UC salaries by rank & dept

uc_salaries_by_dept_and_rank.R

library(XML)
library(ggplot2)

df <- readHTMLTable("http://projects.dailycal.org/paychecker/departments/")[[1]]

DeMoney <- function(x) as.numeric(gsub(",", "", gsub("\\$", "", as.character(x))))

money.columns <- c("All", "Professor", "Associate professor", "Assistant professor", 
                   "Lecturer")

for (money.column in money.columns){
    df[, money.column] <- sapply(df[,money.column], DeMoney)
}

df.long <- df %>%
    dplyr::select(-Lecturer, -All) %>% 
    melt(id.vars = c("Department")) %>%
    group_by(Department) %>%
    mutate(overall = mean(value[variable == "Professor"], na.rm = TRUE))

df.long$Department <- with(df.long, reorder(Department, overall, mean))

ggplot(data = df.long %>% na.omit, aes(x = value, y = Department, shape = variable)) +
    geom_point() +
    scale_x_continuous(labels = scales::dollar) +
    xlab("Annual salary")

The resulting plot is here: https://twitter.com/johnjhorton/status/1002298914354188288