This is a Streamlit web application that predicts house prices based on user input features such as area, number of bathrooms, stories, and more. The model was trained using a normalized dataset and saved using joblib
.
- Interactive UI to input:
- Area (in sq. ft)
- Number of Bathrooms
- Number of Stories
- Parking spots
- Hot Water Heating
- Air Conditioning
- Basement
- Preferred Area
- Normalizes input based on training range
- Loads and uses a pre-trained model (
House1_price_prediction.pkl
) - Predicts and displays house price in Pakistani Rupees (₨)
- Model used: Xgboost
- Trained on normalized features
- Price output is scaled back to actual price range:
1,750,000 – 13,300,000 RS
git clone https://github.com/Shoaib1-coder/HousepricePrediction.git
cd HousepricePrediction
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
pip install -r requirements.txt
streamlit run app.py
├── app.py # Main Streamlit app
├── House1_price_prediction.pkl # Trained ML model
├── requirements.txt # Python dependencies
├── runtime.txt # Python version for deployment
├── data/ # Dataset folder (optional)
├── EDA.ipynb # Exploratory Data Analysis notebook
└── README.md # Project documentation
This app is compatible with Streamlit Cloud. Make sure the following files are in your root folder:
app.py
requirements.txt
runtime.txt
(withpython-3.10
)House1_price_prediction.pkl
Then push to GitHub and deploy from the Streamlit Cloud dashboard.
Muhammad Shoaib Sattar
GitHub | Email
This project is licensed under the MIT License.