@danwwilson @lwpembleton #brms by @paul_buerkner has made Bayesian models incredibly fun and intuitive for me. I love the combination of well thought out defaults and API with a lot of depth and power, should you need it. Other than that, I think #lubridate needs some love! Oh and #igraph, which just works ™️ plus it's lovely descendant #tidygraph 🕸️
#packagelove

@danwwilson @lwpembleton

The full ecosystem of @mcmc_stan is awesome, but if I have to choose just one that makes my life waAaAaAay easier, that would be {brms} by @paul_buerkner . I love it  

#RStats #PackageLove

@johnmackintosh @danwwilson big fan of targets too 👍
I came across {groupdata2} which allowed me to replace a lot of really janky #rstats code for randomly splitting up datasets into cross validation folds/groups, whilst also taking into consideration additional structural factors in the splits, but also keeping things reasonably even 🦸
https://github.com/ludvigolsen/groupdata2
#PackageLove #WeeklyRShare
GitHub - LudvigOlsen/groupdata2: R-package: Methods for dividing data into groups. Create balanced partitions and cross-validation folds. Perform time series windowing and general grouping and splitting of data. Balance existing groups with up- and downsampling or collapse them to fewer groups.

R-package: Methods for dividing data into groups. Create balanced partitions and cross-validation folds. Perform time series windowing and general grouping and splitting of data. Balance existing g...

GitHub
I think it’s time for some #RStats package love. Share a package that makes your life/work easier when you use it, or that sparks joy at how beautifully it addresses a problem you need to solve. For me it is the {targets}  package and associated friends. I don’t have to worry if something has run or not because targets takes care of it. #PackageLove @lwpembleton