Mean Average Precision

Problem

Compute mean average precision over users. Each user has a ranked binary relevance list; AP = sum(precision@i * rel_i) / total relevant, and MAP is the mean of APs.

Users with no relevant items contribute 0.0. Empty input returns 0.0.

Hint

Average precision rewards putting relevant items early in the ranking.

Test cases

case 1

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

expected: 0.6666666666666666

case 2

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

expected: 0.41666666666666663

case 3

in: [[[]]]

expected: 0

Starter codePython

def mean_average_precision(ranked_relevance):
    # Your code here
    pass

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