Average Precision

Problem

Compute average precision from precision-recall points.

For each distinct recall value keep the largest precision, then integrate over increasing recall: AP = sum of (recall - prev_recall) * precision. Empty input returns 0.0.

Hint

Collapse duplicate recalls to their best precision, then accumulate precision times the recall increase.

Test cases

case 1

in: [[[1,0.5],[0.5,0.5],[0.6666666666666666,1],[0.5,1]]]

expected: 0.8333333333333333

case 2

in: [[[1,1]]]

expected: 1

case 3

in: [[[0.5,0.5],[0.6666666666666666,0.6666666666666666],[0.75,1]]]

expected: 0.611111111111111

case 4

in: [[]]

expected: 0

Starter codePython

def average_precision(pr_points):
    # Your code here
    pass

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