Python - Split one CSV file into multiple ones

 

import csv
import os


def split(filehandler, delimiter=',', row_limit=500000,
          output_name_template='output_%s.csv', output_path='.', keep_headers=True):
    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 = 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)


file_path = os.path.join(os.path.abspath(os.path.dirname(__file__)), "your_file_name.csv")
split(open(file_path, 'r'))

New era

 Recenly, I've been trying to learning PySpark and related. like AWS EMR. AWS Glue, AWS Quicksight, SageMaker, Databricks, Athena. It is a new way of processing data(well, compare to what I've been doing), kind of more cloud processing. Very excited, and continue learning.....will get more posts later :)