def getCustomerDetails(self,dataProp_dct,companies_lst,classes,data_prop,birth):
lst=random.choice(companies_lst)
vars()[dataProp_dct['Company']]= lst[0] #gen_data.create_company_name(biz_type="Generic")
vars()[dataProp_dct['Sector']]=lst[1]
vars()[dataProp_dct['Designation']]=gen_data.create_job_title()
while True:
start_date=birth+relativedelta(years=random.randint(18,26))
if start_date<datetime.today():
vars()[dataProp_dct['From_Date']]=start_date
break
else:continue
vars()[dataProp_dct['To_Date']]=vars()[dataProp_dct['From_Date']]+timedelta(days=random.randrange((datetime.today() - vars()[dataProp_dct['From_Date']]).days))
return [vars()[dataProp_dct['Company']],vars()[dataProp_dct['Sector']],vars()[dataProp_dct['Designation']],vars()[dataProp_dct['From_Date']],vars()[dataProp_dct['To_Date']]]
def get_rows():
i=501
#line = input("Enter a row (python dict) into the table: ")
while i < 1000:
fake = Faker()
#Pick an account number and store it in acct
#if the account hasn't been already generated then generate a record with all fields
i=i+1
line = "{'rownum':"+str(i)+",'dunno':"+str(10)+",'CC':"+str(gen_data.cc_number())+",'Employer':"+str(gen_data.create_company_name())+\
",'Custemail':"+str(gen_data.create_email())+",'name':"+\
str(gen_data.create_name())+",'occupation':"+str(gen_data.create_job_title())+",'address_street':"+\
str(gen_data.create_city_state_zip())+",'DOB':"+str(gen_data.create_birthday(min_age=2, max_age=85))+\
",'previous_address_city_state_zip':"+str(gen_data.create_city_state_zip())+",'altcustomer_name':"+str(fake.name())+\
",'altcustomer_occupation':"+str(gen_data.create_job_title())+",'altcustomer_dob':"+str(gen_data.create_birthday(min_age=2, max_age=85))+\
",'ssn':"+str((randrange(101,1000,1),randrange(10,100,1),randrange(1000,10000,1)))+",'phone':"+\
str((randrange(101,1000,1),randrange(101,999,1),randrange(1000,10000,1)))+ \
",'AccountID':"+str(randrange(100000,100000000,1))+",'PepFlag':"+str(max((randrange(0,101,1)-99,0)))+",'altcustomerssn':"+\
str((randrange(101,1000,1),randrange(10,100,1),randrange(1000,10000,1)))+",'demarketed_customer_flag':"+\
str(max((randrange(0,101,1)-99),0))+\
",'SAR_flag':"+str(max((randrange(0,101,1)-99),0))+",'nolonger_a_customer':"+str(max((randrange(0,101,1)-99),0))+\
",'closed_account'"+str(max((randrange(0,101,1)-90),0))+",'High_risk_flag':"+str(max((randrange(0,101,1)-99),0))+\
",'Risk_rating':"+str(max((randrange(0,101,1)-99),0))+"}"
yield ast.literal_eval(line)
def getCustomerDetails(self, dataProp_dct, companies_lst, classes,
data_prop, birth):
lst = random.choice(companies_lst)
for key in dataProp_dct.keys():
if self.checkKeywords(key, 'Company')[0] == 1:
companycolName = self.checkKeywords(key, 'Company')[1]
company = lst[0]
break
else:
company = None
for key in dataProp_dct.keys():
if self.checkKeywords(key, 'Sector')[0] == 1:
sectorcolName = self.checkKeywords(key, 'Sector')[1]
sector = lst[1]
break
else:
sector = None
for key in dataProp_dct.keys():
if self.checkKeywords(key, 'Designation')[0] == 1:
designationcolName = self.checkKeywords(key, 'Designation')[1]
designation = gen_data.create_job_title()
break
else:
designation = None
while True:
start_date = birth + relativedelta(years=random.randint(18, 26))
if start_date < datetime.today():
for key in dataProp_dct.keys():
if self.checkKeywords(key, 'From_Date')[0] == 1:
fromDatecolName = self.checkKeywords(key,
'From_Date')[1]
fromDate = start_date
break
else:
fromDate = None
break
else:
continue
for key in dataProp_dct.keys():
if self.checkKeywords(key, 'To_Date')[0] == 1:
toDatecolName = self.checkKeywords(key, 'To_Date')[1]
toDate = fromDate + timedelta(
days=random.randrange((datetime.today() - fromDate).days))
break
else:
toDate = None
return [company, sector, designation, fromDate, toDate]
def fake_user():
f = open('test_user.txt', 'w')
lat = 40.4365
lng = -99.3925
jobs = [gen_data.create_job_title() for i in xrange(200)]
for i in xrange(100):
lat += 0.001
lng -= 0.001
zipcode, city, state = gen_data.create_city_state_zip()
f.write(fake.first_name() + '|' + fake.last_name() + '|' +
gen_data.create_street() + '|' + city + '|' + state + '|' +
zipcode + '|' + fake.date() + '|' + str(sample(jobs, 1)[0]) +
'|' + str(i) + '|' + fake.email() + '|' +
fake.password(length=6,
special_chars=True,
digits=True,
upper_case=True,
lower_case=True) + '|' + str(lat) + '|' +
str(lng) + '\n')
f.close()
def getProspectDetails(self, companies_lst, classes, data_prop, birth):
lst = random.choice(companies_lst)
vars()[data_prop[classes[1]][4]] = lst[0]
vars()[data_prop[classes[1]][-5]] = lst[1]
vars()[data_prop[classes[1]][7]] = gen_data.create_job_title()
while True:
start_date = birth + relativedelta(years=random.randint(18, 26))
if start_date < datetime.today():
vars()[data_prop[classes[1]][12]] = start_date
break
else:
continue
vars()[data_prop[classes[1]][-2]] = vars()[data_prop[
classes[1]][14]] + timedelta(days=random.randrange(
(datetime.today() - vars()[data_prop[classes[1]][14]]).days))
return [
vars()[data_prop[classes[1]][4]],
vars()[data_prop[classes[1]][-5]],
vars()[data_prop[classes[1]][7]],
vars()[data_prop[classes[1]][12]],
vars()[data_prop[classes[1]][-2]]
]
mdl.insert(No_CCs,'')
#Sets CC_NO to a random credit card number
CC_NO=gen_data.cc_number()
#Extract CC_Number from the tuple returned by CC_Number...Tuple contains CC Number and Type
#while CC_list.count(CC_NO[1][0]) > 0:
CC_TRANS=CC_NO[1][0]
dt = str(datetime.now())
clean=re.sub('\W','',dt)
printCC=str(CC_TRANS[-4:])+str(clean[-12:-3])+str(randrange(1111,9999,randrange(1,10,1)))
#str(CC_TRANS[-4:])+str(clean[-12:-2])+str(randrange(1111,9999,randrange(1,10,1)))
#Add CC_Number to control list to prevent duplicates
#Add data elements to current csv row
row.extend([names[0],mdl[0],ssn[0],names[1],mdl[1],ssn[1],names[2],mdl[2],ssn[2],printCC,CC_NO[0],gen_data.create_company_name()+' '+tmp[1],\
gen_data.create_email(),gen_data.create_job_title()])
#Creates Current Address
zip=random.choice(zips.zip)
addr=geo_data.create_city_state_zip[zip]
#Creates Previous address
zip2=random.choice(zips.zip)
addr2=geo_data.create_city_state_zip[zip2]
#Add additional data elements to current csv row
lrg_cash_ex=random.choice(Yes_No)
#Condition for SARs and Demarketed Clients
if(Clsd=='Yes'):
#1% of closed accounts are demarketed but never had a SAR filed
if (max((randrange(0,101,1)-99),0)==1 and SAR=='No'):
from barnum import gen_data
import csv
with open('demographic.csv','w') as csvfile:
csvwriter =csv.writer(csvfile, delimiter=' ')
for i in range (0,100):
name=gen_data.create_name()
job_title=gen_data.create_job_title()
phone=gen_data.create_phone()
address=gen_data.create_city_state_zip()
csvwriter.writerow([name,job_title,phone,address])
csvfile.close()
def createCusts(N):
#List for client whose net worth is over $500K
HighNetWorth = ['Yes'] + ['No'] * 30
#List for type of account
Related_Type = ['Primary','Secondary','Joint']
#List for how the account was opened
Party_Type = ['Person','Non-Person']
#List for a BMO customer
Party_Relation = ['Customer','Non-Customer']
#List for random Yes/No Flag
Yes_No = ['Yes'] + ['No'] * 12
#List for random Yes/No Consent
Yes_No_Consent = ['Yes'] + ['No'] * 4
#List for equal Yes/No Flag
Yes_No_50 = ['Yes','No']
#List for official language
Official_Lang = ['English'] * 3 + ['French']
#List for method of communication
Preffered_Channel = ['Direct Mail','Telemarketing','Email','SMS']
#List for status of customer
#Customer_Status = ['Prospect','Inactive Customer','Past Customer'] + ['Active Customer'] * 56
#List for LOB Segment Type
Seg_Model_Type = ['LOB Specific','Profitability','Geographical','Behavioral','Risk Tolerance']
#List for Model ID
Model_ID = ['01','02','03','04','05']
#List for Model Name
Seg_Model_Name = ['IRRI', 'CRS Risk Score','Geo Risk','Financial Behavior Risk','CM Risk']
#List for Model Score
Seg_Model_Score = ['200','300','400','100','500']
#List for Model Group
Seg_Model_Group = ['Group 1'] * 2 + ['Group 2','Group 3','Group 4']
#List for Model Description
Seg_Model_Description = ['High Risk Tier','Mid Risk Tier','Low Risk Tier','Vertical Risk','Geographical Risk']
#List for random Arms Dealer flag
Arms_Manufacturer=['Yes'] + ['No'] * 2 + [''] * 392
#List for random auction flag
Auction=['Yes'] + ['No'] * 2 + [''] * 392
#List for random Cash Intensive flag
CashIntensive_Business=['Yes'] + ['No'] * 2 + [''] * 392
#List for random Casino?Gaming flag
Casino_Gambling=['Yes'] + ['No'] * 2 + [''] * 392
#List for random Client Onboarding flag
Channel_Onboarding=['E-mail','In Person','In person - In Branch/Bank Office','In person - Offsite/Client Location','Mail','Online','Phone','Request for Proposal (RFP)'] + ['Not Applicable'] * 10
#List for random Transaction flag
Channel_Ongoing_Transactions=['ATM','E-mail','Fax','Mail','Not Applicable','OTC Communication System','Phone'] + ['Online'] * 4 + ['In Person'] * 31
#List for random HI_Vehicle flag
Complex_HI_Vehicle=['Yes'] + ['No'] * 2 + [''] * 392
#List for random Metals flag
Dealer_Precious_Metal=['Yes'] + ['No'] * 2 + [''] * 392
#List for random Arms Dealer flag
Digital_PM_Operator=['Yes'] + ['No'] * 2 + [''] * 392
#List for random Embassy flag
Embassy_Consulate=['Yes'] + ['No'] * 2 + [''] * 392
#Sets variable to Embassy flag
Exchange_Currency=Embassy_Consulate
#Sets variable to Embassy flag
Foreign_Financial_Institution=Embassy_Consulate
#Sets variable to Embassy flag
Foreign_Government=Embassy_Consulate
#Sets variable to Embassy flag
Foreign_NonBank_Financial_Institution=Embassy_Consulate
#Sets variable to Embassy flag
Internet_Gambling=Embassy_Consulate
#Sets variable to Embassy flag
Medical_Marijuana_Dispensary=Embassy_Consulate
#Sets variable to Embassy flag
Money_Service_Business=Embassy_Consulate
#Sets variable to Embassy flag
NonRegulated_Financial_Institution=Embassy_Consulate
#Sets variable to Embassy flag
Not_Profit=Embassy_Consulate
#List for random occupation
Occupation=['11-1011 Chief Executives',\
'11-3011 Administrative Services Managers',\
'11-3031 Financial Managers',\
'11-3061 Purchasing Managers',\
'13-1011 Agents and Business Managers of Artists Performers and Athletes',\
'13-1031 Claims Adjusters Examiners, and Investigators',\
'13-1199 Business Operations Specialists, All Other',\
'13-2099 Financial Specialists All Other',\
'17-1011 Architects Except Landscape and Naval',\
'23-1011 Lawyers',\
'23-1023 Judges, Magistrate Judges and Magistrates',\
'25-2012 Kindergarten Teachers Except Special Education',\
'25-2021 Elementary School Teachers Except Special Education',\
'29-1041 Optometrists',\
'29-2054 Respiratory Therapy Technicians',\
'33-2011 Firefighters',\
'37-1012 First-Line Supervisors of Landscaping Lawn Service and Groundskeeping Workers',\
'39-1011 Gaming Supervisors',\
'39-2011 Animal Trainers',\
'41-1011 First-Line Supervisors of Retail Sales Workers',\
'41-1012 First-Line Supervisors of Non-Retail Sales Workers',\
'41-2011 Cashiers',\
'41-2031 Retail Salespersons',\
'43-3021 Billing and Posting Clerks',\
'45-1011 First-Line Supervisors of Farming, Fishing, and Forestry Workers',\
'49-2011 Computer Automated Teller and Office Machine Repairers',\
'53-3021 Bus Drivers Transit and Intercity',\
'53-4031 Railroad Conductors and Yardmasters',\
'55-1011 Air Crew Officers',\
'55-1012 Aircraft Launch and Recovery Officers',\
'55-1013 Armored Assault Vehicle Officers',\
]
#Sets variable to Embassy flag
Privately_ATM_Operator=Embassy_Consulate
#List for random products
Products=['Certificate of Deposit',\
'Checking Account',\
'Credit Card',\
'Custodial and Investment Agency - Institutional',\
'Custodial and Investment Agency - Personal',\
'Custodial/Trust Outsourcing Services (BTOS)',\
'Custody Accounts (PTIM)',\
'Custody Accounts (RSTC)',\
'DTF (BHFA)',\
'Investment Agency - Personal',\
'Investment Management Account (PTIM)',\
'Lease',\
'Loan / Letter of Credit',\
'Money Market',\
'Mortgage / Bond / Debentures',\
'None',\
'Savings Account',\
'Trust Administration - Irrevocable and Revocable (PTIM)',\
'Trust Administration - Irrevocable and Revocable Trusts (BDTC)',\
] + ['Nondeposit Investment Products'] * 14 + ['Investment Agency - Institutional'] * 5
#Sets variable to Embassy flag
Sales_Used_Vehicles=Embassy_Consulate
#Dictionary for random Services
Services=['Benefit Payment Services',\
'Domestic Wires and Direct Deposit / ACH',\
'Family Office Services (FOS)',\
'Fiduciary Services',\
'International Wires and IAT',\
'Investment Advisory Services (IAS)',\
'Investment Services',\
'None',\
'Online / Mobile Banking',\
'Payroll',\
'Short Term Cash Management',\
'Trust Services',\
'Trustee Services',\
'Vault Cash Services',\
] + ['Financial Planning'] * 6 + ['Retirement Plans'] * 19
#Dictionary for random SIC_Code
SIC_Code=['6021 National Commercial Banks',\
'6211 Security Brokers Dealers and Flotation Companies',\
'6282 Investment Advice',\
'6311 Life Insurance',\
'6733 Trusts Except Educational Religious and Charitable',\
'8999 Services NEC',\
] + ['6722 Management Investment Offices Open-End'] * 12
#Dictionary for random Market Listing
Stock_Market_Listing=['Australian Stock Exchange',\
'Brussels Stock Exchange',\
'Montreal Stock Exchange',\
'Tiers 1 and 2 of the TSX Venture Exchange (also known as Tiers 1 and 2 of the Canadian Venture Exchange)',\
'Toronto Stock Exchange',\
] + ['Not Found'] * 30
#Sets variable to Embassy flag
Third_Party_Payment_Processor=Embassy_Consulate
#Sets variable to Embassy flag
Transacting_Provider=Embassy_Consulate
#Dictionary for random Low Net Worth
LowNet=[1,2] + [0] * 5
#Dictionary for Consumer vs Business
Acct_Type = ['B'] + ['C'] * 5
#Dictionary for random number of credits cards per account
Number_CC = [1] * 7 + [2] * 11 + [3] * 3 + [4]
#Dictionary for Account list set to blank
acct_list=[]
#Dictionary for CreditCard list set to blank
CC_list = []
#Dictionary for random Wolfsberg scenario
Use_Case = [1,4,7,10,13,16,19,22,25,28,31,34,39] * 4 + [2,5,8,11,14,17,20,23,26,29,32,35,38] * 7 + [3,6,9,12,15,18,21,24,27,30,33,36] * 65 + [37] * 73 + [40,41] * 2
refrating = ['1','1','1','2','3','4','2','4','5','5','5','5','5','5','5','5','5','5','5','5']
fake = Faker()
global liSSNMaster
start=10786147
acct_list=[]
liCSV = []
for i in xrange(N):
#Initiate High Risk Flags
#Politically Exposed Person
PEP='No'
#Customer with a Suspicous Activity Report
SAR='No'
#Customer with a closed account
Clsd='No'
#High risk customer flag
high_risk='No'
#High Risk Rating
hr_rating=''
#Customer that was demarketed by the bank
demarket='No'
dem_date=''
#generate closed acct flag
if (max((randrange(0,98,1)-96),0)==1):
Clsd='Yes'
#Random choice for number of credit card users per account number
No_CCs = random.choice(Number_CC)
#Generate account number
acct=start+1+randrange(1,10,1)
start=acct
#Randomly generate customer name + middle name in tmp
name = fake.name()
tmp=gen_data.create_name()
#Adds account number to account dictionary
acct_list.extend([acct])
#Creates a new row and adds data elements
row = [i]+[acct]+[random.choice(Acct_Type)]+[No_CCs]+[name]+[tmp[0]]+[liSSNMaster[i]]
#Dictionary for names list set to blank
names=[]
#Dictionary for Social Security Number list set to blank
ssn=[]
#Middle Name to reduce name dups
mdl=[]
for j in range(No_CCs-1):
names.insert(j,fake.name())
tmp2=gen_data.create_name()
mdl.insert(j,tmp2[0])
##Pull from SSN Master list
randInt = randrange(1,len(liSSNMaster),1)
if randInt != i:
ssn.insert(j,liSSNMaster[randInt])
else:
ssn.insert(j,liSSNMaster[randInt - 1])
#Name and SSN is set to blank if less than 4 customers on an account
for k in range(4-No_CCs):
names.insert(No_CCs+k,'')
ssn.insert(No_CCs+k,'')
mdl.insert(No_CCs,'')
#Sets CC_NO to a random credit card number
CC_NO=gen_data.cc_number()
#Extract CC_Number from the tuple returned by CC_Number then scramble to ensure uniqueness...Tuple contains CC Number and Type
CC_TRANS=CC_NO[1][0]
dt = str(datetime.now())
clean=re.sub('\W','',dt)
printCC=str(CC_TRANS[-4:])+str(clean[-12:-3])+str(randrange(1111,9999,randrange(1,10,1)))
#Add data elements to current csv row
row.extend([names[0],mdl[0],ssn[0],names[1],mdl[1],ssn[1],names[2],mdl[2],ssn[2],printCC,CC_NO[0],gen_data.create_company_name()+' '+tmp[1],\
gen_data.create_email(),gen_data.create_job_title()])
#Create Current Address
zip=random.choice(zips.zip)
addr=geo_data.create_city_state_zip[zip]
#Create Previous address
zip2=random.choice(zips.zip)
addr2=geo_data.create_city_state_zip[zip2]
#Add additional data elements to current csv row
lrg_cash_ex=random.choice(Yes_No)
#Condition for SARs and Demarketed Clients
if(Clsd=='Yes'):
#1% of closed accounts are demarketed but never had a SAR filed
if (max((randrange(0,101,1)-99),0)==1 and SAR=='No'):
demarket='Yes'
dem_date=gen_data.create_date(past=True)
if (max((randrange(0,11,1)-9),0)==1 and demarket=='No'):
#10% of closed accounts have SARs
SAR='Yes'
#90% of closed accounts with SARs are demarketed
if(max((randrange(0,11,1)-9),0)==0):
demarket='Yes'
dem_date=gen_data.create_date(past=True)
if (max((randrange(0,101,1)-99),0)==1):
PEP='Yes'
row.extend([addr[0],addr[1],zip,'US',addr2[0],addr2[1],zip2,'US',gen_data.create_birthday(min_age=2, max_age=85),PEP,SAR,Clsd])
#Start Generating related accounts from account list once 10,000 accounts are generated - to avoid duplicating accounts in the beginning
if i > 10000:
rel = int(random.choice(acct_list))*max((randrange(0,10001,1)-9999),0)
if rel <> 0:
row.append(rel)
row.append(random.choice(Related_Type))
else:
row.append('')
row.append('')
else:
row.append('')
row.append('')
#Randomly generates account start date
party_start=gen_data.create_date(past=True)
#Randomly selects consent option for sharing info
Consent_Share = random.choice(Yes_No_Consent)
#Add additional data elements to current csv row
row.extend([random.choice(Party_Type),random.choice(Party_Relation),party_start,gen_data.create_date(past=True),\
lrg_cash_ex,demarket,dem_date,randrange(0,100,1),random.choice(Official_Lang)])
#Add data element preferred methond of contact for yes to share info...if not then blank to current row
if Consent_Share == 'Yes':
row.extend(['Yes',random.choice(Preffered_Channel)])
else:
row.extend(['No',''])
row.extend([zip,randrange(0,5,1)])
#Generate Segment ID then add additional Segment data based on the selection to the current csv row
Segment_ID = randrange(0,5,1)%5
if Segment_ID == 0:
row.extend([Model_ID[0],Seg_Model_Type[0],Seg_Model_Name[0],Seg_Model_Group[0],Seg_Model_Description[0],Seg_Model_Score[0]])
if Segment_ID == 1:
row.extend([Model_ID[1],Seg_Model_Type[1],Seg_Model_Name[1],Seg_Model_Group[1],Seg_Model_Description[1],Seg_Model_Score[1]])
if Segment_ID == 2:
row.extend([Model_ID[2],Seg_Model_Type[2],Seg_Model_Name[2],Seg_Model_Group[2],Seg_Model_Description[2],Seg_Model_Score[2]])
if Segment_ID == 3:
row.extend([Model_ID[3],Seg_Model_Type[3],Seg_Model_Name[3],Seg_Model_Group[3],Seg_Model_Description[3],Seg_Model_Score[3]])
if Segment_ID == 4:
row.extend([Model_ID[4],Seg_Model_Type[4],Seg_Model_Name[4],Seg_Model_Group[4],Seg_Model_Description[4],Seg_Model_Score[4]])
#Add additional data elements to current csv row
hr0=random.choice(Arms_Manufacturer)
hr01=random.choice(Auction)
hr02=random.choice(CashIntensive_Business)
hr03=random.choice(Casino_Gambling)
hr04=random.choice(Channel_Onboarding)
hr05=random.choice(Channel_Ongoing_Transactions)
row.extend([hr0,hr01,hr02,hr03,hr04,hr05])
#Randomly select whether customer has a High Net Worth
HighNetWorthFlag = random.choice(HighNetWorth)
#Randomly Generate customer net worth based on the above flag
if HighNetWorthFlag == 'Yes':
row.append(max(max((randrange(0,101,1)-99),0)*randrange(1000000,25000000,1),randrange(1000000,5000000,1)))
else:
flag=random.choice(LowNet)
if flag==0:
row.append(randrange(-250000,600000,1))
else:
if flag==1:
row.append(randrange(149000,151000,1))
else:
row.append(randrange(40000,50000,1))
#Add data elements to current csv row
hr1=random.choice(Complex_HI_Vehicle)
hr2=random.choice(Dealer_Precious_Metal)
hr3=random.choice(Digital_PM_Operator)
hr4=random.choice(Embassy_Consulate)
hr5=random.choice(Exchange_Currency)
hr6=random.choice(Foreign_Financial_Institution)
hr7=random.choice(Foreign_Government)
hr8=random.choice(Foreign_NonBank_Financial_Institution)
hr9=random.choice(Internet_Gambling)
hr10=random.choice(Medical_Marijuana_Dispensary)
hr11=random.choice(Money_Service_Business)
hr12=random.choice(NAICS.NAICS_Code)
hr13=random.choice(NonRegulated_Financial_Institution)
hr14=random.choice(Not_Profit)
#hr15=random.choice(Occupation) - added before through gen_data
hr16=random.choice(Privately_ATM_Operator)
hr17=random.choice(Products)
hr18=random.choice(Sales_Used_Vehicles)
hr19=random.choice(Services)
hr20=random.choice(SIC_Code)
hr21=random.choice(Stock_Market_Listing)
hr22=random.choice(Third_Party_Payment_Processor)
hr23=random.choice(Transacting_Provider)
if(PEP=='Yes' or SAR=='Yes' or lrg_cash_ex=='Yes' or demarket=='Yes' or hr0=='Yes'
or hr01=='Yes' or hr02=='Yes' or hr03=='Yes' or hr1=='Yes' or hr2=='Yes' or hr3=='Yes' or hr4=='Yes' or
hr5=='Yes' or hr6=='Yes' or hr7=='Yes' or hr8=='Yes' or hr9=='Yes' or hr10=='Yes' or hr11=='Yes' or hr13=='Yes' or hr14=='Yes' or
hr16=='Yes' or hr17=='Yes' or hr18=='Yes' or hr22=='Yes' or hr23=='Yes' or HighNetWorthFlag=='Yes'):
high_risk='Yes'
hr_rating=random.choice(refrating)
if(SAR=='No' and high_risk=='No'):
if(max((randrange(0,101,1)-99),0)==1):
high_risk='Yes'
hr_rating=random.choice(refrating)
if(PEP=='No' and high_risk=='No'):
if(max((randrange(0,101,1)-99),0)==1):
high_risk='Yes'
hr_rating=random.choice(refrating)
if(high_risk=='No'):
if(max((randrange(0,101,1)-99),0)==1):
high_risk='Yes'
hr_rating=random.choice(refrating)
row.extend([hr1,hr2,hr3,hr4,hr5,hr6,hr7,hr8,hr9,hr10,hr11,hr12,hr13,hr14,hr16,hr17,hr18,hr19,hr20,hr21,hr22,hr23,
HighNetWorthFlag,high_risk,hr_rating,random.choice(Use_Case)])
liCSV.append(row)
return liCSV
f1,
delimiter=',',
lineterminator='\n',
)
writer.writerow(['rownum'] +['dunno'] + ['CC'] + ['Employer'] + ['Custemail'] + ['name'] \
+ ['occupation'] + ['address_street'] + ['DOB']+['previous address_city_state_zip']+ ['altcustomer_name'] \
+ ['altcustomer_occupation'] + ['altcustomer_dob'] + ['ssn'] + ['phone'] + \
['AccountID'] + ['PepFlag'] + ['altcustomerssn'] + ['demarketed_customer_flag'] + \
['SAR_flag'] + ['nolonger_a_customer'] + ['closed_account'] +['High_risk_flag'] +['Risk_rating'])
while i < 50000000:
#Pick an account number and store it in acct
acct = randrange(100000, 100000000, 1)
#if the account hasn't been already generated then generate a record with all fields
if d.has_key(str(acct)) == False:
row = [i] + [10] + [gen_data.cc_number()]+[gen_data.create_company_name()] + \
[gen_data.create_email()]+[gen_data.create_name()] +[gen_data.create_job_title()] + \
[gen_data.create_city_state_zip()] + [gen_data.create_birthday(min_age=2, max_age=85)] + \
[gen_data.create_city_state_zip()] + [fake.name()] + [gen_data.create_job_title()] + \
[gen_data.create_birthday(min_age=2, max_age=85)] +\
[(randrange(101,1000,1),randrange(10,100,1),randrange(1000,10000,1))] + \
[(randrange(101,1000,1),randrange(101,999,1),randrange(1000,10000,1))] + \
[acct] + \
[max((randrange(0,101,1)-99),0)] + \
[(randrange(101,1000,1),randrange(10,100,1),randrange(1000,10000,1))] + \
[max((randrange(0,101,1)-99),0)] + [max((randrange(0,101,1)-99),0)] + \
[max((randrange(0,101,1)-99),0)] + [max((randrange(0,101,1)-90),0)] + \
[max((randrange(0,101,1)-99),0)] + [max((randrange(0,101,1)-99),0)]
d[str(acct)] = acct
i = i + 1
writer.writerow(row)
from barnum import gen_data
import csv
#gen_data = gen_data()
with open('large.csv','w') as f1:
writer=csv.writer(f1, delimiter=',',lineterminator='\n',)
writer.writerow([''] + range(10))
for i in range(50000000):
row = [i] + [10] + [gen_data.cc_number()]+[gen_data.create_company_name()] +[gen_data.create_email()]+[gen_data.create_name()] +[gen_data.create_job_title()] + [gen_data.create_city_state_zip()] + [gen_data.create_birthday(min_age=2, max_age=85)]
writer.writerow(row)
#row = [i] + [10] + [fake.name()] +[fake.address()]
for dummy in range (0, count):
firstName, lastName = gen_data.create_name()
zip, city, state = gen_data.create_city_state_zip()
postalAddressID=str(random.randint(0, sys.maxint))
UID = str(random.randint(0, sys.maxint))
phoneNumber = gen_data.create_phone()
phoneUri = 'tel:+1' + phoneNumber.translate(allchars,' -()')
birthDay = gen_data.create_birthday()
streetAddress = gen_data.create_street()
emailAddress = gen_data.create_email(name=(firstName, lastName))
xmppAddress = str(firstName+"." + lastName + "@gmail.com").lower()
hasIMAccount = False
hasPhoneNumber = False
jobTitle = gen_data.create_job_title()
generatePostalAddress()
generateEmailAddress()
#Only every 3rd have Phone or IM to add variation.
if random.randint(0, 3) > 2 or count == 1:
generateIMAccount(gen_data, str)
hasIMAccount = True
if random.randint(0, 3) > 2 or count == 1:
generatePhoneNumber()
hasPhoneNumber = True
if (withPhone): generatePhoneCalls(3)
if (withPhone): generateSMS (4)
def generate_customers():
with get_file('uber_cust.csv', 'w') as f1:
# Writer for CSV...Pipe delimited...Return for a new line
writer = csv.writer(
f1,
delimiter='|',
lineterminator='\n',
)
# Header Row
writer.writerow(
['ROWNUM'] + ['accountNumber'] + ['accountCategory'] + ['accountType'] + ['NUM_CCS'] + ['NAME'] + [
'M_NAME'] + [
'SSN'] + [
'AUTHORIZED_NAME2'] + ['M_NAME2'] + ['SSN2'] + \
['AUTHORIZED_NAME3'] + ['M_NAME3'] + ['SSN3'] + ['AUTHORIZED_NAME4'] + ['M_NAME4'] + ['SSN4'] + [
'CREDITCARDNUMBER'] + ['CREDITCARDTYPE'] + ['EMPLOYER'] + ['CUSTEMAIL'] + \
['OCCUPATION'] + ['CITY'] + ['STATE'] + ['ZIP'] + ['COUNTRY'] + ['PREVIOUS_CITY'] + [
'PREVIOUS_STATE'] + \
['PREVIOUS_ZIP'] + ['PREVIOUS_COUNTRY'] + ['DOB'] + ['politically_exposed_person'] + [
'suspicious_activity_report'] + ['CLOSEDACCOUNT'] + [
'RELATED_ACCT'] + ['RELATED_TYPE'] + ['PARTY_TYPE'] + ['PARTY_RELATION'] + [
'PARTY_STARTDATE'] + ['PARTY_ENDDATE'] + \
['LARGE_CASH_EXEMPT'] + ['DEMARKET_FLAG'] + ['DEMARKET_DATE'] + ['PROB_DEFAULT_RISKR'] + [
'OFFICIAL_LANG_PREF'] + ['CONSENT_SHARING'] + \
['PREFERRED_CHANNEL'] + ['PRIMARY_BRANCH_NO'] + ['DEPENDANTS_COUNT'] + ['SEG_MODEL_ID'] + [
'SEG_MODEL_TYPE'] + \
['SEG_MODEL_NAME'] + ['SEG_MODEL_GROUP'] + ['SEG_M_GRP_DESC'] + ['SEG_MODEL_SCORE'] + [
'ARMS_MANUFACTURER'] + ['AUCTION'] + \
['CASHINTENSIVE_BUSINESS'] + ['CASINO_GAMBLING'] + ['CHANNEL_ONBOARDING'] + [
'CHANNEL_ONGOING_TRANSACTIONS'] + ['CLIENT_NET_WORTH'] + \
['COMPLEX_HI_VEHICLE'] + ['DEALER_PRECIOUS_METAL'] + ['DIGITAL_PM_OPERATOR'] + [
'EMBASSY_CONSULATE'] + ['EXCHANGE_CURRENCY'] + \
['FOREIGN_FINANCIAL_INSTITUTION'] + ['FOREIGN_GOVERNMENT'] + [
'FOREIGN_NONBANK_FINANCIAL_INSTITUTION'] + ['INTERNET_GAMBLING'] + \
['MEDICAL_MARIJUANA_DISPENSARY'] + ['MONEY_SERVICE_BUSINESS'] + ['NAICS_CODE'] + [
'NONREGULATED_FINANCIAL_INSTITUTION'] + \
['NOT_PROFIT'] + ['PRIVATELY_ATM_OPERATOR'] + ['PRODUCTS'] + ['SALES_USED_VEHICLES'] + [
'SERVICES'] + \
['SIC_CODE'] + ['STOCK_MARKET_LISTING'] + ['THIRD_PARTY_PAYMENT_PROCESSOR'] + [
'TRANSACTING_PROVIDER'] + ['HIGH_NET_WORTH'] + ['HIGH_RISK'] + ['RISK_RATING'] + [
'USE_CASE_SCENARIO'])
