How garthigan/house-price-prediction works
Project Type and Purpose
• This is a full-stack machine-learning web application for end-to-end prediction of Bangalore house prices.
• The repository includes:
• Data collection and exploration (Jupyter notebooks, raw CSV)
• Model training artifacts (pickle file, columns.json)
• A Python-based backend server
• A browser-based frontend (HTML/CSS/JS)
File Structure Analysis
Top-level
• House_predictor.ipynb, Bengaluru_House_Data.csv: exploratory analysis and model training
• bangalore_house_prices_model.pickle, columns.json: model artifacts
BHP/
• client/: standalone front-end (app.html, app.js, app.css)
• model/: backup of training artifacts and notebook
• server/:
– server.py, util.py: Python web server (likely Flask/FastAPI)
– artifacts/: model and metadata
– static/: served static files (index.html, app.js, app.css)
Configuration & tooling directories: .vscode, .idea, .ipynb_checkpoints
README Insights
• “End-to-End Bangalore House Price Prediction” emphasizing full pipeline from data ingestion through deployment.