In this post I would like to focus on comparing classification algorithms with regards to business metrics. Also we will have a look at some methods to improve the ML workflow.
Nov 10, 2020
Support vector machines (SVM) are very powerful classification methods with a rich and yet fairly intuitively understandable mathematical undercarriage. In trivial examples, where one class of data points lies on one end of the feature range and the other class lies at the opposite end, SVM basically boils down to 'split the distance between them'. If new data comes in and appears to be more than halfway towards class 'A', the data point is now simply classified as belonging to 'A' as well.
Oct 6, 2020
Understanding the ins and outs of a logistic regression is non-trivial. Many sources either only touch the theoretical side or the implementation side respectively. In this post, I would like to create a one-stop-shop for the theoretical basis and the practical implementations of the logistic regression.
Aug 25, 2020
Matters that should b discussed and documented when setting up a data science project contract.
Aug 4, 2020
In absence of a proper automated testing process, we create a Django app to scale out testing to manual testers.
May 24, 2020
In this post, I will try to forecast a company's revenue two years into the future with fbprophet and then compare the forecasted revenue with the actual data collected over those two years.
May 22, 2020
A quick tool to help debugging complicated CTE expressions.
May 20, 2020
Collection of useful code snippets
May 18, 2020
How to get a RasPi started
May 18, 2020