# Loop for number of accounts to generate
start = 10
acct_list = []
li_ssn_master = list(
set([
''.join(str(random.randint(0, 9)) for _ in xrange(9))
for i in xrange(30)
]))
if len(li_ssn_master) < 30:
li_ssn_master = list(
set([
''.join(str(random.randint(0, 9)) for _ in xrange(9))
for i in xrange(30)
]))
for i in xrange(30):
# Initiate High Risk Flags
politically_exposed_person = 'No'
suspicious_activity_report = 'No'
closed_cust_acct = 'No'
# High risk customer flag
high_risk = 'No'
# High Risk Rating
hr_rating = ''
# Customer that was demarketed by the bank
demarket = 'No'
dem_date = ''
# generate closed acct flag
if max((randrange(0, 98, 1) - 96), 0) == 1:
closed_cust_acct = 'Yes'
# Random number generator for account number
# acct = randrange(100000,100000000,1)
# Random choice for number of credit cards per account number
no_ccs = weighted_options('number_cc')
# while acct_list.count(acct) > 0:
# acct = randrange(100000,100000000,1)
# dt = str(datetime.now())
# acct=str(i)++re.sub('\W','',dt)
acct = start + 1 + randrange(1, 10, 1)
start = acct
name = fake.name()
tmp = gen_data.create_name()
# Adds account number to account dictionary
acct_list.extend([acct])
# Creates a new row and adds data elements
## JS - Main Account Holder SSN as current index in master SSN list
## row = [i]+[acct]+[random.choice(acct_type)]+[No_CCs]+[name]+[tmp[0]]+[(str(randrange(101,1000,1))+str(randrange(10,100,1))+str(randrange(1000,10000,1)))]
row = [i] + [acct] + [weighted_options('acct_type')] + [no_ccs] + [
name
] + [tmp[0]] + [li_ssn_master[i]]
# Dictionary for names list set to blank
names = []
# Dictionary for Social Security Number list set to blank
ssn = []
# Generates Name and SSN for Credit Users
# Middle Name to reduce name dups
mdl = []
for j in range(no_ccs - 1):
names.insert(j, fake.name())
tmp2 = gen_data.create_name()
mdl.insert(j, tmp2[0])
## JS - Pull from SSN Master list
# ssn.insert(j,(str(randrange(101,1000,1))+str(randrange(10,100,1))+str(randrange(1000,10000,1))))
randInt = randrange(1, len(li_ssn_master), 1)
if randInt != i:
ssn.insert(j, li_ssn_master[randInt])
else:
ssn.insert(j, li_ssn_master[randInt - 1])
# Name and SSN is set to blank if less than 4 customers on an account
for k in range(4 - no_ccs):
names.insert(no_ccs + k, '')
ssn.insert(no_ccs + k, '')
mdl.insert(no_ccs, '')
# Sets CC_NO to a random credit card number
CC_NO = gen_data.create_cc_number()
# Extract CC_Number from the tuple returned by CC_Number...Tuple contains CC Number and Type
# while credit_cards.count(CC_NO[1][0]) > 0:
CC_TRANS = CC_NO[1][0]
dt = str(datetime.now())
clean = re.sub('\W', '', dt)
printCC = str(CC_TRANS[-4:]) + str(clean[-12:-3]) + str(
randrange(1111, 9999, randrange(1, 10, 1)))
# str(CC_TRANS[-4:])+str(clean[-12:-2])+str(randrange(1111,9999,randrange(1,10,1)))
# Add CC_Number to control list to prevent duplicates
# Add data elements to current csv row
row.extend([
names[0], mdl[0], ssn[0], names[1], mdl[1], ssn[1], names[2],
mdl[2], ssn[2], printCC, CC_NO[0],
gen_data.create_company_name() + ' ' + tmp[1],
gen_data.create_email(),
gen_data.create_job_title()
])
# Creates Current Address
zip = random.choice(zips.zip)
addr = geo_data.create_city_state_zip[zip]
# Creates Previous address
zip2 = random.choice(zips.zip)
addr2 = geo_data.create_city_state_zip[zip2]
# Add additional data elements to current csv row
lrg_cash_ex = weighted_options('yes_no')
# Condition for SARs and Demarketed Clients
if closed_cust_acct == 'Yes':
# 1% of closed accounts are demarketed but never had a suspicious_activity_report filed
if risk_range() and suspicious_activity_report == 'No':
demarket = 'Yes'
dem_date = gen_data.create_date(past=True)
if risk_range() and demarket == 'No':
# 10% of closed accounts have SARs
suspicious_activity_report = 'Yes'
# 90% of closed accounts with SARs are demarketed
if max((randrange(0, 11, 1) - 9), 0) == 0:
demarket = 'Yes'
dem_date = gen_data.create_date(past=True)
if risk_range():
politically_exposed_person = 'Yes'
row.extend([
addr[0], addr[1], zip, 'US', addr2[0], addr2[1], zip2, 'US',
gen_data.create_birthday(min_age=2, max_age=85),
politically_exposed_person, suspicious_activity_report,
closed_cust_acct
])
# Start Generating related accounts from account list once 10,000 accounts are generated
if i > 10000:
rel = int(random.choice(acct_list)) * max(
(randrange(0, 10001, 1) - 9999), 0)
if rel <> 0:
row.append(rel)
row.append(weighted_options('related_type'))
else:
row.append('')
row.append('')
else:
row.append('')
row.append('')
# Randomly generates account start date
party_start = gen_data.create_date(past=True)
# Randomly selects consent option for sharing info
consent_share = weighted_options('yes_no')
# Add additional data elements to current csv row
row.extend([
weighted_options('party_type'),
weighted_options('party_relation'), party_start,
gen_data.create_date(past=True), lrg_cash_ex, demarket,
dem_date,
randrange(0, 100, 1),
weighted_options('official_lang')
])
# Add data element preferred methond of contact for yes to share info...if not then blank to current row
if consent_share == 'Yes':
row.extend(['Yes', weighted_options('preferred_channel')])
else:
row.extend(['No', ''])
# DO NOT USE CUST STATUS BELOW - NOT INTEGRATED WITH CLOSED STATUS! Add additional data elements to current csv row
row.extend([zip, randrange(0, 5, 1)])
# Generates Segment ID then adds additional Segment data based on the selection to the current csv row
Segment_ID = randrange(0, 5, 1) % 5
if Segment_ID == 0:
row.extend([
MODEL_ID[0], SEG_MODEL_TYPE[0], SEG_MODEL_NAME[0],
SEG_MODEL_GROUP[0], SEG_MODEL_DESCRIPTION[0],
SEG_MODEL_SCORE[0]
])
if Segment_ID == 1:
row.extend([
MODEL_ID[1], SEG_MODEL_TYPE[1], SEG_MODEL_NAME[1],
SEG_MODEL_GROUP[1], SEG_MODEL_DESCRIPTION[1],
SEG_MODEL_SCORE[1]
])
if Segment_ID == 2:
row.extend([
MODEL_ID[2], SEG_MODEL_TYPE[2], SEG_MODEL_NAME[2],
SEG_MODEL_GROUP[2], SEG_MODEL_DESCRIPTION[2],
SEG_MODEL_SCORE[2]
])
if Segment_ID == 3:
row.extend([
MODEL_ID[3], SEG_MODEL_TYPE[3], SEG_MODEL_NAME[3],
SEG_MODEL_GROUP[3], SEG_MODEL_DESCRIPTION[3],
SEG_MODEL_SCORE[3]
])
if Segment_ID == 4:
row.extend([
MODEL_ID[4], SEG_MODEL_TYPE[4], SEG_MODEL_NAME[4],
SEG_MODEL_GROUP[4], SEG_MODEL_DESCRIPTION[4],
SEG_MODEL_SCORE[4]
])
# Add additional data elements to current csv row
arms_manufacturer = weighted_options('arms_manufacturers')
auction = weighted_options('auction')
cash_intensive_business = weighted_options(
'cash_intensive_business')
casino_gambling = weighted_options('casino_gambling')
chan_ob = weighted_options('channel_onboarding')
chan_txn = weighted_options('channel_ongoing_txn')
row.extend([
arms_manufacturer, auction, cash_intensive_business,
casino_gambling, chan_ob, chan_txn
])
# Randomly select whether customer has a High Net Worth
high_net_worth_flag = weighted_options('high_net_worth')
# Randomly Generates customer net worth based on the above flag
if high_net_worth_flag == 'Yes':
row.append(
max(
max((randrange(0, 101, 1) - 99), 0) *
randrange(1000000, 25000000, 1),
randrange(1000000, 5000000, 1)))
else:
flag = weighted_options('low_net')
if flag == 0:
row.append(randrange(-250000, 600000, 1))
else:
if flag == 1:
row.append(randrange(149000, 151000, 1))
else:
row.append(randrange(40000, 50000, 1))
# Add data elements to current csv row
hr1 = weighted_options('complex_hi_vehicle')
hr2 = weighted_options('dealer_precious_metal')
hr3 = weighted_options('digital_pm_operator')
hr4 = weighted_options(EMBASSY_CONSULATE)
hr5 = weighted_options(EXCHANGE_CURRENCY)
hr6 = weighted_options(FOREIGN_FINANCIAL_INSTITUTION)
hr7 = weighted_options(FOREIGN_GOVT)
hr8 = weighted_options(FOREIGN_NONBANK_FINANCIAL_INSTITUTION)
hr9 = weighted_options(INTERNET_GAMBLING)
hr10 = weighted_options(MEDICAL_MARIJUANA_DISPENSARY)
hr11 = weighted_options(MONEY_SERVICE_BUSINESS)
hr12 = random.choice(NAICS.NAICS_Code)
hr13 = weighted_options(NONREGULATED_FINANCIAL_INSTITUTION)
hr14 = weighted_options(NOT_PROFIT)
# hr15=random.choice(occupation)
hr16 = weighted_options(PRIVATE_ATM_OPERATOR)
hr17 = weighted_options('products')
hr18 = weighted_options(SALES_USED_VEHICLES)
hr19 = weighted_options('services')
hr20 = weighted_options('sic_code')
hr21 = weighted_options('stock_market_listing')
hr22 = weighted_options(THIRD_PARTY_PAYMENT_PROCESSOR)
hr23 = weighted_options(TRANSACTING_PROVIDER)
if 'Yes' in (politically_exposed_person,
suspicious_activity_report, lrg_cash_ex, demarket,
arms_manufacturer, auction, cash_intensive_business,
casino_gambling, hr1, hr2, hr3, hr4, hr5, hr6, hr7,
hr8, hr9, hr10, hr11, hr13, hr14, hr16, hr17, hr18,
hr22, hr23, high_net_worth_flag):
high_risk = 'Yes'
hr_rating = weighted_options('refrating')
if suspicious_activity_report == 'No' and high_risk == 'No':
if risk_range():
high_risk = 'Yes'
hr_rating = weighted_options('refrating')
if politically_exposed_person == 'No' and high_risk == 'No':
if risk_range():
high_risk = 'Yes'
hr_rating = weighted_options('refrating')
if high_risk == 'No':
if risk_range():
high_risk = 'Yes'
hr_rating = weighted_options('refrating')
row.extend([
