Real-time collaboration for Jupyter Notebooks, Linux Terminals, LaTeX, VS Code, R IDE, and more,
all in one place. Commercial Alternative to JupyterHub.

Model Evaluation and Refinement

This lab considers the evaluation and refinement of prediction models using the following methods:

• Training and Testing (using train_test_split)

• Considering the Cross-Validation Score (which splits the dataset into K equal groups (folds), and some groups are used for testing, and some training. )

• Over-fitting, Under-fitting and Model Selection, using various degrees of polynomial fits

• Ridge Regression (used for Multiple Regression models, and explored in detail within the notebook)

• Grid Search (used to scan through multiple free parameters with few lines of code)

It is best to view the notebook to understand the use of each method, and the syntax used for each section.