Linguist Martin Schweinberger has used base R to perform a sociolinguistic analysis of swear word use in Irish English. The data analyzed is from the Irish component of the International Corpus of English. I'm particularly tickled by the fact that the script contains a set of regular expressions that define swear words. For instance search.pattern2 <- c (" [A|a]rse [s|d]{0 ,1} ") Turns out … [Read more...]
FiveThirtyEight data
FiveThirtyEight are sharing the data and code behind some of their articles. A goldmine for those wishing to learn more about data science. … [Read more...]
Real-world datasets for learning data science in R
R comes with a range datasets that can be used when learning the basics or trying out a new approach/package. mtcars and weather` are popular choices. However, most of the common datasets are "toy" examples. They are great for practising basic techniques, but are useless when it comes to realistically simulating data science tasks. The dslabs package provides datasets more suited to exploring … [Read more...]
Paper in “Handbook of Research Methods in Complexity Science”
My paper on visualizing dynamic networks has just been published in the Handbook of Research Methods in Complexity Science. There's a discount code for those purchasing in the next three months---VIP35. … [Read more...]
Visual Vocabulary tool
Choosing the right type of chart is an essential part of producing an effective data visualization. It's pointless adding bells and whistles to something that's fundamentally unsuited to the message you are trying to convey. The Financial Times Visual Journalism team have a Visual Vocabulary tool that helps them choose the correct chart for a story. It's basically a catalog of charts indexed by … [Read more...]