Aashutosh029/Algerian-Forest-Fire-Prediction
Domain:
environment and energyRecord type:
softwaremodel
Creator:
Aas
Host:
# Forest Fire FWI Prediction Web App
A Flask-based web application for predicting the Fire Weather Index (FWI) using a trained Ridge Regression model. The app accepts nine meteorological and fire data inputs, scales them with a saved standard scaler, and returns a predicted FWI value.
## 🚀 Project Overview
This project is built to demonstrate a machine learning deployment as a web app. It uses:
- `Flask` for the web interface
- `scikit-learn` for the saved Ridge Regression model
- `numpy` for input conversion and prediction handling
- `Bootstrap` and custom CSS for a modern UI
## 📁 Project Structure
```text
Project-One/
│
├── app.py # Flask application entry point
├── README.md # Project documentation
├── requirements.txt # Python dependencies
├── model/
│ ├── ridge.pkl # Trained Ridge Regression model
│ └── scaler.pkl # Saved StandardScaler for input scaling
└── templates/
└── index.html # HTML template for the web app
```
## ✅ Features
- Modern Flask web interface
- Responsive input form
- Model explanation cards at the bottom
- Input validation for numeric values
- Prediction display with polished styling
- Works with saved scaler and model objects
## 💻 Requirements
- Python 3.10+ recommended
- `Flask`
- `numpy`
- `scikit-learn`
## 📦 Installation
1. Clone the repository to your local machine.
2. Create and activate a virtual environment:
```bash
python -m venv venv
.\venv\Scripts\activate
```
3. Install dependencies:
```bash
pip install -r requirements.txt
```
## ▶️ Run the App
From the project root, run:
```bash
python app.py
```
Then open the app in your browser at:
```text
127.0.0.1
```
## 🧪 Test Example
Try these sample values:
- `Temperature`: 30
- `RH`: 50
- `Ws`: 10
- `Rain`: 0
- `FFMC`: 80
- `DMC`: 20
- `ISI`: 5
- `Classes`: 0
- `Region`: 0
Another test example:
- `Temperature`: 35
- `RH`: 30
- `Ws`: 15
- `Rain`: 0
- `FFMC`: 90
- `DMC`: 30
- `ISI`: 10
- `C …