Reading first lines of bz2 files in python - python

I am trying to extract 10'000 first lines from a bz2 file.
import bz2
file = "file.bz2"
file_10000 = "file.txt"
output_file = codecs.open(file_10000,'w+','utf-8')
source_file = bz2.open(file, "r")
count = 0
for line in source_file:
count += 1
if count < 10000:
output_file.writerow(line)
But I get an error "'module' object has no attribute 'open'". Do you have any ideas? Or may be I could save 10'000 first lines to a txt file in some other way? I am on Windows.

Here is a fully working example that includes writing and reading a test file that is much smaller than your 10000 lines. Its nice to have working examples in questions so we can test easily.
import bz2
import itertools
import codecs
file = "file.bz2"
file_10000 = "file.txt"
# write test file with 9 lines
with bz2.BZ2File(file, "w") as fp:
fp.write('\n'.join('123456789'))
# the original script using BZ2File ... and 3 lines for test
# ...and fixing bugs:
# 1) it only writes 9999 instead of 10000
# 2) files don't do writerow
# 3) close the files
output_file = codecs.open(file_10000,'w+','utf-8')
source_file = bz2.BZ2File(file, "r")
count = 0
for line in source_file:
count += 1
if count <= 3:
output_file.write(line)
source_file.close()
output_file.close()
# show what you got
print('---- Test 1 ----')
print(repr(open(file_10000).read()))
A more efficient way to do it is to break out of the for loop after reading the lines you want. you can even leverage iterators to thin up the code like so:
# a faster way to read first 3 lines
with bz2.BZ2File(file) as source_file,\
codecs.open(file_10000,'w+','utf-8') as output_file:
output_file.writelines(itertools.islice(source_file, 3))
# show what you got
print('---- Test 2 ----')
print(repr(open(file_10000).read()))

This is definitely a simpler way of doing it than the other answer, but it would be an easy way to do so in both Python2/3. Also, it would short-circuit if you don't have >= 10,000 lines.
from bz2 import BZ2File as bzopen
# writing to a file
with bzopen("file.bz2", "w") as bzfout:
for i in range(123456):
bzfout.write(b"%i\n" % i)
# reading a bz2 archive
with bzopen("file.bz2", "r") as bzfin:
""" Handle lines here """
lines = []
for i, line in enumerate(bzfin):
if i == 10000: break
lines.append(line.rstrip())
print(lines)

Just another variation.
import bz2
myfile = 'c:\\my_dir\\random.txt.bz2'
newfile = 'c:\\my_dir\\random_10000.txt'
stream = bz2.BZ2File(myfile)
with open(newfile, 'w') as f:
for i in range(1,10000):
f.write(stream.readline())

This worked for me:
sudo apt-get install python-dev
sudo pip install backports.lzma

Related

Counting the number of lines in a gzip file using python

I'm trying to count the number of lines in a gz archive. There is only 1 json format text file per gz. But when I open the archive and count the lines the count is way off what I'd expect. The file contains 522 lines, but my code is returning 668480 lines.
import gzip
f = gzip.open(myfile, 'rb')
file_content = f.read()
for i, l in enumerate(file_content):
pass
i += 1
print("File {1} contain {0} lines".format(i, myfile))
You are iterating over all characters not the lines. You can iterate lines the following way
import gzip
with gzip.open(myfile, 'rb') as f:
for i, l in enumerate(f):
pass
print("File {1} contain {0} lines".format(i + 1, myfile))
For a performant way to count the lines in a gzip file you can use the pragzip package:
import pragzip
result = 0
with pragzip.open(myfile) as file:
while chunk := file.read( 1024*1024 ):
result += chunk.count(b'\n')
print(f"Number of lines: {result}")
Comparing the timing of the above with #DmitryKovriga's answer:
Number of lines: 33468793
Elapsed time is 22.373915 seconds.
File datasets/binance-futures_incremental_book_L2_2020-07-01_BTCUSDT.csv.gz contain 33468793 lines
Elapsed time is 31.278056 seconds.
A speed up of more like 10x should be possible with a suitable setup. See https://unix.stackexchange.com/a/713093/163459 for more info.

