如何以最有效的内存和时间方式获取大文件的行数?
def file_len(filename):
with open(filename) as f:
for i, _ in enumerate(f):
pass
return i + 1
如何以最有效的内存和时间方式获取大文件的行数?
def file_len(filename):
with open(filename) as f:
for i, _ in enumerate(f):
pass
return i + 1
当前回答
下面是一个python程序,使用多处理库将行计数分布到不同的机器/核。使用8核windows 64服务器,我的测试将一个2000万行文件的计数从26秒提高到7秒。注意:不使用内存映射会使运行速度变慢。
import multiprocessing, sys, time, os, mmap
import logging, logging.handlers
def init_logger(pid):
console_format = 'P{0} %(levelname)s %(message)s'.format(pid)
logger = logging.getLogger() # New logger at root level
logger.setLevel( logging.INFO )
logger.handlers.append( logging.StreamHandler() )
logger.handlers[0].setFormatter( logging.Formatter( console_format, '%d/%m/%y %H:%M:%S' ) )
def getFileLineCount( queues, pid, processes, file1 ):
init_logger(pid)
logging.info( 'start' )
physical_file = open(file1, "r")
# mmap.mmap(fileno, length[, tagname[, access[, offset]]]
m1 = mmap.mmap( physical_file.fileno(), 0, access=mmap.ACCESS_READ )
#work out file size to divide up line counting
fSize = os.stat(file1).st_size
chunk = (fSize / processes) + 1
lines = 0
#get where I start and stop
_seedStart = chunk * (pid)
_seekEnd = chunk * (pid+1)
seekStart = int(_seedStart)
seekEnd = int(_seekEnd)
if seekEnd < int(_seekEnd + 1):
seekEnd += 1
if _seedStart < int(seekStart + 1):
seekStart += 1
if seekEnd > fSize:
seekEnd = fSize
#find where to start
if pid > 0:
m1.seek( seekStart )
#read next line
l1 = m1.readline() # need to use readline with memory mapped files
seekStart = m1.tell()
#tell previous rank my seek start to make their seek end
if pid > 0:
queues[pid-1].put( seekStart )
if pid < processes-1:
seekEnd = queues[pid].get()
m1.seek( seekStart )
l1 = m1.readline()
while len(l1) > 0:
lines += 1
l1 = m1.readline()
if m1.tell() > seekEnd or len(l1) == 0:
break
logging.info( 'done' )
# add up the results
if pid == 0:
for p in range(1,processes):
lines += queues[0].get()
queues[0].put(lines) # the total lines counted
else:
queues[0].put(lines)
m1.close()
physical_file.close()
if __name__ == '__main__':
init_logger( 'main' )
if len(sys.argv) > 1:
file_name = sys.argv[1]
else:
logging.fatal( 'parameters required: file-name [processes]' )
exit()
t = time.time()
processes = multiprocessing.cpu_count()
if len(sys.argv) > 2:
processes = int(sys.argv[2])
queues=[] # a queue for each process
for pid in range(processes):
queues.append( multiprocessing.Queue() )
jobs=[]
prev_pipe = 0
for pid in range(processes):
p = multiprocessing.Process( target = getFileLineCount, args=(queues, pid, processes, file_name,) )
p.start()
jobs.append(p)
jobs[0].join() #wait for counting to finish
lines = queues[0].get()
logging.info( 'finished {} Lines:{}'.format( time.time() - t, lines ) )
其他回答
对我来说,这个变体是最快的:
#!/usr/bin/env python
def main():
f = open('filename')
lines = 0
buf_size = 1024 * 1024
read_f = f.read # loop optimization
buf = read_f(buf_size)
while buf:
lines += buf.count('\n')
buf = read_f(buf_size)
print lines
if __name__ == '__main__':
main()
原因:缓冲比逐行和逐字符串读取快。计数也非常快
这个怎么样?
import fileinput
import sys
counter=0
for line in fileinput.input([sys.argv[1]]):
counter+=1
fileinput.close()
print counter
这是我用的,看起来很干净:
import subprocess
def count_file_lines(file_path):
"""
Counts the number of lines in a file using wc utility.
:param file_path: path to file
:return: int, no of lines
"""
num = subprocess.check_output(['wc', '-l', file_path])
num = num.split(' ')
return int(num[0])
更新:这比使用纯python略快,但以内存使用为代价。子进程在执行您的命令时将派生一个与父进程具有相同内存占用的新进程。
这个呢
def file_len(fname):
counts = itertools.count()
with open(fname) as f:
for _ in f: counts.next()
return counts.next()
我修改了缓冲区的情况如下:
def CountLines(filename):
f = open(filename)
try:
lines = 1
buf_size = 1024 * 1024
read_f = f.read # loop optimization
buf = read_f(buf_size)
# Empty file
if not buf:
return 0
while buf:
lines += buf.count('\n')
buf = read_f(buf_size)
return lines
finally:
f.close()
现在空文件和最后一行(不带\n)也被计算在内。