This repository serves as a technical demonstration of my skills in Data Engineering, Backend Integration (SQLite), and Frontend Visualization (Streamlit). It simulates a real-world Industry 4.0 scenario: monitoring Overall Equipment Effectiveness (OEE) in a dairy production line.
The goal of this project is to demonstrate a full-cycle data solution:
- Data Ingestion: Handling raw production data.
- Data Transformation: Processing and cleaning data using Python/Pandas.
- Storage: Structuring and querying a local SQLite database.
- Insight Delivery: Building an interactive dashboard for decision-making.
- Python: Core logic, data manipulation, and automation.
- Pandas & NumPy: Complex data cleaning and KPI calculations (OEE formulas).
- SQLite: Database schema design and SQL integration.
- Streamlit: Rapid development of a web-based UI for data apps.
- Plotly: Creating interactive charts (Pareto, Time-Series, Gauges).
- Real-time KPI Tracking: Instant visibility of OEE, Availability, Performance, and Quality.
- Downtime Analysis: Automatic Pareto charts to identify the main causes of efficiency loss.
- Production Comparison: Dynamic filters to compare performance across different shifts and production lines.
| Filter View 1 | Filter View 2 | Filter View 3 |
|---|---|---|
 |
 |
 |
| Evolution | Comparison | Downtime |
|---|---|---|
 |
 |
 |
This project is structured to showcase clean code and modularity:
Data_Prep.py&Tables_Prep.py: ETL (Extract, Transform, Load) logic.Data_Insert.py: Database management and SQL operations.Dashboard.py: UI/UX design and data visualization layer.
Note: This is a portfolio project and is not intended for production use. It aims to showcase technical proficiency in the Python data ecosystem.
Contact: Ricardo Serenato Junior
Email: ricardoserenato@gmail.com