Last active
April 19, 2016 13:27
-
-
Save fernandomv3/a3d06dfbef1599dcde2c961b1904c0fd to your computer and use it in GitHub Desktop.
Split a CSV file in almost uniform line numbers
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #!/usr/bin/env python | |
| from __future__ import print_function, division | |
| import sys | |
| import math | |
| def main(argv): | |
| if len(argv) < 3: | |
| print("Usage: split_csv.py filename N") | |
| print("filename: File to be split") | |
| print("N: number of files to be split to") | |
| exit() | |
| with open(argv[1],'r') as f: | |
| num_lines = sum(1 for line in f) | |
| lines_per_file = math.ceil(num_lines/float(argv[2])) | |
| f.seek(0) | |
| header = f.readline() | |
| flist = [] | |
| for n in range(0,int(argv[2])): | |
| new_name = "{0:03d}-".format(n) + argv[1] | |
| fo = open(new_name,'w') | |
| fo.write(header) | |
| flist.append(fo) | |
| for i,l in enumerate(f): | |
| file_index = i // lines_per_file | |
| flist[file_index].write(l) | |
| for f in flist: | |
| f.close() | |
| if __name__ == '__main__': | |
| main(sys.argv) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment