A decision-making tool designed for restaurant managers to optimize labor costs and monitor scheduling efficiency. Provides actionable insights into labor-to-sales ratios and payroll error patterns.

Interactive visualization of weekly labor trends and cost-saving opportunities.

• Labor Efficiency: Visualize the correlation between hourly sales and labor costs.
• Cost Savings: Automated calculation of potential savings by optimizing off-peak scheduling.
• Data Integrity: Detecting anomalies in manual time-clock overrides.

• Language: Python 3.10
• Package Manager: uv
• Framework: Streamlit (Interactive Web App)
• Data Libraries: Pandas (Transformation), Plotly (Advanced Visualization)

├── data/                  # Mock datasets for analysis
├── preview/               # Dashboard preview screenshots
├── research/              # EDA experiments
├── data_generator.py      # Generates mock restaurant operations data
├── main.py                # Entry point
├── app.py                 # Streamlit dashboard application
├── pyproject.toml         # Project metadata and dependency definitions
├── requirements.txt       # For deployment (e.g. Streamlit Cloud)
└── uv.lock                # Lockfile for reproducible environments

Install uv if you haven't already:

# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows
powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

# 1. Install dependencies
uv sync

# 2. Generate mock data
uv run python data_generator.py

# 3. Run dashboard
uv run streamlit run app.py

All datasets used in this project are programmatically generated mock data that reflect real-world restaurant operations, including weekend peak trends and role-based wage variances.