Aabhas2/Algerian-Ridge-Prediction

# Algerian Forest Fire Prediction A machine learning project that predicts the Forest Fire Weather Index (FWI) using Ridge Regression. The project provides both Flask web interface and Streamlit application for making predictions. ## Dataset Information The dataset used in this project contains forest fire data from two regions of Algeria: - Bejaia region (Northeast of Algeria) - Sidi Bel-abbes region (Northwest of Algeria) **Period**: June 2012 to September 2012 **Total Instances**: 244 (122 instances for each region) **Classes**: Fire (138 cases) and Not Fire (106 cases) ### Features 1. Temperature (°C) 2. RH (%): Relative Humidity 3. Ws (km/h): Wind Speed 4. Rain (mm): Rainfall 5. FFMC: Fine Fuel Moisture Code 6. DMC: Duff Moisture Code 7. DC: Drought Code 8. ISI: Initial Spread Index 9. BUI: Buildup Index 10. FWI: Fire Weather Index (Target Variable) 11. Classes: Fire / Not Fire 12. Region: Bejaia (0) / Sidi Bel-abbes (1) ## Project Structure ``` ├── application.py # Flask web application ├── streamlit_app.py # Streamlit web application ├── requirements.txt # Project dependencies ├── models/ │ ├── ridge.pkl # Trained Ridge regression model │ └── scaler.pkl # Fitted StandardScaler ├── notebook/ │ ├── Algerian_EDA.ipynb # Exploratory Data Analysis │ ├── Model_Training.ipynb # Model training notebook │ └── Algerian_forest_fires_cleaned_dataset.csv # Dataset └── templates/ ├── home.html # Prediction page template └── index.html # Landing page template ``` ## Installation & Setup 1. Clone the repository: ```bash git clone github.com cd Algerian-Ridge-Prediction ``` 2. Install dependencies: ```bash pip install -r requirements.txt ``` ## Running the Applications ### Flask Web Application ```bash python application.py ``` Access the application at `localhost` ### Streamlit Application ```bash streamlit run streamlit_app.py ``` The app …