def run(batch_id, source_file_name, output_file_name, filter_function=None):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
data_gen.add_formula_column(
'Contact.External_Id__c',
lambda cv: cv['Account.External_Id__c'].replace(
'W_Account', 'W_Contact'))
# add a UUID for each row that is created in this batch
data_gen.add_constant_column('analyticsdemo_batch_id__c', batch_id)
data_gen.apply_transformations()
if filter_function:
data_gen.filter(filter_function)
output_columns = [
'External_Id__c', 'Owner.External_Id__c', 'Account.External_Id__c',
'Contact.External_Id__c', 'CreatedDate__c', 'ClosedDate__c',
'LastActivityDate__c', 'Origin', 'Tier', 'Product_Family_KB__c',
'Priority', 'SLA', 'Reason', 'Type_of_Support__c', 'CSAT__c', 'Status',
'First_Contact_Close__c', 'Time_Open__c', 'Team__c',
'close_date_offset', 'Offer_Voucher__c', 'Send_FieldService__c',
'IsEscalated', 'MilestoneStatus__c', 'analyticsdemo_batch_id__c'
]
data_gen.write(output_file_name, output_columns)
def generate(self, selected_filters=None, columns=None, count=5):
if selected_filters is None:
selected_filters = {}
if columns is None:
columns = self.get_columns()
data_gen = DataGenerator()
if self.local_file_exists:
data_gen.load_source_file_from_disk(self.local_file_name, columns)
else:
data_gen.load_source_file_from_s3(self.source_file_name, columns)
for filter_key, filter_value in selected_filters.items():
data_gen.filter(lambda cv: cv[filter_key] == filter_value)
if data_gen.row_count <= 0:
return []
remaining_count = count
result = []
while remaining_count > 0:
data_gen.shuffle()
if data_gen.row_count >= remaining_count:
data_gen.row_count = remaining_count
result += list(map(lambda r: data_gen.row_to_column_values(r, columns).values(), data_gen.rows))
remaining_count -= data_gen.row_count
return result
def run(batch_id, source_file_name, output_file_name, reference_date=today):
data_gen = DataGenerator()
# load source file
source_columns = ['External_Id__c', 'Name', 'UserRole.Name']
data_gen.load_source_file(source_file_name, source_columns)
data_gen.filter(lambda cv: 'RVP' not in cv['UserRole.Name'])
data_gen.filter(
lambda cv: 'CSM' not in cv['UserRole.Name']) # comes from Service
data_gen.rename_column('External_Id__c', 'QuotaOwner_Id__c')
data_gen.rename_column('Name', 'OwnerName__c')
# generate id
data_gen.add_formula_column(
'External_Id__c',
formula=lambda: 'W_Quota.' + str(data_gen.current_row + 1))
data_gen.duplicate_rows(24)
def quota_formula():
# first month of quarter = 300k
# second month of quarter = 500k
# third month of quarter = 500k
quarter = data_gen.current_row % 3
if quarter == 0:
return 300000
elif quarter == 1:
return 750000
else:
return 500000
data_gen.add_formula_column('QuotaAmount__c', quota_formula)
current_year = reference_date.year
last_year = current_year - 1
def start_date_formula():
user_row = data_gen.current_row % 24
month = str((user_row % 12) + 1).zfill(2)
day = '01'
if user_row < 12:
year = str(last_year)
else:
year = str(current_year)
return dateutil.parser.parse(year + '-' + month + '-' + day).date()
data_gen.add_formula_column('StartDate__c', start_date_formula)
# 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, [
'External_Id__c', 'QuotaOwner_Id__c', 'OwnerName__c', 'StartDate__c',
'QuotaAmount__c'
])
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):
data_gen = DataGenerator()
# load source file
source_columns = ['External_Id__c','UserRole.Name']
data_gen.load_source_file(source_file_name, source_columns)
# data_gen.filter(lambda cv: 'RVP' in cv['UserRole.Name']) # commented out because using shape file from service with no RVP value in UserRole.Name
data_gen.filter(lambda cv: 'CSM' in cv['UserRole.Name']) # comes from Service
data_gen.rename_column('External_Id__c', 'ForecastUser.External_Id__c')
data_gen.rename_column('UserRole.Name', 'Name')
# 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, ['Name','ForecastUser.External_Id__c','analyticsdemo_batch_id__c'])
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,
reference_datetime=today):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
data_gen.rename_column('External_Id__c', 'Case.External_Id__c')
