This repository contains the code, data and images used in the Genetic Algorithm to Optimize Machine Learning Hyper-parameters article published in Towards Data Science
- generate_data.py: it generates and plots x1,x2,f(x1,x2) data
- hyperparams_grid_search.py: it calculates and plots RMSE for a grid of alpha,gamma values
- results_grid.dat: contains the alpha,gamma,RMSE values from hyperparams_grid_search.py
- hyperparams_diff_evol.py: it uses differential evolution to converge the alpha and gamma that minimize RMSE
- hyperparams_grid_and_diff_evol.py: it then plots hyperparameter grid, as well as configurations visited with differential evolution algorithm and optimized values
- figures: folder with all figures used in article
The necessary packages (with the tested versions with Python 3.8.5) are specified in the file requirements.txt. These packages can be installed with pip:
pip3 install -r requirements.txt
© Marcos del Cueto Cordones
Licensed under the MIT License.