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 testIncarcerationPipeline(self):
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])
sentence_group = schema.StateSentenceGroup(sentence_group_id=111,
person_id=fake_person_id)
initial_incarceration = schema.StateIncarcerationPeriod(
incarceration_period_id=1111,
status=StateIncarcerationPeriodStatus.NOT_IN_CUSTODY,
state_code='CA',
county_code='124',
facility='San Quentin',
facility_security_level=StateIncarcerationFacilitySecurityLevel.
MAXIMUM,
admission_reason=StateIncarcerationPeriodAdmissionReason.
NEW_ADMISSION,
projected_release_reason=StateIncarcerationPeriodReleaseReason.
CONDITIONAL_RELEASE,
admission_date=date(2008, 11, 20),
release_date=date(2010, 12, 4),
release_reason=StateIncarcerationPeriodReleaseReason.
SENTENCE_SERVED,
person_id=fake_person_id,
)
first_reincarceration = schema.StateIncarcerationPeriod(
incarceration_period_id=2222,
status=StateIncarcerationPeriodStatus.NOT_IN_CUSTODY,
state_code='CA',
county_code='124',
facility='San Quentin',
facility_security_level=StateIncarcerationFacilitySecurityLevel.
MAXIMUM,
admission_reason=StateIncarcerationPeriodAdmissionReason.
NEW_ADMISSION,
projected_release_reason=StateIncarcerationPeriodReleaseReason.
CONDITIONAL_RELEASE,
admission_date=date(2011, 4, 5),
release_date=date(2014, 4, 14),
release_reason=StateIncarcerationPeriodReleaseReason.
SENTENCE_SERVED,
person_id=fake_person_id)
subsequent_reincarceration = schema.StateIncarcerationPeriod(
incarceration_period_id=3333,
status=StateIncarcerationPeriodStatus.IN_CUSTODY,
state_code='CA',
county_code='124',
facility='San Quentin',
facility_security_level=StateIncarcerationFacilitySecurityLevel.
MAXIMUM,
admission_reason=StateIncarcerationPeriodAdmissionReason.
NEW_ADMISSION,
projected_release_reason=StateIncarcerationPeriodReleaseReason.
CONDITIONAL_RELEASE,
admission_date=date(2017, 1, 4),
person_id=fake_person_id)
incarceration_sentence = schema.StateIncarcerationSentence(
incarceration_sentence_id=1111,
sentence_group_id=sentence_group.sentence_group_id,
incarceration_periods=[
initial_incarceration, first_reincarceration,
subsequent_reincarceration
],
person_id=fake_person_id)
supervision_sentence = schema.StateSupervisionSentence(
supervision_sentence_id=123, person_id=fake_person_id)
sentence_group.incarceration_sentences = [incarceration_sentence]
sentence_group_data = [normalized_database_base_dict(sentence_group)]
incarceration_sentence_data = [
normalized_database_base_dict(incarceration_sentence)
]
supervision_sentence_data = [
normalized_database_base_dict(supervision_sentence)
]
incarceration_periods_data = [
normalized_database_base_dict(initial_incarceration),
normalized_database_base_dict(first_reincarceration),
normalized_database_base_dict(subsequent_reincarceration)
]
state_incarceration_sentence_incarceration_period_association = [
{
'incarceration_period_id':
initial_incarceration.incarceration_period_id,
'incarceration_sentence_id':
incarceration_sentence.incarceration_sentence_id,
},
{
'incarceration_period_id':
first_reincarceration.incarceration_period_id,
'incarceration_sentence_id':
incarceration_sentence.incarceration_sentence_id,
},
{
'incarceration_period_id':
subsequent_reincarceration.incarceration_period_id,
'incarceration_sentence_id':
incarceration_sentence.incarceration_sentence_id,
},
]
data_dict = {
schema.StatePerson.__tablename__:
persons_data,
schema.StatePersonRace.__tablename__:
races_data,
schema.StatePersonEthnicity.__tablename__:
ethnicity_data,
schema.StateSentenceGroup.__tablename__:
sentence_group_data,
schema.StateIncarcerationSentence.__tablename__:
incarceration_sentence_data,
schema.StateSupervisionSentence.__tablename__:
supervision_sentence_data,
schema.StateIncarcerationPeriod.__tablename__:
incarceration_periods_data,
schema.state_incarceration_sentence_incarceration_period_association_table.name:
state_incarceration_sentence_incarceration_period_association,
schema.state_supervision_sentence_incarceration_period_association_table.name:
[{}]
}
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 StateSentenceGroups
sentence_groups = (
test_pipeline
| 'Load StateSentencegroups' >> extractor_utils.BuildRootEntity(
