这是我能想到的最好的算法。
def get_primes(n):
numbers = set(range(n, 1, -1))
primes = []
while numbers:
p = numbers.pop()
primes.append(p)
numbers.difference_update(set(range(p*2, n+1, p)))
return primes
>>> timeit.Timer(stmt='get_primes.get_primes(1000000)', setup='import get_primes').timeit(1)
1.1499958793645562
还能做得更快吗?
这段代码有一个缺陷:由于numbers是一个无序集，不能保证numbers.pop()将从集合中移除最低的数字。尽管如此，它还是适用于(至少对我来说)一些输入数字:
>>> sum(get_primes(2000000))
142913828922L
#That's the correct sum of all numbers below 2 million
>>> 529 in get_primes(1000)
False
>>> 529 in get_primes(530)
True
对于最快的代码，numpy解决方案是最好的。不过，出于纯粹的学术原因，我发布了我的纯python版本，它比上面发布的食谱版本快不到50%。由于我将整个列表放在内存中，所以需要足够的空间来容纳所有内容，但它的可伸缩性似乎相当好。
def daniel_sieve_2(maxNumber):
"""
Given a number, returns all numbers less than or equal to
that number which are prime.
"""
allNumbers = range(3, maxNumber+1, 2)
for mIndex, number in enumerate(xrange(3, maxNumber+1, 2)):
if allNumbers[mIndex] == 0:
continue
# now set all multiples to 0
for index in xrange(mIndex+number, (maxNumber-3)/2+1, number):
allNumbers[index] = 0
return [2] + filter(lambda n: n!=0, allNumbers)
结果是:
>>>mine = timeit.Timer("daniel_sieve_2(1000000)",
... "from sieves import daniel_sieve_2")
>>>prev = timeit.Timer("get_primes_erat(1000000)",
... "from sieves import get_primes_erat")
>>>print "Mine: {0:0.4f} ms".format(min(mine.repeat(3, 1))*1000)
Mine: 428.9446 ms
>>>print "Previous Best {0:0.4f} ms".format(min(prev.repeat(3, 1))*1000)
Previous Best 621.3581 ms
这些都是经过编写和测试的。所以没有必要重新发明轮子。
python -m timeit -r10 -s"from sympy import sieve" "primes = list(sieve.primerange(1, 10**6))"
打破了12.2秒的记录!
10 loops, best of 10: 12.2 msec per loop
如果这还不够快，你可以试试PyPy:
pypy -m timeit -r10 -s"from sympy import sieve" "primes = list(sieve.primerange(1, 10**6))"
结果是:
10 loops, best of 10: 2.03 msec per loop
得到247张赞成票的答案列出了15.9毫秒的最佳解决方案。
比较这个! !
下面是Eratosthenes的一个numpy版本，具有良好的复杂度(低于排序长度为n的数组)和向量化。与@unutbu相比，用46微秒就可以找到100万以下的所有质数。
import numpy as np
def generate_primes(n):
is_prime = np.ones(n+1,dtype=bool)
is_prime[0:2] = False
for i in range(int(n**0.5)+1):
if is_prime[i]:
is_prime[i**2::i]=False
return np.where(is_prime)[0]
计时:
import time
for i in range(2,10):
timer =time.time()
generate_primes(10**i)
print('n = 10^',i,' time =', round(time.time()-timer,6))
>> n = 10^ 2 time = 5.6e-05
>> n = 10^ 3 time = 6.4e-05
>> n = 10^ 4 time = 0.000114
>> n = 10^ 5 time = 0.000593
>> n = 10^ 6 time = 0.00467
>> n = 10^ 7 time = 0.177758
>> n = 10^ 8 time = 1.701312
>> n = 10^ 9 time = 19.322478
对于Python 3
def rwh_primes2(n):
correction = (n%6>1)
n = {0:n,1:n-1,2:n+4,3:n+3,4:n+2,5:n+1}[n%6]
sieve = [True] * (n//3)
sieve[0] = False
for i in range(int(n**0.5)//3+1):
if sieve[i]:
k=3*i+1|1
sieve[ ((k*k)//3) ::2*k]=[False]*((n//6-(k*k)//6-1)//k+1)
sieve[(k*k+4*k-2*k*(i&1))//3::2*k]=[False]*((n//6-(k*k+4*k-2*k*(i&1))//6-1)//k+1)
return [2,3] + [3*i+1|1 for i in range(1,n//3-correction) if sieve[i]]
