Monish-Nallagondalla/Algerian_forest_fires

This project predicts forest fires in Algeria using machine learning models . The dataset includes various meteorological and environmental features such as temperature, humidity, and wind speed. The app cleans the data and builds models to predict the likelihood of forest fires based on historical data and environmental conditions. # Algerian Forest Fires Prediction This project focuses on predicting the likelihood of forest fires in Algeria using weather and environmental data. It employs machine learning models such as Ridge Regression to analyze data and predict fire outbreaks based on factors like temperature, humidity, wind speed, and more. The application provides real-time predictions for fire risk, helping in forest management and safety. --- ## **Project Overview** The Algerian Forest Fires project uses a cleaned dataset with features like temperature, humidity, wind speed, and fire weather index (FWI) to train a predictive model. The project aims to predict fire outbreaks and provide insights into the factors that contribute to these fires, focusing on regions like Bejaia and Sidi-Bel Abbes. --- ## **Repository Contents** - **Notebooks**: - `EDA and FE.ipynb`: Exploratory Data Analysis and Feature Engineering - `Model Training.ipynb`: Model training and evaluation - **Dataset**: - `Algerian_forest_fires_cleaned_dataset.csv`: Cleaned dataset with features like temperature, humidity, wind speed, etc. - `Algerian_forest_fires_dataset_UPDATE.csv`: Updated dataset with region-specific data (Bejaia and Sidi-Bel Abbes). - **Models**: - `ridge.pkl`: Trained Ridge Regression model for fire prediction. - `scaler.pkl`: Scaler used to preprocess the data for model predictions. - **Templates**: - `home.html`: Main page of the web application. - `index.html`: The index page of the web application. - **Application**: - `application.py`: Flask application for deploying the model. - **requirements.txt**: Dependencies needed to run the project. - **LICENSE**: MIT License for project use. --- ## **Technologies Used** - **Programming Language**: Python - **Libraries**: - Data Analysis: `Pandas`, `NumPy` - Machine Learning: `Scikit-learn`, `Ridge Regression` - Data Visualization: `Matplotlib`, `Seaborn` - Web Framework: `Flask` --- ## **Setup Instructions** 1. **Clone the Repository**: ```ba …