import sys import csv import random import re from collections import defaultdict if len(sys.argv) < 2: print("usage: python %s dshield_stats.csv outfile.csv" % sys.argv[0]) sys.exit(1) csv_filename_in = sys.argv[1] csv_fd_in = open(csv_filename_in, newline='') csv_reader = csv.reader(csv_fd_in, delimiter=' ') csv_filename_out = sys.argv[2] csv_fd_out = open(csv_filename_out, "w") print("converting DShield data from %s to %s" % (csv_filename_in, csv_filename_out)) cnt = 0 for val in csv_reader: if len(val) < 9: continue if cnt % 1000000 == 0: print("got %d so far" % cnt) cnt += 1 csv_fd_out.write("%s\t%s\t%s\t%s\t%s\t%s\n" % (val[3], val[4], val[5], val[6], val[7], val[8])) csv_fd_in.close() csv_fd_out.close()