Я хотел бы улучшить производительность Python script и использовал cProfile
для создания отчета об эффективности:
python -m cProfile -o chrX.prof ./bgchr.py ...args...
Я открыл этот файл chrX.prof
с помощью Python pstats
и распечатал статистику:
Python 2.7 (r27:82500, Oct 5 2010, 00:24:22)
[GCC 4.1.2 20080704 (Red Hat 4.1.2-44)] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>> import pstats
>>> p = pstats.Stats('chrX.prof')
>>> p.sort_stats('name')
>>> p.print_stats()
Sun Oct 10 00:37:30 2010 chrX.prof
8760583 function calls in 13.780 CPU seconds
Ordered by: function name
ncalls tottime percall cumtime percall filename:lineno(function)
1 0.000 0.000 0.000 0.000 {_locale.setlocale}
1 1.128 1.128 1.128 1.128 {bz2.decompress}
1 0.002 0.002 13.780 13.780 {execfile}
1750678 0.300 0.000 0.300 0.000 {len}
48 0.000 0.000 0.000 0.000 {method 'append' of 'list' objects}
1 0.000 0.000 0.000 0.000 {method 'close' of 'file' objects}
1 0.000 0.000 0.000 0.000 {method 'disable' of '_lsprof.Profiler' objects}
1750676 0.496 0.000 0.496 0.000 {method 'join' of 'str' objects}
1 0.007 0.007 0.007 0.007 {method 'read' of 'file' objects}
1 0.000 0.000 0.000 0.000 {method 'readlines' of 'file' objects}
1 0.034 0.034 0.034 0.034 {method 'rstrip' of 'str' objects}
23 0.000 0.000 0.000 0.000 {method 'seek' of 'file' objects}
1757785 1.230 0.000 1.230 0.000 {method 'split' of 'str' objects}
1 0.000 0.000 0.000 0.000 {method 'startswith' of 'str' objects}
1750676 0.872 0.000 0.872 0.000 {method 'write' of 'file' objects}
1 0.007 0.007 13.778 13.778 ./bgchr:3(<module>)
1 0.000 0.000 13.780 13.780 <string>:1(<module>)
1 0.001 0.001 0.001 0.001 {open}
1 0.000 0.000 0.000 0.000 {sys.exit}
1 0.000 0.000 0.000 0.000 ./bgchr:36(checkCommandLineInputs)
1 0.000 0.000 0.000 0.000 ./bgchr:27(checkInstallation)
1 1.131 1.131 13.701 13.701 ./bgchr:97(extractData)
1 0.003 0.003 0.007 0.007 ./bgchr:55(extractMetadata)
1 0.064 0.064 13.771 13.771 ./bgchr:5(main)
1750677 8.504 0.000 11.196 0.000 ./bgchr:122(parseJarchLine)
1 0.000 0.000 0.000 0.000 ./bgchr:72(parseMetadata)
1 0.000 0.000 0.000 0.000 /home/areynolds/proj/tools/lib/python2.7/locale.py:517(setlocale)
Вопрос. Что я могу сделать для операций join
, split
и write
, чтобы уменьшить кажущееся влияние на производительность этого script?