hr1, hr2, hr3, hr4, hr5, hr6, hr7, hr8, hr9, hr10, hr11, hr12,
hr13, hr14, hr16, hr17, hr18, hr19, hr20, hr21, hr22, hr23,
high_net_worth_flag, high_risk, hr_rating,
random.choice(USE_CASE)
])
# End the current row
writer.writerow(row)
def createCusts(N):
#List for client whose net worth is over $500K
HighNetWorth = ['Yes'] + ['No'] * 30
#List for type of account
Related_Type = ['Primary', 'Secondary', 'Joint']
#List for how the account was opened
Party_Type = ['Person', 'Non-Person']
#List for a BMO customer
Party_Relation = ['Customer', 'Non-Customer']
#List for random Yes/No Flag
Yes_No = ['Yes'] + ['No'] * 12
#List for random Yes/No Consent
Yes_No_Consent = ['Yes'] + ['No'] * 4
#List for equal Yes/No Flag
Yes_No_50 = ['Yes', 'No']
#List for official language
Official_Lang = ['English'] * 3 + ['French']
#List for method of communication
Preffered_Channel = ['Direct Mail', 'Telemarketing', 'Email', 'SMS']
#List for status of customer
#Customer_Status = ['Prospect','Inactive Customer','Past Customer'] + ['Active Customer'] * 56
#List for LOB Segment Type
Seg_Model_Type = [
'LOB Specific', 'Profitability', 'Geographical', 'Behavioral',
'Risk Tolerance'
]
#List for Model ID
Model_ID = ['01', '02', '03', '04', '05']
#List for Model Name
Seg_Model_Name = [
'IRRI', 'CRS Risk Score', 'Geo Risk', 'Financial Behavior Risk',
'CM Risk'
]
#List for Model Score
Seg_Model_Score = ['200', '300', '400', '100', '500']
#List for Model Group
Seg_Model_Group = ['Group 1'] * 2 + ['Group 2', 'Group 3', 'Group 4']
#List for Model Description
Seg_Model_Description = [
'High Risk Tier', 'Mid Risk Tier', 'Low Risk Tier', 'Vertical Risk',
'Geographical Risk'
]
#List for random Arms Dealer flag
Arms_Manufacturer = ['Yes'] + ['No'] * 2 + [''] * 392
#List for random auction flag
Auction = ['Yes'] + ['No'] * 2 + [''] * 392
#List for random Cash Intensive flag
CashIntensive_Business = ['Yes'] + ['No'] * 2 + [''] * 392
#List for random Casino?Gaming flag
Casino_Gambling = ['Yes'] + ['No'] * 2 + [''] * 392
#List for random Client Onboarding flag
Channel_Onboarding = [
'E-mail', 'In Person', 'In person - In Branch/Bank Office',
'In person - Offsite/Client Location', 'Mail', 'Online', 'Phone',
'Request for Proposal (RFP)'
] + ['Not Applicable'] * 10
#List for random Transaction flag
Channel_Ongoing_Transactions = [
'ATM', 'E-mail', 'Fax', 'Mail', 'Not Applicable',
'OTC Communication System', 'Phone'
] + ['Online'] * 4 + ['In Person'] * 31
#List for random HI_Vehicle flag
Complex_HI_Vehicle = ['Yes'] + ['No'] * 2 + [''] * 392
#List for random Metals flag
Dealer_Precious_Metal = ['Yes'] + ['No'] * 2 + [''] * 392
#List for random Arms Dealer flag
Digital_PM_Operator = ['Yes'] + ['No'] * 2 + [''] * 392
#List for random Embassy flag
Embassy_Consulate = ['Yes'] + ['No'] * 2 + [''] * 392
#Sets variable to Embassy flag
Exchange_Currency = Embassy_Consulate
#Sets variable to Embassy flag
Foreign_Financial_Institution = Embassy_Consulate
#Sets variable to Embassy flag
Foreign_Government = Embassy_Consulate
#Sets variable to Embassy flag
Foreign_NonBank_Financial_Institution = Embassy_Consulate
#Sets variable to Embassy flag
Internet_Gambling = Embassy_Consulate
#Sets variable to Embassy flag
Medical_Marijuana_Dispensary = Embassy_Consulate
#Sets variable to Embassy flag
Money_Service_Business = Embassy_Consulate
#Sets variable to Embassy flag
NonRegulated_Financial_Institution = Embassy_Consulate
#Sets variable to Embassy flag
Not_Profit = Embassy_Consulate
#List for random occupation
Occupation=['11-1011 Chief Executives',\
'11-3011 Administrative Services Managers',\
'11-3031 Financial Managers',\
'11-3061 Purchasing Managers',\
'13-1011 Agents and Business Managers of Artists Performers and Athletes',\
'13-1031 Claims Adjusters Examiners, and Investigators',\
'13-1199 Business Operations Specialists, All Other',\
'13-2099 Financial Specialists All Other',\
'17-1011 Architects Except Landscape and Naval',\
'23-1011 Lawyers',\
'23-1023 Judges, Magistrate Judges and Magistrates',\
'25-2012 Kindergarten Teachers Except Special Education',\
'25-2021 Elementary School Teachers Except Special Education',\
'29-1041 Optometrists',\
'29-2054 Respiratory Therapy Technicians',\
'33-2011 Firefighters',\
'37-1012 First-Line Supervisors of Landscaping Lawn Service and Groundskeeping Workers',\
'39-1011 Gaming Supervisors',\
'39-2011 Animal Trainers',\
'41-1011 First-Line Supervisors of Retail Sales Workers',\
'41-1012 First-Line Supervisors of Non-Retail Sales Workers',\
'41-2011 Cashiers',\
'41-2031 Retail Salespersons',\
'43-3021 Billing and Posting Clerks',\
'45-1011 First-Line Supervisors of Farming, Fishing, and Forestry Workers',\
'49-2011 Computer Automated Teller and Office Machine Repairers',\
'53-3021 Bus Drivers Transit and Intercity',\
'53-4031 Railroad Conductors and Yardmasters',\
'55-1011 Air Crew Officers',\
'55-1012 Aircraft Launch and Recovery Officers',\
'55-1013 Armored Assault Vehicle Officers',\
]
#Sets variable to Embassy flag
Privately_ATM_Operator = Embassy_Consulate
#List for random products
Products=['Certificate of Deposit',\
'Checking Account',\
'Credit Card',\
'Custodial and Investment Agency - Institutional',\
'Custodial and Investment Agency - Personal',\
'Custodial/Trust Outsourcing Services (BTOS)',\
'Custody Accounts (PTIM)',\
'Custody Accounts (RSTC)',\
'DTF (BHFA)',\
'Investment Agency - Personal',\
'Investment Management Account (PTIM)',\
'Lease',\
'Loan / Letter of Credit',\
'Money Market',\
'Mortgage / Bond / Debentures',\
'None',\
'Savings Account',\
'Trust Administration - Irrevocable and Revocable (PTIM)',\
'Trust Administration - Irrevocable and Revocable Trusts (BDTC)',\
] + ['Nondeposit Investment Products'] * 14 + ['Investment Agency - Institutional'] * 5
#Sets variable to Embassy flag
Sales_Used_Vehicles = Embassy_Consulate
#Dictionary for random Services
Services=['Benefit Payment Services',\
'Domestic Wires and Direct Deposit / ACH',\
'Family Office Services (FOS)',\
'Fiduciary Services',\
'International Wires and IAT',\
'Investment Advisory Services (IAS)',\
'Investment Services',\
'None',\
'Online / Mobile Banking',\
'Payroll',\
'Short Term Cash Management',\
'Trust Services',\
'Trustee Services',\
'Vault Cash Services',\
] + ['Financial Planning'] * 6 + ['Retirement Plans'] * 19
#Dictionary for random SIC_Code
SIC_Code=['6021 National Commercial Banks',\
'6211 Security Brokers Dealers and Flotation Companies',\
'6282 Investment Advice',\
'6311 Life Insurance',\
'6733 Trusts Except Educational Religious and Charitable',\
'8999 Services NEC',\
] + ['6722 Management Investment Offices Open-End'] * 12
#Dictionary for random Market Listing
Stock_Market_Listing=['Australian Stock Exchange',\
'Brussels Stock Exchange',\
'Montreal Stock Exchange',\
'Tiers 1 and 2 of the TSX Venture Exchange (also known as Tiers 1 and 2 of the Canadian Venture Exchange)',\
'Toronto Stock Exchange',\
] + ['Not Found'] * 30
#Sets variable to Embassy flag
Third_Party_Payment_Processor = Embassy_Consulate
#Sets variable to Embassy flag
Transacting_Provider = Embassy_Consulate
#Dictionary for random Low Net Worth
LowNet = [1, 2] + [0] * 5
#Dictionary for Consumer vs Business
Acct_Type = ['B'] + ['C'] * 5
#Dictionary for random number of credits cards per account
Number_CC = [1] * 7 + [2] * 11 + [3] * 3 + [4]
#Dictionary for Account list set to blank
acct_list = []
#Dictionary for CreditCard list set to blank
CC_list = []
#Dictionary for random Wolfsberg scenario
Use_Case = [1, 4, 7, 10, 13, 16, 19, 22, 25, 28, 31, 34, 39] * 4 + [
2, 5, 8, 11, 14, 17, 20, 23, 26, 29, 32, 35, 38
] * 7 + [3, 6, 9, 12, 15, 18, 21, 24, 27, 30, 33, 36
] * 65 + [37] * 73 + [40, 41] * 2
refrating = [
'1', '1', '1', '2', '3', '4', '2', '4', '5', '5', '5', '5', '5', '5',
'5', '5', '5', '5', '5', '5'
]
fake = Faker()
global liSSNMaster
start = 10786147
acct_list = []
liCSV = []
for i in xrange(N):
#Initiate High Risk Flags
#Politically Exposed Person
PEP = 'No'
#Customer with a Suspicous Activity Report
SAR = 'No'
#Customer with a closed account
Clsd = 'No'
#High risk customer flag
high_risk = 'No'
#High Risk Rating
hr_rating = ''
#Customer that was demarketed by the bank
demarket = 'No'
dem_date = ''
#generate closed acct flag
if (max((randrange(0, 98, 1) - 96), 0) == 1):
Clsd = 'Yes'
#Random choice for number of credit card users per account number
No_CCs = random.choice(Number_CC)
#Generate account number
acct = start + 1 + randrange(1, 10, 1)
start = acct
#Randomly generate customer name + middle name in tmp
name = fake.name()
tmp = gen_data.create_name()
#Adds account number to account dictionary
acct_list.extend([acct])
#Creates a new row and adds data elements
row = [i] + [acct] + [random.choice(Acct_Type)] + [No_CCs] + [name] + [
tmp[0]
] + [liSSNMaster[i]]
#Dictionary for names list set to blank
names = []
#Dictionary for Social Security Number list set to blank
ssn = []
#Middle Name to reduce name dups
mdl = []
for j in range(No_CCs - 1):
names.insert(j, fake.name())
tmp2 = gen_data.create_name()
mdl.insert(j, tmp2[0])
##Pull from SSN Master list
