RamanKumar-pro/Algerian-Forest-Fire-ML-Project

End-to-End ML Project LifeCycle # Algerian Forest Fire Prediction - End-to-End ML Project ## Overview This project is an end-to-end Machine Learning application that predicts the **Fire Weather Index (FWI)** based on various weather and forest fire index parameters. The model is trained on the **Algerian Forest Fires Dataset**, which includes data from two regions in Algeria: **Bejaia** and **Sidi Bel-Abbes**. The application uses a **Ridge Regression** model for prediction and is deployed as a web application using **Flask**. ## Dataset Information The dataset contains observations from **June 2012 to September 2012**. - **Instances:** 244 - **Attributes:** 11 input features + 1 target variable (FWI) - **Regions:** 1. Bejaia Region (Northeast Algeria) 2. Sidi Bel-Abbes Region (Northwest Algeria) ### Features 1. **Temperature**: Max temperature in noon (°C) 2. **RH**: Relative Humidity (%) 3. **Ws**: Wind speed (km/h) 4. **Rain**: Total day rain (mm) 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. **Classes**: Fire or Not Fire (Categorical) 11. **Region**: 0 for Bejaia, 1 for Sidi Bel-Abbes ### Target Variable - **FWI**: Fire Weather Index ## Tech Stack - **Programming Language**: Python - **Web Framework**: Flask - **Machine Learning**: Scikit-learn (Ridge Regression, StandardScaler) - **Data Manipulation**: Pandas, NumPy - **Visualization**: Matplotlib, Seaborn - **Frontend**: HTML, CSS, JavaScript ## Installation & Usage ### 1. Clone the Repository ```bash git clone cd "Algerian Forest Fire" ``` ### 2. Create a Virtual Environment (Optional but Recommended) ```bash python -m venv venv # Windows venv\Scripts\activate # Mac/Linux source venv/bin/activate ``` ### 3. Install Dependencies ```bash pip install -r requirements.txt ``` ### 4. Run the Application ```bash python application.py ``` The app will start on `localhost`. ## Model Training The model training process …