Sample Entropy Small

Problem

Compute sample entropy with embedding dimension m and tolerance r, excluding self-matches: SampEn = -ln(A / B), where B is the number of matching template pairs of length m and A the number of matching pairs of length m+1, using Chebyshev distance <= r.

Return 0.0 if m < 1, the series is shorter than m + 2, or either count is zero.

Hint

SampEn increases when longer patterns stop repeating.

Test cases

case 1

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

expected: 0.6931471805599453

case 2

in: [[3,3,3,3,3],2,0]

expected: 1.0986122886681098

case 3

in: [[1,2,3,4,5,6],1,1]

expected: 0.2876820724517809

case 4

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

expected: 0.40546510810816444

Starter codePython

import math
def sample_entropy(series, m, r):
    # Your code here
    pass

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