randInt = randrange(1, len(liSSNMaster), 1)
if randInt != i:
ssn.insert(j, liSSNMaster[randInt])
else:
ssn.insert(j, liSSNMaster[randInt - 1])
#Name and SSN is set to blank if less than 4 customers on an account
for k in range(4 - No_CCs):
names.insert(No_CCs + k, '')
ssn.insert(No_CCs + k, '')
mdl.insert(No_CCs, '')
#Sets CC_NO to a random credit card number
CC_NO = gen_data.cc_number()
#Extract CC_Number from the tuple returned by CC_Number then scramble to ensure uniqueness...Tuple contains CC Number and Type
CC_TRANS = CC_NO[1][0]
dt = str(datetime.now())
clean = re.sub('\W', '', dt)
printCC = str(CC_TRANS[-4:]) + str(clean[-12:-3]) + str(
randrange(1111, 9999, randrange(1, 10, 1)))
#Add data elements to current csv row
row.extend([names[0],mdl[0],ssn[0],names[1],mdl[1],ssn[1],names[2],mdl[2],ssn[2],printCC,CC_NO[0],gen_data.create_company_name()+' '+tmp[1],\
gen_data.create_email(),gen_data.create_job_title()])
#Create Current Address
zip = random.choice(zips.zip)
addr = geo_data.create_city_state_zip[zip]
#Create Previous address
zip2 = random.choice(zips.zip)
addr2 = geo_data.create_city_state_zip[zip2]
#Add additional data elements to current csv row
lrg_cash_ex = random.choice(Yes_No)
#Condition for SARs and Demarketed Clients
if (Clsd == 'Yes'):
#1% of closed accounts are demarketed but never had a SAR filed
if (max((randrange(0, 101, 1) - 99), 0) == 1 and SAR == 'No'):
demarket = 'Yes'
dem_date = gen_data.create_date(past=True)
if (max((randrange(0, 11, 1) - 9), 0) == 1 and demarket == 'No'):
#10% of closed accounts have SARs
SAR = 'Yes'
#90% of closed accounts with SARs are demarketed
if (max((randrange(0, 11, 1) - 9), 0) == 0):
demarket = 'Yes'
dem_date = gen_data.create_date(past=True)
if (max((randrange(0, 101, 1) - 99), 0) == 1):
PEP = 'Yes'
row.extend([
addr[0], addr[1], zip, 'US', addr2[0], addr2[1], zip2, 'US',
gen_data.create_birthday(min_age=2, max_age=85), PEP, SAR, Clsd
])
#Start Generating related accounts from account list once 10,000 accounts are generated - to avoid duplicating accounts in the beginning
if i > 10000:
rel = int(random.choice(acct_list)) * max(
(randrange(0, 10001, 1) - 9999), 0)
if rel <> 0:
row.append(rel)
row.append(random.choice(Related_Type))
else:
row.append('')
row.append('')
else:
row.append('')
row.append('')
#Randomly generates account start date
party_start = gen_data.create_date(past=True)
#Randomly selects consent option for sharing info
Consent_Share = random.choice(Yes_No_Consent)
#Add additional data elements to current csv row
row.extend([random.choice(Party_Type),random.choice(Party_Relation),party_start,gen_data.create_date(past=True),\
lrg_cash_ex,demarket,dem_date,randrange(0,100,1),random.choice(Official_Lang)])
#Add data element preferred methond of contact for yes to share info...if not then blank to current row
if Consent_Share == 'Yes':
row.extend(['Yes', random.choice(Preffered_Channel)])
else:
row.extend(['No', ''])
row.extend([zip, randrange(0, 5, 1)])
#Generate Segment ID then add additional Segment data based on the selection to the current csv row
Segment_ID = randrange(0, 5, 1) % 5
if Segment_ID == 0:
row.extend([
Model_ID[0], Seg_Model_Type[0], Seg_Model_Name[0],
Seg_Model_Group[0], Seg_Model_Description[0],
Seg_Model_Score[0]
])
if Segment_ID == 1:
row.extend([
Model_ID[1], Seg_Model_Type[1], Seg_Model_Name[1],
Seg_Model_Group[1], Seg_Model_Description[1],
Seg_Model_Score[1]
])
if Segment_ID == 2:
row.extend([
Model_ID[2], Seg_Model_Type[2], Seg_Model_Name[2],
Seg_Model_Group[2], Seg_Model_Description[2],
Seg_Model_Score[2]
])
if Segment_ID == 3:
row.extend([
Model_ID[3], Seg_Model_Type[3], Seg_Model_Name[3],
Seg_Model_Group[3], Seg_Model_Description[3],
Seg_Model_Score[3]
])
if Segment_ID == 4:
row.extend([
Model_ID[4], Seg_Model_Type[4], Seg_Model_Name[4],
Seg_Model_Group[4], Seg_Model_Description[4],
Seg_Model_Score[4]
])
#Add additional data elements to current csv row
hr0 = random.choice(Arms_Manufacturer)
hr01 = random.choice(Auction)
hr02 = random.choice(CashIntensive_Business)
hr03 = random.choice(Casino_Gambling)
hr04 = random.choice(Channel_Onboarding)
hr05 = random.choice(Channel_Ongoing_Transactions)
row.extend([hr0, hr01, hr02, hr03, hr04, hr05])
#Randomly select whether customer has a High Net Worth
HighNetWorthFlag = random.choice(HighNetWorth)
#Randomly Generate customer net worth based on the above flag
if HighNetWorthFlag == 'Yes':
row.append(
max(
max((randrange(0, 101, 1) - 99), 0) *
randrange(1000000, 25000000, 1),
randrange(1000000, 5000000, 1)))
else:
flag = random.choice(LowNet)
if flag == 0:
row.append(randrange(-250000, 600000, 1))
else:
if flag == 1:
row.append(randrange(149000, 151000, 1))
else:
row.append(randrange(40000, 50000, 1))
#Add data elements to current csv row
hr1 = random.choice(Complex_HI_Vehicle)
hr2 = random.choice(Dealer_Precious_Metal)
hr3 = random.choice(Digital_PM_Operator)
hr4 = random.choice(Embassy_Consulate)
hr5 = random.choice(Exchange_Currency)
hr6 = random.choice(Foreign_Financial_Institution)
hr7 = random.choice(Foreign_Government)
hr8 = random.choice(Foreign_NonBank_Financial_Institution)
hr9 = random.choice(Internet_Gambling)
hr10 = random.choice(Medical_Marijuana_Dispensary)
hr11 = random.choice(Money_Service_Business)
hr12 = random.choice(NAICS.NAICS_Code)
hr13 = random.choice(NonRegulated_Financial_Institution)
hr14 = random.choice(Not_Profit)
#hr15=random.choice(Occupation) - added before through gen_data
hr16 = random.choice(Privately_ATM_Operator)
hr17 = random.choice(Products)
hr18 = random.choice(Sales_Used_Vehicles)
hr19 = random.choice(Services)
hr20 = random.choice(SIC_Code)
hr21 = random.choice(Stock_Market_Listing)
hr22 = random.choice(Third_Party_Payment_Processor)
hr23 = random.choice(Transacting_Provider)
if (PEP == 'Yes' or SAR == 'Yes' or lrg_cash_ex == 'Yes'
or demarket == 'Yes' or hr0 == 'Yes' or hr01 == 'Yes'
or hr02 == 'Yes' or hr03 == 'Yes' or hr1 == 'Yes'
or hr2 == 'Yes' or hr3 == 'Yes' or hr4 == 'Yes' or hr5 == 'Yes'
or hr6 == 'Yes' or hr7 == 'Yes' or hr8 == 'Yes' or hr9 == 'Yes'
or hr10 == 'Yes' or hr11 == 'Yes' or hr13 == 'Yes'
or hr14 == 'Yes' or hr16 == 'Yes' or hr17 == 'Yes'
or hr18 == 'Yes' or hr22 == 'Yes' or hr23 == 'Yes'
or HighNetWorthFlag == 'Yes'):
high_risk = 'Yes'
hr_rating = random.choice(refrating)
if (SAR == 'No' and high_risk == 'No'):
if (max((randrange(0, 101, 1) - 99), 0) == 1):
high_risk = 'Yes'
hr_rating = random.choice(refrating)
if (PEP == 'No' and high_risk == 'No'):
if (max((randrange(0, 101, 1) - 99), 0) == 1):
high_risk = 'Yes'
hr_rating = random.choice(refrating)
if (high_risk == 'No'):
if (max((randrange(0, 101, 1) - 99), 0) == 1):
high_risk = 'Yes'
hr_rating = random.choice(refrating)
row.extend([
hr1, hr2, hr3, hr4, hr5, hr6, hr7, hr8, hr9, hr10, hr11, hr12,
hr13, hr14, hr16, hr17, hr18, hr19, hr20, hr21, hr22, hr23,
HighNetWorthFlag, high_risk, hr_rating,
random.choice(Use_Case)
])
liCSV.append(row)
return liCSV
from random import random
from random import shuffle
from faker import Faker
from barnum import gen_data
import csv
fake = Faker()
with open('large.csv','w') as f1:
writer=csv.writer(f1, delimiter=',',lineterminator='\n',)
writer.writerow(['rownum'] +['dunno'] + ['CC'] + ['Employer'] + ['Custemail'] + ['name'] \
+ ['occupation'] + ['address_street'] + ['DOB']+['previous address_city_state_zip']+ ['altcustomer_name'] \
+ ['altcustomer_occupation'] + ['altcustomer_dob'] + ['ssn'] + ['phone'] + \
['AccountID'] + ['PepFlag'] + ['altcustomerssn'] + ['demarketed_customer_flag'] + \
['SAR_flag'] + ['nolonger_a_customer'] + ['closed_account'] +['High_risk_flag'] +['Risk_rating'])
for i in range(50000000):
row = [i] + [10] + [gen_data.cc_number()]+[gen_data.create_company_name()] + \
[gen_data.create_email()]+[gen_data.create_name()] +[gen_data.create_job_title()] + \
[gen_data.create_city_state_zip()] + [gen_data.create_birthday(min_age=2, max_age=85)] + \
[gen_data.create_city_state_zip()] + [fake.name()] + [gen_data.create_job_title()] + \
[gen_data.create_birthday(min_age=2, max_age=85)] +\
[(randrange(101,1000,1),randrange(10,100,1),randrange(1000,10000,1))] + \
[(randrange(101,1000,1),randrange(101,999,1),randrange(1000,10000,1))] + \
[randrange(100000,100000000,1)] + \
[max((randrange(0,101,1)-99),0)] + \
[(randrange(101,1000,1),randrange(10,100,1),randrange(1000,10000,1))] + \
[max((randrange(0,101,1)-99),0)] + [max((randrange(0,101,1)-99),0)] + \
[max((randrange(0,101,1)-99),0)] + [max((randrange(0,101,1)-90),0)] + \
[max((randrange(0,101,1)-99),0)] + [max((randrange(0,101,1)-99),0)]
writer.writerow(row)
def gen_cust(liSSNMaster, acct_list, i):
fake = Faker()
#Initiate High Risk Flags
#Politically Exposed Person
PEP = 'No'
#Customer with a Suspicous Activity Report
SAR = 'No'
#Customer with a closed account
#generate closed acct flag
Clsd = choice(Clsd_flag)
#High risk customer flag
high_risk = 'No'
#High Risk Rating
hr_rating = ''
#Customer that was demarketed by the bank
demarket = 'No'
dem_date = ''
#Random choice for number of credit cards per account number
No_CCs = choice(Number_CC)
