The importance of labelled data in Machine Learning

Most people don’t realize the massive effort behind training a machine learning algorithm. In this post, I talk about why you should be extra careful when labeling your data.

By Carlos A. Toruño P.

November 18, 2023

Character encodings and why you need to know about them

Working with text data can be fun, but also tricky. Always be careful of which encoding system you are using, specially if you are dealing with characters or graphemes unknown to the English alphabet.

By Carlos A. Toruño P.

September 9, 2023

Exploding geometries with GeoPandas

Some geographical data sources include Taiwan as part of China. In this post, I show you how to split these territories without having to use other data source.

By Carlos A. Toruño P.

July 29, 2023

Programming Web Apps with Streamlit

Streamlit is an increasingly popular framework for developing web applications. In this post, I will introduce the Streamlit library and show a step-by-step guide on how to build simple applications with it.

By Carlos A. Toruño P.

May 25, 2023