Iterative Latin Hypercube Planner for ARES

An iterative Latin Hypercube Design of Experiments (DoE) planner built for the ARES OS 2.0 ecosystem. This package provides a service that dynamically populates hypercube bins based on experimental history, ensuring an even distribution of sampling points across the parameter space.

Features

• Iterative Binning: Automatically tracks parameter history to identify and fill empty hypercube bins.
• ARES Integration: Native support for PyAres and the ARES OS planning request/response protocol.
• Repeatable Results: Supports global random seeding for reproducible research.
• CLI Native: Runs instantly from your terminal with configurable port and network settings.

Installation

You can install the planner directly via pip. Ensure you have Python 3.10 or newer installed.

pip install ares-planner-iterative-latin-hypercube

Dependencies

• PyAres
• numpy >= 2.2.0

Command Line Interface (CLI)

Once installed, the planner service is automatically added to your system's PATH. You can start it from any terminal using the built-in command:

start-latin-hypercube

By default, the service starts on localhost and listens on port 1337.

CLI Arguments

You can customize the service behavior using the following optional arguments:

Usage Examples

**Run multiple