def run(batch_id, source_file_name, output_file_name, source_service_resources, delta=timedelta(days=14)):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
data_gen.add_formula_column('Start',
lambda cv: "" if cv['Start'] == "" else (dateutil.parser.parse(cv['Start']) + timedelta(days=delta.days - 1)).replace(tzinfo=None))
data_gen.add_formula_column('End',
lambda cv: "" if cv['End'] == "" else (dateutil.parser.parse(cv['End']) + timedelta(days=delta.days - 1)).replace(tzinfo=None))
service_resources = data_gen.load_dataset("ServiceResources", source_service_resources, ['Id', 'External_ID__c']).dict('Id', 'External_ID__c')
data_gen.add_map_column('Resource.External_Id__c', 'ResourceId', service_resources)
data_gen.apply_transformations()
data_gen.add_copy_column('CreatedDate__c', 'Start')
data_gen.apply_transformations()
data_gen.write(output_file_name, columns=[
'External_ID__c',
'Resource.External_Id__c',
'CreatedDate__c',
'Start',
'End',
'Type',
#'State',
#'Country',
#'City'
])
def run(batch_id, source_file_name, output_file_name, source_service_resources,
source_service_appointments):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
service_resources = data_gen.load_dataset("ServiceResources",
source_service_resources,
['Id', 'External_ID__c']).dict(
'Id', 'External_ID__c')
data_gen.add_map_column('ServiceResource.External_Id__c',
'ServiceResourceId', service_resources)
service_appointments = data_gen.load_dataset(
"ServiceAppointments", source_service_appointments,
['Id', 'External_ID__c']).dict('Id', 'External_ID__c')
data_gen.add_map_column('ServiceAppointment.External_Id__c',
'ServiceAppointmentId', service_appointments)
data_gen.apply_transformations()
data_gen.write(output_file_name,
columns=[
'External_ID__c', 'ServiceResource.External_Id__c',
'ServiceAppointment.External_Id__c', 'ActualTravelTime',
'EstimatedTravelTime'
])
def run(batch_id,
source_file_name,
output_file_name,
source_operating_hours,
reference_datetime=today_datetime):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
data_gen.add_constant_column('CreatedDate__c',
reference_datetime.isoformat(sep=' '))
operating_hours = data_gen.load_dataset("OperatingHours",
source_operating_hours,
['Id', 'External_ID__c']).dict(
'Id', 'External_ID__c')
data_gen.add_map_column('OperatingHours.External_Id__c',
'OperatingHoursId', operating_hours)
data_gen.apply_transformations()
data_gen.write(output_file_name,
columns=[
'External_ID__c', 'OperatingHours.External_Id__c',
'StartTime', 'EndTime'
])
def run(batch_id, source_file_name, output_file_name, source_accounts):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
accounts = data_gen.load_dataset("Accounts", source_accounts, ['Id', 'External_ID__c']).dict('Id', 'External_ID__c')
data_gen.add_map_column('Account.External_Id__c', 'AccountId', accounts)
data_gen.apply_transformations()
data_gen.write(output_file_name, columns=[
'External_ID__c',
'Account.External_Id__c',
'Subject'
])
def updateCreatedDate(source_file_name,
output_file_name,
source_service_appointments,
reference_datetime=today_datetime):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
service_appointments = data_gen.load_dataset(
"ServiceAppointments", source_service_appointments,
['External_ID__c']).dict('External_ID__c', 'External_ID__c')
service_appointments[None] = 'None'
data_gen.add_map_column('ServiceAppointment.External_Id__c',
'ServiceAppointment.External_Id__c',
service_appointments)
data_gen.apply_transformations()
data_gen.filter(lambda cv: cv['ServiceAppointment.External_Id__c'].
startswith('ServiceAppointment'))
data_gen.apply_transformations()
service_appointment_dates = data_gen.load_dataset(
"ServiceAppointmentDates", source_service_appointments,
['External_ID__c', 'CreatedDate__c']).dict('External_ID__c',
'CreatedDate__c')
service_appointment_dates[None] = reference_datetime + timedelta(days=-1)
data_gen.add_map_column('CreatedDate__c',
'ServiceAppointment.External_Id__c',
service_appointment_dates)
data_gen.apply_transformations()
data_gen.write(output_file_name,
columns=[
'External_ID__c', 'ServiceResource.External_Id__c',
'ServiceAppointment.External_Id__c', 'CreatedDate__c',
'ActualTravelTime', 'EstimatedTravelTime'
])
def run(batch_id, source_file_name, output_file_name, source_products):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
products = data_gen.load_dataset("Products", source_products,
['Id', 'External_ID__c']).dict(
'Id', 'External_ID__c')
data_gen.add_map_column('Product2.External_Id__c', 'Product2Id', products)
data_gen.add_constant_column('Pricebook2.Name', 'Standard Price Book')
data_gen.apply_transformations()
data_gen.write(output_file_name,
columns=[
'External_Id__c', 'Product2.External_Id__c', 'IsActive',
'Pricebook2.Name', 'UnitPrice'
])
def run(batch_id, source_file_name, output_file_name, source_pricebook, source_work_orders):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
pricebook = data_gen.load_dataset("Pricebook", source_pricebook, ['Id', 'External_Id__c']).dict('Id', 'External_Id__c')
data_gen.add_map_column('PricebookEntry.External_Id__c', 'PricebookEntryId', pricebook)
work_orders = data_gen.load_dataset("WorkOrders", source_work_orders, ['Id', 'External_ID__c']).dict('Id', 'External_ID__c')
data_gen.add_map_column('WorkOrder.External_Id__c', 'WorkOrderId', work_orders)
data_gen.apply_transformations()
data_gen.write(output_file_name, columns=[
'External_ID__c',
'PricebookEntry.External_Id__c',
'WorkOrder.External_Id__c',
'QuantityConsumed'
])
def run(batch_id, source_file_name, output_file_name, source_operating_hours):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
operating_hours = data_gen.load_dataset("OperatingHours", source_operating_hours, ['Id', 'External_ID__c']).dict('Id', 'External_ID__c')
data_gen.add_map_column('OperatingHours.External_Id__c', 'OperatingHoursId', operating_hours)
data_gen.apply_transformations()
data_gen.write(output_file_name, columns=[
'External_ID__c',
'Name',
'OperatingHours.External_Id__c',
'State',
'IsActive',
'Country',
'City'
])
def update(source_file_name, output_file_name, source_work_orders):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
service_appointments = data_gen.load_dataset("WorkOrders", source_work_orders, ['External_ID__c']).dict('External_ID__c', 'External_ID__c')
service_appointments[None] = 'None'
data_gen.add_map_column('WorkOrder.External_Id__c', 'WorkOrder.External_Id__c', service_appointments)
data_gen.apply_transformations()
data_gen.filter(lambda cv: cv['WorkOrder.External_Id__c'].startswith('WO.'))
