def generate_metadata_notif():
stream_metadata = Metadata()
stream_metadata.set_name('mcontain-md2k--user-notifications').set_description('Notification generated for the Covid-19 encountered users.') \
.add_dataDescriptor(
DataDescriptor().set_name("user").set_type("string").set_attribute("description", \
"user id")) \
.add_dataDescriptor(
DataDescriptor().set_name("timestamp").set_type("timestamp").set_attribute("description", \
"Unix timestamp when the message was generated")) \
.add_dataDescriptor(
DataDescriptor().set_name("localtime").set_type("timestamp").set_attribute("description", \
"Local timestamp when the message was generated.")) \
.add_dataDescriptor(
DataDescriptor().set_name("message").set_type("string").set_attribute("description", \
"Generated notification message")) \
.add_dataDescriptor(
DataDescriptor().set_name("day").set_type("timestamp").set_attribute("description", \
"day of the encounter")) \
.add_dataDescriptor(
DataDescriptor().set_name("version").set_type("int").set_attribute("description", \
"version"))
stream_metadata.add_module(
ModuleMetadata().set_name('Generated notification for a user encountered with Covid-19 participant') \
.set_attribute("url", "https://mcontain.md2k.org").set_author(
"Md Shiplu Hawlader", "*****@*****.**").set_version(1))
return stream_metadata
def generate_metadata_hourly():
stream_metadata = Metadata()
stream_metadata.set_name('mcontain-md2k--visualization-stats--time-window').set_description('Computes visualization stats every time window defined by start time and end time') \
.add_dataDescriptor(
DataDescriptor().set_name("start_time").set_type("timestamp").set_attribute("description", \
"Start time of the time window localtime")) \
.add_dataDescriptor(
DataDescriptor().set_name("end_time").set_type("timestamp").set_attribute("description", \
"End time of the time window in localtime")) \
.add_dataDescriptor(
DataDescriptor().set_name("latitude").set_type("double").set_attribute("description", \
"Latitude of centroid location, a gps cluster output grouping encounters in similar location together")) \
.add_dataDescriptor(
DataDescriptor().set_name("longitude").set_type("double").set_attribute("description", \
"Longitude of centroid location, a gps cluster output grouping encounters in similar location together")) \
.add_dataDescriptor(
DataDescriptor().set_name("n_users").set_type("integer").set_attribute("description", \
"Number of unique users in that cluster centroid")) \
.add_dataDescriptor(
DataDescriptor().set_name("total_encounters").set_type("double").set_attribute("description", \
"Total encounters happening in the time window in this specific location")) \
.add_dataDescriptor(
DataDescriptor().set_name("normalized_total_encounters").set_type("double").set_attribute("description", \
"Total encounters normalized by the centroid area. (encounters per 10 square meter)")) \
.add_dataDescriptor(
DataDescriptor().set_name("avg_encounters").set_type("double").set_attribute("description", \
"average encounter per participant(participants who had at least one encounter)"))
stream_metadata.add_module(
ModuleMetadata().set_name('Visualization stats computation in a time window between start time and end time') \
.set_attribute("url", "https://mcontain.md2k.org").set_author(
"Md Azim Ullah", "*****@*****.**"))
return stream_metadata
def generate_metadata_dailystats():
stream_metadata = Metadata()
stream_metadata.set_name('mcontain-md2k--daily-stats').set_description('Daily stats for website') \
.add_dataDescriptor(
DataDescriptor().set_name("start_time").set_type("timestamp").set_attribute("description", \
"Start time of the day in localtime")) \
.add_dataDescriptor(
DataDescriptor().set_name("end_time").set_type("timestamp").set_attribute("description", \
"End time of the day in localtime")) \
.add_dataDescriptor(
DataDescriptor().set_name("number_of_app_users").set_type("double").set_attribute("description", \
"Total number of app users")) \
.add_dataDescriptor(
DataDescriptor().set_name("encounter_per_user").set_type("double").set_attribute("description", \
"Average encounter per user")) \
.add_dataDescriptor(
DataDescriptor().set_name("total_covid_encounters").set_type("double").set_attribute("description", \
"Total covid encounters on the day")) \
.add_dataDescriptor(
DataDescriptor().set_name("maximum_concurrent_encounters").set_type("double").set_attribute("description", \
"Maximum concurrent encounters"))
stream_metadata.add_module(
ModuleMetadata().set_name('Daily encounter stats for all the users to be shown in website') \
.set_attribute("url", "https://mcontain.md2k.org").set_author(
"Md Azim Ullah", "*****@*****.**"))
return stream_metadata
def generate_metadata_encounter_daily():
stream_metadata = Metadata()
stream_metadata.set_name('mcontain-md2k-encounter-daily--bluetooth-gps').set_description('Contains each unique encounters between two persons along with the location of encounter') \
.add_dataDescriptor(
DataDescriptor().set_name("start_time").set_type("timestamp").set_attribute("description", \
"Start time of the encounter in localtime")) \
.add_dataDescriptor(
DataDescriptor().set_name("end_time").set_type("timestamp").set_attribute("description", \
"End time of the encounter in localtime")) \
.add_dataDescriptor(
DataDescriptor().set_name("participant_identifier").set_type("string").set_attribute("description", \
"Participant with whom encounter happened")) \
.add_dataDescriptor(
DataDescriptor().set_name("os").set_type("string").set_attribute("description", \
"Operating system of the phone belonging to user")) \
