This task focuses on classification study, and in particular, the decision tree induction method. The specific problem this assignment concerns is whether a specific person has an annual salary of over $50K given the specific description of this person. Clearly, this is a classification/prediction problem. We use a real census data.
Need coding in C++
[login to view URL] up the data set. There are tuples in the data set in which there are missing value. propose and implement a method to clean up the data set. Note that the datasets include [login to view URL] and [login to view URL] both files.
2. Implement a decision tree induction method in which you may use whatever criterion to decide which attribute you will pick up at which level of the tree induction.
[login to view URL] your classification error rate with the reported error rates