splitting one csv into multiple files in python

Question

I have a csv file of about 5000 rows in python i want to split it into five files.

I wrote a code for it but it is not working

import codecs
import c         


        

Answer 1

I suggest you leverage the possibilities offered by pandas. Here are functions you could use to do that :

def csv_count_rows(file):
    """
    Counts the number of rows in a file.
    :param file: path to the file.
    :return: number of lines in the designated file.
    """
    with open(file) as f:
        nb_lines = sum(1 for line in f)
    return nb_lines


def split_csv(file, sep=",", output_path=".", nrows=None, chunksize=None, low_memory=True, usecols=None):
    """
    Split a csv into several files.
    :param file: path to the original csv.
    :param sep: View pandas.read_csv doc.
    :param output_path: path in which to output the resulting parts of the splitting.
    :param nrows: Number of rows to split the original csv by, also view pandas.read_csv doc.
    :param chunksize: View pandas.read_csv doc.
    :param low_memory: View pandas.read_csv doc.
    :param usecols: View pandas.read_csv doc.
    """
    nb_of_rows = csv_count_rows(file)

    # Parsing file elements : Path, name, extension, etc...
    # file_path = "/".join(file.split("/")[0:-1])
    file_name = file.split("/")[-1]
    # file_ext = file_name.split(".")[-1]
    file_name_trunk = file_name.split(".")[0]
    split_files_name_trunk = file_name_trunk + "_part_"

    # Number of chunks to partition the original file into
    nb_of_chunks = math.ceil(nb_of_rows / nrows)
    if nrows:
        log_debug_process_start = f"The file '{file_name}' contains {nb_of_rows} ROWS. " \
            f"\nIt will be split into {nb_of_chunks} chunks of a max number of rows : {nrows}." \
            f"\nThe resulting files will be output in '{output_path}' as '{split_files_name_trunk}0 to {nb_of_chunks - 1}'"
        logging.debug(log_debug_process_start)

    for i in range(nb_of_chunks):
        # Number of rows to skip is determined by (the number of the chunk being processed) multiplied by (the nrows parameter).
        rows_to_skip = range(1, i * nrows) if i else None
        output_file = f"{output_path}/{split_files_name_trunk}{i}.csv"

        log_debug_chunk_processing = f"Processing chunk {i} of the file '{file_name}'"
        logging.debug(log_debug_chunk_processing)

        # Fetching the original csv file and handling it with skiprows and nrows to process its data
        df_chunk = pd.read_csv(filepath_or_buffer=file, sep=sep, nrows=nrows, skiprows=rows_to_skip,
                               chunksize=chunksize, low_memory=low_memory, usecols=usecols)
        df_chunk.to_csv(path_or_buf=output_file, sep=sep)

        log_info_file_output = f"Chunk {i} of file '{file_name}' created in '{output_file}'"
        logging.info(log_info_file_output)

And then in your main or jupyter notebook you put :

# This is how you initiate logging in the most basic way.
logging.basicConfig(level=logging.DEBUG)
file = {#Path to your file}
split_csv(file,sep=";" ,output_path={#Path where you'd like to output it},nrows = 4000000, low_memory = False)

P.S.1 : I put nrows = 4000000 because when it's a personal preference. You can change that number if you wish.

P.S.2 : I used the logging library to display messages. When would apply such a function on big files that exist on a remote server, you really want to avoid 'simple printing' and incorporate logging capabilities. You can replace logging.info or logging.debug with print

P.S.3 : Of course, you need to replace the {# Blablabla} parts of the code with your own parameters.