Represent the greenhouse roof materials

A journey through categories without an invented ranking with Botie.

Data Preparation · A journey with Botie

First visit? Learn the workshop controls

Botie's notebook

Giving Each Category Its Own Question

Part 1 of 2

Statistical models need representations for properties that are names rather than quantities. Indicator variables answer separate membership questions, allowing categories to contribute without forcing their arbitrary codes onto a numerical scale.

Sources for this history

Scikit-learn: Encoding categorical features

← Previous lesson: Principal Component Analysis Read the full lesson and derivations