library(httr2) # To interact with the Pinball Map API
library(jsonlite) # To parse the JSON responses
library(tidyverse) # To munch, crunch, and plot the data
library(ggrepel) # For less crowed labels on plots
library(WDI) # To pull in other country-level data
library(maps) # For plotting maps

# We're going to pull a lot of data here, possibly abusing the Pinball Map API,
# a bit. But I'm an active patreon sponsor, so hopefully that's OK...
# Did I mention that they are on patreon? https://www.patreon.com/pinballmap

# Pulls and parses JSON from the given URL
get_req_json <- \(url) {
  request(url)  |> 
    req_perform() |> 
    resp_body_json(simplifyVector = TRUE)
}

# Pulling all regions defined by the Pinball Map API
regions <- get_req_json("https://pinballmap.com/api/v1/regions.json")$regions

# Now looping over the region names and for each name pull down all locations
region_locations <- lapply(regions$name, \(name) {
  url <- paste0("https://pinballmap.com/api/v1/region/", name, "/locations.json")
  get_req_json(url)$locations
})

# Pull down all "regionless" locations. Actually, most locations are regionless.
regionless_locations <- get_req_json(
  "https://pinballmap.com/api/v1/locations.json?regionless_only=true"
)$locations

# Finally, combine it all...
locations <- bind_rows(region_locations, regionless_locations) |> 
  select(name, country, city, lat, lon, num_machines) |> 
  mutate(lat = as.numeric(lat), lon = as.numeric(lon)) |> 
  # ... and order locations from north to south
  arrange(desc(lat))

sample_n(locations, size = 5)

locations[c(1, nrow(locations)),]

extreme_locations <- locations |> 
  filter(lat %in% range(lat)) |>
  mutate(display_label = paste(city, country, sep = ", "))

ggplot() +
  geom_polygon(data = map_data("world"), aes(x = long, y = lat, group = group), fill = "lightblue", color = "lightblue3") +
  geom_point(data = locations, aes(x = lon, y = lat), color = "magenta4", size = 1, alpha = 0.50) +
  geom_point(data = extreme_locations, aes(x = lon, y = lat), color = "red2", size = 2) +
  geom_text(data = extreme_locations, aes(x = lon, y = lat, label = display_label), nudge_x = -25) +
  theme_void() +
  ggtitle("Pinball Locations Worldwide (according to pinballmap.com)")

pinball_stats <- locations |> 
  group_by(country) |> 
  summarise(
    n_locations = n(),
    n_machines = sum(num_machines)) |> 
  arrange(desc(n_machines))
pinball_stats

country_stats_by_year = WDI(
  indicator = c(
    "NY.GDP.PCAP.CD", "SP.POP.TOTL", "SP.DYN.LE00.IN", 
    "SP.DYN.TFRT.IN", "IT.NET.USER.ZS", "AG.LND.FRST.ZS"
  ), 
  extra = TRUE, 
  latest = 1
)

country_stats <- country_stats_by_year |> 
  arrange(country, year) |> 
  group_by(country) |>
  # Keep the latest indicator for each country
  summarize(across(everything(), \(x) last(na.omit(x)))) |>
  select(
    country_name = country, 
    country_code = iso2c,
    gdp_per_capita = NY.GDP.PCAP.CD,
    population = SP.POP.TOTL,
    life_expectancy = SP.DYN.LE00.IN, 
    births_per_woman = SP.DYN.TFRT.IN,
    internet_usage_perc = IT.NET.USER.ZS,
    forest_coverage_perc = AG.LND.FRST.ZS
  )

pinball_country_stats <- country_stats |> 
  # Let's keep only larger countries
  filter(population > 500000) |> 
  inner_join(pinball_stats, by = join_by(country_code == country)) |>
  mutate(
    n_locations_per_million_capita = round(n_locations / population * 1000000, 3),
    n_machines_per_million_capita = round(n_machines / population * 1000000, 3)) |>
  arrange(desc(n_machines_per_million_capita))

select(pinball_country_stats, 
  country_name, population, n_machines, n_machines_per_million_capita
)

pinball_country_stats |> 
  head(10) |> 
  mutate(
    country_name = forcats::fct_reorder(country_name, n_machines_per_million_capita),
    n_machines_per_million_capita = round(n_machines_per_million_capita, 1)
  ) |>
  ggplot(aes(x = n_machines_per_million_capita, y = country_name)) +
    geom_col(fill = "lightgreen") +
    geom_text(aes(label = n_machines_per_million_capita), hjust = 1.2) +
    labs(
      x = "Number of machines per million capita",
      y = "Country",
      title = "Top 10 countries by number of public pinball machines per million capita"
    )

ggplot(pinball_country_stats, aes(x = life_expectancy, y = n_machines_per_million_capita)) +
  geom_label_repel(aes(label = country_name), fill = "lightblue",  max.overlaps = Inf, box.padding  = -0.2) +
  scale_x_log10(labels = scales::label_comma(), limits = c(67, NA)) +
  scale_y_log10(labels = scales::label_comma()) +
  labs(
    x = "Life expectancy at birth (years)",
    y = "Number of machines per million capita",
    title = "Number of Public Pinball Machines per Capita vs life expectancy"
  )

ggplot(pinball_country_stats, aes(x = births_per_woman, y = n_machines_per_million_capita)) +
  geom_label_repel(aes(label = country_name), fill = "lightcoral",  max.overlaps = Inf, box.padding = -0.2) +
  scale_x_log10(labels = scales::label_comma()) +
  scale_y_log10(labels = scales::label_comma()) +
  labs(
    x = "Fertility rate (no. births per woman)",
    y = "Number of machines per million capita",
    title = "Number of Public Pinball Machines per Capita vs fertility rate"
  )

ggplot(pinball_country_stats, aes(x = gdp_per_capita, y = n_machines_per_million_capita)) +
  geom_label_repel(aes(label = country_name), fill = "lightgreen", max.overlaps = Inf, box.padding  = -0.2) +
  geom_smooth(method = "lm", se = FALSE, color = "#d03030aa") +
  scale_x_log10(labels = scales::label_comma()) +
  scale_y_log10(labels = scales::label_comma()) +
  labs(
    x = "GDP per capita (in USD)",
    y = "Number of machines per million capita",
    title = "Number of Public Pinball Machines per Capita vs GDP per Capita"
  )

cor(
  log(pinball_country_stats$n_machines_per_million_capita),
  log(pinball_country_stats$gdp_per_capita)
)

lm_model <- lm(log(n_machines_per_million_capita) ~ log(gdp_per_capita), data = pinball_country_stats)
pinball_country_stats$residual <- residuals(lm_model)

ggplot(pinball_country_stats, aes(x = gdp_per_capita, y = residual)) +
  geom_label_repel(aes(label = country_name), fill = "lightgreen",  max.overlaps = Inf, box.padding = -0.2) +
  geom_smooth(method = "lm", se = FALSE, color = "#d03030aa") +
  scale_x_log10(labels = scales::label_comma()) +
  labs(
    x = "GDP per capita (in USD)",
    y = "Residual",
    title = "Residual after accounting for GDP per capita"
  )

pinball_country_stats |> 
  select(country_name, country_code, population, n_locations, n_machines,  n_machines_per_million_capita, gdp_per_capita) |>
  write_csv("public_pinball_machines_per_capita_2024.csv")