Sumanth-Siddareddy/Algerian-Forest-Fire-Prediction

My first end to end ML Project. # 🔥 Algerian Forest Fire (FWI) Prediction This project is a machine learning web application built with Streamlit to predict the **Fire Weather Index (FWI)**. The model is trained on a dataset of forest fire observations from two regions in Algeria: Bejaia and Sidi-Bel Abbes. The app allows a user to input various meteorological features and receive a real-time FWI prediction, which is a key indicator of wildfire risk. --- ## 🚀 Live Demo App : --- ## 📸 Application Screenshot --- ## 🛠️ Tech Stack * **Python** * **Data Analysis:** Pandas, NumPy * **ML Model:** Scikit-learn (Ridge Regression, Lasso, Linear Regression) * **Web App:** Streamlit * **EDA:** Matplotlib, Seaborn --- ## ⚙️ How to Run Locally Follow these steps to set up and run the project on your own machine. 1. **Clone the repository:** ```bash git clone github.com cd Algerian-Forest-Fire-Prediction ``` 2. **Create and activate a virtual environment:** ```bash # For Unix/Mac python3 -m venv venv source venv/bin/activate # For Windows python -m venv venv venv\Scripts\activate ``` 3. **Install the required dependencies:** ```bash pip install -r requirements.txt ``` 4. **Run the Streamlit application:** ```bash streamlit run app.py ``` 5. Open your browser and navigate to `localhost`. --- ## 📊 Project Workflow This project followed a standard data science workflow: ### 1. Data Cleaning The raw dataset, which combined data from two regions, required several cleaning steps: * Removed extra headers that were repeated in the middle of the file. * Dropped rows with all `NaN` values. * Created a new `Region` feature (Bejaia=0, Sidi-Bel Abbes=1). * Corrected column data types (e.g., to `int` and `float`). * Stripped extra spaces from column names. * Saved the preprocessed data to a new CSV file. ### 2. Exploratory Data Analysis (EDA) After cleaning, I analyzed the data to find insights: * Dropped the original `day`, …