The idea was to try some clustering machine learning algorithms on european stat, just for fun and self-educational purposes. Here is the list of countries:
## [1] "Belgium" "Bulgaria" "Czechia" "Denmark"
## [5] "Germany" "Estonia" "Ireland" "Greece"
## [9] "Spain" "France" "Croatia" "Italy"
## [13] "Cyprus" "Latvia" "Lithuania" "Luxembourg"
## [17] "Hungary" "Malta" "Netherlands" "Austria"
## [21] "Poland" "Portugal" "Romania" "Slovenia"
## [25] "Slovakia" "Finland" "Sweden" "United Kingdom"
## [29] "Iceland" "Norway" "Switzerland" "Serbia"
## [33] "Turkey"
So what I did, I took a random statistic from eurostat
and run hierarchical clustering. After that I’ve selected 8 classes and here you can see it as a tree
or on the map color-coded by cluster ID.
to be continued…