How to split a huge csv file based on content of first column?

Question

• I have a 250MB+ huge csv file to upload
• file format is group_id, application_id, reading and data could look like

Answer 1

Here some food for though for you:

import csv
from collections import namedtuple

csvfile = namedtuple('scvfile',('file','writer'))

class CSVFileCollections(object):

    def __init__(self,prefix,postfix):
        self.prefix = prefix
        self.files = {}

    def __getitem__(self,item):
        if item not in self.files:
            file = open(self.prefix+str(item)+self.postfix,'wb')
            writer = csv.writer(file,delimiter = ',', quotechar = "'",quoting=csv.QUOTE_MINIMAL)
            self.files[item] = csvfile(file,writer) 
        return self.files[item].writer

    def __enter__(self): pass

    def __exit__(self, exc_type, exc_value, traceback):
        for csvfile in self.files.values() : csvfile.file.close()


with open('huge.csv') as readFile, CSVFileCollections('output','.csv') as output:
    reader = csv.reader(readFile, delimiter=",", quotechar="'")
    for row in reader:
        writer = output[row[0]]
        writer.writerow(row)