Homework 5: Clustering and Text

Clustering

(MDSR Exercise 12.1) Consider the 4,000 biggest cities in the world, given by:

big_cities <- mdsr::world_cities %>% 
  arrange(desc(population)) %>% 
  slice_head(n = 4000)

Construct a k-means clustering of the latitude and longitude of these cities. Describe (qualitatively) the results of clustering with k=2.