Predict median house values for 20,640 California districts from census features. Explore the data with pandas (distributions, correlations and a price map), engineer ratio features, then compare Linear Regression, Random Forest and Histogram Gradient Boosting with 5-fold cross-validated RMSE. Finish with permutation feature importance and a predicted-vs-actual diagnostic of the winning model.
Data Download
Exploration & Features
Model Comparison
Evaluation / Metrics
Premium Project
This guided, GPU-powered project is available to Premium members. Upgrade to train models end-to-end in an interactive notebook.