假设N < 9,080,191, Miller-Rabin's Primality检验的确定性实现

import sys

def miller_rabin_pass(a, n):
    d = n - 1
    s = 0
    while d % 2 == 0:
        d >>= 1
        s += 1

    a_to_power = pow(a, d, n)
    if a_to_power == 1:
        return True
    for i in range(s-1):
        if a_to_power == n - 1:
            return True
        a_to_power = (a_to_power * a_to_power) % n
    return a_to_power == n - 1


def miller_rabin(n):
    if n <= 2:
        return n == 2

    if n < 2_047:
        return miller_rabin_pass(2, n)

    return all(miller_rabin_pass(a, n) for a in (31, 73))


n = int(sys.argv[1])
primes = [2]
for p in range(3,n,2):
  if miller_rabin(p):
    primes.append(p)
print len(primes)

根据维基百科(http://en.wikipedia.org/wiki/Miller -Rabin_primality_test)上的文章，对于a = 37和73，测试N < 9,080,191足以判断N是否为合数。

我从原始米勒-拉宾测试的概率实现中改编了源代码:https://www.literateprograms.org/miller-rabin_primality_test__python_.html

我很惊讶居然没人提到numba。

该版本在2.47 ms±36.5µs内达到1M标记。

几年前，维基百科页面上出现了一个阿特金筛子的伪代码。这已经不存在了，参考阿特金筛似乎是一个不同的算法。一个2007/03/01版本的维基百科页面(Primer number as 2007-03-01)显示了我用作参考的伪代码。

import numpy as np
from numba import njit

@njit
def nb_primes(n):
    # Generates prime numbers 2 <= p <= n
    # Atkin's sieve -- see https://en.wikipedia.org/w/index.php?title=Prime_number&oldid=111775466
    sqrt_n = int(np.sqrt(n)) + 1

    # initialize the sieve
    s = np.full(n + 1, -1, dtype=np.int8)
    s[2] = 1
    s[3] = 1

    # put in candidate primes:
    # integers which have an odd number of
    # representations by certain quadratic forms
    for x in range(1, sqrt_n):
        x2 = x * x
        for y in range(1, sqrt_n):
            y2 = y * y
            k = 4 * x2 + y2
            if k <= n and (k % 12 == 1 or k % 12 == 5): s[k] *= -1
            k = 3 * x2 + y2
            if k <= n and (k % 12 == 7): s[k] *= -1
            k = 3 * x2 - y2
            if k <= n and x > y and k % 12 == 11: s[k] *= -1

    # eliminate composites by sieving
    for k in range(5, sqrt_n):
        if s[k]:
            k2 = k*k
            # k is prime, omit multiples of its square; this is sufficient because
            # composites which managed to get on the list cannot be square-free
            for i in range(1, n // k2 + 1):
                j = i * k2 # j ∈ {k², 2k², 3k², ..., n}
                s[j] = -1
    return np.nonzero(s>0)[0]

# initial run for "compilation" 
nb_primes(10)

时机

In[10]:
%timeit nb_primes(1_000_000)

Out[10]:
2.47 ms ± 36.5 µs per loop (mean ± std. dev. of 7 runs, 100 loops each)

In[11]:
%timeit nb_primes(10_000_000)

Out[11]:
33.4 ms ± 373 µs per loop (mean ± std. dev. of 7 runs, 10 loops each)

In[12]:
%timeit nb_primes(100_000_000)

Out[12]:
828 ms ± 5.64 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)

我测试了一些unutbu的功能，我用饥饿的百万数字计算它

获胜者是使用numpy库的函数，

注意:做一个内存利用率测试也很有趣:)

