Synthetic Citizen Data Generator

This tool is developed under the supervision of Uni Bremen as part of the "IT-Management and Data Science" course. The tool is designed to generate and visualize synthetic datasets for the Chinese Credit System as implemented in Rongcheng city. The tool uses the criteria and subcategories in the Chinese credit system to create simulated data, which can be used for research, testing, or training machine learning algorithms. The datasets generated by this tool are based on the implementation of the Chinese credit system in Rongcheng city and reflect its unique characteristics.

Project Structure

The project consists of the following structure:

• data
  • processed
  • raw
    • actions (contains actions that could be taken by citizens in different formats)
      • actions.json
      • converted_actions.json
      • example_actions.json
    • likelihood (contains the likelihood of each action to be taken)
      • action_likelihoods.rtf
      • subcategories_likelihood_example.json
• src (contains the source code of the project)
  • data_processing (contains classes to generate synthetic citizen data based on actions and their likelihood)
    • __init__.py
    • citizen_data_generator.py
  • data_statistics (contains classes to visualize the data generated)
    • __init__.py
    • categories_visualizer.py
    • citizen_data_visualizer.py
  • utils (contains helper classes)
    • __init__.py
    • actions_converter.py
  • __init__.py
  • main.py (the main class of the program)

Running the Program

The program can be run by executing the main.py file located in the src folder.

Requirements

• Python 3.6 or higher
• Additional library requirements can be found in the requirements.txt file.

Support

If you have any questions or issues with the program, please open an issue on the GitHub repository or contact the developer directly.