Question

我用python2.7运行一段代码，cProfile说35s而pypy上的cProfile说73s！假设pypy是更快的解释器，那怎么可能呢？该代码在输入比特流时实现BWT转换。我有两个文件：bwt.py在fm.py中调用。我将该函数称为：

pypy -m cProfle fm.py inputfile

然后

python -m cProfle fm.py inputfile

bwt.py的代码如下：

def rotations(t):
    ''' Return list of rotations of input string t '''
    tt = t * 2
    return [ tt[i:i+len(t)] for i in xrange(0, len(t)) ]

def bwm(t):
    return sorted(rotations(t))

def bwtViaBwm(t):
    ''' Given T, returns BWT(T) by way of the BWM '''
    return ''.join(map(lambda x: x[-1], bwm(t)))

def rankBwt(bw):
    ''' Given BWT string bw, return parallel list of B-ranks.  Also
        returns tots: map from character to # times it appears. '''
    tots = dict()
    ranks = []
    for c in bw:
        if c not in tots: tots[c] = 0
        ranks.append(tots[c])
        tots[c] += 1
    return ranks, tots
def firstCol(tots):
    ''' Return map from character to the range of rows prefixed by
        the character. '''
    first = {}
    totc = 0
    for c, count in sorted(tots.iteritems()):
        first[c] = (totc, totc + count)
        totc += count
    return first

def reverseBwt(bw):
    ''' Make T from BWT(T) '''
    ranks, tots = rankBwt(bw)
    first = firstCol(tots)
    rowi = 0 # start in first row
    t = '$' # start with rightmost character
    while bw[rowi] != '$':
        c = bw[rowi]
        t = c + t # prepend to answer
        # jump to row that starts with c of same rank
        rowi = first[c][0] + ranks[rowi]
    return t



def suffixArray(s):
    satups = sorted([(s[i:], i) for i in xrange(0, len(s))])
    print satups
    return map(lambda x: x[1], satups)

def bwtViaSa(t):
    # Given T, returns BWT(T) by way of the suffix array
    bw = []
    for si in suffixArray(t):
        if si == 0:
            bw.append('$')
        else:
            bw.append(t[si-1])
    return ''.join(bw) # return string-ized version of list bw



def readfile(sd):
    s=""
    with open(sd,'r') as myfile:
        s =myfile.read()
    return s.rstrip('\n')
def writefile(sd,N):
    with open(sd, "wb") as sink:
        sink.write(''.join(random.choice(string.ascii_uppercase + string.digits) for _ in xrange(N)))
        sink.write('$')
    return



def main():
    data=readfile('inp')
    b=bwtViaBwm(data)
    ranks,tots = rankBwt(b)
    print "Input stream = "+ data
    print "BWT = " + bwtViaSa(data)
    print '\n'.join(bwm(data))
    print ("Lc ranking:")
    print zip(b,ranks) 

    fc=[x[0] for x in bwm(data)]
    fc= ''.join(fc)
    print ("First column="+ fc)
    ranks,tots = rankBwt(fc)
    print("Fc ranking:")
    print zip(fc,ranks) 

    print reverseBwt(bwtViaSa(data))

if __name__=='__main__':
    main()

这是我通过pypy称之为fm.py的代码形式：

import bwt
import sys
from collections import Counter

def build_FM(fname):
    stream=bwt.readfile(fname)
    #print bwt.suffixArray(stream)
    b=bwt.bwtViaBwm(stream)
    ranks,tots = bwt.rankBwt(b)
    lc=zip(b,ranks)
    fc=[x[0] for x in bwt.bwm(stream)]
    fc= ''.join(fc)
    fc= zip(fc,ranks)
    #print lc,fc


def main():
    fname= sys.argv[1]
    build_FM(fname)
    return


if __name__=='__main__':
    main()

Answer 1

Pypy不保证更快地执行程序。

首先，它实现的优化需要花费时间（有时需要很长时间）才能运行。其次，并非所有代码都会在pypy下运行得更快，尽管大多数代码都可以。

此外，配置代码的相对速度可能在它们之间存在很大差异 - pypy代码是低级别的，因此引入分析可能会比CPython更慢（相对而言）。没有分析活动的结果是什么？

我们需要查看您的计划，以便提供更多相关信息。

Answer 2

您的脚本在rotations()中分配了大量内存（O（N ** 2），其中N是输入文件的大小）。从cProfile和vmprof中可以看出，大部分时间都花在那里。

因此，你看到的是PyPy和CPython之间内存处理的差异。我的猜测是你正在交换并且PyPy的峰值内存使用率更高。

如何让python比pypy更快

2 个答案: