https://github.com/mlojek/optilab
Python framework for black-box optimization.
https://github.com/mlojek/optilab
blackbox-optimization cd cec ci cmaes gecco metamodels python surrogate-models
Last synced: 3 months ago
JSON representation
Python framework for black-box optimization.
- Host: GitHub
- URL: https://github.com/mlojek/optilab
- Owner: mlojek
- License: gpl-3.0
- Created: 2024-07-08T13:08:28.000Z (almost 2 years ago)
- Default Branch: main
- Last Pushed: 2026-03-14T19:56:46.000Z (3 months ago)
- Last Synced: 2026-03-14T20:03:53.588Z (3 months ago)
- Topics: blackbox-optimization, cd, cec, ci, cmaes, gecco, metamodels, python, surrogate-models
- Language: Python
- Homepage: https://optilab.readthedocs.io
- Size: 428 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Optilab
[](https://www.gnu.org/licenses/gpl-3.0)
Optilab is a lightweight and flexible python framework for testing black-box optimization.
## Features
- ✅ Intuitive interface to quickly prototype and run optimizers and metamodels.
- 📚 High quality documentation.
- 📈 Objective functions, optimizers, plotting and data handling.
- ⋙ CLI functionality to easily summarize results of previous experiments.
- 🚀 Multiprocessing for faster computation.
## How to install
Optilab has been tested to work on python versions 3.11 and above. To install it from PyPI, run:
```
pip install optilab
```
You can also install from source by cloning this repo and running:
```
make install
```
## Try the demos
Learn how to use optilab and fit it to your needs with demo notebooks in `demo` directory.
## CLI tool
Optilab comes with a powerful CLI tool to easily summarize your experiments. It allows for plotting the results and performing statistical testing to check for statistical significance in optimization results.
```
usage: optilab [-h] [--aggregate_pvalues] [--aggregate_stats] [--entries ENTRIES [ENTRIES ...]]
[--hide_outliers] [--hide_plots] [--no_save] [--raw_values]
[--save_path SAVE_PATH] [--siginificance SIGINIFICANCE] [--test_evals] [--test_y]
pickle_path
Optilab CLI utility.
positional arguments:
pickle_path Path to pickle file or directory with optimization runs.
options:
-h, --help show this help message and exit
--aggregate_pvalues Aggregate pvalues of stat tests against run 0 in each pickle file into
one table.
--aggregate_stats Aggregate median and iqr for all processed runs into one table.
--entries ENTRIES [ENTRIES ...]
Space separated list of indexes of entries to include in analysis.
--hide_outliers If specified, outliers will not be shown in the box plot.
--hide_plots Hide plots when running the script.
--no_save If specified, no artifacts will be saved.
--raw_values If specified, y values below tolerance are not substituted by tolerance
value.
--save_path SAVE_PATH
Path to directory to save the artifacts. Default is the user's working
directory.
--significance SIGNIFICANCE
Statistical significance of the U tests. Default value is 0.05.
--test_evals Perform Mann-Whitney U test on eval values.
--test_y Perform Mann-Whitney U test on y values.
```
## Docker
This project comes with a docker container. You can pull it from dockerhub:
```
docker pull mlojek/optilab
```
Or build it yourself:
```
make docker
```