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, 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 run(batch_id, source_file_name, output_file_name):
data_gen = DataGenerator()
# load source file
source_columns = [
'External_Id__c', 'AccountExternalId__c', 'Owner.External_Id__c',
'Name', 'Amount', 'StageName', 'LeadSource', 'Type',
'ForecastCategoryName', 'CloseDate', 'CreatedDate__c',
'RecordType.DeveloperName', 'LastActivityDate__c', 'Product2Name__c',
'Product2Family__c', 'Region__c', 'TimeToClose__c',
'SalesStageCount__c', 'AccountAnnualRevenue__c',
'AccountNumberOfEmployees__c', 'AccountBookings__c', 'Competitor__c',
'DealSizeCategory__c', 'Exec_Meeting__c', 'Interactive_Demo__c'
]
data_gen.load_source_file(source_file_name, source_columns)
data_gen.rename_column('AccountExternalId__c', 'Account.External_Id__c')
data_gen.rename_column('CreatedDate__c', 'DateTimeCreated__c')
data_gen.add_formula_column(
'LastModifiedDate__c',
lambda cv: dateutil.parser.parse(cv['LastActivityDate__c']))
# 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()
data_gen.write(output_file_name)
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()
data_gen.row_count = count
if 'gender' in selected_filters:
if selected_filters['gender'] == 'male':
data_gen.add_constant_column('Gender', 'Male')
else:
data_gen.add_constant_column('Gender', 'Female')
else:
data_gen.add_formula_column('Gender', formula=fake.gender)
def first_name_formula(column_values):
if column_values['Gender'] == 'Male':
return fake.first_name_male()
else:
return fake.first_name_female()
data_gen.add_formula_column('First Name', first_name_formula)
data_gen.add_formula_column('Last Name', formula=fake.last_name)
data_gen.add_formula_column('Name', lambda cv: cv['First Name'] + ' ' + cv['Last Name'])
data_gen.apply_transformations()
return list(map(lambda r: data_gen.row_to_column_values(r, columns).values(), data_gen.rows))
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 run(batch_id, source_file_name, output_file_name, products_file_name, pricebook_file_name):
data_gen = DataGenerator()
# load source file
source_columns = ['External_Id__c', 'Product2Name__c', 'Amount']
data_gen.load_source_file(source_file_name, source_columns)
# load datasets
products = data_gen.load_dataset('products', products_file_name)
products_by_name = products.group_by('Name')
pricebook = data_gen.load_dataset('pricebook', pricebook_file_name)
pricebook_by_product = pricebook.group_by('Product2.External_Id__c')
# rename columns
data_gen.rename_column('External_Id__c', 'Opportunity.External_Id__c')
data_gen.rename_column('Amount', 'TotalPrice')
data_gen.add_formula_column('External_Id__c', formula=lambda: 'W_OpportunityLineItem.' + str(data_gen.current_row + 1))
# transform product name to code
data_gen.add_formula_column('ProductCode', lambda cv: products_by_name[cv['Product2Name__c']][0]['ProductCode'])
# generate product reference id
data_gen.add_formula_column('Product2.External_Id__c',
lambda cv: products_by_name[cv['Product2Name__c']][0]['External_Id__c'])
# generate list price
data_gen.add_formula_column('ListPrice', lambda cv: pricebook_by_product[cv['ProductCode']][0]['UnitPrice'])
# generate pricebook reference id
data_gen.add_formula_column('PricebookEntry.External_Id__c',
lambda cv: pricebook_by_product[cv['ProductCode']][0]['External_Id__c'])
# generate quantity
def quanity_formula(column_values):
total_price = int(column_values['TotalPrice'])
list_price = int(column_values['ListPrice'])
quantity = total_price / list_price
if quantity <= 0:
quantity = 1
return ceil(quantity)
data_gen.add_formula_column('Quantity', quanity_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()
output_columns = [
'External_Id__c',
'Opportunity.External_Id__c',
'TotalPrice',
'PricebookEntry.External_Id__c',
'Quantity',
'analyticsdemo_batch_id__c'
]
data_gen.write(output_file_name, output_columns)
def run(batch_id, source_file_name, output_file_name, reference_datetime=today, id_offset=0):
data_gen = DataGenerator()
# load source file
source_columns = [
'External_Id__c',
'Owner.External_Id__c',
'CreatedDate__c',
'LastActivityDate__c'
]
data_gen.load_source_file(source_file_name, source_columns)
data_gen.rename_column('External_Id__c', 'What.External_Id__c')
data_gen.rename_column('LastActivityDate__c', 'ActivityDate')
# generate a random number of tasks per opportunity
data_gen.duplicate_rows(duplication_factor=lambda: randint(1, 3))
data_gen.add_formula_column('External_Id__c', formula=lambda: 'W_Task.' + str(id_offset + data_gen.current_row + 1))
data_gen.add_formula_column('TaskSubtype', formula=task.oppty_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):
oppty_create_date = dateutil.parser.parse(column_values['CreatedDate__c'])
oppty_last_activity_date = dateutil.parser.parse(column_values['ActivityDate'])
create_date = fake.date_time_between_dates(oppty_create_date, oppty_last_activity_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 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)
# 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()
data_gen.write(output_file_name)
def run(input_path, output_path, config_source):
configs = json.loads(file_to_string(config_source))
time_shifting_file = configs.get('timeShiftingPivot').get('fileName')
time_shifting_field = configs.get('timeShiftingPivot').get('fieldName')
data_gen = DataGenerator()
data_gen.load_source_file(input_path + time_shifting_file,
time_shifting_field)
