Supercharge your understanding of Principal Component Analysis with a step-by-step derivation — Principal Component Analysis (PCA) is an old technique commonly used for dimensionality reduction. Despite being a well-known topic among data scientists, the derivation of PCA is often overlooked, leaving behind valuable insights about the nature of data and the relationship between calculus, statistics, and linear algebra.

An intuitive introduction to signal aliasing with Python — Time series data is everywhere and full of rich information. Financial markets, industrial processes, sensor readings, health monitors, network traffic, and economic indicators, to name a few, are example applications where time series analysis and signal processing are necessary. With advances in deep learning and other time series forecasting techniques…

Improving a real-time streaming project with ksqlDB — In a previous article, the components of a real-time streaming project that consumes and processes smartphone sensor data with FastAPI, Kafka, QuestDB, and Docker, were explored. This project was a first pass at implementing an architecture that can move streaming data from smartphones, through a Kafka log, and into a…

Gain a deeper understanding of derivatives with Python — Mathematics is a notoriously difficult subject for many. Because of its cumulative and abstract nature, students can find it challenging to make connections and understand how math is applied. In my ongoing journey, I’ve found it extremely helpful to enhance my understanding of math concepts by implementing them in code. …

Conformal multi-quantile regression with Catboost — In a previous article, we explored the capabilities of Catboost’s multi-quantile loss function, which allows for the prediction of multiple quantiles using a single model. This approach elegantly overcomes one of the limitations of traditional quantile regression, which necessitates the development of a separate model for each quantile, or storing…

Exploring multi-quantile regression with Catboost — How confident can we be in a machine learning model’s prediction? This question has been a prominent area of research over the last decade, and it has major implications in high-stakes machine learning applications such as finance and healthcare. While many classification models, particularly calibrated models, come with uncertainty quantification…

A data-driven metric for offensive linemen — The pocket created by an offensive line is a crucial element of the passing game, as the quarterback needs a clean pocket to throw the ball accurately and on time. A good pocket provides the quarterback ample space and time to move and throw, while a poor one collapses quickly…

The actual reason your machine learning model isn’t working — The fields of Artificial Intelligence and Machine Learning are hotter than ever. With models like Chat GPT and Stable Diffusion taking the world by storm, AI and ML hype has made a resurgence and is catching the attention of the masses. …

Consume and Process Smartphone Sensor Data with FastAPI, Kafka, QuestDb, and Docker — Devices are everywhere. Smartphones, refrigerators, doorbells, watches, medical sensors, security systems, and fitness trackers, to name a few, are now commonplace and constantly recording (potentially high-frequency) information. These devices form a network known as the “Internet of Things”, or IoT, and provide rich data sources.