data_gen.apply_transformations()
data_gen.write(output_file_name, columns=[
'External_ID__c',
'PricebookEntry.External_Id__c',
'WorkOrder.External_Id__c',
'QuantityConsumed'
])
def run(batch_id, source_file_name, output_file_name, source_cases, source_accounts, source_work_types, source_service_appointments, reference_datetime=today_datetime):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
cases = data_gen.load_dataset("Cases", source_cases, ['Id', 'External_ID__c']).dict('Id', 'External_ID__c')
data_gen.add_map_column('Case.External_Id__c', 'CaseId', cases)
accounts = data_gen.load_dataset("Accounts", source_accounts, ['Id', 'External_ID__c']).dict('Id', 'External_ID__c')
data_gen.add_map_column('Account.External_Id__c', 'AccountId', accounts)
work_types = data_gen.load_dataset("WorkTypes", source_work_types, ['Id', 'External_ID__c']).dict('Id', 'External_ID__c')
data_gen.add_map_column('WorkType.External_Id__c', 'WorkTypeId', work_types)
data_gen.add_constant_column('Pricebook2.Name', 'Standard Price Book')
service_appointment_dates = data_gen.load_dataset("ServiceAppointmentDates", source_service_appointments, ['WorkOrder.External_Id__c', 'CreatedDate__c']).dict('WorkOrder.External_Id__c', 'CreatedDate__c')
service_appointment_dates[None] = reference_datetime + timedelta(days=-1)
data_gen.add_map_column('CreatedDate__c', 'External_ID__c', service_appointment_dates)
data_gen.apply_transformations()
data_gen.filter(lambda cv: cv['WorkType.External_Id__c'].startswith('WT.'))
data_gen.apply_transformations()
data_gen.write(output_file_name, columns=[
'External_ID__c',
'CreatedDate__c',
'Status',
'Pricebook2.Name',
'Priority',
'Case.External_Id__c',
'Account.External_Id__c',
'WorkType.External_Id__c'
])
def run(batch_id, source_file_name, output_file_name, accounts_file_name, contacts_file_name):
data_gen = DataGenerator()
# load source file
source_columns = [
'External_Id__c',
'AccountExternalId__c',
'Owner.External_Id__c',
'LeadSource',
'CloseDate',
'CreatedDate__c'
]
data_gen.load_source_file(source_file_name, source_columns)
# load accounts as dataset
account_columns = [
'External_Id__c',
'Name',
'BillingState',
'Industry'
]
account_dataset = data_gen.load_dataset('accounts', accounts_file_name, account_columns)
accounts_by_id = account_dataset.group_by('External_Id__c')
# load contacts as dataset
contact_columns = [
'External_Id__c',
'FirstName',
'LastName'
]
contact_dataset = data_gen.load_dataset('contacts', contacts_file_name, contact_columns)
contacts_by_id = contact_dataset.group_by('External_Id__c')
# helper method to get account data
def get_account_data(column_values, account_column_name):
return accounts_by_id.get(column_values['ConvertedAccount.External_Id__c'])[0].get(account_column_name)
# helper method to get contact data
def get_contact_data(column_values, contact_column_name):
return contacts_by_id.get(column_values['ConvertedContact.External_Id__c'])[0].get(contact_column_name)
# rename columns
data_gen.rename_column('External_Id__c', 'ConvertedOpportunity.External_Id__c')
data_gen.rename_column('AccountExternalId__c', 'ConvertedAccount.External_Id__c')
data_gen.rename_column('CloseDate', 'ConvertedDate__c')
# generate converted lead at a random ratio
data_gen.duplicate_rows(duplication_factor=lambda: choice([0, 1], p=[.75, .25]))
# generate id
data_gen.add_formula_column('External_Id__c', formula=lambda: 'W_Lead.' + str(data_gen.current_row + 1))
# generate create date
def create_date_formula(column_values):
oppty_create_date = dateutil.parser.parse(column_values['CreatedDate__c'])
return oppty_create_date - timedelta(days=randint(0, 45))
data_gen.add_formula_column('CreatedDate__c', create_date_formula)
# generate status
data_gen.add_formula_column('Status', formula=lead.lead_status)
# generate status
data_gen.add_map_column('IsConverted', 'Status', {
'Qualified - Convert': 'true',
None: 'false'
})
# generate opportunity
data_gen.add_map_column('ConvertedOpportunity.External_Id__c', 'Status', {
'Qualified - Convert': lambda cv: cv['ConvertedOpportunity.External_Id__c'],
None: ''
})
# generate account
data_gen.add_map_column('ConvertedAccount.External_Id__c', 'Status', {
'Qualified - Convert': lambda cv: cv['ConvertedAccount.External_Id__c'],
None: ''
})
# generate contact
data_gen.add_map_column('ConvertedContact.External_Id__c', 'Status', {
'Qualified - Convert': lambda cv: cv['ConvertedAccount.External_Id__c'].replace('W_Account', 'W_Contact'),
None: ''
})
# generate converted date
data_gen.add_map_column('ConvertedDate__c', 'Status', {
'Qualified - Convert': lambda cv: cv['ConvertedDate__c'],
None: ''
})
# generate name
data_gen.add_map_column('FirstName', 'Status', {
'Qualified - Convert': lambda cv: get_contact_data(cv, 'FirstName'),
None: lambda: fake.first_name()
})
data_gen.add_map_column('LastName', 'Status', {
'Qualified - Convert': lambda cv: get_contact_data(cv, 'LastName'),
None: lambda: fake.last_name()
})
# generate company
data_gen.add_map_column('Company', 'Status', {
'Qualified - Convert': lambda cv: get_account_data(cv, 'Name'),
None: 'Not Applicable'
})
# generate industry
data_gen.add_map_column('Industry', 'Status', {
'Qualified - Convert': lambda cv: get_account_data(cv, 'Industry'),
None: ''
})
# generate state
data_gen.add_map_column('State', 'Status', {
'Qualified - Convert': lambda cv: get_account_data(cv, 'BillingState'),
None: ''
})
# generate is unread by owner
data_gen.add_map_column('IsUnreadByOwner', 'Status', {
'Qualified - Convert': 'false',
None: lead.lead_is_unread_by_owner
})
# generate rating
data_gen.add_formula_column('Rating', formula=lead.lead_rating)
# add a UUID for each row that is created in this batch
data_gen.add_constant_column('analyticsdemo_batch_id__c', batch_id)
# apply transformations and write file
data_gen.apply_transformations()
data_gen.write(output_file_name)
def run(batch_id,
source_file_name,
output_file_name,
reference_datetime=today):
data_gen = DataGenerator()
# load source file
source_columns = [
