我在python 3中运行以下代码以获取.txt文件,每隔一行编辑一次,并存储已编辑的.txt文件。它对小文件很有用,但是我的文件是2GB的,花费的时间太长了。
有人对如何修改代码以提高效率和速度有任何建议吗?
newData = ""
i=0
run=0
j=0
k=1
seqFile = open('temp100.txt', 'r')
seqData = seqFile.readlines()
while i < 14371315:
sLine = seqData[j]
editLine = seqData[k]
tempLine = editLine[0:20]
newLine = editLine.replace(editLine, tempLine)
newData = newData + sLine + newLine
if len(seqData[k]) > 20:
newData += '\n'
i=i+1
j=j+2
k=k+2
run=run+1
print(run)
seqFile.close()
new = open("new_temp100.txt", "w")
sys.stdout = new
print(newData)发布于 2013-10-19 21:09:34
我建议你这样做:
# if python 2.x
#from itertools import tee, izip
# if python 3
from itertols import tee
# http://docs.python.org/2/library/itertools.html#recipes
def pairwise(iterable):
"s -> (s0,s1), (s1,s2), (s2, s3), ..."
a, b = tee(iterable)
next(b, None)
# if python 2.x
#return izip(a, b)
return zip(a, b)
new_data = []
with open('temp100.txt', 'r') as sqFile:
for sLine, edit_line in pairwise(seqFile):
# I think this is just new_line = tempLine
#tempLine = edit_line[:20]
#new_line = editLine.replace(editLine, tempLine)
new_data.append(sLine + editLine[:20])
if len(sLine) > 20:
new_data.append('\n')
with open("new_temp100.txt", "w") as new:
new.write(''.join(new_data))如果您直接流到磁盘,您可能会做得更好。
# if python 2.x
#from itertools import tee, izip
# if python 3
from itertols import tee
# http://docs.python.org/2/library/itertools.html#recipes
def pairwise(iterable):
"s -> (s0,s1), (s1,s2), (s2, s3), ..."
a, b = tee(iterable)
next(b, None)
# if python 2.x
#return izip(a, b)
return zip(a, b)
new_data = []
with open('temp100.txt', 'r') as sqFile:
with open("new_temp100.txt", "w") as new:
for sLine, edit_line in pairwise(seqFile):
tmp_str = sLine + editLine[:20]
if len(sLine) > 20:
tmp_str = tmp_str + '/n'
new.write(tmp_str)所以您不必将文件的全部内容保存在内存中。
https://stackoverflow.com/questions/19470733
复制相似问题