Unlocking the power of data visualization with R

indoor_pollution <- readr::read_csv('https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-04-12/indoor_pollution.csv')
fuel_gdp<- read.csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-04-12/fuel_gdp.csv")
death_timeseries<-read.csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-04-12/death_timeseries.csv")
death_source<-read.csv("https://raw.githubusercontent.com/rfordatascience/tidytuesday/master/data/2022/2022-04-12/death_source.csv")

# indoor_pollution;
# fuel_gdp;
# death_timeseries;
# death_source

indoor_pollution1 <- indoor_pollution%>%
  rename(Deaths_age.std.pct=`Deaths - Cause: All causes - Risk: Household air pollution from solid fuels - Sex: Both - Age: Age-standardized (Percent)`,
Year_death=Year) %>%
  janitor::clean_names()

indoor_pollution1%>%head

fuel_gdp1 <- fuel_gdp%>%
  rename(Clean.fuels="Access.to.clean.fuels.and.technologies.for.cooking....of.population.",
         GDP="GDP.per.capita..PPP..constant.2017.international...",
         Pop="Population..historical.estimates.",
         Year_fuel=Year) %>%
  janitor::clean_names() 

fuel_gdp1 %>%head

deaths_pct <- indoor_pollution1 %>%
  right_join(fuel_gdp1,by=c("year_death"="year_fuel","entity","code"))%>%
  janitor::clean_names()

df <- deaths_pct%>%
  filter(!is.na(deaths_age_std_pct),
         !is.na(clean_fuels),
         !is.na(gdp)) %>%
  select(-continent)
  
# DataExplorer::profile_missing()
df %>%head

df%>%glimpse()

library(countrycode)
df$continent <- countrycode(df$entity,
                            origin= "country.name",
                            destination = "continent")


df%>% filter(is.na(continent)) %>% count(entity)

df <- df %>%
  filter(!entity%in%c("Micronesia (country)","Timor","World"))

df%>%
  head

death_plot <- df %>%
  mutate(year=cut(year_death,5),.after=year_death) %>%
  group_by(year)%>%
  mutate(mean=mean(deaths_age_std_pct),
         sd=sd(deaths_age_std_pct)) %>%
  ungroup() %>% # pull(mean)%>%summary
  select(year,mean,sd) %>%
  distinct()%>%
  ggplot(aes(y=fct_reorder(year,mean),
             xdist = distributional::dist_normal(mean, sd),
             layout = "weave",
             fill = stat(x < 5.094))) + 
  ggdist::stat_dots(position = "dodge", color = "grey70")+
  geom_vline(xintercept = 5.094, alpha = 0.25) +
  scale_x_continuous() +
  tvthemes::scale_fill_hilda()+
  labs(x="",
       y="",color="",
       title="Deaths",
       subtitle="",
       Caption="#30DayChartChallenge 2022 #day16 - Enviroment\nDataSource: Indoor Air Pollution | DataViz: Federica Gazzelloni")+
  tvthemes::theme_avatar()+
  theme(legend.background = element_blank(),
        legend.box.background = element_blank(),
        legend.key = element_blank(),
        legend.key.width = unit(0.5,units="cm"),
        legend.direction = "horizontal",
        legend.position = c(0.8,0.1))
death_plot

df%>%head

fuel_plot <- df %>%
  mutate(year=cut(year_death,5),.after=year_death) %>%
  group_by(year)%>%
  mutate(mean=mean(clean_fuels),
         sd=sd(clean_fuels)) %>%
  ungroup() %>% #pull(mean)%>%summary
  select(year,mean,sd) %>%
  distinct()%>%
  ggplot(aes(y=fct_reorder(year,mean),
             xdist = distributional::dist_normal(mean, sd),
             layout = "weave",
             fill = stat(x < 62.04))) + 
  ggdist::stat_dots(position = "dodge", color = "grey70")+
  geom_vline(xintercept = 62.04, alpha = 0.25) +
  scale_x_continuous() +
  tvthemes::scale_fill_hilda()+
  labs(x="",
       y="",color="",
       title="Fuel",
       subtitle="",
       Caption="#30DayChartChallenge 2022 #day16 - Environment\nDataSource: Indoor Air Pollution | DataViz: Federica Gazzelloni")+
  tvthemes::theme_avatar()+
  theme(legend.background = element_blank(),
        legend.box.background = element_blank(),
        legend.key = element_blank(),
        legend.key.width = unit(0.5,units="cm"),
        legend.direction = "horizontal",
        legend.position = c(0.8,0.1))

library(patchwork)
death_plot|fuel_plot

df

df%>%count(entity)

library(rnaturalearth)
world <- ne_countries(returnclass = "sf")

world%>%
  right_join(df,by=c("name"="entity"))%>% select(name) %>%
  sf::st_drop_geometry() %>%
  count(name)

df1 <- world%>%
  select(name)%>%
  right_join(df,by=c("name"="entity"))

map <- ggplot(data = world) +
  geom_sf(size=0.5)+
  geom_sf(data=df1,
          mapping=aes(geometry=geometry,fill=deaths_age_std_pct),
          size=0.1)+
  coord_sf(xlim = c(-180.0,180.0), ylim = c(-60.0,90.0), expand = FALSE)+
  labs(fill="Deaths (%)",
       title="Deaths caused by Indoor Air Pollution") +
  tvthemes::scale_fill_gravityFalls(178,type="continuous")+
  tvthemes::theme_hildaDay() +
  theme(axis.text = element_blank(),
        axis.ticks = element_blank(),
        legend.background = element_blank(),
        legend.position = c(0.1,0.3),
        plot.background = element_rect(color="beige",fill="beige"))

ggsave("map.png",dpi=320,width = 9,height = 6)

options(scipen = 999)
lines <- ggplot(df, aes(x = clean_fuels, y = deaths_age_std_pct)) +
     geom_point(aes(fill=entity),
                size = 0.5,
                shape=21,color="grey70",
                show.legend = F) + 
     geom_smooth(aes(color = as.factor(year_death)),
                 size=0.2,show.legend = F,se=F)+
     geom_label(data=df%>%
                filter(year_death=="2009")%>%
                group_by(continent)%>%
                mutate(deaths_age_std_pct=max(deaths_age_std_pct),
                                        clean_fuels=max(clean_fuels))%>%
                arrange(-deaths_age_std_pct)%>%
                slice(1:1)%>%
                ungroup() ,
                aes(label=entity),
                position = "identity",
                vjust=0.5,hjust="right",
                size=2,
                inherit.aes = T,
                check_overlap = T)+
     #scale_x_log10()+
     #scale_y_log10(breaks=seq(0,23,5))+
     facet_wrap(vars(continent),scales = "free",ncol = 5)+
     #tvthemes::scale_fill_gravityFalls()+
     tvthemes::scale_colour_gravityFalls()+
     tvthemes::theme_hildaDay() +
     theme(legend.position = "none",
           plot.background = element_rect(color="midnightblue",fill="beige"),
           panel.grid = element_line(size=0.05),
           axis.text = element_blank(),
           axis.title = element_blank())

ggsave("lines.png",
       dpi=320,
       width = 9,height = 4)

library(cowplot)
library(extrafont)
#loadfonts()

ggdraw()+
  draw_plot(map,y=0.2,
            height = 0.6)+
  draw_plot(lines,scale=0.5,
            width = 2,height = 0.5,
            x=-0.5,y=-0.2)

ggsave("day_16_enviroment.png",
       dpi=320,
       width = 9,height = 6)