Audit the held-out greenhouses

A journey through have we really held out a new example? with Botie.

Choosing and Checking a Model · A journey with Botie

First visit? Learn the workshop controls

Botie's notebook

Repeated Measurements Need a Different Evaluation Boundary

Part 1 of 2

Repeated observations are common in scientific datasets. Measurements from one person, device, or location can share properties that distinguish them from other groups. Treating all rows as independent can therefore overstate performance on new groups.

Sources for this history

Scikit-learn: Cross-validation for grouped data

← Previous lesson: Would More Examples Help?Read the full lesson and derivations