gapminderDistributions.r

##Key points

   # Use intersect to find the overlap between two vectors.
   # To make boxplots where grouped variables are adjacaent, color the boxplot by a factor instead of faceting by that factor. This is a way to ease comparisons.
   # The data suggest that the income gap between rich and poor countries has narrowed, not expanded.


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

# Histogram of income in West versus developing world, 1970 and 2010
# add dollars per day variable and define past year
gapminder <- gapminder %>%
    mutate(dollars_per_day = gdp/population/365)
past_year <- 1970

# define Western countries
west <- c("Western Europe", "Northern Europe", "Southern Europe", "Northern America", "Australia and New Zealand")

# facet by West vs devloping
gapminder %>%
    filter(year == past_year & !is.na(gdp)) %>%
    mutate(group = ifelse(region %in% west, "West", "Developing")) %>%
    ggplot(aes(dollars_per_day)) +
    geom_histogram(binwidth = 1, color = "black") +
    scale_x_continuous(trans = "log2") +
    facet_grid(. ~ group)

# facet by West/developing and year
present_year <- 2010
gapminder %>%
    filter(year %in% c(past_year, present_year) & !is.na(gdp)) %>%
    mutate(group = ifelse(region %in% west, "West", "Developing")) %>%
    ggplot(aes(dollars_per_day)) +
    geom_histogram(binwidth = 1, color = "black") +
    scale_x_continuous(trans = "log2") +
    facet_grid(year ~ group)

# Income distribution of West versus developing world, only countries with data 
# define countries that have data available in both years
country_list_1 <- gapminder %>%
    filter(year == past_year & !is.na(dollars_per_day)) %>% .$country
country_list_2 <- gapminder %>%
    filter(year == present_year & !is.na(dollars_per_day)) %>% .$country
country_list <- intersect(country_list_1, country_list_2)

# make histogram including only countries with data available in both years
gapminder %>%
    filter(year %in% c(past_year, present_year) & country %in% country_list) %>%    # keep only selected countries
    mutate(group = ifelse(region %in% west, "West", "Developing")) %>%
    ggplot(aes(dollars_per_day)) +
    geom_histogram(binwidth = 1, color = "black") +
    scale_x_continuous(trans = "log2") +
    facet_grid(year ~ group)
# Boxplots of income in West versus developing world, 1970 and 2010

p <- gapminder %>%
    filter(year %in% c(past_year, present_year) & country %in% country_list) %>%
    mutate(region = reorder(region, dollars_per_day, FUN = median)) %>%
    ggplot() +
    theme(axis.text.x = element_text(angle = 90, hjust = 1)) +
    xlab("") + scale_y_continuous(trans = "log2")
p + geom_boxplot(aes(region, dollars_per_day, fill = continent)) +
    facet_grid(year ~ .)

# arrange matching boxplots next to each other, colored by year
p + geom_boxplot(aes(region, dollars_per_day, fill = factor(year)))