data_gen.rename_column('Owner.External_Id__c', 'User.External_Id__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',
formula=lambda: 'W_AgentWork.' + str(data_gen.current_row + 1))
data_gen.add_copy_column('RequestDateTime__c', 'CreatedDate__c')
def created_date_formula(column_values):
created_date = dateutil.parser.parse(column_values['CreatedDate__c'])
closed_date = dateutil.parser.parse(column_values['ClosedDate__c'])
if closed_date > reference_datetime:
closed_date = reference_datetime
mid_date = created_date + (closed_date - created_date) / 2
return fake.date_time_between_dates(created_date,
mid_date).isoformat(sep=' ')
data_gen.add_formula_column('CreatedDate__c', created_date_formula)
def assigned_date_formula(column_values):
created_date = dateutil.parser.parse(column_values['CreatedDate__c'])
return (created_date +
timedelta(seconds=randint(0, 120))).isoformat(sep=' ')
data_gen.add_formula_column('AssignedDateTime__c', assigned_date_formula)
def accept_date_formula(column_values):
assigned_date = dateutil.parser.parse(
column_values['AssignedDateTime__c'])
return (assigned_date +
timedelta(seconds=randint(30, 600))).isoformat(sep=' ')
data_gen.add_formula_column('AcceptDateTime__c', accept_date_formula)
def close_date_formula(column_values):
accept_date = dateutil.parser.parse(column_values['AcceptDateTime__c'])
return (accept_date +
timedelta(seconds=randint(30, 1800))).isoformat(sep=' ')
data_gen.add_formula_column('CloseDateTime__c', close_date_formula)
def active_time_formula(column_values):
accept_date = dateutil.parser.parse(column_values['AcceptDateTime__c'])
close_date = dateutil.parser.parse(column_values['CloseDateTime__c'])
return int((close_date - accept_date).total_seconds())
data_gen.add_formula_column('ActiveTime__c', active_time_formula)
data_gen.add_formula_column('AgentCapacityWhenDeclined__c',
lambda: randint(30, 1800))
def cancel_date_formula(column_values):
assigned_date = dateutil.parser.parse(
column_values['AssignedDateTime__c'])
return (assigned_date +
timedelta(seconds=randint(30, 600))).isoformat(sep=' ')
data_gen.add_formula_column('CancelDateTime__c', cancel_date_formula)
data_gen.add_formula_column('CapacityPercentage__c',
lambda: randint(1, 101))
data_gen.add_formula_column('CapacityWeight__c', lambda: randint(1, 7))
def decline_date_formula(column_values):
assigned_date = dateutil.parser.parse(
column_values['AssignedDateTime__c'])
return (assigned_date +
timedelta(seconds=randint(30, 600))).isoformat(sep=' ')
data_gen.add_formula_column('DeclineDateTime__c', decline_date_formula)
data_gen.add_formula_column('DeclineReason__c', formula=fake.sentence)
data_gen.add_copy_column('HandleTime__c', 'ActiveTime__c')
data_gen.add_formula_column('OriginalQueue.DeveloperName', [
'GeneralQueue', 'InternationalQueue', 'Knowledge_Translations',
'Social_Queue', 'TargetCampaign', 'Tier1Queue', 'Tier2Queue',
'Tier3Queue'
])
data_gen.add_formula_column('PushTimeout__c', lambda: randint(0, 100))
def push_timeout_date_formula(column_values):
create_date = dateutil.parser.parse(column_values['CreatedDate__c'])
return create_date + timedelta(seconds=column_values['PushTimeout__c'])
data_gen.add_formula_column('PushTimeoutDateTime__c',
push_timeout_date_formula)
data_gen.add_formula_column(
'ServiceChannel.DeveloperName',
['Cases', 'LiveMessage', 'sfdc_liveagent', 'Leads'])
def speed_to_answer_formula(column_values):
request_date = dateutil.parser.parse(
column_values['RequestDateTime__c'])
accept_date = dateutil.parser.parse(column_values['AcceptDateTime__c'])
return int((accept_date - request_date).total_seconds())
data_gen.add_formula_column('SpeedToAnswer__c', speed_to_answer_formula)
data_gen.add_formula_column('Status__c', [
'Assigned', 'Unavailable', 'Declined', 'Opened', 'Closed',
'DeclinedOnPushTimeout', 'Canceled'
])
# 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):
created_date = dateutil.parser.parse(column_values['CreatedDate__c'])
cutoff_date = reference_datetime - timedelta(days=60)
return column_values['Origin'] == 'Chat' and created_date >= cutoff_date
data_gen.filter(filter_function=filter_func)
data_gen.apply_transformations()
data_gen.sort_by('RequestDateTime__c')
