Regression Analysis from Scratch
I have a regression analysis project where I’m implementing the math from scratch rather than calling a library function. The goal is to understand what’s actually happening inside
sklearn.linear_model.LinearRegression()before I use it as a black box.This post is coming soon. It will cover least squares, the normal equation, gradient descent, and polynomial regression, all in raw numpy.
Building a Physics Simulation Engine in Python
How the physics_modeling package is architected: base classes, numerical integrators, separation of physics from visualization, and property-based testing.
The Core Abstraction
Every physics simulation answers the same question: given a system’s current state, what is its state at the next instant? Whether you’re modeling a spring, an epidemic, or a galaxy of gravitating bodies, the computation follows one pattern: compute derivatives, advance time, repeat.
The
physics_modelingpackage encodes this pattern in aSimulationbase class: