2021_02_09_lifetime_earn.Rmd

---
title: "TidyTemplate"
date: 2021-02-09
output: html_output
---

# TidyTuesday

Join the R4DS Online Learning Community in the weekly #TidyTuesday event!
Every week we post a raw dataset, a chart or article related to that dataset, and ask you to explore the data.
While the dataset will be “tamed”, it will not always be tidy! As such you might need to apply various R for Data Science techniques to wrangle the data into a true tidy format.
The goal of TidyTuesday is to apply your R skills, get feedback, explore other’s work, and connect with the greater #RStats community!
As such we encourage everyone of all skills to participate!

```{r setup, include=FALSE}

knitr::opts_chunk$set(echo = TRUE)

library(tidyverse)
library(tidytuesdayR)
library(scales)
theme_set(theme_light())

```

# Load the weekly Data

Dowload the weekly data and make available in the `tt` object.

```{r Load}
tt <- tt_load("2021-02-09")
```

```{r}
# Let's make one graph of each dataset

tt$lifetime_earn %>%
  ggplot(aes(lifetime_earn, race, fill = gender)) +
  geom_col(position = "dodge") +
  scale_x_continuous(labels = dollar)

plot_by_race <- function(data, column, labels = dollar, ...) {
  last_year <- data %>%
    group_by(race) %>%
    top_n(1, year)
  
  data %>%
    mutate(race = fct_reorder(race, -{{ column }}, last)) %>%
    ggplot(aes(year, {{ column }}, color = race, ...)) +
    geom_line() +
    geom_text(aes(label = race, color = NULL),
              hjust = 0, data = last_year,
              nudge_x = .2) +
    expand_limits(y = 0,
                  x = 2020) +
    scale_y_continuous(labels = labels) +
    labs(x = "Year",
         color = "Race") +
    theme(legend.position = "none")
}

tt$student_debt %>%
  plot_by_race(loan_debt_pct, labels = percent) +
  labs(y = "% of families with student loan debt")

tt$student_debt %>%
  plot_by_race(loan_debt) +
  labs(y = "Average family student loan debt for aged 25-55 (2016 dollars)")

tt$retirement %>%
  plot_by_race(retirement) +
  labs(y = "Average family liquid retirement savings (2016 dollars)")

tt$home_owner %>%
  plot_by_race(home_owner_pct, labels = percent) +
  labs(y = "Home ownership percentage")

tt$race_wealth %>%
  plot_by_race(wealth_family) +
  facet_wrap(~ type, scales = "free_y") +
  expand_limits(x = 2025) +
  labs(y = "Family wealth (2016 dollars)")

tt$income_time %>%
  spread(percentile, income_family) %>%
  ggplot(aes(year, `50th`, ymin = `10th`, ymax = `90th`)) +
  geom_line() +
  geom_ribbon(alpha = .25) +
  expand_limits(y = 0) +
  scale_y_continuous(labels = dollar) +
  labs(x = "Year", y = "Family income (median with 10th and 90th percentiles)")

tt$income_limits %>%
  filter(dollar_type == "2019 Dollars",
         !str_detect(race, "or in Combination")) %>%
  distinct(race, year, income_quintile, .keep_all = TRUE) %>%
  spread(income_quintile, income_dollars) %>%
  mutate(race = fct_reorder(race, -Fourth)) %>%
  ggplot(aes(year, ymin = Lowest, ymax = Fourth, fill = race)) +
  geom_ribbon(alpha = .25) +
  expand_limits(y = 0) +
  scale_y_continuous(labels = dollar) +
  labs(y = "20th-80th income quantiles")

tt$income_limits %>%
  filter(dollar_type == "2019 Dollars",
         !str_detect(race, "or in Combination")) %>%
  distinct(race, year, income_quintile, .keep_all = TRUE) %>%
  mutate(income_quintile = fct_reorder(income_quintile, -income_dollars)) %>%
  ggplot(aes(year, income_dollars, color = income_quintile)) +
  geom_line() +
  facet_wrap(~ race) +
  scale_y_continuous(labels = dollar) +
  labs(y = "Income quintile limit",
       color = "")

tt$income_limits %>%
  filter(dollar_type == "2019 Dollars",
         !str_detect(race, "or in Combination")) %>%
  distinct(race, year, income_quintile, .keep_all = TRUE) %>%
  mutate(income_quintile = fct_reorder(income_quintile, income_dollars),
         race = fct_reorder(race, -income_dollars, last)) %>%
  ggplot(aes(year, income_dollars, color = race)) +
  geom_line() +
  facet_wrap(~ income_quintile) +
  scale_y_continuous(labels = dollar) +
  labs(y = "Income quintile limit",
       color = "")

tt$income_mean %>%
  filter(dollar_type == "2019 Dollars",
         !str_detect(race, "or in Combination")) %>%
  distinct(race, year, income_quintile, .keep_all = TRUE) %>%
  mutate(income_quintile = fct_reorder(income_quintile, income_dollars),
         race = fct_reorder(race, -income_dollars, last)) %>%
  ggplot(aes(year, income_dollars, color = race)) +
  geom_line() +
  facet_wrap(~ income_quintile, scales = "free_y") +
  scale_y_continuous(labels = dollar) +
  expand_limits(y = 0) +
  labs(y = "Income quintile",
       color = "")

# library(plotly)
# ggplotly(g)
```

```{r}
tt$income_aggregate %>%
  filter(income_quintile != "Top 5%",
         !str_detect(race, "Combination")) %>%
  mutate(income_share = income_share / 100,
         income_quintile = fct_inorder(income_quintile)) %>%
  ggplot(aes(year, income_share, fill = income_quintile)) +
  geom_area() +
  facet_wrap(~ race) +
  scale_y_continuous(labels = percent) +
  labs(x = "",
       y = "% share of income",
       fill = "Income quintile",
       title = "Income distribution over time")

tt$income_aggregate %>%
  filter(income_quintile == "Top 5%",
         !str_detect(race, "Combination")) %>%
  mutate(income_share = income_share / 100) %>%
  plot_by_race(income_share, labels = percent) +
  labs(y = "Share of income earned by the top 5%")

tt$income_distribution %>%
  filter(!str_detect(race, "Combination")) %>%
  mutate(income_distribution = income_distribution / 100,
         income_bracket = fct_inorder(income_bracket)) %>%
  ggplot(aes(year, income_distribution, fill = income_bracket)) +
  geom_area() +
  facet_wrap(~ race) +
  scale_y_continuous(labels = percent) +
  labs(x = "",
       y = "% share of income",
       fill = "Income bracket",
       title = "Income distribution over time")
```

```{r}
tt$income_distribution %>%
  View()
```