Benchmarking your code is one thing – another thing is to keep and use the gained knowledge for future projects. In this blog, Jakob presents his collection of benchmarks and creates an easy to use a setup for new ones.
Tuning Random Forest on Time Series Data
Training random forests on time series is one thing, but tuning them? It’s not like you can just apply cross validation and be done with it. Or can you? This post forms part two our mini-series “Time Series Forecasting with Random Forest”. Find out how you can tune the hyperparameters of the random forest algorithm when dealing with time series data. The answers might surprise you!
rBokeh – Don’t be stopped by missing arguments!
rBokeh is an interactive plotting library. Since it functions lack some arguments compared to its Python counterpart, plots are sometimes difficult to customize. I will show how to overcome those issues and drill out the plot objects.
rBokeh – Tipps and Tricks with JavaScript and beyond!
rBokeh is an interactive plotting library. It has the capability to extend its features with customized JavaScript code. I show the most important aspects, guide through an example, and provide some useful tipps how to handle likely issues.
Web Scraping 101 in Python with Requests & BeautifulSoup
Want to obtain a specific dataset from a website which does not have an API? In this post, I explain how to do this by scraping data using Python, how you determine whether it is allowed to scrape a specific page and more.
Getting started with flexdashboards in R
In this blog article, you will learn you how to set up a dashboard with the flexdashboard package, how to integrate interactive widgets and how to deploy the app on shinyapps.io.
Bang Bang – How to program with dplyr
Never heard of non-standard evaluation? Then our colleague Markus has the perfect answer for you: Bang Bang! In this blog post, Markus introduces meta-programming when using dplyr.
Revisited: Forecasting Last Christmas Search Volume
It is June and nearly half of the year is over, marking the middle between Christmas 2018 and 2019. Last year in autumn, I’ve published a blog post about predicting Wham’s „Last Christmas“ search volume using Google Trends data with different types of neural network architectures. Of course, now I want to know how good the predictions were, compared to …
Simulating the bias-variance tradeoff in R
In my last blog post, I have elaborated on the Bagging algorithm and showed its prediction performance via simulation. Here, I want to go into the details on how to simulate the bias and variance of a nonparametric regression fitting method using R. These kinds of questions arise here at STATWORX when developing, for example, new machine learning algorithms or …
Optimising your R code – a guided example
Do you want to optimise your code but don’t know where to start? In this post I guide you through my thought process when I optimised my code.