dataset=None,
data_dict=data_dict,
root_schema_class=schema.StateSentenceGroup,
root_entity_class=entities.StateSentenceGroup,
unifying_id_field='person_id',
build_related_entities=True))
# Get StateIncarcerationSentences
incarceration_sentences = (
test_pipeline | 'Load StateIncarcerationSentences' >>
extractor_utils.BuildRootEntity(
dataset=None,
data_dict=data_dict,
root_schema_class=schema.StateIncarcerationSentence,
root_entity_class=entities.StateIncarcerationSentence,
unifying_id_field='person_id',
build_related_entities=True))
# Get StateSupervisionSentences
supervision_sentences = (
test_pipeline | 'Load StateSupervisionSentences' >>
extractor_utils.BuildRootEntity(
dataset=None,
data_dict=data_dict,
root_schema_class=schema.StateSupervisionSentence,
root_entity_class=entities.StateSupervisionSentence,
unifying_id_field='person_id',
build_related_entities=True))
sentences_and_sentence_groups = (
{
'sentence_groups': sentence_groups,
'incarceration_sentences': incarceration_sentences,
'supervision_sentences': supervision_sentences
}
| 'Group sentences to sentence groups' >> beam.CoGroupByKey())
sentence_groups_with_hydrated_sentences = (
sentences_and_sentence_groups
| 'Set hydrated sentences on sentence groups' >> beam.ParDo(
SetSentencesOnSentenceGroup()))
# Group each StatePerson with their related entities
person_and_sentence_groups = (
{
'person': persons,
'sentence_groups': sentence_groups_with_hydrated_sentences
}
| 'Group StatePerson to SentenceGroups' >> beam.CoGroupByKey())
# Identify IncarcerationEvents events from the StatePerson's
# StateIncarcerationPeriods
fake_person_id_to_county_query_result = [{
'person_id':
fake_person_id,
'county_of_residence':
_COUNTY_OF_RESIDENCE
}]
person_id_to_county_kv = (
test_pipeline
| "Read person id to county associations from BigQuery" >>
beam.Create(fake_person_id_to_county_query_result)
|
"Convert to KV" >> beam.ParDo(ConvertDictToKVTuple(), 'person_id'))
person_events = (person_and_sentence_groups
| 'Classify Incarceration Events' >> beam.ParDo(
pipeline.ClassifyIncarcerationEvents(),
AsDict(person_id_to_county_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 IncarcerationMetrics
incarceration_metrics = (
person_events
| 'Get Incarceration Metrics' >> pipeline.GetIncarcerationMetrics(
pipeline_options=all_pipeline_options,
inclusions=ALL_INCLUSIONS_DICT,
calculation_month_limit=-1))
assert_that(incarceration_metrics,
AssertMatchers.validate_metric_type())
test_pipeline.run()
def run_test_pipeline(
fake_person_id: int,
state_code: str,
dataset: str,
expected_metric_types: Set[IncarcerationMetricType],
allow_empty: bool = False,
unifying_id_field_filter_set: Optional[Set[int]] = None,
metric_types_filter: Optional[Set[str]] = None):
"""Runs a test version of the incarceration 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 StateSentenceGroups
sentence_groups = (
test_pipeline
| 'Load StateSentenceGroups' >> # type: ignore
extractor_utils.BuildRootEntity(
dataset=dataset,
root_entity_class=entities.StateSentenceGroup,
unifying_id_field=entities.StatePerson.get_class_id_name(),
build_related_entities=True,
unifying_id_field_filter_set=unifying_id_field_filter_set))
# Get StateIncarcerationSentences
incarceration_sentences = (
test_pipeline
| 'Load StateIncarcerationSentences' >> # type: ignore
extractor_utils.BuildRootEntity(
dataset=dataset,
root_entity_class=entities.StateIncarcerationSentence,
unifying_id_field=entities.StatePerson.get_class_id_name(),
build_related_entities=True,
unifying_id_field_filter_set=unifying_id_field_filter_set))
# Get StateSupervisionSentences
supervision_sentences = (
test_pipeline | 'Load StateSupervisionSentences' >> # type: ignore
extractor_utils.BuildRootEntity(
dataset=dataset,
root_entity_class=entities.StateSupervisionSentence,
unifying_id_field=entities.StatePerson.get_class_id_name(),
build_related_entities=True,
unifying_id_field_filter_set=unifying_id_field_filter_set))
us_mo_sentence_status_rows: List[Dict[str, Any]] = [{
'person_id':
fake_person_id,
'sentence_external_id':
'XXX',
'sentence_status_external_id':
'YYY',
'status_code':
'ZZZ',
'status_date':
'not_a_date',
'status_description':
