Tanishk190/Algerian_prediction

# Algerian Forest Fire Prediction 🚒🌲 **Algerian_prediction** is a small machine learning project for exploring and predicting forest fire occurrences in Algeria using the dataset included in the `Notebook/` folder. The project contains exploratory data analysis, model training, and a simple Flask web app that serves a trained model for making predictions. --- ## 🔍 Project Overview - **Goal:** Explore forest-fire-related data and build a model to predict fire-related outcomes (e.g., area affected or fire occurrence probability) using meteorological and fire-incident features. - **Contents:** EDA notebooks, model training notebook, trained model files, and a Flask app to serve predictions. --- ## 📁 Repository Structure - `application.py` - Flask application that loads a saved model and scaler from `Models/` and serves a web UI for predictions. - `Notebook/` - Data and Jupyter notebooks: - `Algerian_forest_fires_dataset.csv` (raw) - `Algerian_forest_fires_dataset_cleaned.csv` (cleaned copy) - `algerian_p1_EDA.ipynb` (exploratory data analysis) - `algerian_p1_MT.ipynb` (model training & testing) - `Models/` - Trained model(s) and preprocessing artifacts (e.g., `ridge_al.pkl`, `scaler_al.pkl`). - `templates/` - HTML templates used by the Flask app (`index.html`, `home.html`). - `requirements.txt` - Python dependencies. --- ## ⚙️ Setup & Installation 1. Clone the repository or copy files into your working directory. ```bash gh repo clone Tanishk190/Algerian_prediction ``` 2. Create and activate a virtual environment (recommended): ```bash python -m venv venv # Windows PowerShell venv\Scripts\Activate.ps1 # or Command Prompt venv\Scripts\activate ``` 3. Install dependencies: ```bash pip install -r requirements.txt ``` 4. (Optional) If you plan to re-run experiments, open the notebooks in the `Notebook/` folder and follow the steps in `algerian_p1_EDA.ipynb` and `algerian_p1_MT.ipynb`. --- ## 🚀 Running …