if time_shifting_field != 'LastProcessedDate':
aux_date = max([x[0] for x in data_gen.rows])[:10]
else:
# LastProcessedDate is a constant column, do not iterate through all rows
aux_date = data_gen.rows[0][0][:10]
delta_to_increase = (today -
datetime.strptime(aux_date, "%Y-%m-%d").date()).days
def aux_date_formula(dateToShift):
def date_formula(column_values):
if column_values[dateToShift] != "":
create_date = dateutil.parser.parse(column_values[dateToShift])
if len(column_values[dateToShift]) == 19:
return (create_date + timedelta(days=delta_to_increase)
).strftime('%Y-%m-%d %H:%M:%S')
elif len(column_values[dateToShift]) < 24:
return (
create_date +
timedelta(days=delta_to_increase)).strftime('%Y-%m-%d')
else:
return (create_date + timedelta(days=delta_to_increase)
).strftime('%Y-%m-%dT%H:%M:%S.000Z')
data_gen.add_formula_column(dateToShift, date_formula)
if not output_path:
output_path = 'output/'
for input_file in configs.get('inputFiles'):
file_name = input_file.get('fileName')
date_fields = input_file.get('dateFields', [])
print("Timeshifting process for ", file_name, " will start ...")
data_gen.load_source_file(input_path + file_name)
data_gen.add_constant_column('LastProcessedDate', today.isoformat())
for dateToShift in date_fields:
aux_date_formula(dateToShift)
data_gen.apply_transformations()
data_gen.write(output_path + file_name)
def run(batch_id, source_file_name, output_file_name):
data_gen = DataGenerator()
# load source file
source_columns = ['KnowledgeArticle.External_Id__c', 'CreatedDate__c']
data_gen.load_source_file(source_file_name, source_columns)
data_gen.rename_column('KnowledgeArticle.External_Id__c', 'External_Id__c')
data_gen.add_formula_column('ArticleNumber__c',
lambda: data_gen.current_row + 1)
data_gen.add_formula_column('CaseAssociationCount__c',
lambda: randint(1, 6))
def first_published_date_formula(column_values):
create_date = dateutil.parser.parse(column_values['CreatedDate__c'])
return (create_date +
timedelta(days=randint(1, 10))).isoformat(sep=' ')
data_gen.add_formula_column('FirstPublishedDate__c',
formula=first_published_date_formula)
def last_published_date_formula(column_values):
first_publised_date = dateutil.parser.parse(
column_values['FirstPublishedDate__c'])
return (first_publised_date +
timedelta(days=randint(1, 10))).isoformat(sep=' ')
data_gen.add_formula_column('LastPublishedDate__c',
formula=last_published_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()
output_columns = [
'ArticleNumber__c', 'External_Id__c', 'CaseAssociationCount__c',
'CreatedDate__c', 'FirstPublishedDate__c', 'LastPublishedDate__c',
'analyticsdemo_batch_id__c'
]
data_gen.write(output_file_name, output_columns)
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 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):
data_gen = DataGenerator()
# load source file
account_columns = ['External_Id__c']
data_gen.load_source_file(source_file_name, account_columns)
data_gen.rename_column('External_Id__c', 'Account.External_Id__c')
data_gen.add_formula_column(
'External_Id__c', lambda cv: cv['Account.External_Id__c'].replace(
'W_Account', 'W_Contact'))
data_gen.add_formula_column('FirstName', formula=fake.first_name)
data_gen.add_formula_column('LastName', formula=fake.last_name)
# 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()
data_gen.write(output_file_name)
def run(batch_id, source_file_name, output_file_name):
data_gen = DataGenerator()
# load source file
source_columns = ['KnowledgeArticle.External_Id__c']
data_gen.load_source_file(source_file_name, source_columns)
data_gen.rename_column('KnowledgeArticle.External_Id__c',
'Parent.External_Id__c')
data_gen.add_formula_column(
'External_Id__c',
formula=lambda: 'W_KCSArticle_DCS.' + str(data_gen.current_row + 1))
data_gen.add_constant_column('DataCategoryGroupName__c', 'All')
data_gen.add_constant_column('DataCategoryName__c', 'All')
# 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()
output_columns = [
'External_Id__c', 'Parent.External_Id__c', 'DataCategoryGroupName__c',
'DataCategoryName__c', 'analyticsdemo_batch_id__c'
]
data_gen.write(output_file_name, output_columns)
def run(batch_id, source_file_name, output_file_name):
data_gen = DataGenerator()
# load source file
source_columns = [
'KnowledgeArticle.External_Id__c',
'User.External_Id__c',
'CreatedDate__c'
]
data_gen.load_source_file(source_file_name, source_columns)
data_gen.rename_column('KnowledgeArticle.External_Id__c', 'Parent.External_Id__c')
data_gen.rename_column('User.External_Id__c', 'Owner.External_Id__c')
data_gen.add_formula_column('External_Id__c', formula=lambda: 'W_KCSArticle_ViewStat.' + str(data_gen.current_row + 1))
channels = [
'App',
'Desktop Site',
'Mobile Site'
]
data_gen.add_formula_column('Channel__c', channels)
data_gen.add_formula_column('ViewCount__c', formula=lambda: randint(1, 100))
data_gen.add_formula_column('NormalizedScore__c', formula=lambda: round(uniform(1, 10), 3))
# 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()
output_columns = [
'External_Id__c',
'Channel__c',
'Parent.External_Id__c',
'ViewCount__c',
'NormalizedScore__c',
'analyticsdemo_batch_id__c'
]
data_gen.write(output_file_name, output_columns)
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):
data_gen = DataGenerator()
# load source file
source_columns = [
'External_Id__c', 'Owner.External_Id__c', 'CreatedDate__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('Owner.External_Id__c', 'User.External_Id__c')
