def mapreduce_create_sources_from_events(fbl):
fb_mapreduce.start_map(
fbl,
'Create Sources from Events',
'event_scraper.thing_db.map_create_sources_from_event',
'events.eventdata.DBEvent',
)
def get(self):
time_period = self.request.get('time_period', None)
queue = self.request.get('queue', 'fast-queue')
filters = []
if time_period:
filters.append(('search_time_period', '=', time_period))
name = 'Delete %s Bad Autoadds' % time_period
else:
name = 'Delete All Bad Autoadds'
allow_deletes = self.request.get('allow_deletes', None) == '1'
extra_mapper_params = {
'allow_deletes': allow_deletes,
}
fb_mapreduce.start_map(
fbl=self.fbl,
name=name,
handler_spec='events.event_reloading_tasks.map_maybe_delete_bad_event',
entity_kind='events.eventdata.DBEvent',
filters=filters,
extra_mapper_params=extra_mapper_params,
queue=queue,
output_writer_spec='mapreduce.output_writers.GoogleCloudStorageOutputWriter',
output_writer={
'mime_type': 'text/plain',
'bucket_name': 'dancedeets-hrd.appspot.com',
},
)
def mr_load_fb_events(fbl,
load_attending=False,
time_period=None,
update_geodata=True,
only_if_updated=True,
queue='slow-queue'):
if load_attending:
event_or_attending = 'Event Attendings'
mr_func = 'map_load_fb_event_attending'
else:
event_or_attending = 'Events'
mr_func = 'map_load_fb_event'
filters = []
if time_period:
filters.append(('search_time_period', '=', time_period))
name = 'Load %s %s' % (time_period, event_or_attending)
else:
name = 'Load All %s' % (event_or_attending)
fb_mapreduce.start_map(
fbl=fbl,
name=name,
handler_spec='events.event_reloading_tasks.%s' % mr_func,
entity_kind='events.eventdata.DBEvent',
handle_batch_size=20,
filters=filters,
extra_mapper_params={
'update_geodata': update_geodata,
'only_if_updated': only_if_updated
},
queue=queue,
)
def mr_load_potential_events(fbl):
fb_mapreduce.start_map(
fbl=fbl,
name='Load Potential Events For Users',
handler_spec='event_scraper.potential_events_reloading.map_load_potential_events',
entity_kind='users.users.User',
)
def mapreduce_create_sources_from_events(fbl):
fb_mapreduce.start_map(
fbl,
'Create Sources from Events',
'event_scraper.thing_db.map_create_source_from_event',
'events.eventdata.DBEvent',
)
def mr_email_user(fbl):
fb_mapreduce.start_map(
fbl=fbl,
name='Email Users',
#TODO: MOVE
handler_spec='search.email_events.map_email_user',
entity_kind='users.users.User',
)
def mr_email_user(fbl):
fb_mapreduce.start_map(
fbl=fbl,
name='Email Users',
#TODO: MOVE
handler_spec='search.email_events.map_email_user',
entity_kind='users.users.User',
)
def get(self):
# this calls a map function wrapped by mr_user_wrap, so it works correctly on a per-user basis
fb_mapreduce.start_map(
fbl=self.fbl,
name='Load Users',
handler_spec='users.user_tasks.map_load_fb_user',
entity_kind='users.users.User',
)
def get(self):
# this calls a map function wrapped by mr_user_wrap, so it works correctly on a per-user basis
fb_mapreduce.start_map(
fbl=self.fbl,
name='Load Users',
handler_spec='users.user_tasks.map_load_fb_user',
entity_kind='users.users.User',
)
def get(self):
