Process data for metadata agent

📝 Description

Provide a 2-3 sentence high-level summary of the project. Include informative figure if available!

⚙️ Installation

1. Clone the Repository

git clone [https://github.com/WUR-AI/TODO.git](https://github.com/WUR-AI/TODO.git)
cd TODO

2. Set up Environment

🚀 Getting Started

Data Preparation

Explain where to download the data and where to place it (e.g., in a data/ folder).

Running: Training, analysing, etc.

📂 Project Structure

Make use of tree -L 2 -I ".gitignore" to auto-generate the tree.

.
├── CODE_OF_CONDUCT.md                  
├── CONTRIBUTING.md
├── LICENSE
├── README.md
├── data                            # Dataset storage (git-ignored)
│   ├── ready                       # Processed, final data
│   └── source                      # Source data
├── docs                            # Sphinx generated
├── notebooks                       # Jupyter notebooks for exploration
│   └── 01-GT-name_example.ipynb    # Naming: number-intials-name
├── outputs                         # Model weighs/ouput results
├── reports                         #
├── requirements.txt                # Python environment requirements (.yaml/ pyproject.toml)
├── scripts                         # Shell scripts for cluster execution
│   └── schedule.sh
├── src                             # Source code
│   ├── data                        # Data acquistion, preprocessing, loading
│   ├── model                       # Model architecture and training logic
│   ├── train.py                    # Training calls
│   ├── visualisations              # Visualisation functions for reproducable code
│   └── utils                       # Helper functions
└── tests                           # Unit tests

📈 Project Updates & News