Last active
June 10, 2025 13:40
-
-
Save mr-karan/a77986e66534f7d98e3f4f6aa7281772 to your computer and use it in GitHub Desktop.
Python Function to Split CSV File with headers
This file contains hidden or 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
# coding: utf-8 | |
import csv | |
import os | |
from itertools import tee, islice | |
LINES_SPLIT = 1000 | |
def chunks(l, n): | |
""" | |
Source: https://stackoverflow.com/a/22045226/2369204 | |
""" | |
it = iter(l) | |
return iter(lambda: tuple(islice(it, n)), ()) | |
directory = "output" | |
if not os.path.exists(directory): | |
os.makedirs(directory) | |
print("created directory") | |
files = list(filter(lambda f : f.endswith('csv'), os.listdir("."))) | |
for file in files: | |
with open(files[0],'r') as infile: | |
reader = csv.DictReader(infile) | |
for counter, rows in enumerate(chunks(reader, LINES_SPLIT), start=1): | |
headers = rows[0].keys() | |
print("splitting part {} of {}".format(counter,file)) | |
with open("output/{}_split_{}.{}".format(file.split(".")[0], counter, file.split(".")[1]), mode='w') as out_file: | |
dict_writer = csv.DictWriter(out_file, headers, quotechar='\"',quoting=csv.QUOTE_ALL, lineterminator="\r\n") | |
dict_writer.writeheader() | |
dict_writer.writerows(rows) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment