How arpit-kumar05/project-house-price-prediction- works
This is a Flask house-price prediction app. A user submits property details through the web interface; the app forms model inputs, predicts a price, records the inputs and prediction in SQLite, and renders the result. A separate training script fits and saves the prediction pipeline from the supplied dataset. The excerpts establish the app-to-model and app-to-database relationships; template details were not sampled, so the UI connection is based on the app’s explicit render calls.
Main entry points: app.py Flask app · train.py Model trainer · index.html Prediction page · database.py Schema initializer
Components 9
Web application
- Flask app
app.py - Prediction page
templates/index.html - Verification file
static/google58a9c145bd498aaf.html
Model training
- Model trainer
train.py - House dataset
House Price Prediction Dataset.csv - Trained pipeline
model.pkl
Prediction storage
- Schema initializer
database.py - Prediction records
predictions.db
Other components
- Property user
Connections 10
- Property user → Flask app: submits details
app.py - Flask app → Prediction page: renders page
app.py - Prediction page → Property user: shows result
- Model trainer → House dataset: reads data
train.py - Model trainer → Trained pipeline: saves pipeline
train.py - Flask app → Trained pipeline: loads and predicts
app.py - Flask app → Schema initializer: initializes schema
app.py - Schema initializer → Prediction records: creates table
database.py - Flask app → Prediction records: writes prediction
app.py - Flask app → Verification file: serves file
app.py