require(data.table)
# Data takes ~30 seconds to load
flights <- as.data.table(read.csv(url("https://raw.githubusercontent.com/wiki/arunsrinivasan/flights/NYCflights14/flights14.csv")))
length(unique(flights$carrier))

km <- kmeans(flights[,.(dep_delay,carrier)], centers = 4, nstart = 1)