Simulated Annealing for noisy cost functions.
Project description
Josiann: Just anOther SImulated ANNealing
Josiann is a Python library which implements the simulated annealing algorithm for noisy cost functions. It has support for vectorized functions, multiprocessing and provides a parallel mode for optimizing several similar but independent problems at once.
Source code (CeCILL-B): https://github.com/Vidium/josiann
Documentation: https://josiann.readthedocs.io/en/latest/index.html
Installation
Josiann requires Python 3.8+ to run and relies on the following libraries :
- Numpy
- attrs
- tqdm
Pip installation
pip install josiann
Optional diagnostic plots need the library plotly
to be generated. You can install it alongside with Josiann :
pip install josiann[plot]
Examples
Several examples of using Josiann can be found in the docs/tutorials
folder.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for josiann-1.1.3rc2-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 554754920b32a8b5776b73537ec29a22091dbed138728abb983d429d054ebdc4 |
|
MD5 | d5fba4756b677246150836b4908a8547 |
|
BLAKE2b-256 | 4b3e0b917c9b7d6ba5637a45c9161ab2cd3ef6aa7b778cfc38522a2c92aae01b |