Python glob gives no result

I have a directory that contains a lot of .csv files, and I am trying to write a script that runs on all the files in the directory while doing the following operation:
Remove the first and last lines from all the csv files
I am running the following code:
import glob
list_of_files = glob.glob('path/to/directory/*.csv')
for file_name in list_of_files:
fi = open(file_name, 'r')
fo = open(file_name.replace('csv', 'out'), 'w') #make new output file for each file
num_of_lines = file_name.read().count('\n')
file_name.seek(0)
i = 0
for line in fi:
if i != 1 and i != num_of_lines-1:
fo.write(line)
fi.close()
fo.close()
And I run the script using python3 script.py. Though I don't get any error, I don't get any output file either.
There are multiple issues in your code. First of all you count the number of lines on the filename instead of the file-object. The second problem is that you initialize i=0 and compare against it but it never changes.
Personally I would just convert the file to a list of "lines", cut off the first and last and write all of them to the new file:
import glob
list_of_files = glob.glob('path/to/directory/*.csv')
for file_name in list_of_files:
with open(file_name, 'r') as fi:
with open(file_name.replace('csv', 'out'), 'w') as fo:
for line in list(fi)[1:-1]: # for all lines except the first and last
fo.write(line)
Using the with open allows to omit the close calls (because they are done implicitly) even if an exception occurs.
In case that still gives no output you could a print statement that shows which file is being processed:
print(file_name) # just inside the for-loop before any `open` calls.
Since you're using python-3.5 you could also use pathlib:
import pathlib
path = pathlib.Path('path/to/directory/')
# make sure it's a valid directory
assert path.is_dir(), "{} is not a valid directory".format(p.absolute())
for file_name in path.glob('*.csv'):
with file_name.open('r') as fi:
with pathlib.Path(str(file_name).replace('.csv', '.out')).open('w') as fo:
for line in list(fi)[1:-1]: # for all lines except the first and last
fo.write(line)
As Jon Clements pointed out there is a better way than [1:-1] to exclude the first and last line by using a generator function. That way you will definitely reduce the amount of memory used and it might also improve the overall performance. For example you could use:
import pathlib
def ignore_first_and_last(it):
it = iter(it)
firstline = next(it)
lastline = next(it)
for nxtline in it:
yield lastline
lastline = nxtline
path = pathlib.Path('path/to/directory/')
# make sure it's a valid directory
assert path.is_dir(), "{} is not a valid directory".format(p.absolute())
for file_name in path.glob('*.csv'):
with file_name.open('r') as fi:
with pathlib.Path(str(file_name).replace('.csv', '.out')).open('w') as fo:
for line in ignore_first_and_last(fi): # for all lines except the first and last
fo.write(line)

