A set of test cases where the outcome is already known (in our example, cases
where it is already known whether or not the person actually has the disease)
is used to measure the quality (that is, the error rate) of the classifier. A true
positive is a case where the prediction was positive, and the person actually had
the disease,while a false positive is a case where the predictionwas positive, but
the person did not have the disease. True negative and false negative are defined
similarly for the case where the prediction was negative.