def popular_taxi_vendor():
env = StreamExecutionEnvironment.get_execution_environment()
env.set_parallelism(1)
t_env = StreamTableEnvironment.create(stream_execution_environment=env)
t_env.execute_sql(
create_table_ddl(
"WATERMARK FOR pickupTime AS pickupTime - INTERVAL '30' SECONDS"))
taxi_ride = t_env.from_path('TaxiRide')
popular_rides = taxi_ride.select(taxi_ride.vendorId, taxi_ride.pickupTime) \
.window(Slide.over('15.minutes').every('5.minutes').on(taxi_ride.pickupTime).alias('w')) \
.group_by(taxi_ride.vendorId, col('w')) \
.select(taxi_ride.vendorId, \
col('w').start.alias('start'), \
col('w').end.alias('end'), \
taxi_ride.vendorId.count.alias('cnt'))
t_env.to_append_stream(
popular_rides,
Types.ROW_NAMED(['vendorId', 'start', 'end', 'cnt'], [
Types.INT(),
Types.SQL_TIMESTAMP(),
Types.SQL_TIMESTAMP(),
Types.LONG()
])).print()
env.execute('Popular-Taxi-Vendor')
def max_travellers_per_destination():
env = StreamExecutionEnvironment.get_execution_environment()
t_env = StreamTableEnvironment.create(stream_execution_environment=env)
t_env.execute_sql(
create_table_ddl(
"WATERMARK FOR dropOffTime AS dropOffTime - INTERVAL '30' SECONDS")
)
taxi_ride = t_env.from_path('TaxiRide')
no_of_travelers_per_dest = taxi_ride \
.select(taxi_ride.passengerCount, taxi_ride.dropOffTime, taxi_ride.destLocationZone) \
.window(Tumble().over('1.hour').on(taxi_ride.dropOffTime).alias('w')) \
.group_by(taxi_ride.destLocationZone, col('w')) \
.select(taxi_ride.destLocationZone, \
col('w').start.alias('start'), \
col('w').end.alias('end'), \
taxi_ride.passengerCount.count.alias('cnt'))
t_env.to_append_stream(
no_of_travelers_per_dest,
Types.ROW_NAMED(['destLocationZone', 'start', 'end', 'cnt'], [
Types.STRING(),
Types.SQL_TIMESTAMP(),
Types.SQL_TIMESTAMP(),
Types.LONG()
])).print()
env.execute('Max-Travellers-Per-Destination')
def setUp(self):
super(PyFlinkBlinkStreamTableTestCase, self).setUp()
self.env = StreamExecutionEnvironment.get_execution_environment()
self.env.set_parallelism(2)
self.t_env = StreamTableEnvironment.create(
self.env,
environment_settings=EnvironmentSettings.new_instance(
).in_streaming_mode().use_blink_planner().build())
def setUp(self):
super(PyFlinkBlinkStreamTableTestCase, self).setUp()
self.env = StreamExecutionEnvironment.get_execution_environment()
self.env.set_parallelism(2)
self.t_env = StreamTableEnvironment.create(
self.env, environment_settings=EnvironmentSettings.new_instance()
.in_streaming_mode().use_blink_planner().build())
self.t_env.get_config().get_configuration().set_string(
"taskmanager.memory.task.off-heap.size", "80mb")
def setUp(self):
super(PyFlinkBlinkStreamTableTestCase, self).setUp()
self.env = StreamExecutionEnvironment.get_execution_environment()
self.env.set_parallelism(2)
self.t_env = StreamTableEnvironment.create(
self.env, environment_settings=EnvironmentSettings.new_instance()
.in_streaming_mode().use_blink_planner().build())
self.t_env.get_config().get_configuration().set_string(
"python.fn-execution.bundle.size", "1")
def get_stream_table_environment(self) -> StreamTableEnvironment:
"""
Get the StreamTableEnvironment. If the StreamTableEnvironment has not been set,
it initial the StreamTableEnvironment with default Configuration.
:return: the StreamTableEnvironment.
.. versionadded:: 1.11.0
"""
if self._stream_tab_env is None:
self._stream_tab_env = StreamTableEnvironment.create(
StreamExecutionEnvironment.get_execution_environment())
return self._stream_tab_env
def test_create_table_environment(self):
table_config = TableConfig()
table_config.set_max_generated_code_length(32000)
table_config.set_null_check(False)
table_config.set_timezone("Asia/Shanghai")
env = StreamExecutionEnvironment.get_execution_environment()
t_env = StreamTableEnvironment.create(env, table_config)
readed_table_config = t_env.get_config()
self.assertFalse(readed_table_config.get_null_check())
self.assertEqual(readed_table_config.get_max_generated_code_length(), 32000)
self.assertEqual(readed_table_config.get_timezone(), "Asia/Shanghai")
def popular_destination_query():
env = StreamExecutionEnvironment.get_execution_environment()
t_env = StreamTableEnvironment.create(stream_execution_environment=env)
t_env.execute_sql(
create_table_ddl(
"WATERMARK FOR pickupTime AS pickupTime - INTERVAL '30' SECONDS"))
query = f"""SELECT
destLocationId, wstart, wend, cnt
FROM
(SELECT
destLocationId,
HOP_START(pickupTime, INTERVAL '5' MINUTE, INTERVAL '15' MINUTE) AS wstart,
HOP_END(pickupTime, INTERVAL '5' MINUTE, INTERVAL '15' MINUTE) AS wend,
COUNT(destLocationId) AS cnt
FROM
(SELECT
pickupTime,
destLocationId
FROM TaxiRide)
GROUP BY
destLocationId, HOP(pickupTime, INTERVAL '5' MINUTE, INTERVAL '15' MINUTE)
)
WHERE cnt > {args.threshold}
"""
results = t_env.sql_query(query)
t_env.to_append_stream(
results,
Types.ROW_NAMED(['destLocationId', 'wstart', 'wend', 'cnt'], [
Types.INT(),
Types.SQL_TIMESTAMP(),
Types.SQL_TIMESTAMP(),
Types.LONG()
])).print()
env.execute('Popular-Destination')