'External_Id__c', 'Owner.External_Id__c', 'CreatedDate__c',
'ClosedDate__c', 'Origin'
]
data_gen.load_source_file(source_file_name, source_columns)
data_gen.rename_column('External_Id__c', 'Case.External_Id__c')
data_gen.rename_column('ClosedDate__c', 'EndTime__c')
data_gen.duplicate_rows(duplication_factor=lambda: choice(
[1, 2, 3, 4, 5], p=[.65, .15, .10, .05, .05]))
data_gen.add_formula_column(
'External_Id__c',
lambda: 'W_LiveChatTranscript.' + str(data_gen.current_row + 1))
data_gen.add_formula_column('Abandoned__c', lambda: randint(1, 300))
data_gen.add_formula_column('AverageResponseTimeOperator__c',
lambda: randint(1, 180))
data_gen.add_formula_column('AverageResponseTimeVisitor__c',
lambda: randint(1, 180))
data_gen.add_formula_column('Body__c', formula=fake.body)
data_gen.add_formula_column('Browser__c', formula=fake.browser)
data_gen.add_constant_column('BrowserLanguage__c', 'en_US')
data_gen.add_formula_column('ChatDuration__c', lambda: randint(1, 600))
data_gen.add_formula_column('ChatKey__c', formula=fake.md5)
data_gen.add_formula_column('IpAddress__c', formula=fake.ipv4)
data_gen.add_formula_column('LiveChatButton.DeveloperName',
['Public_Website_Chat_Button'])
data_gen.add_formula_column('Location__c', formula=fake.city)
data_gen.add_formula_column('MaxResponseTimeOperator__c',
lambda: randint(1, 120))
data_gen.add_formula_column('MaxResponseTimeVisitor__c',
lambda: randint(1, 240))
data_gen.add_formula_column('Name__c',
lambda: str(data_gen.current_row + 1).zfill(8))
data_gen.add_formula_column('OperatorMessageCount__c',
lambda: randint(1, 100))
data_gen.add_formula_column(
'Platform__c', ['MacOSX', 'iOS', 'Android', 'Windows', 'Unix'])
referrer = [
"https://na17.salesforce.com/setup/forcecomHomepage.apexp?setupid=ForceCom&retURL=%2Fui%2Fsupport%2Fservicedesk%2FServiceDeskPage",
"https://na13.salesforce.com/home/home.jsp",
"https://sdodemo-main.force.com/partners/servlet/servlet.Integration?lid=01ra0000001VlbA&ic=1",
"https://sitestudio.na17.force.com/?exitURL=%2F_ui%2Fnetworks%2Fsetup%2FSetupNetworksPage%2Fd",
"https://mail.google.com/mail/u/0/",
"https://sdodemo-main.force.com/customers/servlet/servlet.Integration?lid=01ra0000001VlbP&ic=1",
"https://sdodemo-main.force.com/consumers/servlet/servlet.Integration?lid=01ro0000000EN78&ic=1",
"https://na17.salesforce.com/servlet/servlet.su?oid=00D300000007EfQ&retURL=%2F0033000000PuxU2&sunetworkuserid=005a000000AuCha&sunetworkid=0DBo0000000Gn4h",
"https://sdodemo-main.force.com/customers/servlet/servlet.Integration?ic=1&lid=01ra0000001VlbP"
]
data_gen.add_formula_column('ReferrerUri__c', referrer)
def create_date_formula(column_values):
case_create_date = dateutil.parser.parse(
column_values['CreatedDate__c'])
case_close_date = dateutil.parser.parse(column_values['EndTime__c'])
create_date = fake.date_time_between_dates(case_create_date,
case_close_date)
if create_date > reference_datetime:
create_date = reference_datetime
return create_date.isoformat(sep=' ')
data_gen.add_formula_column('CreatedDate__c', create_date_formula)
def start_time_formula(column_values):
create_date = dateutil.parser.parse(column_values['CreatedDate__c'])
start_time = create_date + timedelta(seconds=randint(1, 300))
return start_time.isoformat(sep=' ')
data_gen.add_formula_column('StartTime__c', start_time_formula)
def end_time_formula(column_values):
create_date = dateutil.parser.parse(column_values['StartTime__c'])
end_time = create_date + timedelta(seconds=randint(1, 600))
return end_time.isoformat(sep=' ')
data_gen.add_formula_column('EndTime__c', end_time_formula)
data_gen.add_copy_column('RequestTime__c', 'CreatedDate__c')
data_gen.add_formula_column(
'Status__c', lambda: choice(['Missed', 'Completed'], p=[.20, .80]))
data_gen.add_map_column('EndedBy__c', 'Status__c', {
'Completed': ['Visitor', 'Agent'],
None: 'Visitor'
})
data_gen.add_constant_column('SupervisorTranscriptBody__c', '')
data_gen.add_constant_column('ScreenResolution__c', '')
data_gen.add_formula_column('UserAgent__c', formula=fake.user_agent)
data_gen.add_formula_column('VisitorMessageCount__c',
lambda: randint(1, 50))
data_gen.add_formula_column('WaitTime__c', lambda: randint(1, 120))
def last_referenced_date_formula(column_values):
create_date = dateutil.parser.parse(column_values['CreatedDate__c'])
last_referenced_date = create_date + timedelta(seconds=randint(1, 300))
return last_referenced_date.isoformat(sep=' ')
data_gen.add_formula_column('LastReferencedDate__c',
last_referenced_date_formula)
data_gen.add_copy_column('LastViewedDate__c', 'LastReferencedDate__c')
# add a UUID for each row that is created in this batch
data_gen.add_constant_column('analyticsdemo_batch_id__c', batch_id)
def filter_func(column_values):
return column_values['Origin'] == 'Chat'
data_gen.filter(filter_function=filter_func)
# apply transformations and write file
data_gen.apply_transformations()
data_gen.sort_by('StartTime__c')
output_columns = [
'External_Id__c', 'Abandoned__c', 'AverageResponseTimeOperator__c',
'MaxResponseTimeOperator__c', 'OperatorMessageCount__c', 'Body__c',
'Browser__c', 'BrowserLanguage__c', 'Case.External_Id__c',
'ChatDuration__c', 'ChatKey__c', 'CreatedDate__c', 'StartTime__c',
'EndTime__c', 'EndedBy__c', 'LastReferencedDate__c',
'LastViewedDate__c', 'LiveChatButton.DeveloperName', 'Location__c',
'Owner.External_Id__c', 'Platform__c', 'ReferrerUri__c',
'ScreenResolution__c', 'RequestTime__c', 'Status__c',
'SupervisorTranscriptBody__c', 'UserAgent__c',
'AverageResponseTimeVisitor__c', 'IpAddress__c',
'MaxResponseTimeVisitor__c', 'VisitorMessageCount__c', 'WaitTime__c',
'analyticsdemo_batch_id__c'
]
data_gen.write(output_file_name, output_columns)
def run(source_file_name, output_file_name):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
# find mean and std of profit
profits = []
for row in data_gen.rows:
column_values = data_gen.row_to_column_values(row)
profits.append(float(column_values['Profit']))
profit_mean = mean(profits)
profit_std = std(profits)
