We are looking at a classification problem where a restaurant owner is trying to predict a discrete output variable with three different possible categories given some input variables. The categories are 1: to buy the lunch special with dessert 2: to buy the lunch special without dessert 3: to not buy the lunch special. After collecting some data on a sample of customers in the previous month, you run a classification tree to predict the output variable that interests the restaurant owner. The classification tree had three terminal nodes with one node where all the customers bought the lunch special with dessert, another node where all the customers bought the lunch special without dessert and a third node that was a little bit more intricate to use. That node had 250 customers in total. Of those 250 customers, 44 bought the lunch special with dessert and 77 did not buy that lunch special. What is the Gini index measure of impurity of that node?
We are looking at a classification problem where a restaurant owner is trying to predict a discrete output variable with three different possible categories given some input variables. The categories are
1: to buy the lunch special with dessert
2: to buy the lunch special without dessert
3: to not buy the lunch special.
After collecting some data on a sample of customers in the previous month, you run a classification tree to predict the output variable that interests the restaurant owner. The classification tree had three terminal nodes with one node where all the customers bought the lunch special with dessert, another node where all the customers bought the lunch special without dessert and a third node that was a little bit more intricate to use. That node had 250 customers in total. Of those 250 customers, 44 bought the lunch special with dessert and 77 did not buy that lunch special. What is the Gini index measure of impurity of that node?
Step by step
Solved in 2 steps
