Missing Data Mechanisms: MCAR, MAR, MNAR (with a concrete simulation)
Missing data isn’t just empty cells: why it’s missing changes what you can trust. Let’s explore three major classical mechanism to deal with missingness.
Posts by Year
2026
Cosine Similarity, Explained for Everyone
Cosine similarity is a simple way to compare texts: it checks whether two vectors point in the same direction, rather than how long they are. Here’s the begi...
2025
Normalizer and TF-IDF in NLP
In this post, we explore how Normalizer and TF-IDF work in Natural Language Processing, focusing on their differences and when to use them.
Fixing Common Issues When Setting Up Jekyll & GitHub Pages on macOS
This guide walks you through troubleshooting Jekyll and GitHub Pages on macOS and getting your blog up and running.
2021
Video Games Sales Data Analysis
In this post we explore the Video Games sales dataset, and try to perform a data exploration on that source.
2020
The Importance of Preprocessing in a Machine Learning Pipeline
In this post we explore standard preprocessing techniques that should be used as first step in a Machine Learning Pipeline.
An Introduction to Approximate Bayesian Computation
An Introduction to Approximate Bayesian Computation
5 awesome tips about Pandas
5 awesome tips about Pandas
Wrangling Financial Returns with Pandas
Wrangling Financial Returns with Pandas