Next, the following sections take you through the content of the webinar: Setting up the reticulate environment and conversion between environments Finally, I provide a few practical tips for attacking Machine Learning problems with these three libraries. I then compare it with R's well-known Machine Learning libraries tidymodels (Kuhn and Wickham 2020) and mlr3 (Lang et al. In my slide pack I give an overview of Scikit-learn. The result? Immensely faster processing times, with results readily available for reporting and visualization with R's shiny (Chang et al. Personally, I needed access to a much more advanced Machine Learning interface than the ones that are available in R, and so I spent a few weeks building a pipeline with Python's Scikit-learn. The idea is to use the Python elements that are clearly superior to the R counterparts, without necessarily having to master Python. Package reticulate is a game-changer, because the R user like myself gains access to the suite of Python's powerful Machine Learning tools, without necessarily being a Python expert. 2011) and plots some results with ggplot2 (Wickham 2016), in just a few lines of R code: Here is an example where Python runs a text mining process in the background with Scikit-learn (Pedregosa et al. Package reticulate (Ushey, Allaire, and Tang 2020) makes the integration between R and Python so easy that the first time I tried it I really could not believe my eyes. NHS R Community Reticulate Webinar - a happy union
0 kommentar(er)