# todo one case article per case? at most 1? distribution?
data_gen.duplicate_rows(
duplication_factor=lambda: choice([0, 1], p=[.75, .25]))
data_gen.add_formula_column(
'External_Id__c',
formula=lambda: 'W_CaseArticle.' + str(data_gen.current_row + 1))
data_gen.add_formula_column(
'KnowledgeArticle.External_Id__c',
formula=lambda: 'W_KCSArticle.' + str(data_gen.current_row + 1))
data_gen.add_constant_column('ArticleVersionNumber__c', 1)
data_gen.add_constant_column('IsSharedByEmail__c', ['true', '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()
output_columns = [
'External_Id__c', 'User.External_Id__c', 'ArticleVersionNumber__c',
'CreatedDate__c', 'KnowledgeArticle.External_Id__c',
'IsSharedByEmail__c', 'Case.External_Id__c',
'analyticsdemo_batch_id__c'
]
data_gen.write(output_file_name, output_columns)
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(input_path, output_path, config_source):
configs = json.loads(file_to_string(config_source))
time_shifting_file = configs.get('timeShiftingPivot').get('fileName')
time_shifting_field = configs.get('timeShiftingPivot').get('fieldName')
data_gen = DataGenerator()
data_gen.load_source_file(input_path + time_shifting_file,
time_shifting_field)
aux_date = max([x[0] for x in data_gen.rows])[:10]
delta_to_increase = (today -
datetime.strptime(aux_date, "%Y-%m-%d").date()).days
def aux_date_formula(dateToShift):
def date_formula(column_values):
if column_values[dateToShift] != "":
create_date = dateutil.parser.parse(column_values[dateToShift])
if len(column_values[dateToShift]) == 19:
return (create_date + timedelta(days=delta_to_increase)
).strftime('%Y-%m-%d %H:%M:%S')
elif len(column_values[dateToShift]) < 24:
return (
create_date +
timedelta(days=delta_to_increase)).strftime('%Y-%m-%d')
else:
return (create_date + timedelta(days=delta_to_increase)
).strftime('%Y-%m-%dT%H:%M:%S.000Z')
data_gen.add_formula_column(dateToShift, date_formula)
current_year = today.year
map_quota_year = {}
def quotas_date_formula(dateToShift):
def date_formula(column_values):
if column_values[dateToShift] != "":
quota_year = column_values[dateToShift][:4]
d = column_values[dateToShift].replace(
quota_year, map_quota_year[quota_year])
return d
date_index = data_gen.column_names[dateToShift]
dates = [e[date_index] for e in data_gen.rows]
max_year = max(dates)[:4]
min_year = min(dates)[:4]
map_quota_year[max_year] = str(current_year)
map_quota_year[min_year] = str(current_year - 1)
data_gen.add_formula_column(dateToShift, date_formula)
if not output_path:
output_path = 'output/'
for input_file in configs.get('inputFiles'):
file_name = input_file.get('fileName')
date_fields = input_file.get('dateFields', [])
print("Timeshifting process for ", file_name, " will start ...")