How can I split a large file csv file (7GB) in Python

I have a 7GB csv file which I'd like to split into smaller chunks, so it is readable and faster for analysis in Python on a notebook. I would like to grab a small set from it, maybe 250MB, so how can I do this?
You don't need Python to split a csv file. Using your shell:
$ split -l 100 data.csv
Would split data.csv in chunks of 100 lines.
I had to do a similar task, and used the pandas package:
for i,chunk in enumerate(pd.read_csv('bigfile.csv', chunksize=500000)):
chunk.to_csv('chunk{}.csv'.format(i), index=False)
Here is a little python script I used to split a file data.csv into several CSV part files. The number of part files can be controlled with chunk_size (number of lines per part file).
The header line (column names) of the original file is copied into every part CSV file.
It works for big files because it reads one line at a time with readline() instead of loading the complete file into memory at once.
#!/usr/bin/env python3
def main():
chunk_size = 9998 # lines
def write_chunk(part, lines):
with open('data_part_'+ str(part) +'.csv', 'w') as f_out:
f_out.write(header)
f_out.writelines(lines)
with open('data.csv', 'r') as f:
count = 0
header = f.readline()
lines = []
for line in f:
count += 1
lines.append(line)
if count % chunk_size == 0:
write_chunk(count // chunk_size, lines)
lines = []
# write remainder
if len(lines) > 0:
write_chunk((count // chunk_size) + 1, lines)
if __name__ == '__main__':
main()
This graph shows the runtime difference of the different approaches outlined by other posters (on an 8 core machine when splitting a 2.9 GB file with 11.8 million rows of data into ~290 files).
The shell approach is from Thomas Orozco, Python approach s from Roberto, Pandas approach is from Quentin Febvre and here's the Dask snippet:
ddf = dd.read_csv("../nyc-parking-tickets/Parking_Violations_Issued_-_Fiscal_Year_2015.csv", blocksize=10000000, dtype=dtypes)
ddf.to_csv("../tmp/split_csv_dask")
I'd recommend Dask for splitting files, even though it's not the fastest, because it's the most flexible solution (you can write out different file formats, perform processing operations before writing, easily modify compression formats, etc.). The Pandas approach is almost as flexible, but cannot perform processing on the entire dataset (like sorting the entire dataset before writing).
Bash / native Python filesystem operations are clearly quicker, but that's not what I'm typically looking for when I have a large CSV. I'm typically interested in splitting large CSVs into smaller Parquet files, for performant, production data analyses. I don't usually care if the actually splitting takes a couple minutes more. I'm more interested in splitting accurately.
I wrote a blog post that discusses this in more detail. You can probably Google around and find the post.
See the Python docs on file objects (the object returned by open(filename) - you can choose to read a specified number of bytes, or use readline to work through one line at a time.
Maybe something like this?
#!/usr/local/cpython-3.3/bin/python
import csv
divisor = 10
outfileno = 1
outfile = None
with open('big.csv', 'r') as infile:
for index, row in enumerate(csv.reader(infile)):
if index % divisor == 0:
if outfile is not None:
outfile.close()
outfilename = 'big-{}.csv'.format(outfileno)
outfile = open(outfilename, 'w')
outfileno += 1
writer = csv.writer(outfile)
writer.writerow(row)
I agree with #jonrsharpe readline should be able to read one line at a time even for big files.
If you are dealing with big csv files might I suggest using pandas.read_csv. I often use it for the same purpose and always find it awesome (and fast). Takes a bit of time to get used to idea of DataFrames. But once you get over that it speeds up large operations like yours massively.
Hope it helps.
here is my code which might help
import os
import pandas as pd
import uuid
class FileSettings(object):
def __init__(self, file_name, row_size=100):
self.file_name = file_name
self.row_size = row_size
class FileSplitter(object):
def __init__(self, file_settings):
self.file_settings = file_settings
if type(self.file_settings).__name__ != "FileSettings":
raise Exception("Please pass correct instance ")
self.df = pd.read_csv(self.file_settings.file_name,
chunksize=self.file_settings.row_size)
def run(self, directory="temp"):
try:os.makedirs(directory)
except Exception as e:pass
counter = 0
while True:
try:
file_name = "{}/{}_{}_row_{}_{}.csv".format(
directory, self.file_settings.file_name.split(".")[0], counter, self.file_settings.row_size, uuid.uuid4().__str__()
)
df = next(self.df).to_csv(file_name)
counter = counter + 1
except StopIteration:
break
except Exception as e:
print("Error:",e)
break
return True
def main():
helper = FileSplitter(FileSettings(
file_name='sample1.csv',
row_size=10
))
helper.run()
main()
In the case of wanting to split by rough boundaries in bytes, the newest datapoints being the bottom-most ones and wanting to put the newest datapoints in the first file:
from pathlib import Path
TEN_MB = 10000000
FIVE_MB = 5000000
def split_file_into_chunks(path, chunk_size=TEN_MB):
path = str(path)
output_prefix = path.rpartition('.')[0]
output_ext = path.rpartition('.')[-1]
with open(path, 'rb') as f:
seek_positions = []
for x, line in enumerate(f):
if not x:
header = line
seek_positions.append(f.tell())
part = 0
last_seek_pos = seek_positions[-1]
for seek_pos in reversed(seek_positions):
if last_seek_pos-seek_pos >= chunk_size:
with open(f'{output_prefix}.arch.{part}.{output_ext}', 'wb') as f_out:
f.seek(seek_pos)
f_out.write(header)
f_out.write(f.read(last_seek_pos-seek_pos))
last_seek_pos = seek_pos
part += 1
with open(f'{output_prefix}.arch.{part}.{output_ext}', 'wb') as f_out:
f.seek(0)
f_out.write(f.read(last_seek_pos))
Path(path).rename(path+'~')
Path(f'{output_prefix}.arch.0.{output_ext}').rename(path)
Path(path+'~').unlink()

fast method in Python to split a large text file using number of lines as input variable

I am splitting a text file using the number of lines as variable. I wrote this function in order to save in a temporary directory the spitted files. Each file has 4 millions of lines expect the last file.
import tempfile
from itertools import groupby, count
temp_dir = tempfile.mkdtemp()
def tempfile_split(filename, temp_dir, chunk=4000000):
with open(filename, 'r') as datafile:
groups = groupby(datafile, key=lambda k, line=count(): next(line) // chunk)
for k, group in groups:
output_name = os.path.normpath(os.path.join(temp_dir + os.sep, "tempfile_%s.tmp" % k))
for line in group:
with open(output_name, 'a') as outfile:
outfile.write(line)
the main problem is the speed of this function. In order to split one file of 8 million of lines in two files of 4 millions of line the time is than more of 30 min of my windows OS and Python 2.7
for line in group:
with open(output_name, 'a') as outfile:
outfile.write(line)
is opening the file, and writing one line, for each line in group.
This is slow.
Instead, write once per group.
with open(output_name, 'a') as outfile:
outfile.write(''.join(group))
Just did a quick test with an 8million line file(uptime lines) to run the length of the file and split the file in half. Basically, one pass to get the line count, second pass to do the split write.
On my system, the time it took to perform the first pass run was about 2-3 seconds. To complete the run and the write of the split file(s), total time took was under 21 seconds.
Did not implement the lamba functions in the OP's post. Code used below:
#!/usr/bin/env python
import sys
import math
infile = open("input","r")
linecount=0
for line in infile:
linecount=linecount+1
splitpoint=linecount/2
infile.close()
infile = open("input","r")
outfile1 = open("output1","w")
outfile2 = open("output2","w")
print linecount , splitpoint
linecount=0
for line in infile:
linecount=linecount+1
if ( linecount <= splitpoint ):
outfile1.write(line)
else:
outfile2.write(line)
infile.close()
outfile1.close()
outfile2.close()
No, it's not going to win any performance or code elegance tests. :) But short of something else being a performance bottleneck, the lambda functions causing the file to be cached in memory and forcing a swap issue, or that the lines in the file are extremely long, I don't see why it would take 30 minutes to read/split the 8million line file.
EDIT:
My environment: Mac OS X, storage was a single FW800 connected hard drive. File was created fresh to avoid filesystem caching benefits.
You can use tempfile.NamedTemporaryFile directly in the context manager:
import tempfile
import time
from itertools import groupby, count
def tempfile_split(filename, temp_dir, chunk=4*10**6):
fns={}
with open(filename, 'r') as datafile:
groups = groupby(datafile, key=lambda k, line=count(): next(line) // chunk)
for k, group in groups:
with tempfile.NamedTemporaryFile(delete=False,
dir=temp_dir,prefix='{}_'.format(str(k))) as outfile:
outfile.write(''.join(group))
fns[k]=outfile.name
return fns
def make_test(size=8*10**6+1000):
with tempfile.NamedTemporaryFile(delete=False) as fn:
for i in xrange(size):
fn.write('Line {}\n'.format(i))
return fn.name
fn=make_test()
t0=time.time()
print tempfile_split(fn,tempfile.mkdtemp()),time.time()-t0
On my computer, the tempfile_split part runs in 3.6 seconds. It is OS X.
If you're in a linux or unix environment you could cheat a little and use the split command from inside python. Does the trick for me, and very fast too:
def split_file(file_path, chunk=4000):
p = subprocess.Popen(['split', '-a', '2', '-l', str(chunk), file_path,
os.path.dirname(file_path) + '/'], stdout=subprocess.PIPE, stderr=subprocess.PIPE)
p.communicate()
# Remove the original file if required
try:
os.remove(file_path)
except OSError:
pass
return True