示例代码

完整的代码在我的github存储库

#!/usr/bin/env python

import lib
import timeit
import sys
import math
import datetime

import prettyplotlib as ppl
import numpy as np

import matplotlib.pyplot as plt
from prettyplotlib import brewer2mpl

primenumbers_gen = [
    'sieveOfEratosthenes',
    'ambi_sieve',
    'ambi_sieve_plain',
    'sundaram3',
    'sieve_wheel_30',
    'primesfrom3to',
    'primesfrom2to',
    'rwh_primes',
    'rwh_primes1',
    'rwh_primes2',
]

def human_format(num):
    # https://stackoverflow.com/questions/579310/formatting-long-numbers-as-strings-in-python?answertab=active#tab-top
    magnitude = 0
    while abs(num) >= 1000:
        magnitude += 1
        num /= 1000.0
    # add more suffixes if you need them
    return '%.2f%s' % (num, ['', 'K', 'M', 'G', 'T', 'P'][magnitude])


if __name__=='__main__':

    # Vars
    n = 10000000 # number itereration generator
    nbcol = 5 # For decompose prime number generator
    nb_benchloop = 3 # Eliminate false positive value during the test (bench average time)
    datetimeformat = '%Y-%m-%d %H:%M:%S.%f'
    config = 'from __main__ import n; import lib'
    primenumbers_gen = {
        'sieveOfEratosthenes': {'color': 'b'},
        'ambi_sieve': {'color': 'b'},
        'ambi_sieve_plain': {'color': 'b'},
         'sundaram3': {'color': 'b'},
        'sieve_wheel_30': {'color': 'b'},
# # #        'primesfrom2to': {'color': 'b'},
        'primesfrom3to': {'color': 'b'},
        # 'rwh_primes': {'color': 'b'},
        # 'rwh_primes1': {'color': 'b'},
        'rwh_primes2': {'color': 'b'},
    }


    # Get n in command line
    if len(sys.argv)>1:
        n = int(sys.argv[1])

    step = int(math.ceil(n / float(nbcol)))
    nbs = np.array([i * step for i in range(1, int(nbcol) + 1)])
    set2 = brewer2mpl.get_map('Paired', 'qualitative', 12).mpl_colors

    print datetime.datetime.now().strftime(datetimeformat)
    print("Compute prime number to %(n)s" % locals())
    print("")

    results = dict()
    for pgen in primenumbers_gen:
        results[pgen] = dict()
        benchtimes = list()
        for n in nbs:
            t = timeit.Timer("lib.%(pgen)s(n)" % locals(), setup=config)
            execute_times = t.repeat(repeat=nb_benchloop,number=1)
            benchtime = np.mean(execute_times)
            benchtimes.append(benchtime)
        results[pgen] = {'benchtimes':np.array(benchtimes)}

fig, ax = plt.subplots(1)
plt.ylabel('Computation time (in second)')
plt.xlabel('Numbers computed')
i = 0
for pgen in primenumbers_gen:

    bench = results[pgen]['benchtimes']
    avgs = np.divide(bench,nbs)
    avg = np.average(bench, weights=nbs)

    # Compute linear regression
    A = np.vstack([nbs, np.ones(len(nbs))]).T
    a, b = np.linalg.lstsq(A, nbs*avgs)[0]

    # Plot
    i += 1
    #label="%(pgen)s" % locals()
    #ppl.plot(nbs, nbs*avgs, label=label, lw=1, linestyle='--', color=set2[i % 12])
    label="%(pgen)s avg" % locals()
    ppl.plot(nbs, a * nbs + b, label=label, lw=2, color=set2[i % 12])
print datetime.datetime.now().strftime(datetimeformat)

ppl.legend(ax, loc='upper left', ncol=4)

# Change x axis label
ax.get_xaxis().get_major_formatter().set_scientific(False)
fig.canvas.draw()
labels = [human_format(int(item.get_text())) for item in ax.get_xticklabels()]

ax.set_xticklabels(labels)
ax = plt.gca()

plt.show()

你有一个更快的代码和最简单的代码生成质数。 但对于更大的数字，当n=10000, 10000000时，它不起作用，可能是。pop()方法失败了

考虑:N是质数吗?

