Mapping oil production by country

library(tidyverse)
library(sf)
library(rvest)
library(stringr)
library(scales)

df.oil <- read_html("https://en.wikipedia.org/wiki/List_of_countries_by_oil_production") %>%
  html_nodes("table") %>%
  .[[1]] %>%
  html_table()

colnames(df.oil) <- c('rank', 'country', 'oil_bbl_per_day')

df.oil <- df.oil %>% mutate(rank = as.integer(rank)) 

df.oil <- df.oil %>% 
  mutate(oil_bbl_per_day = str_replace_all(oil_bbl_per_day,',','') 
  %>% as.integer())

df.oil <- df.oil %>% 
  mutate(opec_ind = if_else(str_detect(country, 'OPEC'), 1, 0))

df.oil <- df.oil %>% 
  mutate(country = country %>% str_replace(' \\(OPEC\\)', '') %>% str_replace('\\s{2,}',' '))

df.oil <- df.oil %>% 
  select(rank, country, opec_ind, oil_bbl_per_day)

map.world <- map_data('world')

anti_join(df.oil, map.world, by = c('country' = 'region'))

##   rank                           country opec_ind oil_bbl_per_day
## 1    3                     United States        0         8875817
## 2   20                    United Kingdom        0          939760
## 3   30            Congo, Republic of the        0          308363
## 4   34             Sudan and South Sudan        0          255000
## 5   47               Trinidad and Tobago        0           60090
## 6   67 Congo, Democratic Republic of the        0           20000

map.oil <- left_join( map.world, df.oil, by = c('region' = 'country'))

ggplot(map.oil, aes( x = long, y = lat, group = group )) +
  geom_polygon(aes(fill = oil_bbl_per_day))

# PLOT with red highlight around OPEC countries

ggplot(map.oil, aes( x = long, y = lat, group = group )) +
  geom_polygon(aes(color = as.factor(opec_ind))) +
  scale_color_manual(values = c('1' = 'red', '0' = NA))

ggplot(map.oil, aes( x = long, y = lat, group = group )) +
  geom_polygon(aes(color = as.factor(opec_ind), fill = oil_bbl_per_day)) +
  scale_color_manual(values = c('1' = 'red', '0' = NA))

ggplot(map.oil, aes( x = long, y = lat, group = group )) +
  geom_polygon(aes(fill = oil_bbl_per_day, color = as.factor(opec_ind))) +
  scale_fill_gradientn(colours = c('#461863','#404E88','#2A8A8C','#7FD157','#F9E53F')
                       ,values = scales::rescale(c(100,96581,822675,3190373,10000000))
                       ,labels = comma
                       ,breaks = c(100,96581,822675,3190373,10000000)
  ) +
  guides(fill = guide_legend(reverse = T)) +
  labs(fill = 'Barrels per day\n2016'
       ,color = 'OPEC Countries'
       ,title = 'OPEC countries produce roughly 44% of world oil'
       ,x = NULL
       ,y = NULL) +
  theme(text = element_text(family = 'Gill Sans', color = '#EEEEEE')
        ,plot.title = element_text(size = 28)
        ,plot.subtitle = element_text(size = 14)
        ,axis.ticks = element_blank()
        ,axis.text = element_blank()
        ,panel.grid = element_blank()
        ,panel.background = element_rect(fill = '#333333')
        ,plot.background = element_rect(fill = '#333333')
        ,legend.position = c(.18,.36)
        ,legend.background = element_blank()
        ,legend.key = element_blank()
  ) +
  annotate(geom = 'text'
           ,label = 'Source: U.S. Energy Information Administration\nhttps://en.wikipedia.org/wiki/List_of_countries_by_oil_production\nhttps://en.wikipedia.org/wiki/OPEC'
           ,x = 18, y = -55
           ,size = 3
           ,family = 'Gill Sans'
           ,color = '#CCCCCC'
           ,hjust = 'left'
  ) +
  scale_color_manual(values = c('1' = 'orange', '0' = NA), labels = c('1' = 'OPEC'), breaks = c('1'))