def run_test_pipeline(
self,
dataset: str,
fake_supervision_period_id: int,
unifying_id_field_filter_set: Optional[Set[int]] = None,
metric_types_filter: Optional[Set[str]] = None):
"""Runs a test version of the program pipeline."""
test_pipeline = TestPipeline()
# Get StatePersons
persons = (
test_pipeline
| 'Load Persons' >> # type: ignore
extractor_utils.BuildRootEntity(
dataset=dataset,
root_entity_class=entities.StatePerson,
unifying_id_field=entities.StatePerson.get_class_id_name(),
build_related_entities=True))
# Get StateProgramAssignments
program_assignments = (
test_pipeline
| 'Load Program Assignments' >> # type: ignore
extractor_utils.BuildRootEntity(
dataset=dataset,
root_entity_class=entities.StateProgramAssignment,
unifying_id_field=entities.StatePerson.get_class_id_name(),
build_related_entities=True,
unifying_id_field_filter_set=unifying_id_field_filter_set))
# Get StateAssessments
assessments = (
test_pipeline
| 'Load Assessments' >> # type: ignore
extractor_utils.BuildRootEntity(
dataset=dataset,
root_entity_class=entities.StateAssessment,
unifying_id_field=entities.StatePerson.get_class_id_name(),
build_related_entities=False,
unifying_id_field_filter_set=unifying_id_field_filter_set))
# Get StateSupervisionPeriods
supervision_periods = (
test_pipeline
| 'Load SupervisionPeriods' >> # type: ignore
extractor_utils.BuildRootEntity(
dataset=dataset,
root_entity_class=entities.StateSupervisionPeriod,
unifying_id_field=entities.StatePerson.get_class_id_name(),
build_related_entities=False,
unifying_id_field_filter_set=unifying_id_field_filter_set))
supervision_period_to_agent_map = {
'agent_id': 1010,
'agent_external_id': 'OFFICER0009',
'district_external_id': '10',
'supervision_period_id': fake_supervision_period_id
}
supervision_period_to_agent_associations = (
test_pipeline
| 'Create SupervisionPeriod to Agent table' >> beam.Create(
[supervision_period_to_agent_map]))
supervision_period_to_agent_associations_as_kv = (
supervision_period_to_agent_associations
| 'Convert SupervisionPeriod to Agent table to KV tuples' >>
beam.ParDo(pipeline.ConvertDictToKVTuple(),
'supervision_period_id'))
# Group each StatePerson with their other entities
persons_entities = ({
'person': persons,
'program_assignments': program_assignments,
'assessments': assessments,
'supervision_periods': supervision_periods
}
|
'Group StatePerson to StateProgramAssignments and'
>> beam.CoGroupByKey())
# Identify ProgramEvents from the StatePerson's
# StateProgramAssignments
person_program_events = (
persons_entities
| beam.ParDo(
pipeline.ClassifyProgramAssignments(),
AsDict(supervision_period_to_agent_associations_as_kv)))
# Get pipeline job details for accessing job_id
all_pipeline_options = PipelineOptions().get_all_options()
# Add timestamp for local jobs
job_timestamp = datetime.datetime.now().strftime(
'%Y-%m-%d_%H_%M_%S.%f')
all_pipeline_options['job_timestamp'] = job_timestamp
metric_types = metric_types_filter if metric_types_filter else {'ALL'}
# Get program metrics
program_metrics = (
person_program_events
| 'Get Program Metrics' >> # type: ignore
pipeline.GetProgramMetrics(pipeline_options=all_pipeline_options,
metric_types=metric_types,
calculation_end_month=None,
calculation_month_count=-1))
assert_that(program_metrics, AssertMatchers.validate_pipeline_test())
test_pipeline.run()
def testProgramPipeline(self):
"""Tests the program pipeline."""
