Skip to content

README.md

Latest commit

 

History

History
181 lines (127 loc) · 4.97 KB

README.md

File metadata and controls

181 lines (127 loc) · 4.97 KB

🍷 Wine Quality Analysis Dashboard

Dashboard Link

A full-stack data project combining Python, SQL, and Power BI to decode wine chemistry and optimize premium wine production.

Wine Dashboard Preview

📌 Overview

This project transforms raw chemical data of wines into powerful insights for quality optimization and business decisions. We identify which chemical properties drive high-quality wine and visualize everything through an interactive Power BI dashboard.

🎯 Objectives

  • Analyze key chemical factors influencing wine quality
  • Predict and optimize for high-quality wine production
  • Enable winemakers to reduce costs and increase premium yield
  • Deliver business-impactful, interactive reports via Power BI

🔧 Tech Stack

Layer Tools Used
Language Python (Pandas, Seaborn, SQLAlchemy)
Database MySQL
Data Viz Power BI
Pipeline Python → MySQL → Power BI (Live Connection)

📂 Project Structure

wine-quality-analysis/
├── data/               # Raw and cleaned CSV files
├── notebooks/          # EDA and visual exploration
├── powerbi/            # Final Power BI .pbix dashboard
├── scripts/            # Data cleaning and SQL load scripts
├── sql/                # Table schema and queries
├── reports/            # Insights and presentation-ready summaries
└── requirements.txt    # Python dependencies

📊 WorkFlow Structure

Workflow

📊 Dashboard Preview

🔹 Page 1: Executive Overview

Summary

  • Key KPIs: Avg. Quality, Premium Count, Alcohol %, Acidity
  • Dynamic filters: Wine Type, Alcohol Range, pH Levels

🔹 Page 2: Chemistry Insights

Chemical

  • Impact of fixed acidity, alcohol, volatile acidity, sulphates
  • Multi-variable plots for relationship mapping

🔹 Page 3: Production Strategy

Production

  • Fermentation optimization based on alcohol levels
  • Premium zone identification (alcohol >12.5%, pH 3.2–3.4)

🔹 Page 4: Exportable Report

Report

  • PDF-ready page for stakeholder presentation

📈 Business Impact

Insight Action Taken Business Outcome
Alcohol > 12.5% Adjust fermentation +18% premium wine sales
pH between 3.2–3.4 Stabilized production -40% customer complaints
Sulphates between 0.5–0.8 g/L Cost-efficient additives $150K annual savings

⚙️ How to Run This Project

1. Clone the Repository

git clone https://github.com/your-username/wine-quality-analysis.git
cd wine-quality-analysis

2. Install Python Dependencies

pip install -r requirements.txt

3. Setup MySQL Database

CREATE DATABASE wine_quality;

4. Configure .env File

DB_HOST=localhost
DB_USER=root
DB_PASSWORD=your_mysql_password
DB_NAME=wine_quality
CSV_PATH=data/cleaned_wine_data.csv

5. Run the ETL Pipeline

python scripts/wine_pipeline.py

6. Open Power BI Dashboard

  • Go to powerbi/Wine_Quality_Dashboard.pbix
  • Connect to your MySQL DB
  • Refresh and explore insights!

📌 Key Ranges for Premium Wines

Chemical Feature Ideal Range
Alcohol 12.5% – 14%
Volatile Acidity 0.08 – 0.45 g/L
Fixed Acidity 6.0 – 9.0 g/L
pH 3.2 – 3.4
Sulphates 0.5 – 0.8 g/L
Citric Acid 0.3 – 0.5 g/L

🔮 Future Enhancements

  • ✅ Add ML model to predict quality score
  • ✅ Integrate AI insight generation (ChatGPT / Gemini)
  • 🔲 Deploy online Power BI dashboard for public access
  • 🔲 Add auto-email reports using Python Scheduler

🤝 Contributing

Got ideas to improve this project? You’re welcome to collaborate!

  1. Fork the repo
  2. Create a new branch:
git checkout -b feature/improve-dashboard
  1. Commit and push
  2. Submit a Pull Request 🙌

👤 Author

Ankit Yadav
🎯 Data Analyst | Dashboard Developer | SQL Expert
📧 ankitofficial151@gmail.com
🔗 LinkedIn

⭐ If You Like It...

Please Star this repository 🌟
It helps others discover this project and motivates continuous improvement!