Wednesday (20th January 2021) myself and a colleagues Andreas kicked off the first webinar of 2021 for the NHS-R Community with our look at the benefits of using reticulate for joining up R and Python.
What was the webinar about?
The webinar was split into two sections:
- The first session involved me taking the functionality of the reticulate package and how you can easily pass R and Python commands to convert the data from the respective formats. This is actually really intuitive in R and the webinar recording in the next section will show the detail of this. The pipeline was to read data in R and do some basic cleaning, pass the data to Python to split and model with Sci-kit Learn, do some visualisations in Python and then pass back to R. I also showed how you can run external scripts from R.
- Andreas then took us through the benefits of using Sci-kit learn compared with TidyModels and mlr. He mentions caret as well, but this does not factor in, however I still love CARET and refer to the course I did on Advanced Modelling for how to get up and running with CARET quickly. Finally, Andreas concludes which ML platform he prefers, and bad news to R fans, it turns out to be Sci-kit learn, but that is only personal preference.
Where can I watch the webinar?
The webinar has been recorded by the NHS-R Community and has been uploaded to their YouTube site – however I attach hereunder for quick access:
The materials for the session can be found by clicking the GitHub icon below:
What webinars are planned for the future?
The list of webinars can be found on the NHS-R Community website and are linked here. I am doing a TidyModels webinar in April, so watch this space, and get typing.
Furthermore I have a package developed (due to be released on CRAN very soon). This was found on Hadley Wickham’s wall:
Andreas and I would like to thank everyone who tuned in for the webinar and I hope this will be of use in some practical projects?
Take it easy and stay safe!