Если это актуально, вот полный исходный код для script:
#!/usr/bin/env python
import sys, os, time, bz2, locale
def main(*args):
# Constants
global metadataRequiredFileSize
metadataRequiredFileSize = 8192
requiredVersion = (2,5)
# Prep
global whichChromosome
whichChromosome = "all"
checkInstallation(requiredVersion)
checkCommandLineInputs()
extractMetadata()
parseMetadata()
if whichChromosome == "--list":
listMetadata()
sys.exit(0)
# Extract
extractData()
return 0
def checkInstallation(rv):
currentVersion = sys.version_info
if currentVersion[0] == rv[0] and currentVersion[1] >= rv[1]:
pass
else:
sys.stderr.write( "\n\t[%s] - Error: Your Python interpreter must be %d.%d or greater (within major version %d)\n" % (sys.argv[0], rv[0], rv[1], rv[0]) )
sys.exit(-1)
return
def checkCommandLineInputs():
cmdName = sys.argv[0]
argvLength = len(sys.argv[1:])
if (argvLength == 0) or (argvLength > 2):
sys.stderr.write( "\n\t[%s] - Usage: %s [<chromosome> | --list] <bjarch-file>\n\n" % (cmdName, cmdName) )
sys.exit(-1)
else:
global inFile
global whichChromosome
if argvLength == 1:
inFile = sys.argv[1]
elif argvLength == 2:
whichChromosome = sys.argv[1]
inFile = sys.argv[2]
if inFile == "-" or inFile == "--list":
sys.stderr.write( "\n\t[%s] - Usage: %s [<chromosome> | --list] <bjarch-file>\n\n" % (cmdName, cmdName) )
sys.exit(-1)
return
def extractMetadata():
global metadataList
global dataHandle
metadataList = []
dataHandle = open(inFile, 'rb')
try:
for data in dataHandle.readlines(metadataRequiredFileSize):
metadataLine = data
metadataLines = metadataLine.split('\n')
for line in metadataLines:
if line:
metadataList.append(line)
except IOError:
sys.stderr.write( "\n\t[%s] - Error: Could not extract metadata from %s\n\n" % (sys.argv[0], inFile) )
sys.exit(-1)
return
def parseMetadata():
global metadataList
global metadata
metadata = []
if not metadataList: # equivalent to "if len(metadataList) > 0"
sys.stderr.write( "\n\t[%s] - Error: No metadata in %s\n\n" % (sys.argv[0], inFile) )
sys.exit(-1)
for entryText in metadataList:
if entryText: # equivalent to "if len(entryText) > 0"
entry = entryText.split('\t')
filename = entry[0]
chromosome = entry[0].split('.')[0]
size = entry[1]
entryDict = { 'chromosome':chromosome, 'filename':filename, 'size':size }
metadata.append(entryDict)
return
def listMetadata():
for index in metadata:
chromosome = index['chromosome']
filename = index['filename']
size = long(index['size'])
sys.stdout.write( "%s\t%s\t%ld" % (chromosome, filename, size) )
return
def extractData():
global dataHandle
global pLength
global lastEnd
locale.setlocale(locale.LC_ALL, 'POSIX')
dataHandle.seek(metadataRequiredFileSize, 0) # move cursor past metadata
for index in metadata:
chromosome = index['chromosome']
size = long(index['size'])
pLength = 0L
lastEnd = ""
if whichChromosome == "all" or whichChromosome == index['chromosome']:
dataStream = dataHandle.read(size)
uncompressedData = bz2.decompress(dataStream)
lines = uncompressedData.rstrip().split('\n')
for line in lines:
parseJarchLine(chromosome, line)
if whichChromosome == chromosome:
break
else:
dataHandle.seek(size, 1) # move cursor past chromosome chunk
dataHandle.close()
return
def parseJarchLine(chromosome, line):
global pLength
global lastEnd
elements = line.split('\t')
if len(elements) > 1:
if lastEnd:
start = long(lastEnd) + long(elements[0])
lastEnd = long(start + pLength)
sys.stdout.write("%s\t%ld\t%ld\t%s\n" % (chromosome, start, lastEnd, '\t'.join(elements[1:])))
else:
lastEnd = long(elements[0]) + long(pLength)
sys.stdout.write("%s\t%ld\t%ld\t%s\n" % (chromosome, long(elements[0]), lastEnd, '\t'.join(elements[1:])))
else:
if elements[0].startswith('p'):
pLength = long(elements[0][1:])
else:
start = long(long(lastEnd) + long(elements[0]))
lastEnd = long(start + pLength)
sys.stdout.write("%s\t%ld\t%ld\n" % (chromosome, start, lastEnd))
return
if __name__ == '__main__':
sys.exit(main(*sys.argv))
ИЗМЕНИТЬ
Если я комментирую оператор sys.stdout.write
в первом условном выражении parseJarchLine()
, то мое время выполнения идет от 10,2 с до 4,8 секунд:
# with first conditional "sys.stdout.write" enabled
$ time ./bgchr chrX test.bjarch > /dev/null
real 0m10.186s
user 0m9.917s
sys 0m0.160s
# after first conditional "sys.stdout.write" is commented out
$ time ./bgchr chrX test.bjarch > /dev/null
real 0m4.808s
user 0m4.561s
sys 0m0.156s
Является ли запись на stdout
действительно такой дорогой в Python?