Synthesizing CreditCard Data for LoadTesting
Revision as of 12:07, 2 April 2009 by PeterHarding (talk | contribs) (→Quick and Dirty Script to Generate AMEX Transaction Data)
Data Generation
Generate a Valid Credit Card Numbers
#!/usr/bin/env python
#
#
#
#-------------------------------------------------------------------------------
"""
Generate a abitrary collection of pseudo Credit card numbers which
satisfy the validation test
"""
import random
#-------------------------------------------------------------------------------
prefix = '1234'
max_digits = 16
max_numbers = 1000
#-------------------------------------------------------------------------------
def gen(prefix):
no = prefix
l = list(no)
i = len(prefix)
while (i < (max_digits - 1)):
x = random.randint(0, 9)
l.append(str(x))
# print i, l, x
i += 1
no = ''.join(l)
chk_digit = encode(no)
delta = 10 - chk_digit
if delta == 10:
delta = 0
# print chk_digit, delta
l.append(str(delta))
no = ''.join(l)
return no
#-------------------------------------------------------------------------------
def encode(no):
n = 0
tot = 0
for i in range(len(no)):
v = int(no[i])
if i % 2 == 0:
inc = v * 2
if v > 4:
n += 1
else:
inc = v
tot += inc
tot += n
chk = tot % 10
return chk
#-------------------------------------------------------------------------------
def validate(ccnumber):
cnt = 0
tot = 0
for i in range(len(ccnumber)):
val = int(ccnumber[i])
if i % 2 == 0:
inc = val * 2
if val > 4:
cnt += 1
else:
inc = val
tot += inc
tot += cnt
if ((tot % 10) == 0):
return True
else:
return False
#-------------------------------------------------------------------------------
def test():
for no in nos:
print no
if validate(no):
print "Card number VALID"
else:
print "Card number INVALID"
#-------------------------------------------------------------------------------
def main():
i = 0
while i < max_numbers:
cc_no = gen(prefix)
if validate(cc_no):
print cc_no
else:
print "Card number %s - INVALID" % cc_no
cc_no = None
if cc_no:
i += 1
else:
pass
#-------------------------------------------------------------------------------
main()
Synthesizing Credit Card Data
Generate data file for import to Application
Here is a script used to synthetically generate an upload data file for Credit Card data:
#!/usr/bin/env python
#
#---------------------------------------------------------------------
import os
import csv
import sys
import getopt
import random
import datetime
#---------------------------------------------------------------------
debug_flg = False
max_flg = False
random_flg = False
verbose_flg = False
__version__ = '1.0.2'
file = None
no_days = 1
date = datetime.datetime.today()
dates = ['070729', '070730', '070731']
xcodes = [
'1002220',
...
'1211220'
]
#----- Set up credit card transactiuon type list ---------------------
cc_merchants = []
cc_merchants_in = open("cc_merchants.csv", "rb")
reader = csv.reader(cc_merchants_in)
for row in reader:
cc_merchants.append(row)
cc_merchants_in.close() # Explicitly close the file *NOW*
no_merchants = len(cc_merchants)
#----- Set up credit card numbers in cc_no list ----------------------
cc_no = []
cc_in = open("cc_no.txt", "rb")
reader = csv.reader(cc_in)
for row in reader:
cc_no.extend(row)
cc_in.close() # Explicitly close the file *NOW*
#----- Set up the file header and footer -----------------------------
header = """\
01,xxx,xxx,%s,2004,1,,,2/
02,,xxx,1,%s,,AUD,2/
"""
footer = """\
...
"""
#----- Set up the body of the file -----------------------------------
max_no_tx = 10 # Number of transactions per CC
cost = 1000 # Cost of the transaction
tx_id = 0 # Number that appears in transaction description
def write_data(date):
global cost, tx_id
file_date = date.strftime("%y%m%d")
expense_date = (date - datetime.timedelta(days=1)).strftime("%y%m%d")
print "Generating expense data for '%s'" % expense_date
out = open(file_date,"w")
out.write(header % (file_date, expense_date))
for i in range(len(cc_no)):
if random_flg:
no_tx = random.randint(0, max_no_tx)
elif max_flg:
no_tx = 5
else:
no_tx = 1
tx_cnt = 0
total = 0.0
expense_lines = ''
while tx_cnt < no_tx:
cost = random.weibullvariate(alpha=3.0,beta=1) * 2000.0
type = cc_merchants[random.randint(0, no_merchants-1)]
expense_lines += "16,699,%.0f,,%s,,%s\n" % (cost, type[0], type[1])
total += cost
tx_cnt += 1
tx_id += 1
cost += 5
expense_block = "01,%s,,...,%03.0f,%d,,...,,/\n" % (cc_no[i], total, tx_cnt)
expense_block += expense_lines
expense_block += "99,...,%d/\n" % (tx_cnt + 2)
out.write(expense_block)
out.write(footer)
out.close()
#-------------------------------------------------------------------------------
USAGE = """\
Usage:
$ ./gen_user_data.py [-d] [-v] [-f <filename>]
"""
def usage():
sys.stderr.write(USAGE)
#-------------------------------------------------------------------------------
def main(argv):
global debug_flg
global max_flg
global random_flg
global verbose_flg
global file, date, no_days
#----- Process command line arguments ----------------------------
try:
opts, args = getopt.getopt(argv, "dD:f:hmn:rv",
["date", "debug", "file=", "help", "max", "no_days", "random", "verbose"])
except getopt.GetoptError:
usage()
sys.exit(2)
else:
for opt, arg in opts:
if opt in ("-d", "--debug"):
debug_flg = True
elif opt in ("-D", "--date"):
target_date = arg
date = datetime.datetime.strptime(target_date, "%Y%m%d")
print date
elif opt in ("-f", "--file"):
logfile = arg
elif opt in ("-h", "--help"):
usage()
sys.exit(0)
elif opt in ("-m", "--max"):
max_flg = True
elif opt in ("-n", "--no_days"):
no_days = int(arg)
elif opt in ("-r", "--random"):
random_flg = True
elif opt in ("-v", "--verbose"):
verbose_flg = True
dates = []
for n in range(no_days):
d = date - datetime.timedelta(days=n)
print d.strftime("%y%m%d")
dates.append(d)
# print date.strftime("%y%m%d")
for d in dates:
write_data(d)
#-------------------------------------------------------------------------------
if __name__ == "__main__":
main(sys.argv[1:])
#-------------------------------------------------------------------------------
Synthesizing AMEX Credit Card Data
Generates AMEX data file for import to SAP
#!/usr/bin/env python
#------------------------------------------------------------------------
import csv
import sys
import getopt
import random
#----- Define globals ---------------------------------------------------
debug_flg = False
verbose_flg = False
max_no_tx = 3 # Number of transactions to be created per CC
users = []
cc_user_map = {}
#----- Setup header, footer and body format strings ---------------------
header = """\
...
