https://github.com/kpj/genex
Find expressions via genetic algorithms
https://github.com/kpj/genex
dynamic-simulations genetic-algorithm python
Last synced: 20 days ago
JSON representation
Find expressions via genetic algorithms
- Host: GitHub
- URL: https://github.com/kpj/genex
- Owner: kpj
- Created: 2016-08-22T11:51:31.000Z (almost 10 years ago)
- Default Branch: master
- Last Pushed: 2017-02-05T19:12:02.000Z (over 9 years ago)
- Last Synced: 2025-03-11T14:55:24.554Z (over 1 year ago)
- Topics: dynamic-simulations, genetic-algorithm, python
- Language: Python
- Size: 29.3 KB
- Stars: 1
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Model Optimizer
Fit model of dynamical system to data
## Usage
```bash
$ python main.py LotkaVolterra result.pkl
$ python analyze_result.py result.pkl
```
## Tests
```bash
$ nosetests
```
## Presets
Exemplary function definitions can be found in `./presets/examples.py`.
## Features
* Initialization
* Randomized individuals
* Selection
* Fit individuals are more likely to be chosen for reproduction
* Crossover
* Coefficient pulling
* Randomized scale to prevent cycles
* Coefficient sign switch
* Exchange subtrees between terms
* Mutation
* Add scaled Gauss to coefficient
* Switch function with operator of same arity or different arity with randomized arguments
* Misc
* Keep elite (fittest individuals) over generations
* Apply culling technique
* Pause procedure and inspect generation with [CTRL]+[Z]
* Optionally fix certain coefficients
* Fitness
* Root relative squared error of series with multiple initial conditions