---
title: "Problem set 5"
author: "Your name here"
date: "Date here"
---

# Load, clean, and wrangle data

```{r load-packages-data, warning=FALSE, message=FALSE}
library(tidyverse)
library(sf)
library(tidytext)
library(gutenbergr)

# Load and clean RIAA data
# https://www.riaa.com/u-s-sales-database/
riaa <- read_csv("data/riaa.csv") %>% 
  # Only look at these kinds of sales
  filter(Format %in% c("LP/EP", "Cassette", "CD", "Download Album", 
                       "Download Single", "Ringtones & Ringbacks", 
                       "On-Demand Streaming (Ad-Supported)", "Paid Subscription")) %>% 
  # Look at inflation-adjusted sales (the other metrics are for
  # non-inflation-adjusted sales and actual units sold)
  filter(Metric == "Value (Adjusted)") %>% 
  mutate(Value = ifelse(is.na(Value), 0, Value))

# Load and clean internet user data
internet_users <- read_csv("data/share-of-individuals-using-the-internet-1990-2015.csv") %>%
  # Rename country code column to ISO_A3 so it matches what's in the Natural Earth shapefile
  rename(users = `Individuals using the Internet (% of population) (% of population)`,
         ISO_A3 = Code)

# Load world shapefile from Natural Earth
# https://www.naturalearthdata.com/downloads/110m-cultural-vectors/
world_shapes <- st_read("data/ne_110m_admin_0_countries/ne_110m_admin_0_countries.shp",
                        stringsAsFactors = FALSE)

# TODO: Load other shapefiles here as needed
```

```{r get-gutenberg-data}
# TODO: Use the gutenberg_download() function to download a bunch of books

# BONUS: If you don't want to redownload these books every time you knit this
# document, use write_csv() to save a CSV version of the book data frame to your
# data folder. Then use read_csv() to load that data instead of gutenberg_download()
```

# Task 1: RIAA music revenues

Do stuff here. 

Note that these values are adjusted for inflation and represent 2017 dollars. Also, try moving beyond the default colors and consider adding labels directly to the plot rather than using a legend.

Tell a story about what's happening in this chart. Interpret it.


# Task 2: World map

Do stuff here.

Tell a story about what's happening in this map. Interpret it.

```{r plot-2015-internet-users}
# Only look at 2015
users_2015 <- internet_users %>%
  filter(Year == 2015)

# left_join takes two data frames and combines them, based on a shared column
# (in this case ISO_A3)
users_map <- world_shapes %>%
  left_join(users_2015, by = "ISO_A3") %>%
  filter(ISO_A3 != "ATA")  # No internet in Antarctica. Sorry penguins.

# TODO: Make a map of internet users with ggplot() + geom_sf()
```


# Task 3: Personal map

Do stuff here. Tell a story about what's happening in this map.


# Task 4: Word frequencies

Do stuff here. Tell stories about what these charts mean.

## Top 10 most frequent words in each book

Stuff here.

## Top 10 most unique words in each book

Stuff here.

## The most distinctive "he X" vs. "she X" bigrams in the author's entire corpus

Stuff here.