# filter out profits more than 2 std out.
def filter_func(column_values):
profit = float(column_values['Profit'])
z_score = abs((profit - profit_mean) / profit_std)
return z_score <= 2
data_gen.filter(filter_function=filter_func)
store_tier_map = {
'New York 4': "Tier 1",
'New York 3': "Tier 1",
'New York 2': "Tier 1",
'New York 1': "Tier 1",
'Chicago 3': "Tier 1",
'Chicago 2': "Tier 2",
'Chicago 1': "Tier 2",
'Boston 2': "Tier 2",
'Boston 1': "Tier 3"
}
data_gen.add_map_column('Tier', 'Store', store_tier_map)
month_channel_map = {
'January': 'Chat',
'February': 'Chat',
'March': 'Chat',
'April': 'Chat',
'May': 'Chat',
'June': 'Email',
'July': 'Email',
'August': 'Facebook',
'September': 'Phone',
'October': 'Phone',
'November': 'Website',
'December': 'Website'
}
data_gen.add_map_column('Origin', 'Month', month_channel_map)
discount_support_map = {
'0': 'Free',
'0.05': 'Free',
'0.15': 'Basic',
'0.1': 'Silver',
'0.2': 'Platinum'
}
data_gen.add_map_column('Type_of_Support__c', 'Discount', discount_support_map)
camp_reason_map = {
"Bundled": "Documentation",
"Buy More & Save": "Unknown Failure",
"Competitor Focus": "Feature Question",
"Door Buster": "Hardware Question",
"Friends & Family": "Late Delivery",
"Local": "Software Question",
"Paper Circular": "General Question",
"Regional": "Item Damaged",
"Social": "Item Damaged"
}
data_gen.add_map_column('Reason', 'Marketing Campaign', camp_reason_map)
city_priority_map = {
"Boston": "Low",
"Chicago": "Medium",
"New York": "High"
}
data_gen.add_map_column('Priority', 'City', city_priority_map)
comp_sla_map = {
"High": "Violation",
"Normal": "Compliant",
"Low": "Compliant"
}
data_gen.add_map_column('SLA', 'Competition', comp_sla_map)
data_gen.add_constant_column('Status', 'Closed')
sla_first_contact_close_map = {
'Compliant': lambda: choice(['true', 'false'], p=[.9, .1]),
'Violation': lambda: choice(['true', 'false'], p=[.7, .3])
}
data_gen.add_map_column('First_Contact_Close__c', 'SLA', sla_first_contact_close_map)
sla_time_open_map = {
'Compliant': lambda: choice([12, 24, 36, 48], p=[.50, .20, .20, .10]),
'Violation': lambda: choice([60, 72, 84, 96, 108, 120], p=[.60, .20, .10, .05, .03, .02])
}
data_gen.add_map_column('Time_Open__c', 'SLA', sla_time_open_map)
def region_formula(column_values):
average_age = float(column_values['Average Age'])
if average_age < 40:
return 'West CSR'
elif average_age >= 40.0 and average_age < 50:
return 'Central CSR'
else:
return 'East CSR'
data_gen.add_formula_column('Team__c', region_formula)
def user_formula(column_values):
average_age = float(column_values['Average Age'])
if average_age < 40:
return 'W_Services_User.' + str(choice([1, 2, 3, 4, 5]))
elif average_age >= 40.0 and average_age < 50:
return 'W_Services_User.' + str(choice([6, 7, 8, 9, 10, 11]))
else:
return 'W_Services_User.' + str(choice([12, 13, 14, 15, 16, 17]))
data_gen.add_formula_column('Owner.External_Id__c', user_formula)
# generate offer voucher - give vouchers to customers that were unhappy with Video Games or Cables to boost CSAT
def offer_voucher_formula(column_values):
csat = float(column_values['Profit Linear'])
item = column_values['Item']
if item in ['Video Games', 'Cables']:
return choice(['true', 'false'], p=[csat/100, (100 - csat) / 100])
else:
return 'false'
data_gen.add_formula_column('Offer_Voucher__c', offer_voucher_formula)
def send_field_service_formula(column_values):
csat = float(column_values['Profit Linear'])
item = column_values['Item']
if csat >= 80.0 and item == 'Tablet':
return 'true'
else:
return choice(['true', 'false'], p=[.25, .75])
data_gen.add_formula_column('Send_FieldService__c', send_field_service_formula)
data_gen.add_map_column('IsEscalated', 'Tier', {'Tier 1': 'true', None: 'false'})
# generate close date offset
# random offset covering the last 14 months
data_gen.add_formula_column('close_date_offset', lambda: randint(1, 30 * 14))
# generate account id - generate a long tail distribution - cubic function +- randint
# helper dataset used for account selection
data_gen.add_dataset('current_account', {'account_id': 0, 'account_count': 0})
# generate a distribution of account ids
def account_id_formula(column_values):
current_account = data_gen.datasets['current_account']
account_id = current_account['account_id']
account_count = current_account['account_count']
if account_count > 0:
# continue with the current account_id if there are still any to take
# but first decrement account count
account_count += -1
current_account['account_count'] = account_count
else:
# use new account id
account_id += 1
account_count = int(round(lognormal(1))) + randint(1, 7)
# update account dataset for next iteration
account_count += -1
current_account['account_count'] = account_count
current_account['account_id'] = account_id
return 'W_Services_Account.' + str(account_id)
data_gen.add_formula_column('Account.External_Id__c', account_id_formula)
def csat_formula(column_values):
# first normalize csat between 30-90
csat = float(column_values['Profit Linear'])
new_delta = 70
csat = (new_delta * csat / 100) + 30
channel = column_values['Origin']
is_escalated = column_values['IsEscalated']
send_field_service = column_values['Send_FieldService__c']
offer_voucher = column_values['Offer_Voucher__c']
if is_escalated == 'true':
if channel == 'Phone':
csat = csat - 2
else:
csat = csat + 2
if send_field_service == 'true':
if channel == 'Phone':
csat = csat - 2
else:
csat = csat + 4
if offer_voucher == 'true':
if channel == 'Phone':
csat = csat - 2
else:
csat = csat + 4
return csat
data_gen.add_formula_column('CSAT__c', formula=csat_formula)
data_gen.add_map_column('Outlier', 'Outlier', value_map={
'TRUE': 'true',
None: 'false'
})
data_gen.apply_transformations()
data_gen.add_map_column('Time_Open__c', 'First_Contact_Close__c', value_map={
'true': 0,
None: lambda cv: cv['Time_Open__c']
})
data_gen.apply_transformations()
rename_map = {
'Item': 'Product_Family_KB__c'
}
data_gen.rename_columns(rename_map)
output_columns = [
'Origin',
'Store',
'Tier',
'Product_Family_KB__c',
'Priority',
'Average Age',
'Percent Male',
'SLA',
'Daily Revenue',
'Reason',
'Reg Price',
'Type_of_Support__c',
'Price',
'Quantity',
'Cost',
'Profit',
'CSAT__c',
'Profit Log',
'Outlier',
'Status',
'First_Contact_Close__c',
'Time_Open__c',
'Team__c',
'Owner.External_Id__c',
'close_date_offset',
'Account.External_Id__c',
'Offer_Voucher__c',
'Send_FieldService__c',
'IsEscalated'
]
data_gen.write(output_file_name, output_columns)
def run(batch_id,
source_file_name,
output_file_name,
source_accounts,
source_service_resources,
source_service_territories,
source_work_orders,
reference_datetime=today):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
data_gen.add_formula_column(
'EarliestStartTime',
lambda cv: dateutil.parser.parse(cv['EarliestStartTime']))
data_gen.apply_transformations()
data_gen.sort_by('EarliestStartTime', reverse=True)
# shift dates to be 2 weeks prior to the reference date
delta = reference_datetime.date() - data_gen.row_to_column_values(
data_gen.rows[0])['EarliestStartTime'].date()
data_gen.add_formula_column(
'EarliestStartTime', lambda cv: (cv['EarliestStartTime'] + timedelta(
days=delta.days - 1)).replace(tzinfo=None))
data_gen.add_formula_column(
'ActualStartTime', lambda cv: "" if cv['ActualStartTime'] == "" else
(dateutil.parser.parse(cv['ActualStartTime']) + timedelta(
days=delta.days - 1)).replace(tzinfo=None))
data_gen.add_formula_column(
'ActualEndTime', lambda cv: "" if cv['ActualEndTime'] == "" else
(dateutil.parser.parse(cv['ActualEndTime']) + timedelta(
days=delta.days - 1)).replace(tzinfo=None))
data_gen.add_formula_column(
'ArrivalWindowStartTime', lambda cv: ""
if cv['ArrivalWindowStartTime'] == "" else
(dateutil.parser.parse(cv['ArrivalWindowStartTime']) + timedelta(
days=delta.days - 1)).replace(tzinfo=None))
data_gen.add_formula_column(
'ArrivalWindowEndTime', lambda cv: ""
if cv['ArrivalWindowEndTime'] == "" else
(dateutil.parser.parse(cv['ArrivalWindowEndTime']) + timedelta(
days=delta.days - 1)).replace(tzinfo=None))
data_gen.add_formula_column(
'DueDate', lambda cv: ""
if cv['DueDate'] == "" else (dateutil.parser.parse(cv[
'DueDate']) + timedelta(days=delta.days - 1)).replace(tzinfo=None))
data_gen.apply_transformations()
data_gen.add_copy_column('CreatedDate__c', 'EarliestStartTime')
accounts = data_gen.load_dataset("Accounts", source_accounts,
['Id', 'External_ID__c']).dict(
'Id', 'External_ID__c')
data_gen.add_map_column('Account.External_Id__c', 'AccountId', accounts)
service_resources = data_gen.load_dataset("ServiceResources",
source_service_resources,
['Id', 'External_ID__c']).dict(
'Id', 'External_ID__c')
data_gen.add_map_column('ServiceResource.External_Id__c',
'FSLDemoTools_Service_Resource__c',
service_resources)
service_territories = data_gen.load_dataset("ServiceTerritories",
source_service_territories,
['Id', 'External_ID__c']).dict(
'Id', 'External_ID__c')
data_gen.add_map_column('ServiceTerritory.External_Id__c',
'ServiceTerritoryId', service_territories)
work_orders = data_gen.load_dataset("WorkOrders", source_work_orders,
['Id', 'External_ID__c']).dict(
'Id', 'External_ID__c')
data_gen.add_map_column('WorkOrder.External_Id__c', 'ParentRecordId',
work_orders)
data_gen.apply_transformations()
data_gen.filter(
lambda cv: cv['WorkOrder.External_Id__c'].startswith('WO.'))
