TidyTuesday: Women in the Workforce

Analyzing data for #tidytuesday week of 3/05/2019 (source)

library(tidyverse)
library(scales)
library(lubridate)

jobs_gender <- read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-03-05/jobs_gender.csv")

jobs_gender %>%
  filter(year == '2016') %>%
  mutate(male_diff = ((((total_earnings_male/total_earnings)-1)*workers_male)/total_workers),
         female_diff = (((total_earnings_female/total_earnings)-1)*workers_female)/total_workers) %>%
  ggplot() +
  geom_jitter(aes(total_earnings, female_diff), 
              color = 'salmon',
              alpha = 0.5,
              size = 2.5) +
  geom_jitter(aes(total_earnings, male_diff), 
              color = 'steelblue',
              alpha = 0.5, 
              size = 2.5) +
  geom_hline(yintercept = 0, color = 'grey54', lty = 'dashed') +
  facet_wrap(~major_category) +
  scale_x_continuous(labels = dollar_format(),
                     limits = c(0,200000)) +
  scale_y_continuous(labels = percent_format(round(1)),
                     limits = c(-0.3,0.3)) +
  labs(x = "Average Median Earnings",
       y = "Difference from Average",
       caption = "Graphic: @eeysirhc\nSource: Bureau of Labor Statistics",
       title = "2016 Earnings Differences (Weighted) by Job Sector",
       subtitle = "Blue = Male; Red = Female") +
  theme_bw() +
  theme(panel.grid.major = element_blank(),
        panel.grid.minor = element_blank(),
        plot.subtitle = element_text(size = 12),
        legend.position = 'none')