Precision at K

Problem

Compute precision at k for a ranked binary relevance list: relevant items in the first min(k, n) positions divided by the number of positions used.

Return 0.0 if k <= 0 or the list is empty.

Hint

Precision@k measures how many of the top k recommendations are relevant.

case 1

in: [[1,0,1,1,0],2]

expected: 0.5

case 2

in: [[1,0,1,1,0],3]

expected: 0.6666666666666666

case 3

in: [[1,0],0]

expected: 0

case 4

in: [[],2]

expected: 0

Starter codePython

def precision_at_k(relevant, k):
    # Your code here
    pass

4 test cases · run your code against them in the editor