UmdTask120_DATA605_Spring2026_Synthetic_Data_Vault

[tanayaharley31]

Summary

This PR adds my DATA605 Spring 2026 project on Synthetic Data Vault privacy classification.

Project contents

• Main SDV project notebook
• API tutorial notebook
• README documentation
• Docker build/run scripts
• Project check script
• Utility functions
• Model comparison outputs

Main workflow

The project uses the Adult Income dataset to generate synthetic data using SDV. It evaluates synthetic data quality with SDMetrics and compares classification models trained on real data versus synthetic data.

Docker

The Docker run script executes run_project_check.py and verifies the required files and output results.

Author: @tanayaharley31
Reviewers: @gpsaggese @protocorn

Issue

Closes #120

[tanayaharley31]

This PR includes the full project under:

class_project/data605/Spring2026/projects/UmdTask120_DATA605_Spring2026_Synthetic_Data_Vault/

The submission includes:

• main project notebook with the complete SDV workflow
• API tutorial notebook for the core SDV steps
• README documentation with setup, methodology, results, limitations, and conclusion
• Docker build/run scripts
• project check script
• utility functions
• model comparison output files

I also tested the Docker workflow successfully, and the run completed with:

Project check completed successfully.