nonuniform sampling with replacement

Sun Mar 21 08:27:44 EDT 2010

Jah_Alarm wrote:
> I've got a vector length n of integers (some of them are repeating),
> and I got a selection probability vector of the same length. How will
> I sample with replacement k (<=n) values with the probabilty vector.
> In Matlab this function is randsample. I couldn't find anything to
> this extent in Scipy or Numpy.

If all else fails you can do it yourself:
import random
import bisect
def iter_sample_with_replacement(values, weights):
 _random = random.random
 _bisect = bisect.bisect
 acc_weights = []
 sigma = 0
 for w in weights:
 sigma += w
 acc_weights.append(sigma)
 while 1:
 yield values[_bisect(acc_weights, _random()*sigma)]
def sample_with_replacement(k, values, weights):
 return list(islice(iter_sample_with_replacement(values, weights), k))
if __name__ == "__main__":
 from itertools import islice
 N = 10**6
 values = range(4)
 weights = [2, 3, 4, 1]
 histo = [0] * len(values)
 for v in islice(iter_sample_with_replacement(values, weights), N):
 histo[v] += 1
 print histo
 print sample_with_replacement(30, values, weights)
Peter