plastic-waste.Rmd

---
title: "Plastic Waste"
output: html_document
---

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

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

coast_vs_waste <- readr::read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-05-21/coastal-population-vs-mismanaged-plastic.csv")

mismanaged_vs_gdp <- readr::read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-05-21/per-capita-mismanaged-plastic-waste-vs-gdp-per-capita.csv")

waste_vs_gdp <- readr::read_csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2019/2019-05-21/per-capita-plastic-waste-vs-gdp-per-capita.csv")
```

```{r}
library(janitor)

# Data cleaning
clean_dataset <- function(tbl) {
  tbl %>%
    clean_names() %>%
    rename(country = entity,
           country_code = code) %>%
    filter(year == 2010) %>%
    select(-year)
}

plastic_waste <- coast_vs_waste %>%
  clean_dataset() %>%
  select(-total_population_gapminder) %>%
  inner_join(clean_dataset(mismanaged_vs_gdp) %>%
               select(-total_population_gapminder), by = c("country", "country_code")) %>%
  inner_join(clean_dataset(waste_vs_gdp), by = c("country", "country_code")) %>%
  select(country,
         country_code,
         mismanaged_waste = mismanaged_plastic_waste_tonnes,
         coastal_population,
         total_population = total_population_gapminder,
         mismanaged_per_capita = per_capita_mismanaged_plastic_waste_kilograms_per_person_per_day,
         gdp_per_capita = gdp_per_capita_ppp_constant_2011_international_rate) %>%
  filter(!is.na(mismanaged_waste))
```

```{r}
g1 <- plastic_waste %>%
  arrange(-total_population) %>%
  mutate(pct_population_coastal = pmin(1, coastal_population / total_population),
         high_coastal_pop = ifelse(pct_population_coastal >= .8, ">=80%", "<80%")) %>%
  ggplot(aes(gdp_per_capita, mismanaged_per_capita)) +
  geom_point(aes(size = total_population)) +
  geom_text(aes(label = country), vjust = 1, hjust = 1, check_overlap = TRUE) +
  scale_x_log10(labels = dollar_format()) +
  scale_y_log10() +
  scale_size_continuous(guide = FALSE) +
  labs(x = "GDP per capita",
       y = "Mismanaged plastic waste (kg per person per day)",
       color = "Coastal population",
       title = "How plastic waste mismanagement correlates with country income",
       subtitle = "Based in Our World in Data 2010 numbers. Size represents total population")

g1
```

```{r}
plastic_waste %>%
  mutate(pct_population_coastal = pmin(1, coastal_population / total_population)) %>%
  arrange(-total_population) %>%
  ggplot(aes(pct_population_coastal, mismanaged_per_capita)) +
  geom_point(aes(size = total_population)) +
  geom_text(aes(label = country), vjust = 1, hjust = 1, check_overlap = TRUE)
```

```{r}
tbl_df(iso3166)

library(fuzzyjoin)

plastic_data <- plastic_waste %>%
  inner_join(iso3166, by = c("country_code" = "a3"))

map_data("world") %>%
  tbl_df() %>%
  filter(region != "Antarctica") %>%
  regex_left_join(plastic_data, by = c("region" = "mapname")) %>%
  ggplot(aes(long, lat, group = group, fill = mismanaged_per_capita)) +
  geom_polygon() +
  scale_fill_gradient2(trans = "log10",
                       low = "blue",
                       high = "red",
                       mid = "pink",
                       midpoint = log10(.02)) +
  coord_fixed(2) +
  ggthemes::theme_map() +
  labs(fill = "Mismanaged plastic waste per-cap",
       title = "Where in the world is waste mismanaged?")
```

### Comparing to other country stats

```{r}
library(WDI)

indicators <- c("co2_emissions_per_capita" = "EN.ATM.CO2E.PC",
                "cpia_transparency" = "IQ.CPA.TRAN.XQ")

other_data <- WDI(indicator = indicators, start = 2010, end = 2010) %>%
  tbl_df() %>%
  select(-country)

plastic_with_indicators <- other_data %>%
  inner_join(plastic_data, by = c(iso2c = "a2")) %>%
  arrange(desc(total_population))

plastic_with_indicators %>%
  ggplot(aes(gdp_per_capita, co2_emissions_per_capita)) +
  geom_point(aes(size = total_population)) +
  geom_text(aes(label = country), vjust = 1, hjust = 1, check_overlap = TRUE) +
  scale_size_continuous(guide = FALSE) +
  scale_x_log10() +
  scale_y_log10() +
  labs(x = "GDP per capita",
       y = "CO2 emissions (tons per capita)",
       color = "Coastal population",
       title = "How plastic waste mismanagement correlates with country income",
       subtitle = "Based in Our World in Data 2010 numbers. Size represents total population")

library(patchwork)

g2 +
  labs(title = "CO2 emissions are correlated with country income, but not plastic waste") +
  g1 +
  labs(title = "",
       subtitle = "")
```

```{r}
# Looking by CPIA trust rating is a trust
plastic_with_indicators %>%
  filter(!is.na(cpia_transparency)) %>%
  ggplot(aes(cpia_transparency, mismanaged_per_capita, group = cpia_transparency)) +
  geom_boxplot()

plastic_with_indicators %>%
  arrange(desc(cpia_transparency)) %>%
  View()
```