How do I split a huge text file in python

I have a huge text file (~1GB) and sadly the text editor I use won't read such a large file. However, if I can just split it into two or three parts I'll be fine, so, as an exercise I wanted to write a program in python to do it.
What I think I want the program to do is to find the size of a file, divide that number into parts, and for each part, read up to that point in chunks, writing to a filename.nnn output file, then read up-to the next line-break and write that, then close the output file, etc. Obviously the last output file just copies to the end of the input file.
Can you help me with the key filesystem related parts: filesize, reading and writing in chunks and reading to a line-break?
I'll be writing this code test-first, so there's no need to give me a complete answer, unless its a one-liner ;-)
linux has a split command
split -l 100000 file.txt
would split into files of equal 100,000 line size
Check out os.stat() for file size and file.readlines([sizehint]). Those two functions should be all you need for the reading part, and hopefully you know how to do the writing :)
Now, there is a pypi module available that you can use to split files of any size into chunks. Check this out
https://pypi.org/project/filesplit/
As an alternative method, using the logging library:
>>> import logging.handlers
>>> log = logging.getLogger()
>>> fh = logging.handlers.RotatingFileHandler("D://filename.txt",
maxBytes=2**20*100, backupCount=100)
# 100 MB each, up to a maximum of 100 files
>>> log.addHandler(fh)
>>> log.setLevel(logging.INFO)
>>> f = open("D://biglog.txt")
>>> while True:
... log.info(f.readline().strip())
Your files will appear as follows:
filename.txt (end of file)
filename.txt.1
filename.txt.2
...
filename.txt.10 (start of file)
This is a quick and easy way to make a huge log file match your RotatingFileHandler implementation.
This generator method is a (slow) way to get a slice of lines without blowing up your memory.
import itertools
def slicefile(filename, start, end):
lines = open(filename)
return itertools.islice(lines, start, end)
out = open("/blah.txt", "w")
for line in slicefile("/python27/readme.txt", 10, 15):
out.write(line)
don't forget seek() and mmap() for random access to files.
def getSomeChunk(filename, start, len):
fobj = open(filename, 'r+b')
m = mmap.mmap(fobj.fileno(), 0)
return m[start:start+len]
While Ryan Ginstrom's answer is correct, it does take longer than it should (as he has already noted). Here's a way to circumvent the multiple calls to itertools.islice by successively iterating over the open file descriptor:
def splitfile(infilepath, chunksize):
fname, ext = infilepath.rsplit('.',1)
i = 0
written = False
with open(infilepath) as infile:
while True:
outfilepath = "{}{}.{}".format(fname, i, ext)
with open(outfilepath, 'w') as outfile:
for line in (infile.readline() for _ in range(chunksize)):
outfile.write(line)
written = bool(line)
if not written:
break
i += 1
You can use wc and split (see the respective manpages) to get the desired effect. In bash:
split -dl$((`wc -l 'filename'|sed 's/ .*$//'` / 3 + 1)) filename filename-chunk.
produces 3 parts of the same linecount (with a rounding error in the last, of course), named filename-chunk.00 to filename-chunk.02.
I've written the program and it seems to work fine. So thanks to Kamil Kisiel for getting me started.
(Note that FileSizeParts() is a function not shown here)
Later I may get round to doing a version that does a binary read to see if its any quicker.
