GDP Per Capita per Continent

Part 1: Tidying

df <- read_excel("gapminder_broadband_per_100.xlsx") %>% janitor::clean_names()

glimpse(df)

## Rows: 213
## Columns: 15
## $ fixed_broadband_internet_subscribers_per_100_people <chr> "Afghanistan", "Al…
## $ x1998                                               <dbl> NA, NA, NA, NA, NA…
## $ x1999                                               <dbl> NA, NA, NA, NA, NA…
## $ x2000                                               <dbl> NA, NA, NA, NA, NA…
## $ x2001                                               <dbl> 0.0000000000, 0.00…
## $ x2002                                               <dbl> 0.0000000000, 0.00…
## $ x2003                                               <dbl> 0.000000e+00, 0.00…
## $ x2004                                               <dbl> 6.880265e-04, 0.00…
## $ x2005                                               <dbl> 7.356639e-04, 8.65…
## $ x2006                                               <dbl> 0.001625928, NA, 0…
## $ x2007                                               <dbl> 0.001581161, 0.315…
## $ x2008                                               <dbl> 0.001537626, 2.011…
## $ x2009                                               <dbl> 0.00299058, 2.8815…
## $ x2010                                               <dbl> 0.004362367, 3.292…
## $ x2011                                               <lgl> NA, NA, NA, NA, NA…

tidy_df <- df %>% pivot_longer(c(x1998:x2011), 
    names_to = "year",
    names_prefix = "x", 
    names_transform = list(year = as.integer),)

names(tidy_df)[names(tidy_df)=='fixed_broadband_internet_subscribers_per_100_people'] <- 'country'

glimpse(tidy_df)

## Rows: 2,982
## Columns: 3
## $ country <chr> "Afghanistan", "Afghanistan", "Afghanistan", "Afghanistan", "A…
## $ year    <int> 1998, 1999, 2000, 2001, 2002, 2003, 2004, 2005, 2006, 2007, 20…
## $ value   <dbl> NA, NA, NA, 0.0000000000, 0.0000000000, 0.0000000000, 0.000688…

head(tidy_df)

## # A tibble: 6 × 3
##   country      year value
##   <chr>       <int> <dbl>
## 1 Afghanistan  1998    NA
## 2 Afghanistan  1999    NA
## 3 Afghanistan  2000    NA
## 4 Afghanistan  2001     0
## 5 Afghanistan  2002     0
## 6 Afghanistan  2003     0

Min vs Max GDP for each Continent

Table

library(gapminder)

min_max <- gapminder %>% group_by(continent) %>%
  filter(year == 2007) %>% summarize(
    min_value = min(gdpPercap, na.rm = TRUE),
    max_value = max(gdpPercap, na.rm = TRUE)
  )
glimpse(min_max)

## Rows: 5
## Columns: 3
## $ continent <fct> Africa, Americas, Asia, Europe, Oceania
## $ min_value <dbl> 277.5519, 1201.6372, 944.0000, 5937.0295, 25185.0091
## $ max_value <dbl> 13206.48, 42951.65, 47306.99, 49357.19, 34435.37

head(min_max)

## # A tibble: 5 × 3
##   continent min_value max_value
##   <fct>         <dbl>     <dbl>
## 1 Africa         278.    13206.
## 2 Americas      1202.    42952.
## 3 Asia           944     47307.
## 4 Europe        5937.    49357.
## 5 Oceania      25185.    34435.

rounded_minmax <- min_max %>% mutate(across(where(is.numeric), ~ round(.x, 2)))
rounded_minmax

## # A tibble: 5 × 3
##   continent min_value max_value
##   <fct>         <dbl>     <dbl>
## 1 Africa         278.    13206.
## 2 Americas      1202.    42952.
## 3 Asia           944     47307.
## 4 Europe        5937.    49357.
## 5 Oceania      25185.    34435.

Companion Graph

tidy_minmax <- rounded_minmax %>% pivot_longer(min_value:max_value,names_to = "min_max_col", values_to="value")

head(tidy_minmax)

## # A tibble: 6 × 3
##   continent min_max_col  value
##   <fct>     <chr>        <dbl>
## 1 Africa    min_value     278.
## 2 Africa    max_value   13206.
## 3 Americas  min_value    1202.
## 4 Americas  max_value   42952.
## 5 Asia      min_value     944 
## 6 Asia      max_value   47307.

plot <- ggplot(tidy_minmax, aes(x=value, y=continent, fill=min_max_col)) + geom_col() + labs(x = "GDP per capita", y = "Continent", title = "Min and Max GDP per Capita per Continent in the Year 2007") + scale_x_continuous(
    limits = c(0, 70000), 
    labels = abs 
  ) + geom_text(aes(label = abs(tidy_minmax$value)), 
          hjust = ifelse(tidy_minmax$value < 0, 1.1, -0.1), 
          size = 2) + scale_fill_manual(name = "GDP", labels = c("Maximum", "Minimum"), values = c('lavender', 'cadetblue')) + theme_minimal()


plot

## Warning: Use of `tidy_minmax$value` is discouraged.
## ℹ Use `value` instead.