data_gen.load_source_file(input_path + file_name)
if file_name not in [
'FscDemoWeeks.csv', 'WM_Add_Assets_Prediction_Final.csv',
'WM_Churn_Predictions_Final.csv'
]:
data_gen.add_constant_column('LastProcessedDate',
today.isoformat())
for dateToShift in date_fields:
if file_name != 'FscDemoQuota.csv':
aux_date_formula(dateToShift)
else:
quotas_date_formula(dateToShift)
data_gen.apply_transformations()
data_gen.write(output_path + file_name)
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,
id_offset=0):
data_gen = DataGenerator()
# load source file
source_columns = [
'External_Id__c', 'Owner.External_Id__c', 'CreatedDate__c',
'LastActivityDate__c'
]
data_gen.load_source_file(source_file_name, source_columns)
data_gen.rename_column('External_Id__c', 'What.External_Id__c')
data_gen.rename_column('LastActivityDate__c', 'ActivityDate')
# generate a random number of events per opportunity
data_gen.duplicate_rows(duplication_factor=lambda: randint(1, 3))
data_gen.add_formula_column(
'External_Id__c',
formula=lambda: 'W_Event.' + str(id_offset + data_gen.current_row + 1))
data_gen.add_formula_column('Subject', formula=event.event_subject)
data_gen.add_formula_column('EventSubtype', formula=event.event_subtype)
data_gen.add_formula_column('DurationInMinutes',
formula=event.event_call_duration)
is_first = True
def create_date_formula(column_values):
oppty_create_date = dateutil.parser.parse(
column_values['CreatedDate__c'])
oppty_last_activity_date = dateutil.parser.parse(
column_values['ActivityDate'])
nonlocal is_first
if is_first:
create_date = oppty_last_activity_date
else:
create_date = fake.date_time_between_dates(
oppty_create_date, oppty_last_activity_date)
is_first = False
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 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)
def activity_datetime_formula(column_values):
return dateutil.parser.parse(column_values['ActivityDate'])
data_gen.add_formula_column('ActivityDateTime', activity_datetime_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
data_gen.apply_transformations()
data_gen.write(output_file_name)
def run(batch_id, source_file_name, output_file_name):
data_gen = DataGenerator()
# load source file
source_columns = [
'KnowledgeArticle.External_Id__c', 'User.External_Id__c',
'CreatedDate__c'
]
data_gen.load_source_file(source_file_name, source_columns)
data_gen.rename_column('KnowledgeArticle.External_Id__c',
'KCSArticle__ka.External_Id__c')
data_gen.rename_column('User.External_Id__c', 'Owner.External_Id__c')
data_gen.add_formula_column(
'External_Id__c',
formula=lambda: 'W_KCSArticleVersion.' + str(data_gen.current_row + 1))
data_gen.add_formula_column('ArticleNumber__c',
lambda: data_gen.current_row + 1)
data_gen.add_formula_column('PublishStatus__c', ['Archived', 'Online'])
data_gen.add_constant_column('IsLatestVersion__c', 'true')
data_gen.add_constant_column('IsVisibleInApp__c', 'true')
data_gen.add_constant_column('IsVisibleInCsp__c', 'true')
data_gen.add_constant_column('IsVisibleInPkb__c', 'true')
data_gen.add_constant_column('IsVisibleInPrm__c', 'true')
data_gen.add_constant_column('VersionNumber__c', '1')
data_gen.add_constant_column('Language__c', 'en_US')
titles = [
"Health", "Computers", "Music", "Tools", "Home", "Outdoors",
"Jewelery", "Toys", "Grocery", "Clothing", "Games", "Automotive",
"Beauty", "Garden", "Books", "Industrial", "Baby", "Kids", "Movies",
"Sports", "Shoes", "Electronics"
]
data_gen.add_formula_column('Title__c', titles)
# 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()
output_columns = [
'External_Id__c', 'ArticleNumber__c', 'CreatedDate__c',
'Owner.External_Id__c', 'PublishStatus__c', 'IsLatestVersion__c',
'IsVisibleInApp__c', 'IsVisibleInCsp__c', 'IsVisibleInPkb__c',
'IsVisibleInPrm__c', 'KCSArticle__ka.External_Id__c', 'Title__c',
'VersionNumber__c', 'Language__c', 'analyticsdemo_batch_id__c'
]
data_gen.write(output_file_name, output_columns)
def run(batch_id, source_file_name, output_file_name):
data_gen = DataGenerator()
# load source file
source_columns = ['AccountExternalId__c', 'AccountName__c']
data_gen.load_source_file(source_file_name, source_columns)
# rename columns
data_gen.rename_column('AccountExternalId__c', 'External_Id__c')
data_gen.rename_column('AccountName__c', 'Name')
# filter out duplicate data
data_gen.unique()
# load shape data as dataset
shape_columns = [
'AccountExternalId__c',
'AccountAnnualRevenue__c',
'AccountNumberOfEmployees__c',
'AccountBookings__c',
'Region__c',
'Owner.External_Id__c',
'CloseDate',
'CreatedDate__c']
shape_dataset = data_gen.load_dataset('shape', source_file_name, shape_columns)
# build map of account values
shape_account_map = shape_dataset.group_by('AccountExternalId__c')
