Categorical Attribute

Classification algorithms in the field of machine learning divide attributes into discrete and continuous, where discrete attributes have finite or infinite countable values that may or may not be represented by integers, for example, the attributes hair_color, smoker, medical_test, and drink_size all have finite values.

If the set of possible values for an attribute is infinite, but a one-to-one correspondence with natural numbers can be established, then the attribute is infinitely countable, for example, the attribute customer_ID is infinitely countable.