# this calls a map function wrapped by mr_user_wrap, so it works correctly on a per-user basis
mailchimp_list_id = mailchimp_api.get_list_id()
fb_mapreduce.start_map(
fbl=self.fbl,
name='Load Users',
handler_spec='users.user_tasks.map_load_fb_user',
entity_kind='users.users.User',
extra_mapper_params={
'mailchimp_list_id': mailchimp_list_id,
},
queue='fast-queue')
def mr_generate_training_data(fbl):
fb_mapreduce.start_map(
fbl=fbl,
name='Write Training Data',
handler_spec='ml.gprediction.map_training_data_for_pevents',
output_writer_spec='mapreduce.output_writers.GoogleCloudStorageOutputWriter',
handle_batch_size=20,
entity_kind='event_scraper.potential_events.PotentialEvent',
output_writer={
'mime_type': 'text/plain',
'bucket_name': 'dancedeets-hrd.appspot.com',
},
queue=None,
)
def mapreduce_export_sources(fbl, queue='fast-queue'):
fb_mapreduce.start_map(
fbl,
'Export All Sources',
'event_scraper.thing_db.map_export_sources',
'event_scraper.thing_db.Source',
output_writer_spec='mapreduce.output_writers.GoogleCloudStorageOutputWriter',
output_writer={
'mime_type': 'text/plain',
'bucket_name': 'dancedeets-hrd.appspot.com',
},
handle_batch_size=10,
queue=queue,
)
def mr_private_events(fbl):
fb_mapreduce.start_map(
fbl,
'Dump Private Events',
'servlets.tools.map_dump_private_events',
'events.eventdata.DBEvent',
handle_batch_size=80,
queue=None,
output_writer_spec='mapreduce.output_writers.GoogleCloudStorageOutputWriter',
output_writer={
'mime_type': 'text/plain',
'bucket_name': 'dancedeets-hrd.appspot.com',
},
)
def mapreduce_scrape_all_sources(fbl, min_potential_events=None, queue='slow-queue'):
# Do not do the min_potential_events>1 filter in the mapreduce filter,
# or it will want to do a range-shard on that property. Instead, pass-it-down
# and use it as an early-return in the per-Source processing.
# TODO:....maybe we do want a range-shard filter? save on loading all the useless sources...
fb_mapreduce.start_map(
fbl,
'Scrape All Sources',
'event_scraper.thing_scraper.map_scrape_events_from_sources',
'event_scraper.thing_db.Source',
handle_batch_size=10,
extra_mapper_params={'min_potential_events': min_potential_events},
queue=queue,
randomize_tokens=True,
)
def mr_dump_events(fbl):
fb_mapreduce.start_map(
fbl,
'Dump Potential FB Event Data',
'logic.mr_dump.map_dump_fb_json',
'event_scraper.potential_events.PotentialEvent',
handle_batch_size=80,
queue=None,
filters=[('looked_at', '=', None)],
output_writer_spec='mapreduce.output_writers.GoogleCloudStorageOutputWriter',
output_writer={
'mime_type': 'text/plain',
'bucket_name': 'dancedeets-hrd.appspot.com',
},
)
def mapreduce_export_sources(fbl, queue='fast-queue'):
fb_mapreduce.start_map(
fbl,
'Export All Sources',
'event_scraper.thing_db.map_export_sources',
'event_scraper.thing_db.Source',
output_writer_spec=
'mapreduce.output_writers.GoogleCloudStorageOutputWriter',
output_writer={
'mime_type': 'text/plain',
'bucket_name': 'dancedeets-hrd.appspot.com',
},
handle_batch_size=10,
queue=queue,
)
def mapreduce_scrape_all_sources(fbl, min_potential_events=None, queue='super-slow-queue'):
