Our latest tool development at STATWORX: random boost, an algorithm twice as fast as gradient boosting, with comparable prediction performance.
We at STATWORX use mostly R or Python for our projects. But why not both? With the help of the reticulate package we can use Python within R. Here we show an example of how to train a Support Vector Machine.
In today’s blog post, we show you how to improve the interactivity of Plotly histograms with automatically new rebinning.
This blogpost explains step by step how you can build your own Docker Image and include R scripts. With this you can have scripts running at every image’s beginning.
It’s Valentine’s day, making this the most romantic time of the year. But actually, already 2018 was a year full of love here at STATWORX: many of my STATWORX colleagues got engaged. And so we began to wonder – some fearful, some hopeful – who will be next? Therefore, today we’re going to tackle this question in the only true way: with data science!
In this blog we will explore the plotly library for python and R. We show how plotly is structured and use the LA Metro Bike dataset as an example to create interactive plots.
In this blog we will explore the Bagging algorithm and a computational more efficient variant thereof, Subagging. With minor modifications these algorithms are also known as Random Forest and are widely applied here at STATWORX, in industry and academia.
In the last 23 days I presented one function each day from the helfRlein package we created here at STATWORX. I hope you found some of the functions useful and had some fun discovering new ways of doing things with R! Since today is Christmas, only one thing remains to say: To see all functions you can either check out …
This little helper adds functionality to the base R function
strsplit – hence the same name!
This little helper does the same thing as the "Find in files" search within RStudio.