Jack Kennedy 🐀 @_jcken@social.cleverlibre.org

The bests stats commentary category for this year's Journalism Awards recognises excellent statistical contributions to the public debate by non-journalists.

Other awards (for #journalists) are:
Data Visualisation #DataViz
Explaining the facts
Investigative Journalism

✍️Nominate by 20 March - either self, or of someone else's work!
Work published in 2022, in English anywhere in the world. (2000 words/10 mins max)
Info: https://rss.org.uk/training-events/events/excellence-awards/journalism-awards/

#RoyalStatisticalSociety #RSSJournalismAwards.

Mixing #TidyTuesday with vegetation index from multispectral images (the kind of data I use most frequently at work!) to test if numbats distribution is related to vegetation, at national and local scale. Answer in plot below...

#RStats code https://github.com/BjnNowak/TidyTuesday/blob/main/SC_numbats.R

@_jcken @mcmc_stan There seems to be a lot of use of Stan in the industry. The first two examples that come to my mind are Pharmacometrics ---we have some examples in Section 1.1 of this paper (https://ascpt.onlinelibrary.wiley.com/doi/10.1002/psp4.12812); and forecasting in tech, notably via the software Prophet (https://facebook.github.io/prophet/) built on top of Stan.

Ethiopian Language Sentiment analysis for #TidyTuesday : religious terms are mostly tweeted in a positive way, whereas the opinion of others is poorly considered...

#RStats code at https://github.com/BjnNowak/TidyTuesday/blob/main/SC_language.R

This week we look at sentiment analysis in 14 African languages. #TidyTuesday

Special thanks to @Shmuhammadd for providing the datasets. Read his paper at https://arxiv.org/pdf/2302.08956.pdf

Code: https://github.com/mvbloois/tidytuesday

#rstats #data #dataviz

It's #TidyTuesday again! Thanks to Shamsuddeen Hassan Muhammad for sharing the data this week on African language sentiments 🌍

I made use of {ggtext} again this week to try some alternative approaches to labelling bar charts! 📊

Code: https://github.com/nrennie/tidytuesday/tree/main/2023/2023-02-28

#RStats #R4DS #DataViz

Suppose, in a #QuartoPub document, using #rStats I have a list of length G, each item in this list is a flextable - I need to use flextable as opposed to kable, to allow for output to docx.
G is unknown apriori, but will be at least 1.

Is there any way to create a sequence of tables with associated labels and captions that could be worked out dynamically/parsed?
Manually, this can be done really easily (creating new labels etc) and knowing when to stop, but is there a way of automating this?

Did you know that the #RoyalStatisticalSociety has awards for excellence in statistical journalism?
You don't need to be UK based to enter.
Categories this year
- Data visualisation
- Explaining the facts
- Investigative journalism (using previously unpublished statistics either through unpublished data that have been sourced and analysed by the journalist or new analyses of existing data)
- Best statistical commentary by a non-journalist

More info and entry criteria
https://rss.org.uk/training-events/events/excellence-awards/journalism-awards/

For the Bob Ross paintings data for #TidyTuesday this week, I went for a cross between data viz and generative art 🎨

I created a sankey chart to visualise the colours used across different seasons of the show! 🖼️🖼️

Code: https://github.com/nrennie/tidytuesday/tree/main/2023/2023-02-21

#R4DS #RStats #GenArtClub

A book we can all get behind.
#git #github

Have recently been playing around with `ggh4x`, which provides some nice drop-in extensibility for ggplot2.

E.g. Tufte-style "floating axes". (Very easy in base plot, but a bit of a pain in vanilla ggplot2.) https://teunbrand.github.io/ggh4x/reference/guide_axis_truncated.html#ref-examples