# helper method to get shape data related to an account
def get_shape_data(column_values, shape_column_name):
return shape_account_map.get(column_values['External_Id__c'])[0].get(shape_column_name)
# generate owner
def owner_formula(column_values):
return get_shape_data(column_values, 'Owner.External_Id__c')
data_gen.add_formula_column('Owner.External_Id__c', owner_formula)
# update number employees based on shape data
def employees_formula(column_values):
employees = get_shape_data(column_values, 'AccountNumberOfEmployees__c')
return randint(*account.client_size_employees_bands[employees])
data_gen.add_formula_column('NumberOfEmployees', employees_formula)
# update annual revenue based on shape data
def revenue_formula(column_values):
revenue = get_shape_data(column_values, 'AccountAnnualRevenue__c')
return 1000 * randint(*account.client_size_rev_bands[revenue])
data_gen.add_formula_column('AnnualRevenue', revenue_formula)
# generate account source
data_gen.add_formula_column('AccountSource', formula=account.account_source)
# update type based on shape data
def type_formula(column_values):
return get_shape_data(column_values, 'AccountAnnualRevenue__c')
data_gen.add_formula_column('Type', type_formula)
# generate industry
data_gen.add_formula_column('Industry', formula=account.account_industry)
# generate billing street
data_gen.add_formula_column('BillingStreet', formula=lambda: fake.building_number() + ' ' + fake.street_name())
# generate billing city
data_gen.add_formula_column('BillingCity', formula=fake.city)
# update billing state based on shape data
def state_formula(column_values):
region = get_shape_data(column_values, 'Region__c')
return choice(account.region_state_map[region])
data_gen.add_formula_column('BillingState', state_formula)
# generate billing country
data_gen.add_constant_column('BillingCountry', 'USA')
# generate year started
data_gen.add_formula_column('YearStarted', formula=account.account_year_started)
# generate ownership
data_gen.add_formula_column('Ownership', formula=account.account_ownership)
# generate rating
data_gen.add_formula_column('Rating', formula=account.account_rating)
# generate earliest created date
def create_date_formula(column_values):
opptys = shape_account_map.get(column_values['External_Id__c'])
create_dates = [dateutil.parser.parse(oppty['CreatedDate__c']) for oppty in opptys]
create_dates.sort()
return create_dates[0]
data_gen.add_formula_column('CreatedDate__c', create_date_formula)
# generate earliest close date
def close_date_formula(column_values):
opptys = shape_account_map.get(column_values['External_Id__c'])
close_dates = [dateutil.parser.parse(oppty['CloseDate']).date() for oppty in opptys]
close_dates.sort()
return close_dates[0]
data_gen.add_formula_column('OpportunityCloseDate__c', close_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)
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, 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(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_datetime=today):
data_gen = DataGenerator()
# load source file
account_columns = [
'External_Id__c', 'Owner.External_Id__c', 'OpportunityCloseDate__c'
]
data_gen.load_source_file(source_file_name, account_columns)
data_gen.rename_column('External_Id__c', 'Account.External_Id__c')
data_gen.rename_column('OpportunityCloseDate__c', 'CreatedDate__c')
# generate a random number of cases per account
data_gen.duplicate_rows(
duplication_factor=lambda: int(lognormal(0) + randint(0, 2)))
data_gen.add_formula_column(
'External_Id__c',
formula=lambda: 'W_Sales_Case.' + str(data_gen.current_row + 1))
# generate contact
def contact_formula(column_values):
return column_values['Account.External_Id__c'].replace(
'W_Account', 'W_Contact')
data_gen.add_formula_column('Contact.External_Id__c', contact_formula)
data_gen.add_formula_column('IsEscalated', case.case_is_escalated)
data_gen.add_formula_column('CSAT__c', case.case_csat)
data_gen.add_formula_column('Origin', formula=case.case_origin)
data_gen.add_formula_column('Type', formula=case.case_type)
data_gen.add_formula_column('Subject', formula=case.case_subject)
data_gen.add_formula_column('Priority', formula=case.case_priority)
data_gen.add_formula_column('Status', formula=case.case_status)
def create_date_formula(column_values):
oppty_close_date = dateutil.parser.parse(
column_values['CreatedDate__c'])
create_date = oppty_close_date + timedelta(days=randint(0, 90))
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 close_date_formula(column_values):
create_date = dateutil.parser.parse(column_values['CreatedDate__c'])
if column_values['Status'] == 'Closed':
