Quick Python script for splitting large CSV files using Pandas and NumPy.

csv_spliter.py

#!/usr/bin/env python3
import argparse
import math
import os.path

import pandas as pd
import numpy as np


def main(filepath):
    if filepath.endswith('.csv'):
        df_org = pd.read_csv(filepath)
    elif filepath.endswith('.xlsx') or filepath.endswith('.xls'):
        df_org = pd.read_excel(filepath)
    else:
        raise Exception("I don't know what the file is.")

    row_count, column_count = df_org.shape

    split_by = math.ceil(row_count / 5000)

    dfs = np.array_split(df_org, split_by)

    filename = os.path.basename(filepath).replace('.csv', '')
    directory = os.path.dirname(filepath)

    for index, df in enumerate(dfs):
        df.to_csv(os.path.join(directory,
                               '{0}_{1}.csv'.format(filename,
                                                    index)))


if __name__ == '__main__':
    parser = argparse.ArgumentParser()
    parser.add_argument('large_csv_file')
    args = parser.parse_args()

    main(args.large_csv_file)