# load rds
acc_base_teams <- readRDS("~/byc/posts/byc_025/acc_base_teams.rds")
# find ids
ids <- acc_base_teams$team_id
# function to scrape schedule
acc_results <- function(id) {
ncaa_schedule_info(team_id = id, year = 2023) %>%
filter(home_team_conference == "ACC" & away_team_conference == "ACC") %>%
filter(!is.na(home_team_score))
}
# grab acc games
acc_scores <- lapply(ids, acc_results)
acc_results_2023 <- as.data.frame(do.call(rbind, acc_scores)) %>%
distinct(contest_id, .keep_all = TRUE )
# find differential by team
home_diffs <- acc_results_2023 %>%
mutate(h_diff = home_team_score - away_team_score) %>%
group_by(home_team) %>%
summarize(home_diff = sum(h_diff)) %>%
rename(team = home_team)
away_diffs <- acc_results_2023 %>%
mutate(a_diff = away_team_score - home_team_score) %>%
group_by(away_team) %>%
summarize(away_diff = sum(a_diff)) %>%
rename(team = away_team)
full_diffs <- merge(home_diffs, away_diffs, by = "team") %>%
mutate(full_diff = (home_diff + away_diff)) %>%
select(team, full_diff, home_diff, away_diff)
# find conference records by team
home_results <- acc_results_2023 %>%
mutate(h_result = if_else(home_team_score > away_team_score, "W", "L")) %>%
group_by(home_team, h_result) %>%
count() %>%
pivot_wider(
names_from = h_result,
values_from = n) %>%
rename(team = home_team, h_w = W, h_l = L)
away_results <- acc_results_2023 %>%
mutate(a_result = if_else(away_team_score > home_team_score, "W", "L")) %>%
group_by(away_team, a_result) %>%
count() %>%
pivot_wider(
names_from = a_result,
values_from = n) %>%
rename(team = away_team, a_w = W, a_l = L)
full_recs <- merge(home_results, away_results, by = "team") %>%
replace(is.na(.), 0) %>%
mutate(W = (h_w + a_w), L = (h_l + a_l)) %>%
select(team, W, L, h_w, h_l, a_w, a_l)
diffs_recs <- merge(full_diffs, full_recs, by ="team")
# function to get RPI data
rpi_ranks <- function(url) {
rpi_page <- read_html(url)
rpi_rk <- rpi_page %>%
html_nodes("table") %>%
.[1] %>%
html_table(fill = TRUE)
rpi_table <- as.data.frame(rpi_rk)
rpi_table <- rpi_table %>%
mutate(record = str_split(Record, "-", simplify = T),
wins = record[,1],
losses = record[,2]
)
}
rpi <- rpi_ranks(url = "https://www.ncaa.com/rankings/baseball/d1/rpi")
# make rpi table
acc_rpi <- rpi %>%
filter(Conference == "ACC") %>%
select(School, Rank, wins, losses) %>%
rename(team = School, rpi = Rank, o_w = wins, o_l = losses)
# atlantic teams
atl_teams = c("Wake Forest", "Boston College", "Louisville", "NC State", "Notre Dame", "Florida St.", "Clemson")
# make the big table
total_records <- merge(acc_rpi, diffs_recs, by = "team") %>%
mutate(div = if_else(team %in% atl_teams, "Atlantic", "Coastal")) %>%
select(div, team, rpi, o_w, o_l, W, L, full_diff, h_w, h_l, home_diff, a_w, a_l, away_diff)