close_date = create_date + timedelta(days=randint(0, 10))
if close_date > reference_datetime:
close_date = reference_datetime
return close_date.isoformat(sep=' ')
else:
return ''
data_gen.add_formula_column('ClosedDate__c', close_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)
data_gen.apply_transformations()
data_gen.write(output_file_name)
def run(batch_id,
source_file_name,
output_file_name,
reference_date=today_datetime):
data_gen = DataGenerator()
# load source file
source_columns = [
'External_Id__c', 'StageName', 'Amount', 'ForecastCategory',
'CloseDate', 'CreatedDate__c', 'SalesStageCount__c'
]
data_gen.load_source_file(source_file_name, source_columns)
data_gen.rename_columns({
'StageName': 'StageName__c',
'Amount': 'Amount__c',
'ForecastCategory': 'ForecastCategory__c',
'CloseDate': 'CloseDate__c'
})
data_gen.add_copy_column('Opportunity.External_Id__c', 'External_Id__c')
# 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()
stages = ['Qualification', 'Discovery', 'Proposal/Quote', 'Negotiation']
forecast_categories = ['BestCase', 'Pipeline', 'Commit']
pipe_bucket = [
'No Change', 'Reopen', 'Expand', 'Reduce', 'Moved Out', 'Moved In',
'Stage Change'
]
pipe_bucket_ratio = [0.10, 0.05, 0.15, 0.15, 0.30, 0.10, 0.15]
qualification_pipe_bucket = [
'No Change', 'Reopen', 'Expand', 'Reduce', 'Moved Out', 'Moved In'
]
qualification_pipe_bucket_ratio = [0.20, 0.05, 0.20, 0.10, 0.35, 0.10]
zero_amount_pipe_bucket = [
'No Change', 'Reopen', 'Moved Out', 'Moved In', 'Stage Change'
]
zero_amount_pipe_bucket_ratio = [0.20, 0.05, 0.35, 0.10, 0.30]
current_count = 1
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)
opportunity_id = column_values['Opportunity.External_Id__c']
close_date = dateutil.parser.parse(column_values['CloseDate__c'])
create_date = dateutil.parser.parse(column_values['CreatedDate__c'])
final_amount = int(column_values['Amount__c'])
final_forecast_category = column_values['ForecastCategory__c']
final_stage_name = column_values['StageName__c']
stage_count = int(column_values['SalesStageCount__c'])
# initialize most recent event date to reference_date or earlier
event_date_range_start = create_date + (close_date - create_date) / 2
event_date_range_end = close_date
if close_date > reference_date:
event_date_range_end = reference_date
event_date_range_start = create_date + (reference_date -
create_date) / 2
# ensure event happens on or after opportunity create_date
event_date = fake.date_time_between_dates(event_date_range_start,
event_date_range_end)
# create final state
column_values['CreatedDate__c'] = event_date
column_values['External_Id__c'] = 'W_OpportunityHistory.' + str(
current_count)
current_count += 1
new_rows.append(data_gen.column_values_to_row(column_values))
next_create_date = event_date
next_stage_name = final_stage_name
next_forecast_category = final_forecast_category
next_close_date = close_date
next_amount = final_amount
movedOut = False
movedIn = False
expand = False
reduce = False
reopen = False
initialized = False
# generate events in reverse order until create_date
for current_stage_count in range(stage_count):
# choose the proper bucket depending on the scenario
bucket = pipe_bucket
ratio = pipe_bucket_ratio
if next_amount <= 0:
bucket = zero_amount_pipe_bucket
ratio = zero_amount_pipe_bucket_ratio
elif next_stage_name == 'Qualification':
bucket = qualification_pipe_bucket
ratio = qualification_pipe_bucket_ratio
event = choice(bucket, p=ratio)
event_date_range_end = event_date
event_date_range_start = create_date + (event_date -
create_date) / 2
event_date = fake.date_time_between_dates(event_date_range_start,
event_date_range_end)
# if next stage is closed, make the previous event a stage change
if 'Closed' in next_stage_name:
event = 'Stage Change'
# if the event date is the create date, create the initial state
if current_stage_count == stage_count - 1:
event_date = create_date
event = 'Initial State'
if event != 'No Change':
curr_close_date = next_close_date
curr_amount = next_amount
curr_stage_name = next_stage_name
curr_forecast_category = next_forecast_category
if event == 'Reopen' and not reopen:
curr_stage_name = 'Closed Lost'
curr_forecast_category = 'Omitted'
reopen = True
elif event == 'Initial State':
curr_stage_name = 'Qualification'
curr_forecast_category = 'Pipeline'
initialized = True
elif event == 'Expand' and not expand:
curr_amount = next_amount - int(
uniform(.15, .45) * final_amount)
if curr_amount <= 0:
# reduce instead
curr_amount = next_amount + int(
uniform(.15, .45) * final_amount)
expand = True
elif event == 'Reduce' and not reduce:
curr_amount = next_amount + int(
uniform(.15, .45) * final_amount)
