In beanumber/colleges: Data about college enrollments, donations, and athletics

Data about colleges

devtools::install_github("beanumber/colleges")

library(tidyverse)
library(colleges)
ncaa %>%
  group_by(Year) %>%
  summarize(N = n(),
            num_bball_teams = sum(!is.na(bball_wins)),
            num_fball_teams = sum(!is.na(fball_wins)),
            num_bball_no_fball = sum(!is.na(bball_wins) & is.na(fball_wins)),
            num_fball_no_bball = sum(is.na(bball_wins) & !is.na(fball_wins)),
            bball_wins = sum(bball_wins, na.rm = TRUE), bball_losses = sum(bball_losses, na.rm = TRUE),
            fball_wins = sum(fball_wins, na.rm = TRUE), fball_losses = sum(fball_losses, na.rm = TRUE),
            bball_champs = sum(bb_champs, na.rm = TRUE), fball_champs = sum(fb_champs, na.rm = TRUE),
            bb_champs = max(ifelse(bb_champs, school_name, "")),
            fb_champs = max(ifelse(fb_champs, school_name, ""), na.rm = TRUE),
            enrolled = sum(enrolled, na.rm = TRUE),
            admitted = sum(admitted, na.rm = TRUE),
            applied = sum(applied, na.rm = TRUE),
            act_composite_75 = mean(act_composite_75, na.rm = TRUE),
            sat_75 = mean(sat_75_avg, na.rm = TRUE)) %>%
  mutate(admit_rate = admitted / applied,
         yield = enrolled / admitted)

ggplot(ncaa, aes(x = Year, y = yield, group = school_name)) + 
  geom_point() + geom_line()

beanumber/colleges documentation built on May 17, 2019, 5:47 p.m.