從你的代碼：..

weight_sample_indexes = lambda weights, k: random.sample([val

for val, cnt in enumerate(weights) for i in range(cnt)], k)

..我認為權重是正整數,而“沒有替換”你的意思是沒有替換解開的序列.

這是一個基于random.sample和O(log n)__getitem__的解決方案：

import bisect

import random

from collections import Counter, Sequence

def weighted_sample(population, weights, k):

return random.sample(WeightedPopulation(population, weights), k)

class WeightedPopulation(Sequence):

def __init__(self, population, weights):

assert len(population) == len(weights) > 0

self.population = population

self.cumweights = []

cumsum = 0 # compute cumulative weight

for w in weights:

cumsum += w

self.cumweights.append(cumsum)

def __len__(self):

return self.cumweights[-1]

def __getitem__(self, i):

if not 0 <= i < len(self):

raise IndexError(i)

return self.population[bisect.bisect(self.cumweights, i)]

例

total = Counter()

for _ in range(1000):

sample = weighted_sample("abc", [1,10,2], 5)

total.update(sample)

print(sample)

print("Frequences %s" % (dict(Counter(sample)),))

# Check that values are sane

print("Total " + ', '.join("%s: %.0f" % (val, count * 1.0 / min(total.values()))

for val, count in total.most_common()))

產量

['b', 'b', 'b', 'c', 'c']

Frequences {'c': 2, 'b': 3}

Total b: 10, c: 2, a: 1

總結

以上是生活随笔為你收集整理的python 加权随机算法_python中的加权随机样本的全部內容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網站內容還不錯，歡迎將生活随笔推薦給好友。