How avinandanroyy/car-price-prediction-ml works
This is a Streamlit used-car valuation app. A user enters vehicle details, the app encodes them for a bundled regression model, then presents an estimated price, depreciation, price range, and supporting analysis. The sampled source supports this interactive workflow and model loading; the CSV and notebook are present in the tree, but their role is not established by the available excerpts.
Main entry points: app.py Streamlit app · car_prediction_model.pkl Prediction model
Components 10
User Interface
- Streamlit app
app.py - Vehicle inputs
app.py
Valuation
- Model loader
app.py - Prediction model
car_prediction_model.pkl - Feature encoding
app.py - Price inference
app.py
Results
- Depreciation analysis
app.py - Valuation results
app.py - Price gauge
app.py
Other components
- Car owner
Connections 11
- Car owner → Streamlit app: opens
- Streamlit app → Vehicle inputs: collects
- Streamlit app → Model loader: loads model
- Model loader → Prediction model: reads
- Streamlit app → Feature encoding: encodes inputs
- Streamlit app → Price inference: runs prediction
- Price inference → Prediction model: predicts with
- Streamlit app → Depreciation analysis: calculates
- Streamlit app → Valuation results: renders
- Streamlit app → Price gauge: renders chart
- Depreciation analysis → Valuation results: supplies metrics