Hi everyone,
This month’s meeting will be the last one during this academic year! We’ll be on hiatus until September, but meanwhile (and as usual), we’re very interested in finding speakers for future sessions. So please let us know if you have an R topic you’d like to present.

The upcoming meeting will be held on Wednesday 18th of July, at 5.30pm. The venue is the Psychology Building, room S1, in 7 George Square (kindly supported by The Data Lab; see map below). By the way, don’t be put off by the road work in front of the building - the entrance is still accessible. Our meetings are open for all to attend, and newcomers / beginners are very welcome!

Our first speaker is Dr. Russell Hyde, research associate within the Paul O’Gorman Leukaemia Research Centre. He has been working on his very own R package, which he will be presenting to us:

Polyply package

(slides here)

Briefly, polyply allows you to do dplyr-type commands over a list of heterogeneous data frames. I mostly use it for interactive work where it saves me some memory issues, cleans up pipelines that look like: (filter(table, ...) %>% join(filter(table, ...)) %>% join(.....)) and reduces my temp-variable count.

Our second speaker is Dr. Gavin Bowick, data scientist and marketer in the hotel and tourism industry. He will be giving an overview on:

Becoming a regular useR

From haemorrhagic fevers to sustainable fashion, marketing and business analytics (slides here)

While I’m a relative newcomer to R, it has now become a central part of (nearly) every day’s work. The functionality and flexibility of R and its myriad packages make it an ideal platform for virtually every type of analysis across every discipline. In this talk, I will discuss how I have used R to perform techniques such as machine learning using support vector machines and random forests, to regression, survival analysis, sentiment analysis and more, in fields from infectious diseases to marketing analytics, as well as how R Markdown and API integrations can make the regular reporting of key performance indicators much more efficient.

For any newcomers, here’s a map of where we’ll be:

See you there!

Caterina Constantinescu