_data_2017.RData?raw=TRUE") atp_data<-load(url) glimpse(atp_data) ``` ## 1.2. Flag Code Rankings ```{r} singles_winners<-left_join(tourney_df,player_df,by=c("singles_winner_player_id"="player_id")) champ_flags_df<-singles_winners%>%select(singles_winner_player_id,flag_code)%>%count(flag_code,sort=T) champ_flags_df ``` ## 1.3. Rank countries which did not get any singles championships by the games won when they win the match ```{r} nonchamp_players<- player_df %>%select(player_id, flag_code) %>%anti_join(., champ_flags_df,by="flag_code") nonchamp_players %>% left_join(.,score_df, by= c("player_id"="winner_player_id")) %>%group_by(flag_code) %>%summarise(total_won= sum(winner_games_won, na.rm=TRUE)) %>%arrange(desc(total_won)) ``` ## 1.3. Hand Details of Champions ```{r} prize_money <- inner_join(tourney_df, player_df, by=c("singles_winner_player_id" = "player_id")) %>% count(handedness, backhand) %>% arrange(desc(n)) prize_money ``` ## 1.4. Total Match Counts And Average Match Durations of Tournaments ```{r} stats_df <- stats_df %>% mutate(num_tourney_id=as.numeric(tourney_id)) tournaments <- inner_join(tourney_df, stats_df, by=c("tourney_id" ="num_tourney_id")) %>% group_by(tourney_name) %>% summarise(total_duration = sum(match_duration)) %>% arrange(desc(total_duration)) tournaments ```