Question

1. Consider the training examples shown in the table below for a binary classification problem. (60 points) der Car Type Shirt Size Class CO Customer ID Gen Small Medium Medium Large Family Sports Sports Sports SportsExtra LargeCO SportsExtra Large CO Sports Sports Sports Luxury Family FamilyExtra Large C1 Family LuxuryExtra Large C1 Luxury Luxury Luxury Luxury Luxury Luxury Small Small Medium Large Large 10 C1 12 13 14 15 16 17 18 19 20 Medium C1 Small Small Medium Medium Medium Large C1 C1 C1 C1 C1 C1 (1) Compute the Gini index for the overall collection of training examples. (2) Compute the Gini index for the Gender attribute (3) Compute the Gini index for the Car Type attribute using multiway split. (4) Compute the Gini index for the Shirt Size attribute using multiway split. (5) Which attribute is better, Gender, Car Type, or Shirt Size? (6) Compute the Gini index for the Customer ID attribute. Explain why Customer ID should not be used as the attribute test condition even though it has the lowest Gini.

Answer 1

senGiven that 2) Canputa the Gini index Rố 4he Gord attribute Roth the cild (malalPemaleholds ini nelex is lire the aeall Gini o1625 4)ca fat. .tho Gri İndex Pos the shit. Size 아hribate using mdfung split niae 6) Explain whycut Ip shuld not be used os te Customoli c assigied to nou dustamey D