.add_dataDescriptor(
DataDescriptor().set_name("latitude").set_type("double").set_attribute("description", \
"Latitude of encounter location")) \
.add_dataDescriptor(
DataDescriptor().set_name("longitude").set_type("double").set_attribute("description", \
"Longitude of encounter location")) \
.add_dataDescriptor(
DataDescriptor().set_name("durations").set_type("array").set_attribute("description", \
"Mean distance between participants in encounter")) \
.add_dataDescriptor(
DataDescriptor().set_name("covid").set_type("integer").set_attribute("description", \
"0, 1 or 2 indicating if this encounter contained a covid user -- 0 - no covid-19 affected, 1 - user is, 2 - participant identifier is"))
stream_metadata.add_module(
ModuleMetadata().set_name('Encounter computation after parsing raw bluetooth-gps data, clustering gps locations and removing double counting') \
.set_attribute("url", "https://mcontain.md2k.org").set_author(
"Md Azim Ullah", "*****@*****.**"))
return stream_metadata
def _gen_metadata(self):
from pyspark.sql.group import GroupedData
if isinstance(self._data, GroupedData):
return Metadata()
else:
schema = self._data.schema
stream_metadata = Metadata()
for field in schema.fields:
stream_metadata.add_dataDescriptor(DataDescriptor().set_name(
str(field.name)).set_type(str(field.dataType)))
stream_metadata.add_module(ModuleMetadata().set_name(
"cerebralcortex.core.datatypes.datastream.DataStream"
).set_attribute("url", "https://md2k.org").set_author(
"Nasir Ali", "*****@*****.**"))
return stream_metadata
def generate_metadata_user_encounter_count():
stream_metadata = Metadata()
stream_metadata.set_name('mcontain-md2k--user--encounter-count').set_description('Number of encounter in a given time window') \
.add_dataDescriptor(
DataDescriptor().set_name("start_time").set_type("timestamp").set_attribute("description", \
"Start time of the time window in localtime")) \
.add_dataDescriptor(
DataDescriptor().set_name("end_time").set_type("timestamp").set_attribute("description", \
"End time of the time window in localtime")) \
.add_dataDescriptor(
DataDescriptor().set_name("encounter_count").set_type("int").set_attribute("description", \
"Total number of encounter for the user in the given time window"))
stream_metadata.add_module(
ModuleMetadata().set_name('Total number of encounter for a user in a given time window') \
.set_attribute("url", "https://mcontain.md2k.org").set_author(
"Md Shiplu Hawlader, Md Azim Ullah", "[email protected], [email protected]").set_version(1))
return stream_metadata
def generate_metadata_notification_daily():
stream_metadata = Metadata()
stream_metadata.set_name('mcontain-md2k--crowd--notification--daily').set_description('Computes notifications for each user who dwelled in a crowded hotspot') \
.add_dataDescriptor(
DataDescriptor().set_name("start_time").set_type("timestamp").set_attribute("description", \
"Start time of the time window localtime")) \
.add_dataDescriptor(
DataDescriptor().set_name("end_time").set_type("timestamp").set_attribute("description", \
"End time of the time window in localtime")) \
.add_dataDescriptor(
DataDescriptor().set_name("centroid_latitude").set_type("double").set_attribute("description", \
"Latitude of centroid location, a gps cluster output grouping encounters in similar location together")) \
.add_dataDescriptor(
DataDescriptor().set_name("centroid_longitude").set_type("double").set_attribute("description", \
"Longitude of centroid location, a gps cluster output grouping encounters in similar location together")) \
.add_dataDescriptor(
DataDescriptor().set_name("centroid_area").set_type("double").set_attribute("description", \
"area of centroid")) \
.add_dataDescriptor(
DataDescriptor().set_name("durations").set_type("double").set_attribute("description", \
"duration of stay in the centroid in hours")) \
.add_dataDescriptor(
DataDescriptor().set_name("unique_users").set_type("integer").set_attribute("description", \
"Number of unique users in that cluster centroid")) \
.add_dataDescriptor(
DataDescriptor().set_name("total_encounters").set_type("double").set_attribute("description", \
"Total encounters happening in the time window in this specific location")) \
.add_dataDescriptor(
DataDescriptor().set_name("normalized_total_encounters").set_type("double").set_attribute("description", \
"Total encounters normalized by the centroid area. (encounters per 10 square meter)")) \
.add_dataDescriptor(
DataDescriptor().set_name("avg_encounters").set_type("double").set_attribute("description", \
"average encounter per participant(participants who had at least one encounter)"))
stream_metadata.add_module(
ModuleMetadata().set_name('Notification messages to be shown to each user') \
.set_attribute("url", "https://mcontain.md2k.org").set_author(
"Md Azim Ullah", "*****@*****.**"))
return stream_metadata
def get_metadata(stress_imputed_data, output_stream_name, input_stream_name):
"""
generate metadata for a datastream.
Args:
stress_imputed_data (DataStream):
output_stream_name (str):
Returns:
"""
schema = stress_imputed_data.schema
stream_metadata = Metadata()
stream_metadata.set_name(output_stream_name).set_description("stress imputed")\
.add_input_stream(input_stream_name)
for field in schema.fields:
stream_metadata.add_dataDescriptor(DataDescriptor().set_name(
str(field.name)).set_type(str(field.dataType)))
stream_metadata.add_module(
ModuleMetadata().set_name("stress forward fill imputer") \
.set_attribute("url", "hhtps://md2k.org").set_author(
"Md Azim Ullah", "*****@*****.**"))
return stream_metadata
