jatin02k/Forest-Fire-ML-Prediction

A simple regression project that predicts the algerian forest fire Index. # Algerian Forest Fire Weather Prediction (FWI) **🌳 Project Overview** This project implements a machine learning model to predict the Forest Fire Weather Index (FWI) based on various meteorological and forest fire activity metrics derived from the Algerian Forest Fire Dataset. The solution involves a full data science pipeline: Data Cleaning, Exploratory Data Analysis (EDA), Regression Modeling using Ridge Regression, and deployment via a Flask web application. Users can input nine key parameters on the web page to receive a real-time FWI prediction. **🛠️ Technology Stack** --- Language: Python, HTML Web Framework: Flask Data Analysis: Pandas, NumPy, Matplotlib, Seaborn Machine Learning: Scikit-learn (Ridge Regression, StandardScaler) Model Persistence: pickle **📊 Dataset and Methodology** --- Data Source: - The project utilizes the Algerian Forest Fire Dataset, which provides daily weather data and fire-related indices across two regions in Algeria. Pipeline: - Data Cleaning: Handled missing values, standardized column names, and converted necessary features to numeric types. - Exploratory Data Analysis (EDA): Performed visualization and statistical analysis to understand feature distributions, correlations, and the relationship between weather factors and the FWI target variable. - Feature Engineering: Categorical features (like Region and Classes) were prepared for model consumption. - Modeling: A Ridge Regression model was trained to predict the FWI. - Scaling: A StandardScaler was fitted to the training data and saved to ensure new inputs from the web application are scaled correctly before prediction. **🚀 Getting Started** --- Follow these instructions to set up and run the Flask application locally. Prerequisites: - Python (3.8+) - pip (Python package installer) 1. Clone the Repository ``` git clone github.com cd your-repo-name ``` 2. Set Up the Environment It is highly recommended to use …