What is the difference between One-Hot Encoding and Label Encoding?

What is the difference between One-Hot Encoding and Label Encoding?

Approach: Compare binary vector representation vs integer mapping.

Label Encoding assigns each unique category an integer (0, 1, 2...). One-Hot Encoding creates a new binary column for each category. Label encoding can imply an incorrect order; One-Hot avoids this but increases dimensionality.

Follow-up: Which one is better for linear models?

Key concepts: categorical variables, ordinality.