mahima720/testforestfires

A Machine Learning web application that predicts the occurrence or intensity of forest fires based on the Algerian Forest Fires Dataset. This project utilizes a Ridge Regression model and is deployed using a Flask web framework. # 🔥 Forest Fire Prediction System A Machine Learning web application that predicts the occurrence or intensity of forest fires based on the Algerian Forest Fires Dataset. This project utilizes a Ridge Regression model and is deployed using a Flask web framework. ## ✨ Features * **📈 Predictive Analytics:** Uses meteorological features (Temperature, Humidity, Wind Speed) to predict fire behavior. * **🌐 Flask Web Interface:** A user-friendly web portal to input environmental parameters and receive real-time predictions. * **🧪 Scaled Data Processing:** Implements StandardScaler to ensure input data is normalized, matching the training environment for high accuracy. * **💾 Model Persistence:** Utilizes pickle to load pre-trained models and scalers, ensuring fast inference without retraining. ## 🏗️ Skills Developed * **Model Deployment:** Moving a model from a Jupyter Notebook to a production-ready Flask API. * **Pipeline Consistency:** Ensuring that the data preprocessing (scaling) used during training is identical to the one used during inference. * **Web Integration:** Handling POST and GET requests to create an interactive data-driven experience. * **Pickle Serialization:** Managing binary files for efficient model loading. ## 🏁 Conclusion The Forest Fire Prediction System demonstrates the end-to-end lifecycle of a machine learning project—from data handling and feature scaling to building a functional user interface. By using Ridge Regression, the project effectively manages multicollinearity in environmental data, providing a robust tool for fire risk assessment.