acct = start + 1 + randrange(1, 10, 1)
start = acct
#Randomly generates customer name
name = fake.name()
tmp = gen_data.create_name()
#Adds account number to account dictionary
acct_list.extend([acct])
#Creates a new row and adds data elements
## JS - Main Account Holder SSN as current index in master SSN list
row = [i] + [acct] + [choice(Acct_Type)
] + [No_CCs] + [name] + [tmp[0]] + [liSSNMaster[i]]
#Dictionary for names list set to blank
names = []
#Dictionary for Social Security Number list set to blank
ssn = []
#Generates Name and SSN for Credit Users
#Middle Name to reduce name dups
mdl = []
for j in range(No_CCs - 1):
names.insert(j, fake.name())
tmp2 = gen_data.create_name()
mdl.insert(j, tmp2[0])
## JS - Pull from SSN Master list
randInt = randrange(1, len(liSSNMaster), 1)
if randInt != i:
ssn.insert(j, liSSNMaster[randInt])
else:
ssn.insert(j, liSSNMaster[randInt - 1])
#Name and SSN is set to blank if less than 4 customers on an account
for k in range(4 - No_CCs):
names.insert(No_CCs + k, '')
ssn.insert(No_CCs + k, '')
mdl.insert(No_CCs, '')
#Sets CC_NO to a random credit card number
CC_NO = gen_data.create_cc_number()
CC_TRANS = CC_NO[1][0]
dt = str(datetime.now())
clean = re.sub('\W', '', dt)
printCC = str(CC_TRANS[-4:]) + str(clean[-12:-3]) + str(
randrange(1111, 9999, randrange(1, 10, 1)))
#Add data elements to current csv row
row.extend([names[0],mdl[0],ssn[0],names[1],mdl[1],ssn[1],names[2],mdl[2],ssn[2],printCC,CC_NO[0],gen_data.create_company_name()+' '+tmp[1],\
gen_data.create_email(),gen_data.create_job_title()])
#Creates Current Address
zip = choice(zips.zip)
addr = geo_data.create_city_state_zip[zip]
#Creates Previous address
zip2 = choice(zips.zip)
addr2 = geo_data.create_city_state_zip[zip2]
#Add additional data elements to current csv row
lrg_cash_ex = choice(Yes_No)
#Condition for SARs and Demarketed Clients
if (Clsd == 'Yes'):
#1% of closed accounts are demarketed but never had a SAR filed
if (max((randrange(0, 101, 1) - 99), 0) == 1 and SAR == 'No'):
demarket = 'Yes'
dem_date = gen_data.create_date(past=True)
if (max((randrange(0, 11, 1) - 9), 0) == 1 and demarket == 'No'):
#10% of closed accounts have SARs
SAR = 'Yes'
#90% of closed accounts with SARs are demarketed
if (max((randrange(0, 11, 1) - 9), 0) == 0):
demarket = 'Yes'
dem_date = gen_data.create_date(past=True)
#1% of accounts are PEP
if (max((randrange(0, 101, 1) - 99), 0) == 1):
PEP = 'Yes'
row.extend([
addr[0], addr[1], zip, 'US', addr2[0], addr2[1], zip2, 'US',
gen_data.create_birthday(min_age=2, max_age=85), PEP, SAR, Clsd
])
#Start Generating related accounts from account list once 10,000 accounts are generated
if i > 10000:
rel = int(choice(acct_list)) * max((randrange(0, 10001, 1) - 9999), 0)
if rel <> 0:
row.append(rel)
row.append(choice(Related_Type))
else:
row.append('')
row.append('')
else:
row.append('')
row.append('')
#Randomly generates account start date
party_start = gen_data.create_date(past=True)
#Randomly selects consent option for sharing info
Consent_Share = choice(Yes_No_Consent)
#Add additional data elements to current csv row
row.extend([choice(Party_Type),choice(Party_Relation),party_start,gen_data.create_date(past=True),\
lrg_cash_ex,demarket,dem_date,randrange(0,100,1),choice(Official_Lang)])
#Add data element preferred methond of contact for yes to share info...if not then blank to current row
if Consent_Share == 'Yes':
row.extend(['Yes', choice(Preffered_Channel)])
else:
row.extend(['No', ''])
#DO NOT USE CUST STATUS BELOW - NOT INTEGRATED WITH CLOSED STATUS! Add additional data elements to current csv row
row.extend([zip, randrange(0, 5, 1)])
#Generates Segment ID then adds additional Segment data based on the selection to the current csv row
Segment_ID = randrange(0, 5, 1)
if Segment_ID == 0:
row.extend(
['01', 'LOB Specific', 'IRRI', 'Group 1', 'High Risk Tier', '200'])
if Segment_ID == 1:
row.extend([
'02', 'Profitability', 'CRS Risk Score', 'Group 1',
'Mid Risk Tier', '300'
])
if Segment_ID == 2:
row.extend([
'03', 'Geographical', 'Geo Risk', 'Group 2', 'Low Risk Tier', '400'
])
if Segment_ID == 3:
row.extend([
'04', 'Behavioral', 'Financial Behavior Risk', 'Group 3',
'Vertical Risk', '100'
])
if Segment_ID == 4:
row.extend([
'05', 'Risk Tolerance', 'CM Risk', 'Group 4', 'Geographical Risk',
'500'
])
#Arms Manufacturer random choice
hr0 = choice(Yes_No_Cust_Flag)
#Auction random choice
hr01 = choice(Yes_No_Cust_Flag)
#Cash Intensive Business random choice
hr02 = choice(Yes_No_Cust_Flag)
#Casino Gambling random choice
hr03 = choice(Yes_No_Cust_Flag)
#Channel Onboarding random choice
hr04 = choice(Channel_Onboarding)
#Channel Ongoing Transactions random choice
hr05 = choice(Channel_Ongoing_Transactions)
#Add additional data elements to current csv row
row.extend([hr0, hr01, hr02, hr03, hr04, hr05])
#Randomly select whther customer has a High Net Worth
HighNetWorthFlag = choice(HighNetWorth)
#Randomly Generates customer net worth based on the above flag
if HighNetWorthFlag == 'Yes':
row.append(
max(
max((randrange(0, 101, 1) - 99), 0) *
randrange(5000000, 25000000, 1),
randrange(1000000, 5000000, 1)))
else:
flag = choice(LowNet)
if flag == 0:
row.append(randrange(-250000, 600000, 1))
else:
if flag == 1:
row.append(randrange(149000, 151000, 1))
else:
row.append(randrange(40000, 50000, 1))
#Add data elements to current csv row
#Complex_HI_Vehicle random choice
hr1 = choice(Yes_No_Cust_Flag)
#Dealer_Precious_Metal random choice
hr2 = choice(Yes_No_Cust_Flag)
#Digital_PM_Operator random choice
hr3 = choice(Yes_No_Cust_Flag)
#Embassy_Consulate random choice
hr4 = choice(Yes_No_Cust_Flag)
#Exchange_Currency random choice
hr5 = choice(Yes_No_Cust_Flag)
#Foreign_Financial_Institution random choice
hr6 = choice(Yes_No_Cust_Flag)
#Foreign_Government random choice
hr7 = choice(Yes_No_Cust_Flag)
#Foreign_NonBank_Financial_Institution random choice
hr8 = choice(Yes_No_Cust_Flag)
#Internet_Gambling random choice
hr9 = choice(Yes_No_Cust_Flag)
#Medical_Marijuana_Dispensary random choice
hr10 = choice(Yes_No_Cust_Flag)
#Money_Service_Business random choice
hr11 = choice(Yes_No_Cust_Flag)
hr12 = choice(NAICS.NAICS_Code)
#NonRegulated_Financial_Institution random choice
hr13 = choice(Yes_No_Cust_Flag)
#Not_Profit random choice
hr14 = choice(Yes_No_Cust_Flag)
#Occupation random choice
#hr15=choice(Occupation)
#Privately_ATM_Operator random choice
hr16 = choice(Yes_No_Cust_Flag)
#Products random choice
hr17 = choice(Products)
#Sales_Used_Vehicles random choice
hr18 = choice(Yes_No_Cust_Flag)
#Services random choice
hr19 = choice(Services)
#SIC_Code random choice
hr20 = choice(SIC_Code)
#Stock_Market_Listing random choice
hr21 = choice(Stock_Market_Listing)
#Third_Party_Payment_Processor random choice
hr22 = choice(Yes_No_Cust_Flag)
#Transacting_Provider random choice
hr23 = choice(Yes_No_Cust_Flag)
refrating = ['1'] * 3 + ['2', '4'] * 2 + ['3'] + ['5'] * 12
if (PEP == 'Yes' or SAR == 'Yes' or lrg_cash_ex == 'Yes'
or demarket == 'Yes' or hr0 == 'Yes' or hr01 == 'Yes'
or hr02 == 'Yes' or hr03 == 'Yes' or hr1 == 'Yes' or hr2 == 'Yes'
or hr3 == 'Yes' or hr4 == 'Yes' or hr5 == 'Yes' or hr6 == 'Yes'
or hr7 == 'Yes' or hr8 == 'Yes' or hr9 == 'Yes' or hr10 == 'Yes'
or hr11 == 'Yes' or hr13 == 'Yes' or hr14 == 'Yes' or hr16 == 'Yes'
or hr17 == 'Yes' or hr18 == 'Yes' or hr22 == 'Yes' or hr23 == 'Yes'
or HighNetWorthFlag == 'Yes'):
high_risk = 'Yes'
hr_rating = choice(refrating)
if (high_risk == 'No'):
if (max((randrange(0, 101, 1) - 99), 0) == 1):
high_risk = 'Yes'
hr_rating = choice(refrating)
row.extend([
hr1, hr2, hr3, hr4, hr5, hr6, hr7, hr8, hr9, hr10, hr11, hr12, hr13,
hr14, hr16, hr17, hr18, hr19, hr20, hr21, hr22, hr23, HighNetWorthFlag,
high_risk, hr_rating,
choice(Use_Case)
])
#End the current row
return row
+ ["High_risk_flag"]
+ ["Risk_rating"]
)
while i < 50000000:
# Pick an account number and store it in acct
acct = randrange(100000, 100000000, 1)
# if the account hasn't been already generated then generate a record with all fields
if d.has_key(str(acct)) == False:
row = (
[i]
+ [10]
+ [gen_data.cc_number()]
+ [gen_data.create_company_name()]
+ [gen_data.create_email()]
+ [gen_data.create_name()]
+ [gen_data.create_job_title()]
+ [gen_data.create_city_state_zip()]
+ [gen_data.create_birthday(min_age=2, max_age=85)]
+ [gen_data.create_city_state_zip()]
+ [fake.name()]
+ [gen_data.create_job_title()]
+ [gen_data.create_birthday(min_age=2, max_age=85)]
+ [(randrange(101, 1000, 1), randrange(10, 100, 1), randrange(1000, 10000, 1))]
+ [(randrange(101, 1000, 1), randrange(101, 999, 1), randrange(1000, 10000, 1))]
+ [acct]
+ [max((randrange(0, 101, 1) - 99), 0)]
+ [(randrange(101, 1000, 1), randrange(10, 100, 1), randrange(1000, 10000, 1))]
+ [max((randrange(0, 101, 1) - 99), 0)]
+ [max((randrange(0, 101, 1) - 99), 0)]
+ [max((randrange(0, 101, 1) - 99), 0)]
+ [max((randrange(0, 101, 1) - 90), 0)]
#Sets CC_NO to a random credit card number
CC_NO = gen_data.create_cc_number()
#Extract CC_Number from the tuple returned by CC_Number...Tuple contains CC Number and Type
#while CC_list.count(CC_NO[1][0]) > 0:
