Publications by n Posts on A stats websiten n
Analysing tweets from the Virtual Madrid Open
With the world in lockdown and no live tennis in the horizon in the near future the Madrid Open decided to organise an online tournament with male and female players facing each other using the Tennis World Tour video game. I was curious to see how fans reacted to the event. I downloaded twitter data using the rtweet package. I tried to include a...
8742 sym R (3626 sym/16 pcs) 14 img 1 tbl
Grand Slam title history as an animated bar chart race
I’ve spoiled it by putting the gif at the start of the post but if you are interested in how it was made then read on! I’ve seen this kind of charts around the web so I wanted to make a tennis-related one and what better than using Grand Slam wins since the very beginning; 1877. The main package that is needed for the animation is gganimate. ...
3564 sym R (2988 sym/6 pcs) 2 img
Tidymodels and XGBooost; a few learnings
This post will look at how to fit an XGBoost model using the tidymodels framework rather than using the XGBoost package directly. Tidymodels is a collection of packages that aims to standardise model creation by providing commands that can be applied across different R packages. For example, once the code is written to fit an XGBoost model a larg...
10804 sym R (5852 sym/20 pcs) 4 img 4 tbl
Syntax Highlighting in Blogdown; a very specific solution
If you spend more than 5 seconds on this site you will be able to tell that it is not one of the snazziest ones around. This is mostly by design but also a because I know very little about web development. These days it is really easy to have your own R website thanks to blogdown. blogdown interfaces with Hugo to let you have a working site up an...
4606 sym R (547 sym/3 pcs) 2 img
Machine learning using H2O
This post will be a quick introduction to using H2O through R. H2O is a platform for machine learning; it is distributed which means it can use all the cores in your computer offering parallelisation out of the box. You can also hook it up to already set up Hadoop or Spark clusters. It is also supposed to be industrial scale and able to cope with...
3011 sym R (2026 sym/9 pcs) 2 img 1 tbl
Useful R functions: mgsub
Many a-time I come across R functions and packages that I was not aware existed. Once I find what I was looking for I always think ‘Cool! Learned something new today’. However, most of the time the problem I was trying to solve is so specific that I end up not needing to use that new knowledge for a while. When I need to use that function I s...
2563 sym R (768 sym/4 pcs)