output_columns = [
'External_Id__c', 'RequestDateTime__c', 'CreatedDate__c',
'AssignedDateTime__c', 'AcceptDateTime__c', 'CloseDateTime__c',
'ActiveTime__c', 'AgentCapacityWhenDeclined__c', 'CancelDateTime__c',
'CapacityPercentage__c', 'CapacityWeight__c', 'DeclineDateTime__c',
'DeclineReason__c', 'HandleTime__c', 'OriginalQueue.DeveloperName',
'PushTimeout__c', 'PushTimeoutDateTime__c',
'ServiceChannel.DeveloperName', 'SpeedToAnswer__c', 'Status__c',
'User.External_Id__c', 'Case.External_Id__c',
'analyticsdemo_batch_id__c'
]
return data_gen.write(output_file_name, output_columns, 6000)
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,
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(batch_id, source_file_name, output_file_name, reference_date=today_datetime, filter_function=None):
def get_close_date(values):
return dateutil.parser.parse(values['CloseDate'])
def get_create_date(values):
return dateutil.parser.parse(values['CreatedDate__c'])
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
# add a UUID for each row that is created in this batch
data_gen.add_constant_column('analyticsdemo_batch_id__c', batch_id)
# add an age column
data_gen.add_copy_column('Age__c', 'TimeToClose__c')
# 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 = get_create_date(column_values)
close_date = get_close_date(column_values)
if close_date > reference_date:
close_date = reference_date
if create_date > reference_date:
create_date = reference_date
return fake.date_time_between_dates(create_date, close_date).date()
data_gen.add_formula_column('LastActivityDate__c', formula=last_activity_date_formula)
data_gen.apply_transformations()
if filter_function:
data_gen.filter(filter_function)
new_rows = []
row_count = len(data_gen.rows)
for i in range(row_count):
row = data_gen.rows.pop()
column_values = data_gen.row_to_column_values(row)
close_day = get_close_date(column_values)
create_day = get_create_date(column_values)
# if close date is before reference date keep it exactly as is
if close_day <= reference_date:
new_rows.append(row)
# if create date is before reference date, but the close date is after reference date
elif (create_day <= reference_date) and (close_day > reference_date):
# set age
age = (reference_date - create_day).days
column_values['Age__c'] = age
ttc = float(column_values['TimeToClose__c'])
pct = age / ttc
# set IsClosed to blank
column_values['IsClosed'] = ''
# set IsWon to blank
column_values['IsWon'] = ''
# set a stage name
stage_name_index = int(floor(pct * 4) + choice([-1, 0, 1], p=[.2, .7, .1]))
# adjust the stage name index
if stage_name_index < 0:
stage_name_index = 0
if stage_name_index > 3:
stage_name_index = 3
column_values['StageName'] = definitions.stage_name[stage_name_index]
column_values['Probability'] = definitions.probabilities[stage_name_index]
column_values['ForecastCategory'] = definitions.forecast_category[choice([1, 2, 4], p=[.625, .25, .125])]
column_values['ForecastCategoryName'] = definitions.forecast_category_name[column_values['ForecastCategory']]
column_values['SalesStageCount__c'] = ceil(pct * float(column_values['SalesStageCount__c']))
new_rows.append(data_gen.column_values_to_row(column_values))
data_gen.rows = new_rows
data_gen.reverse()
data_gen.write(output_file_name)
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 generate_status_file(source_file,
original_status_file,
tmp_folder=today.isoformat(),
file_name=''):
"""Takes a CSV file and generates another file containing mappings of External_Ids and intermediate and final statuses for the records.
Some MFG objects require intermediate status.
Parameters
----------
source_file : str
The name of the file (including the path) to be processed. File must have Id, External_Id__c and Status.
original_status_file : str
The file name (including path) of the CSV file containing the orginal Id and Status.
tmp_folder : str
Name of the folder for archive path. Default = today's date.
file_name : str
Name of Status file.
Returns
-------
None
Generates file(s) with corresponding statuses. Note that for SalesAgreements multiple files are generated and the name of these files will depend on the intermediate status name.
