How med-rhaled/car-price-prediction works
This repository is a notebook-based used-car price prediction project. Its documented workflow takes vehicle data through exploratory analysis and cleaning, prepares and encodes features, then trains and evaluates a tuned Random Forest model. The README also describes feature-importance analysis. Notebook internals were not sampled, so the graph reflects documented stages and relationships rather than verified code-level calls.
Main entry points: 03_modeling.ipynb Random Forest training · 01_eda.ipynb Exploratory analysis · 02_preprocessing.ipynb Data preprocessing · car_price_prediction_cleaned.csv Cleaned vehicle data
Components 10
Vehicle data
- Raw vehicle data
data/car_price_prediction.csv - Cleaned vehicle data
data/car_price_prediction_cleaned.csv
Analysis and preparation
- Exploratory analysis
notebooks/01_eda.ipynb - Data preprocessing
notebooks/02_preprocessing.ipynb
Modeling and evaluation
- Feature encoding
notebooks/03_modeling.ipynb - Random Forest training
notebooks/03_modeling.ipynb - Hyperparameter search
notebooks/03_modeling.ipynb - Model evaluation
notebooks/03_modeling.ipynb - Feature importance
notebooks/03_modeling.ipynb
Other components
- Analyst
Connections 12
- Analyst → Exploratory analysis: runs first
README.md - Raw vehicle data → Exploratory analysis: analyzes
README.md - Analyst → Data preprocessing: runs next
README.md - Exploratory analysis → Data preprocessing: precedes
README.md - Data preprocessing → Cleaned vehicle data: saves cleaned data
README.md - Analyst → Feature encoding: runs modeling
README.md - Cleaned vehicle data → Feature encoding: prepares features
README.md - Feature encoding → Random Forest training: encodes features
README.md - Random Forest training → Hyperparameter search: tunes model
README.md - Hyperparameter search → Model evaluation: evaluates model
README.md - Random Forest training → Model evaluation: reports metrics
README.md - Random Forest training → Feature importance: examines importance
README.md