Pass@k from Correct Rate

Problem

Given c correct completions out of n samples, treat p = c / n as the per-sample success probability and return the binomial pass@k probability 1 - (1 - p)^k. Return 0.0 when n <= 0, k <= 0, or c <= 0, and 1.0 when c >= n.

Test cases

case 1

in: [2,10,5]

expected: 0.6723199999999999

case 2

in: [1,4,2]

expected: 0.4375

case 3

in: [0,5,3]

expected: 0

case 4

in: [5,5,2]

expected: 1

case 5

in: [3,4,1]

expected: 0.75

Starter codePython

def pass_at_k_rate(c, n, k):
    # Your code here
    pass

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