Sources

urban dictionary :
https://www.kaggle.com/therohk/urban-dictionary-words-dataset/

Wiki popularity :
https://figshare.com/articles/WikiRank_05_2019_-_quality_scores_popularity_and_AI_for_Wikipedia_articles/8231273/2

Unix
  sort
  uniq
  
R
  'small' -> file
  wiki <- read.table(file, header = TRUE, sep = '\t', quote = '')
# sort
  wikisort.bot <- wiki[order(wiki$popularity),]
  wikisort.top <- wiki[order(wiki$popularity, decreasing = TRUE),]

  head(wikisort.bot)
  head(wikisort.top)

  plot(wiki$popularity, wiki$authors_interest)

  # TODO linear regression
  # hexbin ??

  # outliers
  wiki[which((wiki$popularity > 1700 & wiki$authors_interest < 10)), ]