case 1: You got some factors of N, for i in range(2, N): If N is prime loop is performed for ~(N-2) times. else less number of times case 2: for i in range(2, int(math.sqrt(N)): Loop is performed for almost ~(sqrt(N)-2) times if N is prime else will break somewhere case 3: Better We Divide N With Only number of primes<=sqrt(N) Where loop is performed for only π(sqrt(N)) times π(sqrt(N)) << sqrt(N) as N increases from math import sqrt from time import * prime_list = [2] n = int(input()) s = time() for n0 in range(2,n+1): for i0 in prime_list: if n0%i0==0: break elif i0>=int(sqrt(n0)): prime_list.append(n0) break e = time() print(e-s) #print(prime_list); print(f'pi({n})={len(prime_list)}') print(f'{n}: {len(prime_list)}, time: {e-s}') Output 100: 25, time: 0.00010275840759277344 1000: 168, time: 0.0008606910705566406 10000: 1229, time: 0.015588521957397461 100000: 9592, time: 0.023436546325683594 1000000: 78498, time: 4.1965954303741455 10000000: 664579, time: 109.24591708183289 100000000: 5761455, time: 2289.130858898163

小于1000似乎很慢，但小于10^6我认为更快。

然而，我无法理解时间的复杂性。

这里有一个来自Python Cookbook的非常简洁的示例——该URL的最快版本是:

import itertools
def erat2( ):
    D = {  }
    yield 2
    for q in itertools.islice(itertools.count(3), 0, None, 2):
        p = D.pop(q, None)
        if p is None:
            D[q*q] = q
            yield q
        else:
            x = p + q
            while x in D or not (x&1):
                x += p
            D[x] = p

这就给出了

def get_primes_erat(n):
  return list(itertools.takewhile(lambda p: p<n, erat2()))

在shell提示符(正如我喜欢做的那样)中测量这段代码在pri.py中，我观察到:

$ python2.5 -mtimeit -s'import pri' 'pri.get_primes(1000000)'
10 loops, best of 3: 1.69 sec per loop
$ python2.5 -mtimeit -s'import pri' 'pri.get_primes_erat(1000000)'
10 loops, best of 3: 673 msec per loop

所以看起来食谱解决方案的速度是原来的两倍多。

如果你接受itertools，但不接受numpy，这里有一个针对Python 3的rwh_primes2的改编版本，它在我的机器上运行速度大约是原来的两倍。唯一的实质性变化是使用bytearray而不是列表来表示布尔值，并使用压缩而不是列表推导来构建最终列表。(如果可以的话，我会把这句话作为moarningsun之类的评论。)

import itertools
izip = itertools.zip_longest
chain = itertools.chain.from_iterable
compress = itertools.compress
def rwh_primes2_python3(n):
    """ Input n>=6, Returns a list of primes, 2 <= p < n """
    zero = bytearray([False])
    size = n//3 + (n % 6 == 2)
    sieve = bytearray([True]) * size
    sieve[0] = False
    for i in range(int(n**0.5)//3+1):
      if sieve[i]:
        k=3*i+1|1
        start = (k*k+4*k-2*k*(i&1))//3
        sieve[(k*k)//3::2*k]=zero*((size - (k*k)//3 - 1) // (2 * k) + 1)
        sieve[  start ::2*k]=zero*((size -   start  - 1) // (2 * k) + 1)
    ans = [2,3]
    poss = chain(izip(*[range(i, n, 6) for i in (1,5)]))
    ans.extend(compress(poss, sieve))
    return ans

比较:

>>> timeit.timeit('primes.rwh_primes2(10**6)', setup='import primes', number=1)
0.0652179726976101
>>> timeit.timeit('primes.rwh_primes2_python3(10**6)', setup='import primes', number=1)
0.03267321276325674

and

>>> timeit.timeit('primes.rwh_primes2(10**8)', setup='import primes', number=1)
6.394284538007014
>>> timeit.timeit('primes.rwh_primes2_python3(10**8)', setup='import primes', number=1)
3.833829450302801