def Split(inputFile,numParts,outputName):
fileSize=os.stat(inputFile).st_size
parts=FileSizeParts(fileSize,numParts)
openInputFile = open(inputFile, 'r')
outPart=1
for part in parts:
if openInputFile.tell()<fileSize:
fullOutputName=outputName+os.extsep+str(outPart)
outPart+=1
openOutputFile=open(fullOutputName,'w')
openOutputFile.writelines(openInputFile.readlines(part))
openOutputFile.close()
openInputFile.close()
return outPart-1
usage - split.py filename splitsizeinkb
import os
import sys
def getfilesize(filename):
with open(filename,"rb") as fr:
fr.seek(0,2) # move to end of the file
size=fr.tell()
print("getfilesize: size: %s" % size)
return fr.tell()
def splitfile(filename, splitsize):
# Open original file in read only mode
if not os.path.isfile(filename):
print("No such file as: \"%s\"" % filename)
return
filesize=getfilesize(filename)
with open(filename,"rb") as fr:
counter=1
orginalfilename = filename.split(".")
readlimit = 5000 #read 5kb at a time
n_splits = filesize//splitsize
print("splitfile: No of splits required: %s" % str(n_splits))
for i in range(n_splits+1):
chunks_count = int(splitsize)//int(readlimit)
data_5kb = fr.read(readlimit) # read
# Create split files
print("chunks_count: %d" % chunks_count)
with open(orginalfilename[0]+"_{id}.".format(id=str(counter))+orginalfilename[1],"ab") as fw:
fw.seek(0)
fw.truncate()# truncate original if present
while data_5kb:
fw.write(data_5kb)
if chunks_count:
chunks_count-=1
data_5kb = fr.read(readlimit)
else: break
counter+=1
if __name__ == "__main__":
if len(sys.argv) < 3: print("Filename or splitsize not provided: Usage: filesplit.py filename splitsizeinkb ")
else:
filesize = int(sys.argv[2]) * 1000 #make into kb
filename = sys.argv[1]
splitfile(filename, filesize)
Here is a python script you can use for splitting large files using subprocess:
"""
Splits the file into the same directory and
deletes the original file
"""
import subprocess
import sys
import os
SPLIT_FILE_CHUNK_SIZE = '5000'
SPLIT_PREFIX_LENGTH = '2' # subprocess expects a string, i.e. 2 = aa, ab, ac etc..
if __name__ == "__main__":
file_path = sys.argv[1]
# i.e. split -a 2 -l 5000 t/some_file.txt ~/tmp/t/
subprocess.call(["split", "-a", SPLIT_PREFIX_LENGTH, "-l", SPLIT_FILE_CHUNK_SIZE, file_path,
os.path.dirname(file_path) + '/'])
# Remove the original file once done splitting
try:
os.remove(file_path)
except OSError:
pass
You can call it externally:
import os
fs_result = os.system("python file_splitter.py {}".format(local_file_path))
You can also import subprocess and run it directly in your program.
The issue with this approach is high memory usage: subprocess creates a fork with a memory footprint same size as your process and if your process memory is already heavy, it doubles it for the time that it runs. The same thing with os.system.
Here is another pure python way of doing this, although I haven't tested it on huge files, it's going to be slower but be leaner on memory:
CHUNK_SIZE = 5000
def yield_csv_rows(reader, chunk_size):
"""
Opens file to ingest, reads each line to return list of rows
Expects the header is already removed
Replacement for ingest_csv
:param reader: dictReader
:param chunk_size: int, chunk size
"""
chunk = []
for i, row in enumerate(reader):
if i % chunk_size == 0 and i > 0:
yield chunk
del chunk[:]
chunk.append(row)
yield chunk
with open(local_file_path, 'rb') as f:
f.readline().strip().replace('"', '')
reader = unicodecsv.DictReader(f, fieldnames=header.split(','), delimiter=',', quotechar='"')
chunks = yield_csv_rows(reader, CHUNK_SIZE)
