How surya2324/house-price-prediction-using-machine-learning works
This is a Bengaluru house-price prediction project. A user enters property details in the Streamlit app, which uses the cleaned dataset to offer locations and a saved model to predict and display a price. The README also documents preprocessing, exploratory analysis, multiple-model training, and evaluation in the notebook; notebook internals were not sampled, so those capabilities are represented without inferring their detailed wiring.
Main entry points: app.py Streamlit predictor · Machine_Learning_Project-House_Price_Prediction.ipynb Analysis and model training · House_prediction_model.pkl Saved price model · Cleaned_data.csv Cleaned housing data
Components 6
Prediction app
- Streamlit predictor
app.py
ML workflow
- Saved price model
House_prediction_model.pkl - Analysis and model training
Machine_Learning_Project-House_Price_Prediction.ipynb
Project data
- Cleaned housing data
Cleaned_data.csv - Bengaluru housing data
Bengaluru_House_Data.csv
Other components
- Home seeker
Connections 8
- Home seeker → Streamlit predictor: enters features
- Streamlit predictor → Cleaned housing data: reads locations
- Streamlit predictor → Saved price model: loads model
- Streamlit predictor → Saved price model: predicts price
- Streamlit predictor → Home seeker: shows estimate
- Analysis and model training → Bengaluru housing data: analyzes data
- Analysis and model training → Cleaned housing data: prepares data
- Analysis and model training → Saved price model: trains and evaluates