n end-to-end data analytics and machine learning system for monitoring, analyzing, and predicting drinking water quality across Egypt's governorates and water companies.
# 💧 Egypt Water Quality Analysis & Prediction System
An end-to-end data analytics and machine learning system for monitoring, analyzing, and predicting drinking water quality across Egypt's governorates and water companies.
---
## 📌 Project Overview
This project was developed as part of the **ITI (Information Technology Institute) graduation project**, built on real data from the **Egyptian Water Company**. It combines business intelligence, data engineering, and machine learning to deliver a comprehensive water quality monitoring solution.
The system covers:
- 📊 **20 Power BI Dashboards** analyzing water quality, consumption, waste, companies, and governorates
- 📋 **6 SSRS Reports** covering operational KPIs across companies and usage metrics
- 🤖 **AI Prediction Model** (Random Forest, 99.3% accuracy) predicting water safety from 14 chemical parameters
- 💬 **GPT-powered Chatbot** for interactive water quality consultation
- 🗄️ **SQL Server Database** as the centralized data source for all analytics
---
## 🗂️ Project Structure
```
Egypt_Water_Quality_System/
│
├── 📁 DataBase/
│ ├── schema.sql # Database schema & table definitions
│ ├── stored_procedures.sql # Stored procedures used across the system
│ └── sample_data.sql # Sample/anonymized data for testing
│
├── 📁 Egypt_Water_Quality_ML/
│ ├── app2.py # Streamlit web application (main entry point)
│ ├── model_training.ipynb # Model training notebook (EDA + Random Forest)
│ ├── water_quality_model.pkl # Trained XGBoost model
│ ├── feature_names.pkl # Feature names for model input
│ └── requirements.txt # Python dependencies
│
├── 📁 Water_Quality_Project_SSRS/
│ ├── Report_Companies.rdl # Company-level report
│ ├── Report_Consumption.rdl # Water consumption report
│ ├── Report_Usage.rdl # Usage analysis report
│ ├── Report_Waste.rdl # Water waste report
│ …