#EcoDtaFlow Project
This is my major project that I built to show a complete data pipeline and prediction system.
It’s called EcoDataFlow, and it works on waste-management data from Indian cities.
I created it fully in Python from scratch – it reads data from CSV, cleans and transforms it, stores it in a database, and then shows useful visualizations and predictions.
- Built a full ETL (Extract, Transform, Load) pipeline using Python and pandas
- Cleaned and structured data before storing it in SQLite database
- Created graphs to show city-wise and month-wise recycling performance
- Used Linear Regression to predict recycling efficiency for the next 3 months
- Automated everything so that the results are exported as charts and CSV files
Python 3 | pandas | sqlite3 | matplotlib | seaborn | scikit-learn | GitHub
The outputs show:
- Which city recycles the most waste
- How the recycling trend changes every month
- Future forecast graph for next 3 months based on past data
All charts and CSVs are saved inside the outputs folder.
I wanted this project to look real and clean, not just theory.
So I kept the data simple but the process advanced – complete flow from raw data → database → visualization → prediction.
Naren Reddy
Master’s student in Cybersecurity | learning AI, Data & ML side by side
GitHub: [naren38]. (https://github.com/naren38)