🏠 PropVision – Price Insight Engine

A full-stack web application that predicts housing prices in Bangalore using a machine learning regression model. The project includes data preprocessing, model training, REST API development with Flask, and a clean, responsive frontend using HTML, CSS, and JavaScript.

---

🔧 Tech Stack

• Frontend: HTML, CSS, JavaScript
• Backend: Python, Flask
• Machine Learning: Scikit-learn, Pandas, NumPy
• Model Serialization: Pickle
• Others: Nginx (optional), Jupyter Notebook

---

📁 Project Structure

├── artifacts/                   # Stored model and column metadata
│   ├── columns.json
│   └── model.pickle
│
├── client/                      # Frontend files
│   ├── app.html
│   ├── app.css
│   └── app.js
│
├── model/                       # Jupyter notebook and raw data
│   ├── banglore\_home\_prices\_final.ipynb
│   └── bengaluru\_house\_prices.csv
│
├── nginx\_files/                 # Optional Nginx config files
│
├── server/                      # Flask backend
│   ├── server.py
│   ├── util.py
│   └── **pycache**/
│
├── requirements.txt             # Python dependencies
└── README.md                    # Project overview

---

📊 Dataset

• Source:Kaggle (CSV file in model/)
• Features:
  • Location
  • Total square footage
  • Number of bedrooms (BHK)
  • Number of bathrooms

---

🤖 ML Model

• Algorithm: Linear Regression
• Trained using cleaned and engineered features
• Serialized with pickle for deployment
• Feature names stored in columns.json for API reference

---

🌐 Web App Overview

🖼️ Frontend

• Built with vanilla HTML/CSS/JavaScript
• Takes user input (location, sqft, BHK, bath)
• Sends AJAX request to Flask server
• Displays predicted price instantly

🔌 Backend

• Flask app with two routes:
  • / : Serves the frontend (app.html)
  • /predict_home_price : Receives POST request and returns predicted price

---

🚀 How to Run

1. Clone the Repository

git clone https://github.com/yourusername/bangalore-house-price-predictor.git
cd bangalore-house-price-predictor

2. Create Virtual Environment

python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

3. Install Dependencies

pip install -r requirements.txt

4. Run the Flask Server

cd server
python server.py

5. Open the App

Open your browser and go to: http://127.0.0.1:5000

---

📌 Example Prediction

Input:

• Location: Whitefield
• Area: 1200 sqft
• BHK: 2
• Bathroom: 2

Output:

• Predicted Price: ₹84 Lakhs (example)

---

✅ Future Improvements

• Deploy on Heroku / Render
• Add authentication
• Add charts for data insights
• Integrate Google Maps API

---

• Developed by: Pothamsetti Radha Krishna

---

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

---

Would you like a `LICENSE` file (MIT or Apache 2.0) added as well?  
Also, if you'd like to deploy this and link it in your resume/GitHub, I can guide you with **Render/Heroku deployment** in one step.