reduce = True
elif event == 'Moved In' and not movedIn:
curr_close_date = curr_close_date + timedelta(
days=randint(0, 30))
movedIn = True
elif event == 'Moved Out' and not movedOut:
curr_close_date = curr_close_date - timedelta(
days=randint(30, 90))
movedOut = True
elif event == 'Stage Change':
# if next stage is not closed, use previous stage
if 'Closed' not in next_stage_name and stages.index(
next_stage_name) - 1 > 0:
curr_stage_name = stages[stages.index(next_stage_name)
- 1]
# if next stage is closed, use any stage
elif 'Closed' in next_stage_name:
curr_stage_name = stages[randint(1, len(stages) - 1)]
else:
curr_stage_name = stages[0]
curr_forecast_category = forecast_categories[randint(
0,
len(forecast_categories) - 1)]
new_column_values = {
'External_Id__c':
'W_OpportunityHistory.' + str(current_count),
'Opportunity.External_Id__c': opportunity_id,
'StageName__c': curr_stage_name,
'Amount__c': curr_amount,
'ForecastCategory__c': curr_forecast_category,
'CreatedDate__c': event_date.isoformat(sep=' '),
'CloseDate__c': curr_close_date.date().isoformat(),
'analyticsdemo_batch_id__c': batch_id
}
current_count += 1
new_rows.append(
data_gen.column_values_to_row(new_column_values))
next_stage_name = curr_stage_name
next_forecast_category = curr_forecast_category
next_close_date = curr_close_date
next_amount = curr_amount
data_gen.rows = new_rows
data_gen.reverse()
data_gen.write(output_file_name, [
'External_Id__c', 'Amount__c', 'StageName__c', 'ForecastCategory__c',
'CloseDate__c', 'CreatedDate__c', 'Opportunity.External_Id__c',
'analyticsdemo_batch_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):
data_gen = DataGenerator()
# load source file
source_columns = [
'External_Id__c', 'Owner.External_Id__c', 'CreatedDate__c',
'EndTime__c', 'EndedBy__c', 'Status__c'
]
data_gen.load_source_file(source_file_name, source_columns)
data_gen.rename_column('Owner.External_Id__c', 'Agent.External_Id__c')
data_gen.add_copy_column('LiveChatTranscript.External_Id__c',
'External_Id__c')
data_gen.add_copy_column('Time__c', 'CreatedDate__c')
data_gen.add_constant_column('Type__c', '')
data_gen.add_constant_column('Detail__c', '')
# 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()
type_detail_map = {
"ChatRequest": "Visitor requested chat.",
"ChoiceRoute":
"Choice chat request routed to all available qualified agents.",
"CancelNoAgent":
"Chat request canceled because no qualifying agents were available.",
"Accept": "Chat request accepted by agent.",
"CancelVisitor": "Visitor clicked Cancel Chat.",
"LeaveAgent": "Agent left chat.",
"EndAgent": "Agent clicked End Chat.",
"LeaveVisitor": "Visitor left chat.",
"EndVisitor": "Visitor clicked End Chat."
}
current_count = 1
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)
live_chat = column_values['LiveChatTranscript.External_Id__c']
agent = column_values['Agent.External_Id__c']
create_date = dateutil.parser.parse(column_values['CreatedDate__c'])
end_date = dateutil.parser.parse(column_values['EndTime__c'])
ended_by = column_values['EndedBy__c']
status = column_values['Status__c']
# initialize chat request
new_column_values = {
'External_Id__c':
'W_LiveChatTranscriptEvent.' + str(current_count),
'LiveChatTranscript.External_Id__c': live_chat,
'Agent.External_Id__c': agent,
'CreatedDate__c': create_date.isoformat(sep=' '),
'Time__c': create_date.isoformat(sep=' '),
'Type__c': 'ChatRequest',
'Detail__c': 'Visitor requested chat.',
'analyticsdemo_batch_id__c': batch_id
}
current_count += 1
new_rows.append(data_gen.column_values_to_row(new_column_values))
if status == 'Missed':
type__c = choice(['CancelVisitor', 'CancelNoAgent'])
if type__c == 'CancelNoAgent':
# no agents
create_date = fake.date_time_between_dates(
create_date, end_date)
new_column_values = {
'External_Id__c':
'W_LiveChatTranscriptEvent.' + str(current_count),
'LiveChatTranscript.External_Id__c':
live_chat,
'Agent.External_Id__c':
agent,
'CreatedDate__c':
create_date.isoformat(sep=' '),
'Time__c':
create_date.isoformat(sep=' '),
'Type__c':
'ChoiceRoute',
'Detail__c':
'Choice chat request routed to all available qualified agents.',
'analyticsdemo_batch_id__c':
batch_id
}
current_count += 1
new_rows.append(
data_gen.column_values_to_row(new_column_values))
create_date = fake.date_time_between_dates(
create_date, end_date)
new_column_values = {
'External_Id__c':
'W_LiveChatTranscriptEvent.' + str(current_count),
'LiveChatTranscript.External_Id__c':
live_chat,
'Agent.External_Id__c':
agent,
'CreatedDate__c':
create_date.isoformat(sep=' '),
'Time__c':
create_date.isoformat(sep=' '),
'Type__c':
type__c,
'Detail__c':
type_detail_map[type__c],
'analyticsdemo_batch_id__c':
batch_id
}
