Publications by Matt Bowers
SHAP from Scratch
Ahh, SHAP. As you know it’s become one of the leading frameworks for explaining ML model predictions. I’d guess it’s popularity is due to its appealing theoretical basis, its universal applicability to any type of ML model, and its easy-to-use python package. SHAP promises to turn your black box ML model into a nice friendly interpretable mod...
16026 sym Python (7767 sym/19 pcs) 44 img
The Ultimate Guide to XGBoost Parameter Tuning
Ahh, the dark art of hyperparameter tuning. It’s a key step in the machine learning workflow, and it’s an activity that can easily be overlooked or be overkill. Therefore, dear reader, it is an art that requires the application of both skill and wisdom to realize its full potential while avoiding its perils. Today I’ll show you my approach fo...
17108 sym Python (8811 sym/19 pcs) 12 img
XGBoost for Binary and Multi-Class Classification in Python
Today we continue the saga on gradient boosting with a down-to-Earth tutorial on the essentials of solving classification problems with XGBoost. We’ll run through two examples: one for binary classification and another for multi-class classification. In both cases I’ll show you how to train XGBoost models using either the scikit-learn interface...
9342 sym Python (13272 sym/43 pcs) 24 img
Gradient Boosting Multi-Class Classification from Scratch
Tell me dear reader, who among us, while gazing in wonder at the improbably verdant aloe vera clinging to the windswept rock at Cape Point near the southern tip of Africa, hasn’t wondered: how the heck do gradient boosting trees implement multi-class classification? Today, we’ll unravel this mystery by reviewing the theory and implementing the ...
10344 sym Python (7629 sym/16 pcs) 76 img
Blogging with Quarto and Jupyter: The Complete Guide
Ahh, blogging. I think we can all agree it’s probably one of the greatest forms of written communication to have ever existed.Whats that you say? You’d like to set up your own blog? And you say you want to use a dead simple, data science friendly tech stack? And you wouldn’t be caught dead handing over your painstakingly crafted content to Me...
24002 sym Python (1943 sym/35 pcs) 10 img
XGBoost for Regression in Python
In this post I’m going to show you my process for solving regression problems with XGBoost in python, using either the native xgboost API or the scikit-learn interface. This is a powerful methodology that can produce world class results in a short time with minimal thought or effort. While we’ll be working on an old Kagle competition for predic...
14181 sym Python (19490 sym/41 pcs) 8 img 1 tbl