def createFacts(events, users):
try:
events_uid = etl.cutout(events, 'tracking_id', 'utm_medium', 'utm_campaign')
events_tui = etl.cutout(events, 'user_id')
stage_uid = etl.join(users, events_uid, key='user_id')
stage_tui = etl.join(users, events_tui, key='tracking_id')
stage_utm = etl.cut(stage_tui, 'user_id', 'utm_medium', 'utm_campaign')
stage_uid_utm = etl.join(stage_uid, stage_utm, key='user_id')
stage_m_s = etl.mergesort(stage_uid_utm, stage_tui, key=['created_at', 'email'])
mappings = OrderedDict()
mappings['tid'] = 'tracking_id'
mappings['uid'] = 'user_id'
mappings['utm_medium'] = 'utm_medium'
mappings['utm_campaign'] = 'utm_campaign', {'audio': 'none', 'social': 'none'}
mappings['utm_campaigntype'] = 'utm_campaign'
mappings['email'] = 'email'
mappings['subscription'] = 'type'
mappings['sub_order'] = 'type', {'Signup Completed': '1', 'Trial Started': '2', 'Subscription Started': '3', 'Subscription Ended': '4'}
mappings['created_at'] = 'created_at'
# Mapping
stage_mapping = etl.fieldmap(stage_m_s, mappings)
# Sort
stage_mapping_ordered = etl.sort(stage_mapping, key=['created_at', 'email', 'sub_order'])
# Datetime split
t1 = etl.split(stage_mapping_ordered, 'created_at', 'T', ['date', 'time'], include_original=True)
t2 = etl.split(t1, 'date', '-', ['year', 'month', 'day'])
stage_ready = etl.split(t2, 'time', ':', ['hour', 'minute', 'second'])
# Export as csv to load folder
etl.tocsv(stage_ready, 'load/facts.csv')
except Exception as e:
print("Something went wrong. Error {0}".format(e))
# using the include_original argument
table3 = capture(table1, 'variable', '(\\w)(\\d+)', ['treat', 'time'], include_original=True)
look(table3)
# split
table1 = [['id', 'variable', 'value'],
['1', 'parad1', '12'],
['2', 'parad2', '15'],
['3', 'tempd1', '18'],
['4', 'tempd2', '19']]
from petl import split, look
look(table1)
table2 = split(table1, 'variable', 'd', ['variable', 'day'])
look(table2)
# select
table1 = [['foo', 'bar', 'baz'],
['a', 4, 9.3],
['a', 2, 88.2],
['b', 1, 23.3],
['c', 8, 42.0],
['d', 7, 100.9],
['c', 2]]
from petl import select, look
look(table1)
# using the include_original argument
table3 = capture(table1, 'variable', '(\\w)(\\d+)', ['treat', 'time'], include_original=True)
look(table3)
# split
table1 = [['id', 'variable', 'value'],
['1', 'parad1', '12'],
['2', 'parad2', '15'],
['3', 'tempd1', '18'],
['4', 'tempd2', '19']]
from petl import split, look
look(table1)
table2 = split(table1, 'variable', 'd', ['variable', 'day'])
look(table2)
# select
table1 = [['foo', 'bar', 'baz'],
['a', 4, 9.3],
['a', 2, 88.2],
['b', 1, 23.3],
['c', 8, 42.0],
['d', 7, 100.9],
['c', 2]]
from petl import select, look
look(table1)
mappings['utm_medium'] = 'utm_medium'
mappings['utm_campaign'] = 'utm_campaign', {'audio': 'none', 'social': 'none'}
mappings['utm_campaign_type'] = 'utm_campaign'
mappings['email'] = 'email'
mappings['subscription'] = 'type'
mappings['sub_order'] = 'type', {
'Signup Completed': '1',
'Trial Started': '2',
'Subscription Started': '3',
'Subscription Ended': '4'
}
mappings['created_at'] = 'created_at'
# Mapping
stage_mapping = etl.fieldmap(stage_m_s, mappings)
# Sort
stage_mapping_ordered = etl.sort(stage_mapping,
key=['created_at', 'email', 'sub_order'])
# Datetime split
t1 = etl.split(stage_mapping_ordered,
'created_at',
'T', ['date', 'time'],
include_original=True)
t2 = etl.split(t1, 'date', '-', ['year', 'month', 'day'])
stage_ready = etl.split(t2, 'time', ':', ['hour', 'minute', 'second'])
# Export as csv to load folder
etl.tocsv(stage_ready, 'load/facts.csv')
