Melbourne Public Art Analysis

View the report at https://classic-magnolia-8b6.notion.site/Carved-Into-the-City-Melbourne-s-Story-Through-Public-Art-210b78e40b24808eb46ff5a9bc3731fb?source=copy_lin

This project analyzes public artworks in Melbourne using data science and machine learning techniques. The repository includes data processing, enrichment, and analysis workflows, with a focus on leveraging large language models (LLMs) for enhanced insights.

Project Structure

• data/
  • landing/: Raw data files (e.g., outdoor-artworks.parquet)
  • processed/: Cleaned and processed data
• models/: Saved models and related artifacts
• notebooks/: Jupyter notebooks for data download, enrichment, and analysis
  • data_download.ipynb: Scripts for downloading and preparing data
  • llm_enrichment.ipynb: Enrichment of data using LLMs
  • analysis.ipynb: Exploratory data analysis and visualization
• requirements.txt: Python dependencies

Getting Started

1. Clone the repository:

   git clone <repo-url>
   cd Melbourne-Public-Art-Analysis

2. Install dependencies:

   pip install -r requirements.txt

3. Run the notebooks: Open the notebooks in JupyterLab or VSCode and follow the instructions in each notebook.

Data Sources

• The primary dataset is a collection of outdoor artworks in Melbourne, provided in Parquet format.

Features

• Data download and preprocessing
• Data enrichment using LLMs
• Exploratory data analysis and visualization

Requirements

• Python 3.8+
• See requirements.txt for full list of dependencies

License

This project is licensed under the MIT License.

Acknowledgements

• City of Melbourne open data
• OpenAI, Hugging Face, and other contributors to the Python data science ecosystem