に追加しました:私は問題を開いた jnnnnn
import collections
import random
import bisect
def sample(xs, sample_size = None, replace=False, sample_probabilities = None):
"""Mimics the functionality of http://statistics.ats.ucla.edu/stat/r/library/bootstrap.htm sample()"""
if not isinstance(xs, collections.Iterable):
xs = range(xs)
if not sample_size:
sample_size = len(xs)
if not sample_probabilities:
if replace:
return [random.choice(xs) for _ in range(sample_size)]
else:
return random.sample(xs, sample_size)
else:
if replace:
total, cdf = 0, []
for x, p in zip(xs, sample_probabilities):
total += p
cdf.append(total)
return [ xs[ bisect.bisect(cdf, random.uniform(0, total)) ]
for _ in range(sample_size) ]
else:
assert len(sample_probabilities) == len(xs)
xps = list(zip(xs, sample_probabilities))
total = sum(sample_probabilities)
result = []
for _ in range(sample_size):
# choose an item based on weights, and remove it from future iterations.
# this is slow (N^2), a tree structure for xps would be better (NlogN)
target = random.uniform(0, total)
current_total = 0
for index, (x,p) in enumerate(xps):
current_total += p
if current_total > target:
xps.pop(index)
result.append(x)
total -= p
break
return result
感謝をパンダと一緒にこの機能を追加するのに興味があるかどうかを確認してください。 https://github.com/pydata/pandas/issues/2963 – gliptak