"""
def get_original_final_status(status_by_id, record_id):
return status_by_id[record_id][0].get('Status')
data_gen = DataGenerator()
data_gen.load_source_file(source_file, ['Id', 'External_Id__c', 'Status'])
object_status = data_gen.load_dataset('object_status',
original_status_file,
['Id', 'Status'])
status_by_id = object_status.group_by('Id')
## Order and Contract records can go from DRAFT directly to their final status
## That is why only one file containing all final statuses is needed
## Note: For reference, an ALL status file, containing SAs and their final status, is created for SalesAgreements
new_rows = []
row_count = len(data_gen.rows)
for r in range(row_count):
row = data_gen.rows.pop()
column_values = data_gen.row_to_column_values(row)
column_values['Status'] = get_original_final_status(
status_by_id, column_values['Id'])
new_rows.append(data_gen.column_values_to_row(column_values))
data_gen.rows = new_rows
data_gen.reverse()
# write file containing all statuses
status_file = definitions.mfg_temporal_path.format(tmp_folder) + file_name
data_gen.write(status_file, columns=['External_Id__c', 'Id', 'Status'])
# clear objects
new_rows.clear()
status_by_id.clear()
data_gen.remove_dataset('object_status')
if file_name == 'SalesAgreement.status.ALL.csv':
## SalesAgreements require to be updated in steps up to their final status
## 1> Draft (already inserted)
## 2> Approved (all records but the ones with final_status=Draft must be updated to Approved)
## 3> Discarded (only records with final status as Discarded)
## 4> Cancelled (only records with final status as Cancelled)
## 5> Expired (only records with final status as Expired)
## Note: Some status like Activated are automatically handled in the Org once a record is Approved
data_gen.load_source_file(status_file)
data_gen.add_dataset('sa_all_status', copy.deepcopy(data_gen.rows))
for status_name in ['Approved', 'Discarded', 'Cancelled', 'Expired']:
status_file = definitions.mfg_temporal_path.format(
tmp_folder) + 'SalesAgreement.status.' + status_name.upper(
) + '.csv'
if status_name == 'Approved':
data_gen.add_constant_column('Status', 'Approved')
data_gen.apply_transformations()
else:
data_gen.rows = copy.deepcopy(
data_gen.datasets['sa_all_status'])
data_gen.filter(lambda cv: cv['Status'] == status_name)
if data_gen.row_count:
data_gen.write(status_file,
columns=['External_Id__c', 'Status'])
else:
print("No records for {}".format(status_file))
def run(batch_id,
source_file_name,
output_file_name,
config,
reference_date=today_datetime,
filter_function=None):
data_gen = DataGenerator()
# load source file
data_gen.load_source_file(source_file_name)
# generate external id
col_name = config['externalIdColumnName']
data_gen.add_formula_column(col_name,
formula=lambda: config['externalIdFormat'] +
str(data_gen.current_row + 1))
# iterate through the columns to be mapped
# load current foreign file
# if replaceSourceColumn is true, replace the 'sourceColumn' by 'replacementColumnName'
# retrieve 'foreignRetrieveColumn' where 'foreignMappingColumn' == 'sourceColumn'
for mapCol in config['mappings']:
if '.source.' in mapCol['foreignFile']:
foreign_file = definitions.mfg_source_path + mapCol['foreignFile']
else:
foreign_file = definitions.mfg_temporal_path.format(
today.isoformat()) + mapCol['foreignFile']
foreignRetrieveColumn = mapCol['foreignRetrieveColumn']
sourceColumn = mapCol['sourceColumn']
aux_dataset = data_gen.load_dataset('aux', foreign_file)
aux_by_id = aux_dataset.group_by('Id')
def get_aux_data(column_values):
if column_values[sourceColumn] == '':
aux_data = ''
else:
aux_data = aux_by_id.get(
column_values[sourceColumn])[0].get(foreignRetrieveColumn)
return aux_data
data_gen.add_formula_column(sourceColumn, formula=get_aux_data)
data_gen.apply_transformations()
if mapCol['replaceSourceColumn']:
data_gen.rename_column(sourceColumn,
mapCol['replacementColumnName'])
# always empty the auxiliary lists
aux_dataset = []
aux_by_id = []
# remove auxiliary dataset to free up memory
if 'aux' in data_gen.datasets:
data_gen.remove_dataset('aux')
if 'Status' in data_gen.column_names:
data_gen.add_constant_column('Status', 'Draft')
# generate LastProcessedDate
data_gen.add_constant_column('LastProcessedDate', today.isoformat())
# add a UUID for each row that is created in this batch
data_gen.add_constant_column('analyticsdemo_batch_id__c', batch_id)
data_gen.apply_transformations()
if filter_function:
data_gen.filter(filter_function)
data_gen.write(output_file_name)
# Now the creation of the status file begins
tmp_folder = reference_date.strftime("%Y-%m-%d")
if 'Contract.csv' in output_file_name:
generate_status_file(source_file=output_file_name,
original_status_file=definitions.source_contract,
tmp_folder=tmp_folder,
file_name='Contract.status.ALL.csv')
elif 'Order.csv' in output_file_name:
generate_status_file(source_file=output_file_name,
original_status_file=definitions.source_order,
tmp_folder=tmp_folder,
file_name='Order.status.ALL.csv')
elif 'SalesAgreement.csv' in output_file_name:
generate_status_file(
source_file=output_file_name,
original_status_file=definitions.source_sales_agreement,
tmp_folder=tmp_folder,
file_name='SalesAgreement.status.ALL.csv')
