gapminderStackedPlots.r

# load and inspect gapminder data
library(dslabs)
data(gapminder)
head(gapminder)

# Faceted smooth density plots

# see the code below the previous video for variable definitions

# smooth density plots - area under each curve adds to 1
gapminder %>%
    filter(year == past_year & country %in% country_list) %>%
    mutate(group = ifelse(region %in% west, "West", "Developing")) %>% group_by(group) %>%
    summarize(n = n()) %>% knitr::kable()

# smooth density plots - variable counts on y-axis
p <- gapminder %>%
    filter(year == past_year & country %in% country_list) %>%
    mutate(group = ifelse(region %in% west, "West", "Developing")) %>%
    ggplot(aes(dollars_per_day, y = ..count.., fill = group)) +
    scale_x_continuous(trans = "log2")
p + geom_density(alpha = 0.2, bw = 0.75) + facet_grid(year ~ .)

# Add new region groups with case_when

# add group as a factor, grouping regions
gapminder <- gapminder %>%
    mutate(group = case_when(
        .$region %in% west ~ "West",
        .$region %in% c("Eastern Asia", "South-Eastern Asia") ~ "East Asia",
        .$region %in% c("Caribbean", "Central America", "South America") ~ "Latin America",
        .$continent == "Africa" & .$region != "Northern Africa" ~ "Sub-Saharan Africa",
        TRUE ~ "Others"))

# reorder factor levels
gapminder <- gapminder %>%
    mutate(group = factor(group, levels = c("Others", "Latin America", "East Asia", "Sub-Saharan Africa", "West")))

Code: Stacked density plot

# note you must redefine p with the new gapminder object first
p <- gapminder %>%
  filter(year %in% c(past_year, present_year) & country %in% country_list) %>%
    ggplot(aes(dollars_per_day, fill = group)) +
    scale_x_continuous(trans = "log2")

# stacked density plot
p + geom_density(alpha = 0.2, bw = 0.75, position = "stack") +
    facet_grid(year ~ .)

# Weighted stacked density plot

# weighted stacked density plot
gapminder %>%
    filter(year %in% c(past_year, present_year) & country %in% country_list) %>%
    group_by(year) %>%
    mutate(weight = population/sum(population*2)) %>%
    ungroup() %>%
    ggplot(aes(dollars_per_day, fill = group, weight = weight)) +
    scale_x_continuous(trans = "log2") +
    geom_density(alpha = 0.2, bw = 0.75, position = "stack") + facet_grid(year ~ .)
    
## The ecological fallacy is assuming that conclusions made from the average of a group apply to all members of that group.    
# add additional cases
gapminder <- gapminder %>%
    mutate(group = case_when(
        .$region %in% west ~ "The West",
        .$region %in% "Northern Africa" ~ "Northern Africa",
        .$region %in% c("Eastern Asia", "South-Eastern Asia") ~ "East Asia",
        .$region == "Southern Asia" ~ "Southern Asia",
        .$region %in% c("Central America", "South America", "Caribbean") ~ "Latin America",
        .$continent == "Africa" & .$region != "Northern Africa" ~ "Sub-Saharan Africa",
        .$region %in% c("Melanesia", "Micronesia", "Polynesia") ~ "Pacific Islands"))

# define a data frame with group average income and average infant survival rate
surv_income <- gapminder %>%
    filter(year %in% present_year & !is.na(gdp) & !is.na(infant_mortality) & !is.na(group)) %>%
    group_by(group) %>%
    summarize(income = sum(gdp)/sum(population)/365,
                        infant_survival_rate = 1 - sum(infant_mortality/1000*population)/sum(population))
surv_income %>% arrange(income)

# plot infant survival versus income, with transformed axes
surv_income %>% ggplot(aes(income, infant_survival_rate, label = group, color = group)) +
    scale_x_continuous(trans = "log2", limit = c(0.25, 150)) +
    scale_y_continuous(trans = "logit", limit = c(0.875, .9981),
                                       breaks = c(.85, .90, .95, .99, .995, .998)) +
    geom_label(size = 3, show.legend = FALSE)