Question

Python

Question: The Pennsylvania Chocolate Institute of Health has identified a new type of disease caused by a diet containing insufficient amount of chocolate. Treatment requires expensive imported chocolates, covered by most insurance plans. There are only two types of patients: A. Healthy chocolate eaters B. Patients suffering from low chocolate levels The insurance company has developed a test (machine learning model) which predicts p, the probability that the current patient is of type A. The company is experimenting with a cost model: • The cost of treating a patient of type A is α • The cost of treating a patient of type B is some number treatB • The cost of not treating a patient of type A is some number notTreatA • The cost of not treating a patient of type B is some number notTreatB

Template

def q1(p,treatB, notTreatA, notTreatB):

Fill in the function q1(p, treatB, notTreatA, notTreatB), where p is the predicted probability the patient is of type A. The output of this function should be the value of α for which the insurance company is indifferent between treating and not treating the patient.

Answer 1

def q1(p,treatB,notTreatA,notTreatB):

CostB = min(notTreatB,treatB)

CostA = ((1-p)/p)*CostB

if (notTreatA >= CostA):

return CostA

else:

return notTreatA