在perfplot分析之后，必须推荐缓冲读取解决方案

def buf_count_newlines_gen(fname):
    def _make_gen(reader):
        while True:
            b = reader(2 ** 16)
            if not b: break
            yield b

    with open(fname, "rb") as f:
        count = sum(buf.count(b"\n") for buf in _make_gen(f.raw.read))
    return count

它速度快，内存效率高。大多数其他解决方案大约要慢20倍。

代码重现情节:

import mmap
import subprocess
from functools import partial

import perfplot


def setup(n):
    fname = "t.txt"
    with open(fname, "w") as f:
        for i in range(n):
            f.write(str(i) + "\n")
    return fname


def for_enumerate(fname):
    i = 0
    with open(fname) as f:
        for i, _ in enumerate(f):
            pass
    return i + 1


def sum1(fname):
    return sum(1 for _ in open(fname))


def mmap_count(fname):
    with open(fname, "r+") as f:
        buf = mmap.mmap(f.fileno(), 0)

    lines = 0
    while buf.readline():
        lines += 1
    return lines


def for_open(fname):
    lines = 0
    for _ in open(fname):
        lines += 1
    return lines


def buf_count_newlines(fname):
    lines = 0
    buf_size = 2 ** 16
    with open(fname) as f:
        buf = f.read(buf_size)
        while buf:
            lines += buf.count("\n")
            buf = f.read(buf_size)
    return lines


def buf_count_newlines_gen(fname):
    def _make_gen(reader):
        b = reader(2 ** 16)
        while b:
            yield b
            b = reader(2 ** 16)

    with open(fname, "rb") as f:
        count = sum(buf.count(b"\n") for buf in _make_gen(f.raw.read))
    return count


def wc_l(fname):
    return int(subprocess.check_output(["wc", "-l", fname]).split()[0])


def sum_partial(fname):
    with open(fname) as f:
        count = sum(x.count("\n") for x in iter(partial(f.read, 2 ** 16), ""))
    return count


def read_count(fname):
    return open(fname).read().count("\n")


b = perfplot.bench(
    setup=setup,
    kernels=[
        for_enumerate,
        sum1,
        mmap_count,
        for_open,
        wc_l,
        buf_count_newlines,
        buf_count_newlines_gen,
        sum_partial,
        read_count,
    ],
    n_range=[2 ** k for k in range(27)],
    xlabel="num lines",
)
b.save("out.png")
b.show()

一句话解决方案:

import os
os.system("wc -l  filename")  

我的代码片段:

>>> os.system('wc -l *.txt')

0 bar.txt
1000 command.txt
3 test_file.txt
1003 total

如果你的文件中的所有行都是相同的长度(并且只包含ASCII字符)*，你可以非常便宜地执行以下操作:

fileSize     = os.path.getsize( pathToFile )  # file size in bytes
bytesPerLine = someInteger                    # don't forget to account for the newline character
numLines     = fileSize // bytesPerLine

*如果使用像é这样的unicode字符，我怀疑需要更多的努力来确定一行中的字节数。

这个呢?

import sys
sys.stdin=open('fname','r')
data=sys.stdin.readlines()
print "counted",len(data),"lines"

创建一个可执行脚本文件count.py:

#!/usr/bin/python

import sys
count = 0
for line in sys.stdin:
    count+=1

然后将文件的内容导入python脚本:cat huge.txt | ./count.py。管道也适用于Powershell，因此您将最终计算行数。

对我来说，在Linux上它比简单的解决方案快30%:

count=1
with open('huge.txt') as f:
    count+=1

使用Numba

我们可以使用Numba来JIT(及时)编译我们的函数到机器代码。Def numbacountparallel(fname)运行速度快2.8倍 然后从问题中定义file_len(fname)。

注:

在运行基准测试之前，操作系统已经将文件缓存到内存中，因为我在我的PC上没有看到太多的磁盘活动。 第一次读取文件时，时间会慢得多，因此使用Numba的时间优势并不显著。

第一次调用函数时，JIT编译需要额外的时间。

如果我们不只是计算行数，这个就很有用了。

Cython是另一个选择。

http://numba.pydata.org/

结论

因为计算行数是IO绑定的，所以使用问题中的def file_len(fname)，除非你想做的不仅仅是计算行数。

import timeit

from numba import jit, prange
import numpy as np

from itertools import (takewhile,repeat)

FILE = '../data/us_confirmed.csv' # 40.6MB, 371755 line file
CR = ord('\n')


# Copied from the question above. Used as a benchmark
def file_len(fname):
    with open(fname) as f:
        for i, l in enumerate(f):
            pass
    return i + 1


# Copied from another answer. Used as a benchmark
def rawincount(filename):
    f = open(filename, 'rb')
    bufgen = takewhile(lambda x: x, (f.read(1024*1024*10) for _ in repeat(None)))
    return sum( buf.count(b'\n') for buf in bufgen )


# Single thread
@jit(nopython=True)
def numbacountsingle_chunk(bs):

    c = 0
    for i in range(len(bs)):
        if bs[i] == CR:
            c += 1

    return c


def numbacountsingle(filename):
    f = open(filename, "rb")
    total = 0
    while True:
        chunk = f.read(1024*1024*10)
        lines = numbacountsingle_chunk(chunk)
        total += lines
        if not chunk:
            break

    return total


# Multi thread
@jit(nopython=True, parallel=True)
def numbacountparallel_chunk(bs):

    c = 0
    for i in prange(len(bs)):
        if bs[i] == CR:
            c += 1

    return c


def numbacountparallel(filename):
    f = open(filename, "rb")
    total = 0
    while True:
        chunk = f.read(1024*1024*10)
        lines = numbacountparallel_chunk(np.frombuffer(chunk, dtype=np.uint8))
        total += lines
        if not chunk:
            break

    return total

print('numbacountparallel')
print(numbacountparallel(FILE)) # This allows Numba to compile and cache the function without adding to the time.
print(timeit.Timer(lambda: numbacountparallel(FILE)).timeit(number=100))

print('\nnumbacountsingle')
print(numbacountsingle(FILE))
print(timeit.Timer(lambda: numbacountsingle(FILE)).timeit(number=100))

print('\nfile_len')
print(file_len(FILE))
print(timeit.Timer(lambda: rawincount(FILE)).timeit(number=100))

print('\nrawincount')
print(rawincount(FILE))
print(timeit.Timer(lambda: rawincount(FILE)).timeit(number=100))

每个函数调用100次的时间(以秒为单位)

numbacountparallel
371755
2.8007332000000003

numbacountsingle
371755
3.1508585999999994

file_len
371755
6.7945494

rawincount
371755
6.815438