"""
body_1 = """
...
"""
body_2 = """\
...
"""
#===== Define classes ===================================================
class User:
pass
def __init__(self, csv):
self.UserId = csv[0]
self.APS = csv[0]
self.CostCenter = csv[1]
self.CreditCardNumber = csv[2]
self.Name = 'tester'
#===== Define functions =================================================
#----- Read in user data and set up credit card numbers in cc_no list ---
def read_user_data():
users_in = open("users.dat", "rb")
reader = csv.reader(users_in)
for row in reader:
user = User(row)
users.append(user)
cc_user_map[user.CreditCardNumber] = user
users_in.close()
#----- Now create a sorted list of keys to the cc catalog ---------------
def gen_cc_list():
global cc_list
cc_list = cc_user_map.keys()
cc_list.sort() # cc_list is *NOW* a sorted list of credit card numbers.
#----- Write the file -----------------------------------------------------------
def generate_data():
line_cnt = 3 # Counts the number of lines in the file
tx_id = 0 # CC Transaction ID
gen_cnt = 0 # No of cards for which data was generated
body_cnt = 0 # No of card entries generated
total_cost = 0.0 # Total costs generated
no_cards = len(cc_list)
sift = open("XXXXXX.SFT","w")
sift.write(header)
for i in range(no_cards):
card_no = cc_list[i]
user = cc_user_map[card_no]
aps = user.APS
name = user.Name
name_25 = name.ljust(25)
name_26 = name.ljust(26)
no_tx = random.randint(0, max_no_tx)
if no_tx > 0:
if debug_flg: print card_no
gen_cnt += 1
tx_idx = 0
while tx_idx < no_tx:
cost = random.weibullvariate(alpha=3.0,beta=1) * 20.0
description = "Description for transaction %05d".ljust(167) % tx_id
total_cost += cost
sift.write(body_1 %(card_no, name, aps, cost, cost, random.choice(["060901", "060831"]), description))
line_cnt += 1
tx_idx += 1
tx_id += 1
body_cnt += 1
sift.write(body_2 %(card_no, name_25, aps))
line_cnt +=1
line_cnt +=2
sift.write(footer % line_cnt)
sift.close()
print "Generated %d cc entries for %d cards with total cost of $%8.2f" % (body_cnt, gen_cnt, total_cost)
#------------------------------------------------------------------------
def process():
read_user_data()
gen_cc_list()
generate_data()
#------------------------------------------------------------------------
Usage = """
Usage: AMEX_file.py [--help] [--logfile=<filename>] [--date=<DATE>] [--verbose]
Generates AMEX data file for import to SAP"
e.g:
$ ./AMEX__file.py
"""
def usage():
print >> sys.stderr, Usage
#------------------------------------------------------------------------
def main(argv):
global debug_flg
global verbose_flg
global logfile
global target_date
try:
opts, args = getopt.getopt(argv, "dhl:u:t",
["date=", "debug", "help", "logfile=", "verbose"])
except getopt.GetoptError:
usage()
sys.exit(2)
else:
for opt, arg in opts:
if opt in ("-d", "--debug"):
debug_flg = True
elif opt in ("-D", "--date"):
target_date = arg
elif opt in ("-h", "--help"):
usage()
sys.exit(0)
elif opt in ("-l", "--logfile"):
logfile = arg
elif opt in ("-v", "--verbose"):
verbose_flg = True
process()
#------------------------------------------------------------------------
if __name__ == "__main__":
main(sys.argv[1:])
#------------------------------------------------------------------------
#
#
#------------------------------------------------------------------------
Quick and Dirty Script to Generate Transaction Data
An early and very simple version of the script...
#!/usr/bin/env python
EMAIL = "xxx@performiq.com.au"
fmt = """\
...
"""
#---------------------------------------------------------------------
def gen_data(day):
print "Generating data for date - %s" % day
ofd = open("%s.txt" % day, "w+")
ofd.write(fmt % (day, ))
ofd.close()
#---------------------------------------------------------------------
dates = ['070612', '070613', '070614', '070615']
for day in dates:
gen_data(day)
#---------------------------------------------------------------------