current_count += 1
new_rows.append(
data_gen.column_values_to_row(new_column_values))
type__c = choice(['LeaveVisitor', 'EndVisitor'])
new_column_values = {
'External_Id__c':
'W_LiveChatTranscriptEvent.' + str(current_count),
'LiveChatTranscript.External_Id__c':
live_chat,
'Agent.External_Id__c':
agent,
'CreatedDate__c':
end_date.isoformat(sep=' '),
'Time__c':
end_date.isoformat(sep=' '),
'Type__c':
type__c,
'Detail__c':
type_detail_map[type__c],
'analyticsdemo_batch_id__c':
batch_id
}
current_count += 1
new_rows.append(
data_gen.column_values_to_row(new_column_values))
else:
# visitor canceled
new_column_values = {
'External_Id__c':
'W_LiveChatTranscriptEvent.' + str(current_count),
'LiveChatTranscript.External_Id__c':
live_chat,
'Agent.External_Id__c':
agent,
'CreatedDate__c':
end_date.isoformat(sep=' '),
'Time__c':
end_date.isoformat(sep=' '),
'Type__c':
type__c,
'Detail__c':
type_detail_map[type__c],
'analyticsdemo_batch_id__c':
batch_id
}
current_count += 1
new_rows.append(
data_gen.column_values_to_row(new_column_values))
else:
type__c = 'ChoiceRoute'
new_column_values = {
'External_Id__c':
'W_LiveChatTranscriptEvent.' + str(current_count),
'LiveChatTranscript.External_Id__c': live_chat,
'Agent.External_Id__c': agent,
'CreatedDate__c': create_date.isoformat(sep=' '),
'Time__c': create_date.isoformat(sep=' '),
'Type__c': type__c,
'Detail__c': type_detail_map[type__c],
'analyticsdemo_batch_id__c': batch_id
}
current_count += 1
new_rows.append(data_gen.column_values_to_row(new_column_values))
type__c = 'Accept'
create_date = fake.date_time_between_dates(create_date, end_date)
new_column_values = {
'External_Id__c':
'W_LiveChatTranscriptEvent.' + str(current_count),
'LiveChatTranscript.External_Id__c': live_chat,
'Agent.External_Id__c': agent,
'CreatedDate__c': create_date.isoformat(sep=' '),
'Time__c': create_date.isoformat(sep=' '),
'Type__c': type__c,
'Detail__c': type_detail_map[type__c],
'analyticsdemo_batch_id__c': batch_id
}
current_count += 1
new_rows.append(data_gen.column_values_to_row(new_column_values))
if ended_by == 'Visitor':
type__c = choice(['LeaveVisitor', 'EndVisitor'])
new_column_values = {
'External_Id__c':
'W_LiveChatTranscriptEvent.' + str(current_count),
'LiveChatTranscript.External_Id__c':
live_chat,
'Agent.External_Id__c':
agent,
'CreatedDate__c':
end_date.isoformat(sep=' '),
'Time__c':
end_date.isoformat(sep=' '),
'Type__c':
type__c,
'Detail__c':
type_detail_map[type__c],
'analyticsdemo_batch_id__c':
batch_id
}
current_count += 1
new_rows.append(
data_gen.column_values_to_row(new_column_values))
else:
type__c = choice(['LeaveAgent', 'EndAgent'])
new_column_values = {
'External_Id__c':
'W_LiveChatTranscriptEvent.' + str(current_count),
'LiveChatTranscript.External_Id__c':
live_chat,
'Agent.External_Id__c':
agent,
'CreatedDate__c':
end_date.isoformat(sep=' '),
'Time__c':
end_date.isoformat(sep=' '),
'Type__c':
type__c,
'Detail__c':
type_detail_map[type__c],
'analyticsdemo_batch_id__c':
batch_id
}
current_count += 1
new_rows.append(
data_gen.column_values_to_row(new_column_values))
data_gen.rows = new_rows
# apply transformations and write file
output_columns = [
'External_Id__c', 'LiveChatTranscript.External_Id__c',
'Agent.External_Id__c', 'Type__c', 'Detail__c', 'CreatedDate__c',
'Time__c', 'analyticsdemo_batch_id__c'
]
data_gen.write(output_file_name, output_columns)
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'
]
data_gen.load_source_file(source_file_name, source_columns)
data_gen.rename_column('External_Id__c', 'Case.External_Id__c')
data_gen.duplicate_rows(duplication_factor=lambda: randint(0, 3))
data_gen.add_formula_column('External_Id__c', formula=lambda: 'W_Services_Event.' + str(data_gen.current_row + 1))
data_gen.add_formula_column('Subject', formula=event.event_subject)
data_gen.add_formula_column('EventSubtype', formula=event.event_subtype)
data_gen.add_formula_column('DurationInMinutes', formula=event.event_call_duration)
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['LastActivityDate__c']), case_create_date.time())
if case_close_date > reference_datetime:
case_close_date = reference_datetime
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)
def activity_datetime_formula(column_values):
return dateutil.parser.parse(column_values['ActivityDate'])
data_gen.add_formula_column('ActivityDateTime', activity_datetime_formula)
data_gen.add_constant_column('ShowAs', 'Busy')
# 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',
'Subject',
'EventSubtype',
'DurationInMinutes',
'ShowAs',
'CreatedDate__c',
'LastModifiedDate__c',
'ActivityDate',
'ActivityDateTime',
'analyticsdemo_batch_id__c'
]
data_gen.write(output_file_name, output_columns)