fake_person_id = 12345
fake_person = schema.StatePerson(
person_id=fake_person_id,
gender=Gender.MALE,
birthdate=date(1970, 1, 1),
residency_status=ResidencyStatus.PERMANENT)
persons_data = [normalized_database_base_dict(fake_person)]
race_1 = schema.StatePersonRace(person_race_id=111,
state_code='CA',
race=Race.BLACK,
person_id=fake_person_id)
race_2 = schema.StatePersonRace(person_race_id=111,
state_code='ND',
race=Race.WHITE,
person_id=fake_person_id)
races_data = normalized_database_base_dict_list([race_1, race_2])
ethnicity = schema.StatePersonEthnicity(person_ethnicity_id=111,
state_code='CA',
ethnicity=Ethnicity.HISPANIC,
person_id=fake_person_id)
ethnicity_data = normalized_database_base_dict_list([ethnicity])
program_assignment = schema.StateProgramAssignment(
program_assignment_id=123,
referral_date=date(2015, 5, 10),
person_id=fake_person_id)
assessment = schema.StateAssessment(assessment_id=298374,
assessment_date=date(2015, 3, 19),
assessment_type='LSIR',
person_id=fake_person_id)
supervision_period = schema.StateSupervisionPeriod(
supervision_period_id=1111,
state_code='CA',
county_code='124',
start_date=date(2015, 3, 14),
termination_date=date(2016, 12, 29),
supervision_type=StateSupervisionType.PROBATION,
person_id=fake_person_id)
program_assignment_data = [
normalized_database_base_dict(program_assignment)
]
assessment_data = [normalized_database_base_dict(assessment)]
supervision_periods_data = [
normalized_database_base_dict(supervision_period)
]
supervision_violation_response = \
database_test_utils.generate_test_supervision_violation_response(
fake_person_id)
supervision_violation_response_data = [
normalized_database_base_dict(supervision_violation_response)
]
data_dict = {
schema.StatePerson.__tablename__: persons_data,
schema.StatePersonRace.__tablename__: races_data,
schema.StatePersonEthnicity.__tablename__: ethnicity_data,
schema.StateSupervisionViolationResponse.__tablename__:
supervision_violation_response_data,
schema.StateSupervisionPeriod.__tablename__:
supervision_periods_data,
schema.StateProgramAssignment.__tablename__:
program_assignment_data,
schema.StateAssessment.__tablename__: assessment_data
}
test_pipeline = TestPipeline()
# Get StatePersons
persons = (test_pipeline
| 'Load Persons' >> extractor_utils.BuildRootEntity(
dataset=None,
data_dict=data_dict,
root_schema_class=schema.StatePerson,
root_entity_class=entities.StatePerson,
unifying_id_field='person_id',
build_related_entities=True))
# Get StateProgramAssignments
program_assignments = (
test_pipeline
| 'Load Program Assignments' >> extractor_utils.BuildRootEntity(
dataset=None,
data_dict=data_dict,
root_schema_class=schema.StateProgramAssignment,
root_entity_class=entities.StateProgramAssignment,
unifying_id_field='person_id',
build_related_entities=True))
# Get StateAssessments
assessments = (test_pipeline
| 'Load Assessments' >> extractor_utils.BuildRootEntity(
dataset=None,
data_dict=data_dict,
root_schema_class=schema.StateAssessment,
root_entity_class=entities.StateAssessment,
unifying_id_field='person_id',
build_related_entities=False))
# Get StateSupervisionPeriods
supervision_periods = (
test_pipeline
| 'Load SupervisionPeriods' >> extractor_utils.BuildRootEntity(
dataset=None,
data_dict=data_dict,
root_schema_class=schema.StateSupervisionPeriod,
root_entity_class=entities.StateSupervisionPeriod,
unifying_id_field='person_id',
build_related_entities=False))
supervision_period_to_agent_map = {
'agent_id': 1010,
'agent_external_id': 'OFFICER0009',
'district_external_id': '10',
'supervision_period_id': supervision_period.supervision_period_id
}
supervision_period_to_agent_associations = (
test_pipeline
| 'Create SupervisionPeriod to Agent table' >> beam.Create(
[supervision_period_to_agent_map]))
supervision_period_to_agent_associations_as_kv = (
supervision_period_to_agent_associations
| 'Convert SupervisionPeriod to Agent table to KV tuples' >>
beam.ParDo(pipeline.ConvertDictToKVTuple(),
'supervision_period_id'))
# Group each StatePerson with their other entities
persons_entities = ({
'person': persons,
'program_assignments': program_assignments,
'assessments': assessments,
'supervision_periods': supervision_periods
}
|
'Group StatePerson to StateProgramAssignments and'
>> beam.CoGroupByKey())
# Identify ProgramEvents from the StatePerson's
# StateProgramAssignments
person_program_events = (
persons_entities
| beam.ParDo(
pipeline.ClassifyProgramAssignments(),
AsDict(supervision_period_to_agent_associations_as_kv)))
# Get pipeline job details for accessing job_id
all_pipeline_options = PipelineOptions().get_all_options()
# Add timestamp for local jobs
job_timestamp = datetime.datetime.now().strftime(
'%Y-%m-%d_%H_%M_%S.%f')
all_pipeline_options['job_timestamp'] = job_timestamp
# Get program metrics
program_metrics = (person_program_events
|
'Get Program Metrics' >> pipeline.GetProgramMetrics(
pipeline_options=all_pipeline_options,
inclusions=ALL_INCLUSIONS_DICT,
calculation_month_limit=-1))
assert_that(program_metrics, AssertMatchers.validate_pipeline_test())
test_pipeline.run()