CC_TRANS = CC_NO[1][0]
dt = str(datetime.now())
clean = re.sub('\W', '', dt)
printCC = str(CC_TRANS[-4:]) + str(clean[-12:-3]) + str(
randrange(1111, 9999, randrange(1, 10, 1)))
#str(CC_TRANS[-4:])+str(clean[-12:-2])+str(randrange(1111,9999,randrange(1,10,1)))
#Add CC_Number to control list to prevent duplicates
#Add data elements to current csv row
row.extend([names[0],mdl[0],ssn[0],names[1],mdl[1],ssn[1],names[2],mdl[2],ssn[2],printCC,CC_NO[0],gen_data.create_company_name()+' '+tmp[1],\
gen_data.create_email(),gen_data.create_job_title()])
#Creates Current Address
zip = random.choice(zips.zip)
addr = geo_data.create_city_state_zip[zip]
#Creates Previous address
zip2 = random.choice(zips.zip)
addr2 = geo_data.create_city_state_zip[zip2]
#Add additional data elements to current csv row
lrg_cash_ex = random.choice(Yes_No)
#Condition for SARs and Demarketed Clients
if (Clsd == 'Yes'):
#1% of closed accounts are demarketed but never had a SAR filed
if (max((randrange(0, 101, 1) - 99), 0) == 1 and SAR == 'No'):
def __init__(self, i, acct, liSSNMaster, acct_list):
self.ROWNUM = i
self.ACCOUNTID = acct
self.SSN = liSSNMaster[i]
self.ACCT_TYPE = choice(Acct_Type)
self.NUM_CCS = choice(Number_CC)
self.NAME = fake.name()
self.CUSTEMAIL = gen_data.create_email()
self.OCCUPATION = gen_data.create_job_title()
self.COUNTRY = 'US'
self.PREVIOUS_COUNTRY = 'US'
self.DOB = gen_data.create_birthday(min_age=2, max_age=85)
self.PARTY_ENDDATE = gen_data.create_date(past=True)
self.CONSENT_SHARING = choice(Yes_No_Consent)
self.LARGE_CASH_EXEMPT = choice(Yes_No)
self.PARTY_TYPE = choice(Party_Type)
self.PARTY_RELATION = choice(Party_Relation)
self.PROB_DEFAULT_RISKR = randrange(0, 100, 1)
self.OFFICIAL_LANG_PREF = choice(Official_Lang)
self.DEPENDANTS_COUNT = randrange(0, 5, 1)
self.USE_CASE_SCENARIO = choice(Use_Case)
self.CLOSEDACCOUNT = choice(Clsd_flag)
self.HIGH_NET_WORTH = choice(HighNetWorth)
self.PARTY_STARTDATE = gen_data.create_date(past=True)
self.ARMS_MANUFACTURER = choice(Yes_No_Cust_Flag)
self.AUCTION = choice(Yes_No_Cust_Flag)
self.CASHINTENSIVE_BUSINESS = choice(Yes_No_Cust_Flag)
self.CASINO_GAMBLING = choice(Yes_No_Cust_Flag)
self.CHANNEL_ONBOARDING = choice(Channel_Onboarding)
self.CHANNEL_ONGOING_TRANSACTIONS = choice(
Channel_Ongoing_Transactions)
self.COMPLEX_HI_VEHICLE = choice(Yes_No_Cust_Flag)
self.DEALER_PRECIOUS_METAL = choice(Yes_No_Cust_Flag)
self.DIGITAL_PM_OPERATOR = choice(Yes_No_Cust_Flag)
self.EMBASSY_CONSULATE = choice(Yes_No_Cust_Flag)
self.EXCHANGE_CURRENCY = choice(Yes_No_Cust_Flag)
self.FOREIGN_FINANCIAL_INSTITUTION = choice(Yes_No_Cust_Flag)
self.FOREIGN_GOVERNMENT = choice(Yes_No_Cust_Flag)
self.FOREIGN_NONBANK_FINANCIAL_INSTITUTION = choice(Yes_No_Cust_Flag)
self.INTERNET_GAMBLING = choice(Yes_No_Cust_Flag)
self.MEDICAL_MARIJUANA_DISPENSARY = choice(Yes_No_Cust_Flag)
self.MONEY_SERVICE_BUSINESS = choice(Yes_No_Cust_Flag)
self.NAICS_CODE = choice(NAICS.NAICS_Code)
self.NONREGULATED_FINANCIAL_INSTITUTION = choice(Yes_No_Cust_Flag)
self.NOT_PROFIT = choice(Yes_No_Cust_Flag)
self.PRIVATELY_ATM_OPERATOR = choice(Yes_No_Cust_Flag)
self.PRODUCTS = choice(Products)
self.SALES_USED_VEHICLES = choice(Yes_No_Cust_Flag)
self.SERVICES = choice(Services)
self.SIC_CODE = choice(SIC_Code)
self.STOCK_MARKET_LISTING = choice(Stock_Market_Listing)
self.THIRD_PARTY_PAYMENT_PROCESSOR = choice(Yes_No_Cust_Flag)
self.TRANSACTING_PROVIDER = choice(Yes_No_Cust_Flag)
self.ZIP = choice(zips.zip)
self.PREVIOUS_ZIP = choice(zips.zip)
addr = geo_data.create_city_state_zip[self.ZIP]
addr2 = geo_data.create_city_state_zip[self.PREVIOUS_ZIP]
self.CITY = addr[0]
self.STATE = addr[1]
self.PREVIOUS_CITY = addr2[0]
self.PREVIOUS_STATE = addr2[1]
self.PRIMARY_BRANCH_NO = self.ZIP
tmp = gen_data.create_name()
self.M_NAME = tmp[0]
self.EMPLOYER = gen_data.create_company_name() + ' ' + tmp[1]
No_CCs = choice(Number_CC)
#Dictionary for names list set to blank
names = []
#Dictionary for Social Security Number list set to blank
ssn = []
#Middle Name to reduce name dups
mdl = []
#Generates Name and SSN for Credit Users
for j in range(4):
if No_CCs > j:
names.insert(j, fake.name())
tmp2 = gen_data.create_name()
mdl.insert(j, tmp2[0])
randInt = randrange(1, len(liSSNMaster), 1)
if randInt != i:
ssn.insert(j, liSSNMaster[randInt])
else:
ssn.insert(j, liSSNMaster[randInt - 1])
#Name and SSN is set to blank if less than 4 customers on an account
else:
names.insert(No_CCs + j, '')
ssn.insert(No_CCs + j, '')
mdl.insert(No_CCs + j, '')
self.AUTHORIZED_NAME2 = names[0]
self.M_NAME2 = mdl[0]
self.SSN2 = ssn[0]
self.AUTHORIZED_NAME3 = names[1]
self.M_NAME3 = mdl[1]
self.SSN3 = ssn[1]
self.AUTHORIZED_NAME4 = names[2]
self.M_NAME4 = mdl[2]
self.SSN4 = ssn[2]
#Sets CC_NO to a random credit card number
CC_NO = gen_data.create_cc_number()
CC_TRANS = CC_NO[1][0]
dt = str(datetime.now())
clean = re.sub('\W', '', dt)
self.CREDITCARDNUMBER = str(CC_TRANS[-4:]) + str(clean[-12:-3]) + str(
randrange(1111, 9999, randrange(1, 10, 1)))
self.CREDITCARDTYPE = CC_NO[0]
self.RELATED_ACCT = ''
self.RELATED_TYPE = ''
if i > 10000:
rel = int(choice(acct_list)) * max(
(randrange(0, 10001, 1) - 9999), 0)
if rel <> 0:
self.RELATED_ACCT = rel
self.RELATED_TYPE = choice(Related_Type)
self.PREFERRED_CHANNEL = ''
if self.CONSENT_SHARING == 'Yes':
self.PREFERRED_CHANNEL = choice(Prefered_Channel)
## #Generates Segment ID then adds additional Segment data based on the selection to the current csv row
Segment_ID = randrange(0, 5, 1)
if Segment_ID == 0:
self.SEG_MODEL_ID = '01'
self.SEG_MODEL_TYPE = 'LOB Specific'
self.SEG_MODEL_NAME = 'IRRI'
self.SEG_MODEL_GROUP = 'Group 1'
self.SEG_M_GRP_DESC = 'High Risk Tier'
self.SEG_MODEL_SCORE = '200'
if Segment_ID == 1:
self.SEG_MODEL_ID = '02'
self.SEG_MODEL_TYPE = 'Profitability'
self.SEG_MODEL_NAME = 'CRS Risk Score'
self.SEG_MODEL_GROUP = 'Group 1'
self.SEG_M_GRP_DESC = 'Mid Risk Tier'
self.SEG_MODEL_SCORE = '300'
if Segment_ID == 2:
self.SEG_MODEL_ID = '03'
self.SEG_MODEL_TYPE = 'Geographical'
self.SEG_MODEL_NAME = 'Geo Risk'
self.SEG_MODEL_GROUP = 'Group 2'
self.SEG_M_GRP_DESC = 'Low Risk Tier'
self.SEG_MODEL_SCORE = '400'
if Segment_ID == 3:
self.SEG_MODEL_ID = '04'
self.SEG_MODEL_TYPE = 'Behavioral'
self.SEG_MODEL_NAME = 'Financial Behavior Risk'
self.SEG_MODEL_GROUP = 'Group 3'
self.SEG_M_GRP_DESC = 'Vertical Risk'
self.SEG_MODEL_SCORE = '100'
if Segment_ID == 4:
self.SEG_MODEL_ID = '05'
self.SEG_MODEL_TYPE = 'Risk Tolerance'
self.SEG_MODEL_NAME = 'CM Risk'
self.SEG_MODEL_GROUP = 'Group 4'
self.SEG_M_GRP_DESC = 'Geographical Risk'
self.SEG_MODEL_SCORE = '500'
self.CLIENT_NET_WORTH = ''
if self.HIGH_NET_WORTH == 'Yes':
self.CLIENT_NET_WORTH = max(
max((randrange(0, 101, 1) - 99), 0) *
randrange(5000000, 25000000, 1),
randrange(1000000, 5000000, 1))
else:
flag = choice(LowNet)
if flag == 0:
self.CLIENT_NET_WORTH = randrange(-250000, 600000, 1)
else:
if flag == 1:
self.CLIENT_NET_WORTH = randrange(149000, 151000, 1)
else:
self.CLIENT_NET_WORTH = randrange(40000, 50000, 1)
#Politically Exposed Person
self.PEP = 'No'
#1% of accounts are PEP
if (max((randrange(0, 101, 1) - 99), 0) == 1):
self.PEP = 'Yes'
#Customer that was demarketed by the bank
self.DEMARKET_FLAG = 'No'
self.DEMARKET_DATE = ''
#Customer with a Suspicous Activity Report
self.SAR = 'No'
#Customer with a closed account
#generate closed acct flag
#Condition for SARs and Demarketed Clients
if (self.CLOSEDACCOUNT == 'Yes'):
#1% of closed accounts are demarketed but never had a SAR filed
if (max((randrange(0, 101, 1) - 99), 0) == 1):
self.DEMARKET_FLAG = 'Yes'
self.DEMARKET_DATE = gen_data.create_date(past=True)
if (self.DEMARKET_FLAG == 'No' and max(
(randrange(0, 11, 1) - 9), 0) == 1):
#10% of closed accounts have SARs
self.SAR = 'Yes'
#90% of closed accounts with SARs are demarketed
if (max((randrange(0, 11, 1) - 9), 0) == 0):
self.DEMARKET_FLAG = 'Yes'
self.DEMARKET_DATE = gen_data.create_date(past=True)
self.HIGH_RISK = 'No'
self.RISK_RATING = ''
if (self.PEP == 'Yes' or self.SAR == 'Yes'
or self.LARGE_CASH_EXEMPT == 'Yes'
or self.DEMARKET_FLAG == 'Yes'
or self.ARMS_MANUFACTURER == 'Yes' or self.AUCTION == 'Yes'
or self.CASHINTENSIVE_BUSINESS == 'Yes'
or self.CASINO_GAMBLING == 'Yes'
or self.COMPLEX_HI_VEHICLE == 'Yes'
or self.DEALER_PRECIOUS_METAL == 'Yes'
or self.DIGITAL_PM_OPERATOR == 'Yes'
or self.EMBASSY_CONSULATE == 'Yes'
or self.EXCHANGE_CURRENCY == 'Yes'
or self.FOREIGN_FINANCIAL_INSTITUTION == 'Yes'
or self.FOREIGN_GOVERNMENT == 'Yes'
or self.FOREIGN_NONBANK_FINANCIAL_INSTITUTION == 'Yes'
or self.INTERNET_GAMBLING == 'Yes'
or self.MEDICAL_MARIJUANA_DISPENSARY == 'Yes'
or self.MONEY_SERVICE_BUSINESS == 'Yes'
or self.NONREGULATED_FINANCIAL_INSTITUTION == 'Yes'
or self.NOT_PROFIT == 'Yes'
or self.PRIVATELY_ATM_OPERATOR == 'Yes'
or self.SALES_USED_VEHICLES == 'Yes'
or self.THIRD_PARTY_PAYMENT_PROCESSOR == 'Yes'
or self.TRANSACTING_PROVIDER == 'Yes'
or self.HIGH_NET_WORTH == 'Yes'):
self.HIGH_RISK = 'Yes'
self.RISK_RATING = choice(refrating)
elif (max((randrange(0, 101, 1) - 99), 0) == 1):
self.HIGH_RISK = 'Yes'
self.RISK_RATING = choice(refrating)
