Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Integrate New User Statistics into Profile Retrieval #153

Merged
merged 1 commit into from
Dec 22, 2024
Merged

Integrate New User Statistics into Profile Retrieval #153

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion utils/constants.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,7 @@
"inferred_section_summary",
]

valid_uuids_columns = [
VALID_UUIDS_COLS = [
'user_token',
'user_id',
'update_ts',
Expand Down
74 changes: 26 additions & 48 deletions utils/db_utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -437,57 +437,35 @@ def add_user_stats(user_data, batch_size=5):
def process_user(user):
with ect.Timer() as process_user_timer:
user_uuid = UUID(user['user_id'])

# Fetch aggregated data for all users once and cache it
ts_aggregate = esta.TimeSeries.get_aggregate_time_series()

# Fetch data for the user, cached for repeated queries
profile_data = edb.get_profile_db().find_one({'user_id': user_uuid})
# Fetch data for the user, cached for repeated queries
logging.info(f'keyspr: {profile_data}')
if not profile_data:
profile_data = {}
# Assign existing profile attributes to the user dictionary
user['platform'] = profile_data.get('curr_platform')
user['manufacturer'] = profile_data.get('manufacturer')
user['app_version'] = profile_data.get('client_app_version')
user['os_version'] = profile_data.get('client_os_version')
user['phone_lang'] = profile_data.get('phone_lang')

total_trips = ts_aggregate.find_entries_count(
key_list=["analysis/confirmed_trip"],
extra_query_list=[{'user_id': user_uuid}]
)
labeled_trips = ts_aggregate.find_entries_count(
key_list=["analysis/confirmed_trip"],
extra_query_list=[{'user_id': user_uuid}, {'data.user_input': {'$ne': {}}}]
)
# Assign newly stored statistics to the user dictionary
user['total_trips'] = profile_data.get('total_trips')
user['labeled_trips'] = profile_data.get('labeled_trips')

user['total_trips'] = total_trips
user['labeled_trips'] = labeled_trips

if profile_data:
user['platform'] = profile_data.get('curr_platform')
user['manufacturer'] = profile_data.get('manufacturer')
user['app_version'] = profile_data.get('client_app_version')
user['os_version'] = profile_data.get('client_os_version')
user['phone_lang'] = profile_data.get('phone_lang')

if total_trips > 0:
ts = esta.TimeSeries.get_time_series(user_uuid)
first_trip_ts = ts.get_first_value_for_field(
key='analysis/confirmed_trip',
field='data.end_ts',
sort_order=pymongo.ASCENDING
)
if first_trip_ts != -1:
user['first_trip'] = arrow.get(first_trip_ts).format(time_format)

last_trip_ts = ts.get_first_value_for_field(
key='analysis/confirmed_trip',
field='data.end_ts',
sort_order=pymongo.DESCENDING
)
if last_trip_ts != -1:
user['last_trip'] = arrow.get(last_trip_ts).format(time_format)

last_call_ts = ts.get_first_value_for_field(
key='stats/server_api_time',
field='data.ts',
sort_order=pymongo.DESCENDING
)
if last_call_ts != -1:
user['last_call'] = arrow.get(last_call_ts).format(time_format)
# Retrieve and assign pipeline range
pipeline_range = profile_data.get('pipeline_range', {})
start_ts = pipeline_range.get('start_ts')
end_ts = pipeline_range.get('end_ts')
if start_ts:
user['first_trip'] = arrow.get(start_ts).format(time_format)
if end_ts:
user['last_trip'] = arrow.get(end_ts).format(time_format)

# Retrieve and assign last API call timestamp
last_call_ts = profile_data.get('last_call_ts')
if last_call_ts:
user['last_call'] = arrow.get(last_call_ts).format('YYYY-MM-DD')

esdsq.store_dashboard_time(
"admin/db_utils/add_user_stats/process_user",
Expand Down
2 changes: 1 addition & 1 deletion utils/permissions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -93,7 +93,7 @@ def get_allowed_trip_columns():


def get_uuids_columns():
columns = set(constants.valid_uuids_columns)
columns = set(constants.VALID_UUIDS_COLS)
for column in permissions.get("data_uuids_columns_exclude", []):
columns.discard(column)
return columns
Expand Down