data_gen.apply_transformations()
data_gen.write(
output_file_name,
columns=[
'External_ID__c', 'CreatedDate__c',
'ServiceResource.External_Id__c',
'ServiceTerritory.External_Id__c', 'WorkOrder.External_Id__c',
'ActualStartTime', 'ArrivalWindowStartTime', 'ActualDuration',
'EarliestStartTime', 'Duration', 'DurationType', 'Status',
'DueDate', 'ActualEndTime', 'ArrivalWindowEndTime'
])
return delta
def run(batch_id, source_file_name, output_file_name, reference_datetime=today):
data_gen = DataGenerator()
# load source file
source_columns = [
'External_Id__c',
'Owner.External_Id__c',
'CreatedDate__c',
'LastActivityDate__c',
'Team__c'
]
data_gen.load_source_file(source_file_name, source_columns)
data_gen.rename_column('External_Id__c', 'Case.External_Id__c')
data_gen.rename_column('LastActivityDate__c', 'ActivityDate')
data_gen.rename_column('Team__c', 'CallObject')
# generate a random number of tasks per case
data_gen.duplicate_rows(duplication_factor=lambda: randint(0, 3))
data_gen.add_formula_column('External_Id__c', formula=lambda: 'W_Services_Task.' + str(data_gen.current_row + 1))
data_gen.add_formula_column('TaskSubtype', formula=task.task_subtype)
data_gen.add_formula_column('CallDurationInSeconds', formula=task.task_call_duration)
data_gen.add_formula_column('CallDisposition', formula=task.task_call_disposition)
data_gen.add_formula_column('CallType', formula=task.task_call_type)
data_gen.add_formula_column('Status', formula=task.task_status)
data_gen.add_formula_column('Priority', formula=task.task_priority)
def create_date_formula(column_values):
case_create_date = dateutil.parser.parse(column_values['CreatedDate__c'])
case_close_date = datetime.combine(dateutil.parser.parse(column_values['ActivityDate']), case_create_date.time())
create_date = fake.date_time_between_dates(case_create_date, case_close_date)
if create_date > reference_datetime:
create_date = reference_datetime
return create_date.isoformat(sep=' ')
data_gen.add_formula_column('CreatedDate__c', create_date_formula)
data_gen.add_copy_column('LastModifiedDate__c', 'CreatedDate__c')
def activity_date_formula(column_values):
create_date = dateutil.parser.parse(column_values['CreatedDate__c']).date()
return (create_date + timedelta(days=randint(0, 14))).isoformat()
data_gen.add_formula_column('ActivityDate', activity_date_formula)
data_gen.add_formula_column('Subject', formula=task.task_subject_simple)
data_gen.add_map_column('Type', 'Subject', value_map={
'Call': lambda: choice(['Call', 'Meeting'], p=[.70, .30]),
'Send Letter': 'Email',
'Send Quote': 'Email',
None: lambda: choice(['Meeting', 'Prep', 'Other'], p=[.50, .25, .25])
})
# add a UUID for each row that is created in this batch
data_gen.add_constant_column('analyticsdemo_batch_id__c', batch_id)
# apply transformations and write
data_gen.apply_transformations()
output_columns = [
'External_Id__c',
'Owner.External_Id__c',
'Case.External_Id__c',
'CreatedDate__c',
'LastModifiedDate__c',
'ActivityDate',
'Subject',
'Type',
'TaskSubtype',
'CallDurationInSeconds',
'CallDisposition',
'CallType',
'CallObject',
'Status',
'Priority',
'analyticsdemo_batch_id__c'
]
data_gen.write(output_file_name, output_columns)
def run(source_file_name, output_file_name):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
rename_map = {
'Supplies Group': 'Product2Family__c',
'Region': 'Region__c',
'Route To Market': 'LeadSource',
'Elapsed Days In Sales Stage': 'TimeToClose__c',
'Sales Stage Change Count': 'SalesStageCount__c',
'Opportunity Amount USD': 'Amount',
'Deal Size Category': 'DealSizeCategory__c'
}
data_gen.rename_columns(rename_map)
# multiple time to close by 2
data_gen.add_formula_column('TimeToClose__c',
lambda cv: int(cv['TimeToClose__c']) * 2)
# map existing columns to new columns
data_gen.add_map_column('Competitor__c', 'Competitor Type',
definitions.competitor_type)
data_gen.add_map_column('Product2Name__c', 'Supplies Subgroup',
definitions.supplies_subgroup_map)
data_gen.add_map_column('AccountAnnualRevenue__c',
'Client Size By Revenue',
definitions.client_size_rev)
data_gen.add_map_column('AccountNumberOfEmployees__c',
'Client Size By Employee Count',
definitions.client_size_employees)
data_gen.add_map_column('AccountBookings__c',
'Revenue From Client Past Two Years',
definitions.client_past_revenue)
data_gen.add_map_column('IsWon', 'Opportunity Result', definitions.isWon)
# generate external id
data_gen.add_formula_column(
'External_Id__c',
formula=lambda: 'W_Opportunity.' + str(data_gen.current_row + 1))
data_gen.add_formula_column(
'Exec_Meeting__c', lambda: choice(['true', 'false'], p=[.35, .65]))
data_gen.add_formula_column(
'Interactive_Demo__c', lambda: choice(['true', 'false'], p=[.30, .70]))
def ttc_formula(column_values):
ttc = int(column_values['TimeToClose__c'])
exec_meeting = column_values['Exec_Meeting__c']
competitor_type = column_values['Competitor Type']
demo = column_values['Interactive_Demo__c']
rev = column_values['AccountAnnualRevenue__c']
if ttc == 0:
return 0
if exec_meeting == 'true':
if competitor_type == 'None':
ttc = ttc + 4
else:
ttc = ttc - 6
if demo == 'true':
if rev == 'T100':
ttc = ttc + 6
else:
ttc = ttc - 5
if ttc < 0:
return 0
return ttc
data_gen.add_formula_column('TimeToClose__c', formula=ttc_formula)
data_gen.add_constant_column('IsClosed', 'true')
data_gen.add_formula_column(
'RecordType.DeveloperName',
formula=lambda: choice(['SimpleOpportunity', 'ChannelPartner'],
p=[.70, .30]))
# generate opportunity type
types = [
'Add-On Business', 'Existing Business', 'New Business',
'New Business / Add-on'
]
data_gen.add_formula_column(
'Type', formula=lambda: choice(types, p=[0.1, 0.3, 0.5, 0.1]))
# generate a close date year and quarter
data_gen.add_formula_column('close_date_year',
formula=lambda: choice(list(range(0, 30))))
data_gen.add_formula_column(
'close_date_quarter',
formula=lambda: choice([1, 2, 3, 4], p=[0.21, 0.24, 0.22, 0.33]))
# generate a close date offset from the year and quarter
def offset_formula(column_values):
day = int(round(chisquare(9) * 5))
offset = 365 * (column_values['close_date_year']) + 91 * (
column_values['close_date_quarter'] - 1) + day
return offset
data_gen.add_formula_column('close_date_offset__c', offset_formula)
# generate a close date
def close_date_formula(column_values):
last_day = date(date.today().year, 12, 31)
offset = column_values['close_date_offset__c']
# last day of current year - offset
close_date = last_day - timedelta(days=int(offset))
return str(close_date)
