women-workplace.Rmd

---
title: "Women in the Workplace"
output: html_document
---

```{r setup, include=FALSE}
knitr::opts_chunk$set(echo = TRUE)
```

```{r}
library(tidyverse)
library(scales)
theme_set(theme_light())

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

```{r}
summarize_jobs_gender <- function(tbl) {
  tbl %>%
    summarize(total_earnings = sum(total_earnings * total_workers) / sum(total_workers),
              total_earnings_male = sum(total_earnings_male * workers_male, na.rm = TRUE) /
                sum(workers_male[!is.na(total_earnings_male)]),
              total_earnings_female = sum(total_earnings_female * workers_female, na.rm = TRUE) /
                sum(workers_female[!is.na(total_earnings_female)]),
              total_workers = sum(total_workers),
              workers_male = sum(workers_male),
              workers_female = sum(workers_female)) %>%
    mutate(wage_percent_of_male = total_earnings_female / total_earnings_male)
}

by_year_major_category <- jobs_gender %>%
  filter(complete.cases(.)) %>%
  group_by(year, major_category) %>%
  summarize_jobs_gender()

by_year_major_category %>%
  mutate(major_category = fct_reorder(major_category, -total_earnings)) %>%
  ggplot(aes(year, total_earnings, color = major_category)) +
  geom_line() +
  expand_limits(y = 0)

by_year_major_category %>%
  mutate(major_category = fct_reorder(major_category, -wage_percent_of_male)) %>%
  ggplot(aes(year, wage_percent_of_male, color = major_category)) +
  geom_line()
```

```{r}
by_minor_category_2016 <- jobs_gender %>%
  filter(year == 2016) %>%
  group_by(major_category, minor_category) %>%
  summarize_jobs_gender() %>%
  ungroup()
```

```{r}
by_minor_category_2016 %>%
  mutate(minor_category = fct_reorder(minor_category, wage_percent_of_male)) %>%
  ggplot(aes(minor_category, wage_percent_of_male, fill = major_category)) +
  geom_col() +
  coord_flip()
```

```{r}
library(plotly)

p <- jobs_gender %>%
  filter(year == 2016) %>%
  filter(major_category == "Healthcare Practitioners and Technical") %>%
  arrange(desc(wage_percent_of_male)) %>%
  ggplot(aes(workers_female / total_workers,
             total_earnings,
             size = total_workers,
             label = occupation)) +
  geom_point() +
  scale_size_continuous(range = c(1, 10)) +
  labs(size = "Total # of workers",
       x = "% of workforce reported as female",
       y = "Median salary in the occupation") +
  scale_x_continuous(labels = percent_format()) +
  scale_y_continuous(labels = dollar_format()) +
  expand_limits(y = 0)

ggplotly(p)
```

```{r}
p <- jobs_gender %>%
  filter(year == 2016,
         total_workers >= 20000) %>%
  filter(major_category == "Computer, Engineering, and Science") %>%
  arrange(desc(wage_percent_of_male)) %>%
  ggplot(aes(workers_female / total_workers,
             total_earnings_female / total_earnings_male,
             color = minor_category,
             size = total_workers,
             label = occupation)) +
  geom_point() +
  scale_size_continuous(range = c(1, 10)) +
  labs(size = "Total # of workers",
       x = "% of workforce reported as female",
       y = "% of median female salary / median male") +
  scale_x_continuous(labels = percent_format()) +
  scale_y_continuous(labels = percent_format())

ggplotly(p)
```