STEM Occupations and Wages, BLS.gov/OES data

STEM_OES.R

library(tidyverse)
library(colorplaner)
library(scales)

tmp <- tempfile()
download.file("https://www.bls.gov/oes/2018/may/stem_2018.xlsx", tmp, mode = "wb")
STEM <- read_excel(tmp, sheet = "State")

STEM1 <- group_by(STEM, area_name) %>%
  summarise(total_all = sum(tot_emp))

STEM2 <- select(STEM, 1:4, 7) %>%
  left_join(., STEM1) %>%
  filter(STEM_group == "STEM") %>%
  mutate(Per_STEM = round(tot_emp/total_all, 4)) %>%
  rename(state = area_name,
         hourly = h_mean) %>%
  select(state, Per_STEM, hourly)

state_coords <- structure(list(abbrev = c(state.abb, "PR", "VI", "GU", "DC"),
                                 state = c(state.name, "Puerto Rico", 
                                           "Virgin Islands", "Guam", 
                                           "District of Columbia"),
                                 col = c(8L, 1L, 3L, 6L, 2L, 4L, 11L, 11L, 
                                         10L, 9L, 1L, 3L, 7L, 7L, 6L, 5L, 7L, 6L, 
                                         12L, 10L, 11L, 8L, 6L, 7L, 6L, 4L, 5L, 
                                         3L, 12L, 10L, 4L, 10L, 8L, 5L, 8L, 5L, 
                                         2L, 9L, 12L, 9L, 5L, 7L, 5L, 3L, 11L, 9L,
                                         2L, 8L, 7L, 4L, 12L, 12L, 1L, 10L),
                                 row = c(7L, 1L, 6L, 6L, 5L, 5L, 4L, 5L, 8L, 
                                         7L, 7L, 3L, 3L, 4L, 4L, 6L, 5L, 7L, 1L, 
                                         5L, 3L, 3L, 3L, 7L, 5L, 3L, 5L, 4L, 2L, 
                                         4L, 6L, 3L, 6L, 3L, 4L, 7L, 4L, 4L, 4L, 
                                         6L, 4L, 6L, 8L, 5L, 2L, 5L, 3L, 5L, 2L, 
                                         4L, 8L, 7L, 8L, 6L)),
                            .Names = c("abbrev", "state", "x", "y"),
                            class = "data.frame", row.names = c(NA, -54L)) %>%
  arrange(state) %>% mutate(y = -y) %>%
  right_join(., STEM2)

ggplot(state_coords, aes(x, y)) + 
  geom_tile(aes(fill = Per_STEM), width=0.95, height=0.95) + 
  geom_text(aes(label = abbrev), color = "white") + 
  coord_fixed(ratio = 1) +
  scale_x_continuous(breaks = NULL) + 
  scale_y_continuous(breaks = NULL) +
  aes(fill2 = hourly) + 
  scale_fill_colorplane(labels = scales::percent(c(0.03, 0.06, 
                                                     0.09), 
                                                   accuracy = 1),
                        limits = c(0, 0.1),
                        breaks = c(0.03, 0.06, 0.09)) +
  theme(legend.title=element_blank(),
        legend.position = "right",
        plot.subtitle = element_text(color = "#666666"),
        plot.title = element_text(face = "bold"),
        plot.caption = element_text(color = "#AAAAAA", size = 6),
        panel.background = element_blank()) +
  labs(title = paste("STEM Occupations and Wages"),
       subtitle = "California and Washington do not have a monopoly on STEM occupations and high wages",
       fill = "% of STEM Occupations",
       fill2 = "Average Hourly",
       x = "", y = "",
       caption = paste("BLS.gov/OES,", Sys.Date()))