data_gen.add_formula_column('CloseDate', close_date_formula)
# generate a create date
def create_date_formula(column_values):
close_date = dateutil.parser.parse(column_values['CloseDate'])
offset = column_values['TimeToClose__c']
create_date = close_date - timedelta(days=int(offset))
return create_date.isoformat(sep=' ')
data_gen.add_formula_column('CreatedDate__c', create_date_formula)
# generate last activity date
def last_activity_date_formula(column_values):
create_date = dateutil.parser.parse(column_values['CreatedDate__c'])
close_date = dateutil.parser.parse(column_values['CloseDate'])
if close_date > today_datetime:
close_date = today_datetime
if create_date > today_datetime:
create_date = today_datetime
return fake.date_time_between_dates(create_date, close_date).date()
data_gen.add_formula_column('LastActivityDate__c',
formula=last_activity_date_formula)
# generate StageName, ForecastCategory, and Probability
data_gen.add_map_column('StageName',
'Opportunity Result',
value_map={
'Won': 'Closed Won',
None: 'Closed Lost'
})
data_gen.add_map_column('ForecastCategory',
'Opportunity Result',
value_map={
'Won': 'Closed',
None: 'Omitted'
})
data_gen.add_map_column('ForecastCategoryName',
'Opportunity Result',
value_map={
'Won': 'Closed',
None: 'Omitted'
})
data_gen.add_map_column('Probability',
'Opportunity Result',
value_map={
'Won': '100',
None: '0'
})
# randomly pick an owner from the same region
region_territory_map = {
'Pacific':
lambda: 'W_Sales_User.' + str(choice([1, 2, 3, 4, 5, 6])),
"Northwest":
lambda: 'W_Sales_User.' + str(choice([1, 2, 3, 4, 5, 6])),
"Midwest":
lambda: 'W_Sales_User.' + str(choice([7, 8, 9, 10, 11])),
"Southwest":
lambda: 'W_Sales_User.' + str(choice([7, 8, 9, 10, 11])),
"Mid-Atlantic":
lambda: 'W_Sales_User.' + str(choice([7, 8, 9, 10, 11])),
"Northeast":
lambda: 'W_Sales_User.' + str(choice([12, 13, 14, 15, 16, 17])),
"Southeast":
lambda: 'W_Sales_User.' + str(choice([12, 13, 14, 15, 16, 17]))
}
data_gen.add_map_column('Owner.External_Id__c', 'Region__c',
region_territory_map)
# build out helper column for account selection
def account_cat_formula(column_values):
x1 = column_values['Client Size By Revenue']
x2 = column_values['Client Size By Employee Count']
x3 = column_values['Revenue From Client Past Two Years']
return str(x1) + '.' + str(x2) + '.' + str(x3)
data_gen.add_formula_column('account_cat', account_cat_formula)
# apply pending transformations now so we can sort by account_cat
data_gen.apply_transformations()
data_gen.sort_by('account_cat')
# helper dataset used for account selection
data_gen.add_dataset('account_segment', {
'account_id': 0,
'account_count': 0,
'current_account_cat': None
})
# generate a distribution of account ids
def account_id_formula(column_values):
account_segment = data_gen.datasets['account_segment']
account_id = account_segment['account_id']
account_count = account_segment['account_count']
current_account_cat = account_segment['current_account_cat']
if column_values[
'account_cat'] == current_account_cat and account_count > 0:
# continue with the current account_id if there are still any to take
# but first decrement account count
account_count += -1
account_segment['account_count'] = account_count
return account_id
else:
# use new account id
account_id += 1
# generate a random number of opportunties to associate to an account
account_count = int(round(lognormal(1))) + randint(1, 7)
current_account_cat = column_values['account_cat']
# update account segment dataset for next iteration
account_count += -1
account_segment['account_id'] = account_id
account_segment['account_count'] = account_count
account_segment['current_account_cat'] = current_account_cat
return account_id
data_gen.add_formula_column('AccountId__c', account_id_formula)
# generate account id string
data_gen.add_formula_column(
'AccountExternalId__c',
formula=lambda cv: 'W_Account.' + str(cv['AccountId__c']))
# generate account name string
account_names = {}
def account_name_formula(column_values):
account_id = column_values['AccountId__c']
if account_id in account_names:
return account_names[account_id]
else:
account_name = account.account_name()
account_names[account_id] = account_name
return account_name
data_gen.add_formula_column('AccountName__c', formula=account_name_formula)
# generate name
def name_formula(column_values):
account_name = column_values['AccountName__c']
amount = column_values['Amount']
product_2_name = column_values['Product2Name__c']
return account_name + ' ' + str(data_gen.current_row % 256)
data_gen.add_formula_column('Name', name_formula)
# apply remaining transformations
data_gen.apply_transformations()
# sort by account id
data_gen.sort_by('AccountId__c')
columns_to_write = [
'External_Id__c', 'Product2Name__c', 'Product2Family__c', 'Region__c',
'LeadSource', 'TimeToClose__c', 'SalesStageCount__c', 'Amount',
'AccountAnnualRevenue__c', 'AccountNumberOfEmployees__c',
'AccountBookings__c', 'Competitor__c', 'DealSizeCategory__c',
'AccountExternalId__c', 'AccountName__c', 'close_date_year',
'close_date_quarter', 'close_date_offset__c', 'Exec_Meeting__c',
'Interactive_Demo__c', 'IsWon', 'IsClosed', 'Owner.External_Id__c',
'Name', 'Type', 'StageName', 'ForecastCategory',
'ForecastCategoryName', 'Probability', 'RecordType.DeveloperName'
]
data_gen.write(output_file_name, columns_to_write)
def run(batch_id, source_file_name, output_file_name, manager_output_file_name):
data_gen = DataGenerator()
# load source file
source_columns = ['Owner.External_Id__c', 'Team__c']
data_gen.load_source_file(source_file_name, source_columns)
data_gen.unique()
# rename columns
data_gen.rename_column('Owner.External_Id__c', 'External_Id__c')
data_gen.rename_column('Team__c', 'UserRole.Name')
# add 3 manager users
west_manager = ['W_User.M.' + str(len(data_gen.rows) + 1), 'West CSM']
east_manager = ['W_User.M.' + str(len(data_gen.rows) + 2), 'East CSM']
central_manager = ['W_User.M.' + str(len(data_gen.rows) + 3), 'Central CSM']
## managers from Sales ##
# west_manager = ['RVP West', 'W_Sales_User.M.' + str(len(data_gen.rows) + 1)]
# east_manager = ['RVP East', 'W_Sales_User.M.' + str(len(data_gen.rows) + 2)]
# central_manager = ['RVP Central', 'W_Sales_User.M.' + str(len(data_gen.rows) + 3)]
########################
data_gen.rows.append(west_manager)
data_gen.rows.append(east_manager)
data_gen.rows.append(central_manager)
# generate company name
data_gen.add_formula_column('CompanyName', formula=fake.company)