# Do not do the min_potential_events>1 filter in the mapreduce filter,
# or it will want to do a range-shard on that property. Instead, pass-it-down
# and use it as an early-return in the per-Source processing.
# TODO:....maybe we do want a range-shard filter? save on loading all the useless sources...
fb_mapreduce.start_map(
fbl,
'Scrape All Sources',
'event_scraper.thing_scraper.map_scrape_events_from_sources',
'event_scraper.thing_db.Source',
handle_batch_size=10,
extra_mapper_params={'min_potential_events': min_potential_events},
queue=queue,
randomize_tokens=True,
)
def mr_classify_potential_events(fbl):
fb_mapreduce.start_map(
fbl,
'Auto-Classify Events',
'ml.mr_prediction.map_classify_events',
'event_scraper.potential_events.PotentialEvent',
filters=[('looked_at', '=', None)],
handle_batch_size=20,
queue='slow-queue',
output_writer_spec='mapreduce.output_writers.GoogleCloudStorageOutputWriter',
output_writer={
'mime_type': 'text/plain',
'bucket_name': 'dancedeets-hrd.appspot.com',
},
)
def mr_private_events(fbl):
fb_mapreduce.start_map(
fbl,
'Dump Private Events',
'servlets.tools.map_dump_private_events',
'events.eventdata.DBEvent',
handle_batch_size=80,
queue=None,
output_writer_spec=
'mapreduce.output_writers.GoogleCloudStorageOutputWriter',
output_writer={
'mime_type': 'text/plain',
'bucket_name': 'dancedeets-hrd.appspot.com',
},
)
def mr_dump_events(fbl):
fb_mapreduce.start_map(
fbl,
'Dump Potential FB Event Data',
'logic.mr_dump.map_dump_fb_json',
'event_scraper.potential_events.PotentialEvent',
handle_batch_size=80,
queue=None,
filters=[('looked_at', '=', None)],
output_writer_spec=
'mapreduce.output_writers.GoogleCloudStorageOutputWriter',
output_writer={
'mime_type': 'text/plain',
'bucket_name': 'dancedeets-hrd.appspot.com',
},
)
def mr_classify_potential_events(fbl, past_event):
filters = [('looked_at', '=', None), ('should_look_at', '=', True)]
if past_event is not None:
filters.append(('past_event', '=', past_event))
fb_mapreduce.start_map(
fbl,
'Auto-Add Events',
'event_scraper.auto_add.map_classify_events',
'event_scraper.potential_events.PotentialEvent',
filters=filters,
handle_batch_size=20,
queue='fast-queue',
output_writer_spec='mapreduce.output_writers.GoogleCloudStorageOutputWriter',
output_writer={
'mime_type': 'text/plain',
'bucket_name': 'dancedeets-hrd.appspot.com',
},
)
def mr_classify_potential_events(fbl, past_event):
filters = [('looked_at', '=', None), ('should_look_at', '=', True)]
if past_event is not None:
filters.append(('past_event', '=', past_event))
fb_mapreduce.start_map(
fbl,
'Auto-Add Events',
'event_scraper.auto_add.map_classify_events',
'event_scraper.potential_events.PotentialEvent',
filters=filters,
handle_batch_size=20,
queue='fast-queue',
output_writer_spec=
'mapreduce.output_writers.GoogleCloudStorageOutputWriter',
output_writer={
'mime_type': 'text/plain',
'bucket_name': 'dancedeets-hrd.appspot.com',
},
)
def mr_load_fb_events(fbl, load_attending=False, time_period=None, update_geodata=True, only_if_updated=True, queue='slow-queue'):
if load_attending:
event_or_attending = 'Event Attendings'
mr_func = 'map_load_fb_event_attending'
else:
event_or_attending = 'Events'
mr_func = 'map_load_fb_event'
filters = []
if time_period:
filters.append(('search_time_period', '=', time_period))
name = 'Load %s %s' % (time_period, event_or_attending)
else:
name = 'Load All %s' % (event_or_attending)
fb_mapreduce.start_map(
fbl=fbl,
name=name,
handler_spec='events.event_reloading_tasks.%s' % mr_func,
entity_kind='events.eventdata.DBEvent',
handle_batch_size=20,
filters=filters,
extra_mapper_params={'update_geodata': update_geodata, 'only_if_updated': only_if_updated},
queue=queue,
)
