According to the classification error rate, which attribute would be chosen as the first splitting attribute? For each attribute, show the contingency table and the gains in classification error rate.

The following table summarizes a data set with three attributes A, B, C and

two class labels +, ?. Build a two-level decision tree.



The error rate for the data without partitioning on any attribute is


image


After splitting on attribute A, the gain in error rate is:


image


After splitting on attribute B, the gain in error rate is:


image


After splitting on attribute C, the gain in error rate is:





The algorithm chooses attribute A because it has the highest gain.

Computer Science & Information Technology

You might also like to view...

The internal vulnerability assessment is usually performed against every device that is exposed to the Internet, using every possible penetration testing approach. __________

Answer the following statement true (T) or false (F)

Computer Science & Information Technology

Besides making your code easier to modify, using a ____ makes the code easier to understand.

A. standard constant B. named constant C. literal constant D. named variable

Computer Science & Information Technology