Created
April 2, 2019 07:29
-
-
Save duchenpaul/c93fbe7593a4f1d94dc9965d6cbc038b to your computer and use it in GitHub Desktop.
Split csv into X line, with or without header
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
import os | |
def split(filehandler, delimiter=',', row_limit=1000, | |
output_name_template='output_%s.csv', output_path='.', keep_headers=True): | |
import csv | |
reader = csv.reader(filehandler, delimiter=delimiter) | |
current_piece = 1 | |
current_out_path = os.path.join( | |
output_path, | |
output_name_template % current_piece | |
) | |
current_out_writer = csv.writer(open(current_out_path, 'w', newline=''), delimiter=delimiter) | |
current_limit = row_limit | |
if keep_headers: | |
# headers = reader.next() | |
headers = next(reader) | |
current_out_writer.writerow(headers) | |
for i, row in enumerate(reader): | |
if i + 1 > current_limit: | |
current_piece += 1 | |
current_limit = row_limit * current_piece | |
current_out_path = os.path.join( | |
output_path, | |
output_name_template % current_piece | |
) | |
current_out_writer = csv.writer(open(current_out_path, 'w', newline=''), delimiter=delimiter) | |
if keep_headers: | |
current_out_writer.writerow(headers) | |
current_out_writer.writerow(row) | |
if __name__ == '__main__': | |
file_name = 'snakes_count_10000.csv' | |
basename = os.path.splitext(file_name)[0] | |
# Create folder if not exists | |
try: | |
os.mkdir(basename) | |
except Exception as e: | |
pass | |
with open(file_name) as filehandler: | |
split(filehandler, delimiter=',', row_limit=100, | |
output_name_template='{}_%s.csv'.format(basename), output_path=basename, keep_headers=True) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment