autocode

Auto Code Improvement by Metrics Optimization.

Description

Autocode selects the best values for optimized metrics. The value types could be bool, int, float, and choice (including but not limited to code). This project utilizes a Large Language Model and Mixed-Variable Many-Objective Optimization. Based on our research/literature review, this project hypothetically can contribute to the economic performance of companies.

Features

• Many-software Value-level Mixed-variable Many-objective Optimization.
• Value types include bool, int, float, and choice (code).
• Code scoring and variation generators using LLM.
• Software cross-language support.
• Easy software deployment using docker-compose.
• Scalable to infinite cores to speed up processing in parallel.

How to Use

1. Install the requirements

pip install -U autocode-py

2. Prepare software to be processed as in the ./example/client folder.
3. Prepare deployment as in the ./example/client/docker-compose.yml file.
4. Prepare controller as in the ./example/controller.ipynb file.
5. Instantiate optimization then execute optimization.deploy() in controller.
6. Open dashboard in http://localhost:{dashboard_port}/ to see the process in real-time.
7. Wait until all client are ready (need to wait for long time because the libraries need to be re-downloaded for each client).
8. Execute optimization.run() in controller.
9. Wait until the run is finished.
10. Analyze and decide the best values.
11. Execute optimization.reset(keys=["clients"]) then optimization.deploy() to apply different client states.
12. Try to execute optimization.reset() to totally reset the tool if needed (i.e. data inconsistency).

Demo

• Controller
• Client
• Dashboard

Compatibility

• Python 3.10, 3.11
• Linux
• Docker
• autocode-go