Use the ID3 algorithm to build the full decision tree for the data set given in Section 10.9.2.

Transcribed Image Text:

10.9.2 Example We will start with the training data given below: Film Country of origin Big star Genre Success Film 1 United States yes Science Fiction true Film 2 United States no Comedy false Film 3 United States yes Comedy true Film 4 Europe no Comedy true Film 5 Europe yes Science fiction false Film 6 Europe yes Romance false Film 7 Rest of World yes Comedy false Film 8 Rest of World no Science fiction false Film 9 Europe yes Comedy true Film 10 United States yes Comedy true We will now calculate the information gain for the three different attributes of the films, to select which one to use at the top of the tree. First, let us calculate the information gain of the attribute "country of ori- gin." Our collection of training data consists of five positive examples and five negative examples, so currently it has an entropy value of 1. Four of the training data are from the United States, four from Europe, and the remaining two from the rest of the world.