The Algerian Forest Fires Dataset is a popular machine learning dataset used for classification (Fire vs Not Fire) and sometimes regression tasks involving fire risk prediction.
# π₯ Algerian Forest Fire Prediction
A machine learning web application that predicts the **Fire Weather Index (FWI)** and classifies fire risk levels based on environmental and weather conditions.
Built using **Python, Scikit-learn, and Streamlit**, this project provides an interactive interface for real-time predictions.
---
## π Live Demo
π Deploy easily using **Streamlit Community Cloud**
---
## π Features
* Predicts **Fire Weather Index (FWI)**
* Classifies risk levels:
* π’ Low
* π‘ Moderate
* π High
* π΄ Extreme
* Interactive UI with user inputs
* Real-time predictions
* Clean and simple dashboard
---
## π§ Machine Learning
* Model: Ridge Regression
* Preprocessing: Standard Scaler
* Libraries:
* NumPy
* Pandas
* Scikit-learn
---
## π Project Structure
```
algerianforestfires/
β
βββ app.py # Streamlit application
βββ requirements.txt # Dependencies
βββ models/
β βββ ridge.pkl # Trained ML model
β βββ scaler.pkl # Scaler for preprocessing
βββ README.md
```
---
## βοΈ Installation & Setup
### 1. Clone the repository
```
git clone
github.com
cd algerianforestfires
```
### 2. Install dependencies
```
pip install -r requirements.txt
```
### 3. Run the app locally
```
streamlit run app.py
```
---
## π Deployment
This project is deployed using **Streamlit Community Cloud**:
1. Push your code to GitHub
2. Go to Streamlit Cloud
3. Select your repository
4. Set `app.py` as the main file
5. Deploy π
---
## π Input Parameters
The model uses the following features:
* Temperature
* Relative Humidity (RH)
* Wind Speed (Ws)
* Rain
* FFMC
* DMC
* ISI
* Classes
* Region
---
## π Output
* **FWI Score** (numeric prediction)
* **Risk Level Classification**
---
## π οΈ Tech Stack
* Python
* Streamlit
* Scikit-learn
* Pandas
* NumPy
---
## π€ Contributing
Contributions are welcome! Feel free to fork this repo and submit a pull request.
---
## π License
This projec β¦