for chunk in chunks:
if not chunk:
break
# Do something with your chunk here
Here is another example using readlines():
"""
Simple example using readlines()
where the 'file' is generated via:
seq 10000 > file
"""
CHUNK_SIZE = 5
def yield_rows(reader, chunk_size):
"""
Yield row chunks
"""
chunk = []
for i, row in enumerate(reader):
if i % chunk_size == 0 and i > 0:
yield chunk
del chunk[:]
chunk.append(row)
yield chunk
def batch_operation(data):
for item in data:
print(item)
with open('file', 'r') as f:
chunks = yield_rows(f.readlines(), CHUNK_SIZE)
for _chunk in chunks:
batch_operation(_chunk)
The readlines example demonstrates how to chunk your data to pass chunks to function that expects chunks. Unfortunately readlines opens the whole file in memory, its better to use the reader example for performance. Although if you can easily fit what you need into memory and need to process it in chunks this should suffice.
You can achieve splitting any file to chunks like below, here the CHUNK_SIZE is 500000 bytes(500kb) and content can be any file :
for idx,val in enumerate(get_chunk(content, CHUNK_SIZE)):
data=val
index=idx
def get_chunk(content,size):
for i in range(0,len(content),size):
yield content[i:i+size]
This worked for me
import os
fil = "inputfile"
outfil = "outputfile"
f = open(fil,'r')
numbits = 1000000000
for i in range(0,os.stat(fil).st_size/numbits+1):
o = open(outfil+str(i),'w')
segment = f.readlines(numbits)
for c in range(0,len(segment)):
o.write(segment[c]+"\n")
o.close()
I had a requirement to split csv files for import into Dynamics CRM since the file size limit for import is 8MB and the files we receive are much larger. This program allows user to input FileNames and LinesPerFile, and then splits the specified files into the requested number of lines. I can't believe how fast it works!
# user input FileNames and LinesPerFile
FileCount = 1
FileNames = []
while True:
FileName = raw_input('File Name ' + str(FileCount) + ' (enter "Done" after last File):')
FileCount = FileCount + 1
if FileName == 'Done':
break
else:
FileNames.append(FileName)
LinesPerFile = raw_input('Lines Per File:')
LinesPerFile = int(LinesPerFile)
for FileName in FileNames:
File = open(FileName)
# get Header row
for Line in File:
Header = Line
break
FileCount = 0
Linecount = 1
for Line in File:
#skip Header in File
if Line == Header:
continue
#create NewFile with Header every [LinesPerFile] Lines
if Linecount % LinesPerFile == 1:
FileCount = FileCount + 1
NewFileName = FileName[:FileName.find('.')] + '-Part' + str(FileCount) + FileName[FileName.find('.'):]
NewFile = open(NewFileName,'w')
NewFile.write(Header)
NewFile.write(Line)
Linecount = Linecount + 1
NewFile.close()
import subprocess
subprocess.run('split -l number_of_lines file_path', shell = True)
For example if you want 50000 lines in one files and path is /home/data then you can run below command
subprocess.run('split -l 50000 /home/data', shell = True)
If you are not sure how many lines to keep in split files but knows how many split you want then In Jupyter Notebook/Shell you can check total number of Lines using below command and then divide by total number of split you want
! wc -l file_path
in this case
! wc -l /home/data
And Just so you know output file will not have file extension but its same extension as input file You can change it manually if Windows
Or, a python version of wc and split:
lines = 0
for l in open(filename): lines += 1
Then some code to read the first lines/3 into one file, the next lines/3 into another , etc.

Categories