# generate fake first and last name
def first_name_formula(column_values):
id = int(column_values['External_Id__c'].split('.')[-1])
return fake.first_name_female() if id < 13 else fake.first_name_male()
data_gen.add_formula_column('FirstName', formula=first_name_formula)
data_gen.add_formula_column('LastName', formula=fake.last_name)
# generate data based on fake first and last name
data_gen.add_formula_column('Name', lambda cv: cv['FirstName'] + ' ' + cv['LastName'])
# generate data based on fake first and last name
def alias_formula(column_values):
alias = (column_values['FirstName'][0] + column_values['LastName']).lower()
trimmed_alias = alias[:8] if len(alias) > 8 else alias
return trimmed_alias
data_gen.add_formula_column('Alias', formula=alias_formula)
data_gen.add_formula_column('Username', lambda cv: cv['Alias'] + '@demo.user')
data_gen.add_formula_column('CommunityNickname', lambda cv: cv['Alias'] + str(randint(100, 999)))
data_gen.add_formula_column('Email', lambda cv: cv['Alias'] + '@webmail.com')
data_gen.add_formula_column('Phone', formula=fake.phone_number)
titles = ['Customer Service Representative', 'Senior Customer Service Representative']
data_gen.add_formula_column('Title', lambda: choice(titles, p=[.70, .30]))
# generate constant values
data_gen.add_constant_column('IsActive', 'false')
data_gen.add_constant_column('TimeZoneSidKey', 'America/Los_Angeles')
data_gen.add_constant_column('Profile.Name', 'Standard User')
# from oppty> data_gen.add_constant_column('Profile.Name', 'Standard User')
data_gen.add_constant_column('LocaleSidKey', 'en_US')
data_gen.add_constant_column('LanguageLocaleKey', 'en_US')
data_gen.add_constant_column('EmailEncodingKey', 'ISO-8859-1')
data_gen.add_constant_column('ForecastEnabled', 'true') # this comes from Sales
data_gen.add_constant_column('UserPermissionsAvantgoUser', 'false')
data_gen.add_constant_column('UserPermissionsCallCenterAutoLogin', 'false')
data_gen.add_constant_column('UserPermissionsChatterAnswersUser', 'false')
data_gen.add_constant_column('UserPermissionsInteractionUser', 'false')
data_gen.add_constant_column('UserPermissionsJigsawProspectingUser', 'false')
data_gen.add_constant_column('UserPermissionsKnowledgeUser', 'false')
data_gen.add_constant_column('UserPermissionsLiveAgentUser', 'false')
data_gen.add_constant_column('UserPermissionsMarketingUser', 'false')
data_gen.add_constant_column('UserPermissionsMobileUser', 'false')
data_gen.add_constant_column('UserPermissionsOfflineUser', 'false')
data_gen.add_constant_column('UserPermissionsSFContentUser', 'false')
data_gen.add_constant_column('UserPermissionsSiteforceContributorUser', 'false')
data_gen.add_constant_column('UserPermissionsSiteforcePublisherUser', 'false')
data_gen.add_constant_column('UserPermissionsSupportUser', 'false')
data_gen.add_constant_column('UserPermissionsWorkDotComUserFeature', 'false')
data_gen.add_constant_column('UserPreferencesActivityRemindersPopup', 'false')
data_gen.add_constant_column('UserPreferencesApexPagesDeveloperMode', 'false')
data_gen.add_constant_column('UserPreferencesCacheDiagnostics', 'false')
data_gen.add_constant_column('UserPreferencesContentEmailAsAndWhen', 'false')
data_gen.add_constant_column('UserPreferencesContentNoEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisableAllFeedsEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisableBookmarkEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisableChangeCommentEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisableEndorsementEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisableFeedbackEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisableFileShareNotificationsForApi', 'false')
data_gen.add_constant_column('UserPreferencesDisableFollowersEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisableLaterCommentEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisableLikeEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisableMentionsPostEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisableMessageEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisableProfilePostEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisableRewardEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisableSharePostEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisableWorkEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisCommentAfterLikeEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisMentionsCommentEmail', 'false')
data_gen.add_constant_column('UserPreferencesDisProfPostCommentEmail', 'false')
data_gen.add_constant_column('UserPreferencesEnableAutoSubForFeeds', 'false')
data_gen.add_constant_column('UserPreferencesEventRemindersCheckboxDefault', 'false')
data_gen.add_constant_column('UserPreferencesHideBiggerPhotoCallout', 'false')
data_gen.add_constant_column('UserPreferencesHideChatterOnboardingSplash', 'false')
data_gen.add_constant_column('UserPreferencesHideCSNDesktopTask', 'false')
data_gen.add_constant_column('UserPreferencesHideCSNGetChatterMobileTask', 'false')
data_gen.add_constant_column('UserPreferencesHideEndUserOnboardingAssistantModal', 'false')
data_gen.add_constant_column('UserPreferencesHideLightningMigrationModal', 'false')
data_gen.add_constant_column('UserPreferencesHideS1BrowserUI', 'false')
data_gen.add_constant_column('UserPreferencesHideSecondChatterOnboardingSplash', 'false')
data_gen.add_constant_column('UserPreferencesHideSfxWelcomeMat', 'false')
data_gen.add_constant_column('UserPreferencesJigsawListUser', 'false')
data_gen.add_constant_column('UserPreferencesLightningExperiencePreferred', 'false')
data_gen.add_constant_column('UserPreferencesPathAssistantCollapsed', 'false')
data_gen.add_constant_column('UserPreferencesPreviewLightning', 'false')
data_gen.add_constant_column('UserPreferencesReminderSoundOff', 'false')
