PyRADE Documentation๏ƒ

Welcome to PyRADE (Python Rapid Algorithm for Differential Evolution) - a high-performance, modular Differential Evolution optimization package.

Contents:

Overview๏ƒ

PyRADE is a production-ready optimization library implementing Differential Evolution (DE), a powerful evolutionary algorithm for global optimization. Unlike traditional implementations that sacrifice code quality for performance, PyRADE proves you can have both through intelligent design.

Key Features๏ƒ

  • โšก High Performance: 3-5x faster than traditional implementations through aggressive NumPy vectorization

  • ๐Ÿ—๏ธ Clean Architecture: Strategy pattern for all operators - easy to understand and extend

  • ๐Ÿ”ง Modular Design: Plug-and-play mutation, crossover, and selection strategies

  • ๐Ÿ“ฆ Production Ready: Well-documented, tested, professional-quality code

  • ๐ŸŽฏ Easy to Use: Simple, intuitive API similar to scikit-learn optimizers

  • ๐Ÿงช Comprehensive: Includes 12 benchmark functions and multiple real-world examples

Quick Example๏ƒ

import numpy as np
from pyrade import DifferentialEvolution

# Define your objective function
def sphere(x):
    return np.sum(x**2)

# Create optimizer
optimizer = DifferentialEvolution(
    objective_func=sphere,
    bounds=[(-100, 100)] * 10,
    pop_size=50,
    max_iter=200
)

# Run optimization
result = optimizer.optimize()
print(f"Best fitness: {result['best_fitness']:.6e}")

Indices and tables๏ƒ