PLEASE BE QUICK ... 30MIN DEADLINE

An Internet Service Provider (ISP) a dataset that it uses to extract spam emails shown. The property space for these data used is the number of words in the e-mail (word count) for the "x1" axis, For the "x2" axis, the total of two words ("sir" and "madam") in the relevant e-mail used in number. Database on the autonomous system making decisions accordingly and prioritizing working e-mails. It was asked to convey to the user quickly and quickly. For example, also in this way As can be seen, the independent variable vector x values x1 = 600, x2 = 10 Email works so well (y = 1), but x vector values x1 = 700, x2 = 8 e-mail, on the other hand, is defined as "spam" (y = 0). This autonomous The system sends a new email with the values of the vector "x" (x1 = 600, x 2 = 5) when detected, will send it to the user as useless (spam) has been wondered. In accordance with the "Decision Tree Algorithm", this feature After dividing the space according to entropy calculations, draw it and find the dependent variable ("y") value of this incoming e-mail.

Occurences of words "sir" or "madam" = GOOD EMAIL = SPAM I - 1 1 30 25 E 20 15 A H 10 03 B B 5 .. 0:FO) F F 100 200 600 700 300 400 500 Word Count Occurences of words "sir" or "madam" = GOOD EMAIL = SPAM I - 1 1 30 25 E 20 15 A H 10 03 B B 5 .. 0:FO) F F 100 200 600 700 300 400 500 Word Count