'XYZ'
}]
us_mo_sentence_statuses = (test_pipeline
| 'Create MO sentence statuses' >>
beam.Create(us_mo_sentence_status_rows))
us_mo_sentence_status_rankings_as_kv = (
us_mo_sentence_statuses
| 'Convert sentence status ranking table to KV tuples' >>
beam.ParDo(ConvertDictToKVTuple(), 'person_id'))
sentences_and_statuses = (
{
'incarceration_sentences': incarceration_sentences,
'supervision_sentences': supervision_sentences,
'sentence_statuses': us_mo_sentence_status_rankings_as_kv
}
| 'Group sentences to the sentence statuses for that person' >>
beam.CoGroupByKey())
sentences_converted = (
sentences_and_statuses
| 'Convert to state-specific sentences' >> beam.ParDo(
ConvertSentencesToStateSpecificType()).with_outputs(
'incarceration_sentences', 'supervision_sentences'))
sentences_and_sentence_groups = (
{
'sentence_groups': sentence_groups,
'incarceration_sentences':
sentences_converted.incarceration_sentences,
'supervision_sentences':
sentences_converted.supervision_sentences
}
| 'Group sentences to sentence groups' >> beam.CoGroupByKey())
sentence_groups_with_hydrated_sentences = (
sentences_and_sentence_groups
| 'Set hydrated sentences on sentence groups' >> beam.ParDo(
SetSentencesOnSentenceGroup()))
# Identify IncarcerationEvents events from the StatePerson's
# StateIncarcerationPeriods
fake_person_id_to_county_query_result = [{
'person_id':
fake_person_id,
'county_of_residence':
_COUNTY_OF_RESIDENCE
}]
person_id_to_county_kv = (
test_pipeline
| "Read person id to county associations from BigQuery" >>
beam.Create(fake_person_id_to_county_query_result)
| "Convert person_id to counties to KV" >> beam.ParDo(
ConvertDictToKVTuple(), 'person_id'))
incarceration_period_judicial_district_association_row = \
{'person_id': fake_person_id, 'incarceration_period_id': 123, 'judicial_district_code': 'NW'}
ip_to_judicial_district_kv = (
test_pipeline
|
"Read incarceration_period to judicial_district associations from BigQuery"
>> beam.Create(
[incarceration_period_judicial_district_association_row])
| "Convert ips to judicial districts to KV" >> beam.ParDo(
ConvertDictToKVTuple(), 'person_id'))
state_race_ethnicity_population_count = {
'state_code': state_code,
'race_or_ethnicity': 'BLACK',
'population_count': 1,
'representation_priority': 1
}
state_race_ethnicity_population_counts = (
test_pipeline
| 'Create state_race_ethnicity_population_count table' >>
beam.Create([state_race_ethnicity_population_count]))
# Group each StatePerson with their related entities
person_entities = (
{
'person':
persons,
'sentence_groups':
sentence_groups_with_hydrated_sentences,
'incarceration_period_judicial_district_association':
ip_to_judicial_district_kv
}
| 'Group StatePerson to SentenceGroups' >> beam.CoGroupByKey())
# Identify IncarcerationEvents events from the StatePerson's StateIncarcerationPeriods
person_incarceration_events = (
person_entities | 'Classify Incarceration Events' >> beam.ParDo(
pipeline.ClassifyIncarcerationEvents(),
AsDict(person_id_to_county_kv)))
person_metadata = (
persons
| "Build the person_metadata dictionary" >> beam.ParDo(
BuildPersonMetadata(),
AsList(state_race_ethnicity_population_counts)))
person_incarceration_events_with_metadata = (
{
'person_events': person_incarceration_events,
'person_metadata': person_metadata
}
| 'Group IncarcerationEvents with person-level metadata' >>
beam.CoGroupByKey()
|
'Organize StatePerson, PersonMetadata and IncarcerationEvents for calculations'
>> beam.ParDo(ExtractPersonEventsMetadata()))
# 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 IncarcerationMetrics
incarceration_metrics = (
person_incarceration_events_with_metadata
| 'Get Incarceration Metrics' >> # type: ignore
pipeline.GetIncarcerationMetrics(
pipeline_options=all_pipeline_options,
metric_types=metric_types,
calculation_end_month=None,
calculation_month_count=-1))
assert_that(
incarceration_metrics,
AssertMatchers.validate_metric_type(allow_empty=allow_empty),
'Assert that all metrics are of the expected type.')
assert_that(
incarceration_metrics,
AssertMatchers.validate_pipeline_test(expected_metric_types),
'Assert the type of metrics produced are expected')
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()