Bonus: Basic EDA Analysing Games
This section will perform some exploratory data analysis on the data extracted by get_raw_chessdotcom(), and then having used some of the analysis functions explained above. It is by no means an exhaustive list of topics to analyse, rather, it is designed to give the user a few ideas of what can be done with the analysis data provided.
chessdotcom_game_data_all_months %>%
count(TimeClass) %>%
ggplot(aes(x= reorder(TimeClass,n), y= n)) +
geom_col(fill = "steelblue", colour = "grey40", alpha = 0.7) +
labs(x= "Game Style", y= "Number of Games") +
ggtitle("WHICH TIME CLASSES ARE PLAYED MOST BY USER") +
coord_flip() +
theme_minimal() +
theme(panel.grid.major.y = element_blank())
chessdotcom_game_data_all_months %>%
mutate(MonthEnd = paste(year(EndDate), str_pad(lubridate::month(ymd(EndDate)), 2, side = "left", pad = "0"), sep = "-")) %>%
mutate(UserResult = ifelse(Winner == Username, "Win", ifelse(Winner == "Draw", "Draw", "Loss"))) %>%
group_by(MonthEnd, UserResult) %>%
summarise(n = n()) %>%
mutate(WinPercentage = n / sum(n)) %>%
filter(UserResult == "Win") %>%
ggplot(aes(x= MonthEnd, y= WinPercentage, group=1)) +
geom_line(colour= "steelblue", size=1) +
geom_hline(yintercept = 0.5, linetype = 2, colour = "grey40") +
scale_y_continuous(limits = c(0,1)) +
labs(x= "Month Game Ended", y= "Win %") +
ggtitle("MONTHLY WINNING %") +
theme_minimal()
chessdotcom_game_data_all_months %>%
filter(TimeClass %in% c("blitz", "daily")) %>%
mutate(UserELO = as.numeric(ifelse(Username == White, WhiteElo, BlackElo))) %>%
mutate(MonthEnd = paste(year(EndDate), str_pad(lubridate::month(ymd(EndDate)), 2, side = "left", pad = "0"), sep = "-")) %>%
group_by(MonthEnd, TimeClass) %>%
summarise(AverageELO = mean(UserELO, na.rm = T)) %>%
ggplot(aes(x= MonthEnd, y= AverageELO, group=1)) +
geom_line(colour= "steelblue", size=1) +
labs(x= "Month Game Ended", y= "Average ELO") +
ggtitle("MONTHLY AVERAGE ELO RATING") +
facet_wrap(~ TimeClass, scales = "free_y", ncol = 1) +
theme_minimal()
chessdotcom_game_data_all_months %>%
mutate(OpponentELO = as.numeric(ifelse(Username == White, BlackElo, WhiteElo)),
UserResult = ifelse(Winner == Username, "Win", ifelse(Winner == "Draw", "Draw", "Loss"))) %>%
filter(TimeClass %in% c("blitz", "daily")) %>%
ggplot(aes(x= OpponentELO, fill = UserResult)) +
geom_density(alpha = 0.3) +
ggtitle("HOW DO WE FARE AGAINST DIFFERENT ELOs?") +
facet_wrap(~ TimeClass, scales = "free", ncol = 1) +
theme_minimal()