Problem 1 (20 points): The following table consists of training data from an employee database. The data have been generalized. For example, "31 . . .35" for age represents the age category with range of 31 to 35. For a given row entry, count represents the number of data tuples having the values for department, status, age, and salary given in that row. (a) Construct a decision tree from the given data using information gain. Using Formula: Info( D) = -_ p. log;(p.) , We get: Info (Data) = -(52/165) x logz (52/165) - (113/165) x logz(113/165) = 0.89903 Using formula: HIDI , We get: Infodept (Data) = 0.8504 Infoage (Data) = 0.474 Infosel (Data) = 0.3615 Gain(D) = Info(D) - Info A(D) That implies, Gain(Sal) is the highest. [Since, Gain(Sal) = 0.89903 - 0.36153 ] Construction a tree with Salary as the first Node, Salary 26-30k 31-35k 36-40k 46-50k 66-70k Junior Junior Junior Marketing Sales Secretary Senior