Boston Housing Price Prediction Web App
This is a full-stack Machine Learning web application that predicts Boston house prices based on the average number of rooms using a regression model trained with Mini-Batch Gradient Descent and deployed using Flask and Render.
Live App
Model
Training Dashboard (W&B)
Project Structure
app.py: Flask backendtemplates/index.html: UI formrequirements.txt: Python dependenciesProcfile: Render deployment configinference.py: inference script for local use
How to Run Locally
1- Clone the repository / locally create exact same Project Structure:
git clone
https://github.com/Nabeeha-Shafiq/boston-housing-web-app.git
cd boston-housing-web-app
2- Install dependencies:
pip install -r requirements.txt
3- Run the app:
python app.py
How to Use the web application :
1- Enter average number of rooms in the web text box.
2- Enter PREDICT buttom to get house price prediction.
3- Model is loaded from Hugging Face at runtime.
Usage
import joblib
import numpy as np
model = joblib.load("mini_batch_model.joblib")
scaler = joblib.load("scaler.joblib")
Example input: 6.5 rooms
X_new = scaler.transform([[6.5]])
prediction = model.predict(X_new)
print(prediction)