data_gen.add_constant_column('UserPreferencesShowCityToExternalUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowCityToGuestUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowCountryToExternalUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowCountryToGuestUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowEmailToExternalUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowEmailToGuestUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowFaxToExternalUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowFaxToGuestUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowManagerToExternalUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowManagerToGuestUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowMobilePhoneToExternalUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowMobilePhoneToGuestUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowPostalCodeToExternalUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowPostalCodeToGuestUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowProfilePicToGuestUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowStateToExternalUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowStateToGuestUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowStreetAddressToExternalUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowStreetAddressToGuestUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowTitleToExternalUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowTitleToGuestUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowWorkPhoneToExternalUsers', 'false')
data_gen.add_constant_column('UserPreferencesShowWorkPhoneToGuestUsers', 'false')
data_gen.add_constant_column('UserPreferencesSortFeedByComment', 'false')
data_gen.add_constant_column('UserPreferencesTaskRemindersCheckboxDefault', 'false')
data_gen.add_constant_column('EmailPreferencesAutoBcc', 'false')
data_gen.add_constant_column('EmailPreferencesAutoBccStayInTouch', 'false')
data_gen.add_constant_column('EmailPreferencesStayInTouchReminder', 'false')
data_gen.add_constant_column('UserPreferencesGlobalNavBarWTShown', 'false')
data_gen.add_constant_column('UserPreferencesGlobalNavGridMenuWTShown', 'false')
data_gen.add_constant_column('UserPreferencesCreateLEXAppsWTShown', 'false')
# add a UUID for each row that is created in this batch
data_gen.add_constant_column('analyticsdemo_batch_id__c', batch_id)
# apply transformations and write file
data_gen.apply_transformations()
data_gen.write(output_file_name)
# create manager file
data_gen.filter(lambda cv: 'CSM' not in cv['UserRole.Name'])
manager_map = {
'West CSR': west_manager[0],
'East CSR': east_manager[0],
'Central CSR': central_manager[0]
}
### this is the manager file section in Sales> ###
# # create manager file
# data_gen.filter(lambda cv: 'RVP' not in cv['UserRole.Name'])
# manager_map = {
# 'West Sales': west_manager[1],
# 'East Sales': east_manager[1],
# 'Central Sales': central_manager[1],
# }
##################################################
data_gen.add_map_column('Manager.External_Id__c', 'UserRole.Name', manager_map)
data_gen.apply_transformations()
data_gen.write(manager_output_file_name, ['External_Id__c', 'Manager.External_Id__c'])
def run(batch_id, source_file_name, output_file_name, source_profiles):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
accounts = data_gen.load_dataset("Profiles", source_profiles, ['Id', 'Name']).dict('Id', 'Name')
data_gen.add_map_column('Profile.Name', 'ProfileId', accounts)
data_gen.apply_transformations()
data_gen.write(output_file_name, columns=[
'External_ID__c',
'FirstName',
'LastName',
'Alias',
'Email',
'TimeZoneSidKey',
'Profile.Name',
'LocaleSidKey',
'LanguageLocaleKey',
'EmailEncodingKey',
'UserPermissionsAvantgoUser',
'UserPermissionsCallCenterAutoLogin',
#'UserPermissionsChatterAnswersUser',
'UserPermissionsInteractionUser',
#'UserPermissionsJigsawProspectingUser',
'UserPermissionsKnowledgeUser',
'UserPermissionsLiveAgentUser',
'UserPermissionsMarketingUser',
'UserPermissionsMobileUser',
'UserPermissionsOfflineUser',
'UserPermissionsSFContentUser',
'UserPermissionsSiteforceContributorUser',
'UserPermissionsSiteforcePublisherUser',
'UserPermissionsSupportUser',
'UserPermissionsWorkDotComUserFeature',
'UserPreferencesActivityRemindersPopup',
'UserPreferencesApexPagesDeveloperMode',
'UserPreferencesCacheDiagnostics',
'UserPreferencesContentEmailAsAndWhen',
'UserPreferencesContentNoEmail',
'UserPreferencesDisableAllFeedsEmail',
'UserPreferencesDisableBookmarkEmail',
'UserPreferencesDisableChangeCommentEmail',
'UserPreferencesDisableEndorsementEmail',
'UserPreferencesDisableFeedbackEmail',
'UserPreferencesDisableFileShareNotificationsForApi',
'UserPreferencesDisableFollowersEmail',
'UserPreferencesDisableLaterCommentEmail',
'UserPreferencesDisableLikeEmail',
'UserPreferencesDisableMentionsPostEmail',
'UserPreferencesDisableMessageEmail',
'UserPreferencesDisableProfilePostEmail',
'UserPreferencesDisableRewardEmail',
'UserPreferencesDisableSharePostEmail',
'UserPreferencesDisableWorkEmail',
'UserPreferencesDisCommentAfterLikeEmail',
'UserPreferencesDisMentionsCommentEmail',
'UserPreferencesDisProfPostCommentEmail',
'UserPreferencesEnableAutoSubForFeeds',
'UserPreferencesEventRemindersCheckboxDefault',
'UserPreferencesHideBiggerPhotoCallout',
'UserPreferencesHideChatterOnboardingSplash',
'UserPreferencesHideCSNDesktopTask',
'UserPreferencesHideCSNGetChatterMobileTask',
'UserPreferencesHideEndUserOnboardingAssistantModal',
'UserPreferencesHideLightningMigrationModal',
'UserPreferencesHideS1BrowserUI',
'UserPreferencesHideSecondChatterOnboardingSplash',
'UserPreferencesHideSfxWelcomeMat',
#'UserPreferencesJigsawListUser',
'UserPreferencesLightningExperiencePreferred',
'UserPreferencesPathAssistantCollapsed',
'UserPreferencesPreviewLightning',
'UserPreferencesReminderSoundOff',
'UserPreferencesShowCityToExternalUsers',
'UserPreferencesShowCityToGuestUsers',
'UserPreferencesShowCountryToExternalUsers',
'UserPreferencesShowCountryToGuestUsers',
'UserPreferencesShowEmailToExternalUsers',
'UserPreferencesShowEmailToGuestUsers',
'UserPreferencesShowFaxToExternalUsers',
'UserPreferencesShowFaxToGuestUsers',
'UserPreferencesShowManagerToExternalUsers',
'UserPreferencesShowManagerToGuestUsers',
'UserPreferencesShowMobilePhoneToExternalUsers',
'UserPreferencesShowMobilePhoneToGuestUsers',
'UserPreferencesShowPostalCodeToExternalUsers',
'UserPreferencesShowPostalCodeToGuestUsers',
'UserPreferencesShowProfilePicToGuestUsers',
'UserPreferencesShowStateToExternalUsers',
'UserPreferencesShowStateToGuestUsers',
'UserPreferencesShowStreetAddressToExternalUsers',
'UserPreferencesShowStreetAddressToGuestUsers',
'UserPreferencesShowTitleToExternalUsers',
'UserPreferencesShowTitleToGuestUsers',
'UserPreferencesShowWorkPhoneToExternalUsers',
'UserPreferencesShowWorkPhoneToGuestUsers',
'UserPreferencesSortFeedByComment',
'UserPreferencesTaskRemindersCheckboxDefault',
'EmailPreferencesAutoBcc',
'EmailPreferencesAutoBccStayInTouch',
'EmailPreferencesStayInTouchReminder',
'UserPreferencesGlobalNavBarWTShown',
'UserPreferencesGlobalNavGridMenuWTShown',
'UserPreferencesCreateLEXAppsWTShown'
])
