🇹🇳 Climate & Energy Intelligence platform for Tunisia using Machine Learning
# 🇹🇳 Tunisia Climate & Energy Intelligence
An end-to-end Machine Learning platform designed to analyze and predict climate and energy patterns in Tunisia.
The project combines real weather data, energy consumption data, Machine Learning, an API and an interactive dashboard to provide a complete climate & energy intelligence workflow.
---
## 🎯 Project Overview
**Tunisia Climate & Energy Intelligence** is a portfolio project focused on applying Data Science and Artificial Intelligence to climate and energy challenges in Tunisia.
The platform provides a complete pipeline:
**Data Collection → Data Processing → Feature Engineering → Machine Learning → Prediction API → Interactive Dashboard**
The objective is to demonstrate how Machine Learning can be integrated into a real-world data application.
---
## 🚀 Key Features
* 🌦️ Real weather data collection
* ⚡ Energy data processing and analysis
* 🤖 XGBoost Machine Learning model
* 📊 Model performance evaluation
* 🧠 Feature Importance analysis
* 🚀 FastAPI prediction API
* 📈 Interactive Streamlit dashboard
* 🔐 Secure API key management using environment variables
* 🔄 Automated data processing pipeline
---
## 🧠 Machine Learning
The project uses **XGBoost** for Machine Learning predictions.
### Model Performance
| Metric | Result |
| -------- | -------: |
| R² Score | **0.91** |
An R² score of **0.91** indicates that the model explains approximately 91% of the variance in the target variable on the evaluated dataset.
### Feature Importance
The project includes a feature importance analysis to understand which variables contribute most to the model's predictions.
---
## 🌦️ Data Sources
### Weather Data
Weather information is collected using the **Meteosource API**.
The project uses weather variables such as:
* Temperature
* Humidity
* Wind
* Weather conditions
* Other meteorological indicators
### Energy Data
The current version uses **synthetic energy data** as a Proof of Concept.
This allows th …