def test_validate_instance_invalid_environment(self):
instance = {'feature': np.array(['A'])}
schema = text_format.Parse(
"""
default_environment: "TRAINING"
default_environment: "SERVING"
feature {
name: "label"
not_in_environment: "SERVING"
value_count { min: 1 max: 1 }
presence { min_count: 1 }
type: BYTES
}
feature {
name: "feature"
value_count { min: 1 max: 1 }
presence { min_count: 1 }
type: BYTES
}
""", schema_pb2.Schema())
options = stats_options.StatsOptions(schema=schema)
with self.assertRaisesRegexp(ValueError,
'Environment.*not found in the schema.*'):
_ = validation_api.validate_instance(instance,
options,
environment='INVALID')
def test_validate_instance_stats_options_without_schema(self):
instance = {'feature': np.array(['A'])}
# This instance of StatsOptions has no schema.
options = stats_options.StatsOptions()
with self.assertRaisesRegexp(ValueError,
'options must include a schema.'):
_ = validation_api.validate_instance(instance, options)
def test_validate_instance_environment(self):
instance = {'feature': np.array(['A'])}
schema = text_format.Parse(
"""
default_environment: "TRAINING"
default_environment: "SERVING"
feature {
name: "label"
not_in_environment: "SERVING"
value_count { min: 1 max: 1 }
presence { min_count: 1 }
type: BYTES
}
feature {
name: "feature"
value_count { min: 1 max: 1 }
presence { min_count: 1 }
type: BYTES
}
""", schema_pb2.Schema())
options = stats_options.StatsOptions(schema=schema)
# Validate the instance in TRAINING environment.
expected_anomalies_training = {
'label':
text_format.Parse(
"""
description: "Column is completely missing"
severity: ERROR
short_description: "Column dropped"
reason {
type: SCHEMA_MISSING_COLUMN
short_description: "Column dropped"
description: "Column is completely missing"
}
""", anomalies_pb2.AnomalyInfo())
}
anomalies_training = validation_api.validate_instance(
instance, options, environment='TRAINING')
self._assert_equal_anomalies(anomalies_training,
expected_anomalies_training)
# Validate the instance in SERVING environment.
anomalies_serving = validation_api.validate_instance(
instance, options, environment='SERVING')
self._assert_equal_anomalies(anomalies_serving, {})
def test_validate_instance_global_only_anomaly_type(self):
instance = {'annotated_enum': np.array(['D'])}
# This schema has a presence.min_count > 1, which will generate an anomaly
# of type FEATURE_TYPE_LOW_NUMBER_PRESENT when any single example is
# validated using this schema. This test checks that this anomaly type
# (which is not meaningful in per-example validation) is not included in the
# Anomalies proto that validate_instance returns.
schema = text_format.Parse(
"""
string_domain {
name: "MyAloneEnum"
value: "A"
value: "B"
value: "C"
}
feature {
name: "annotated_enum"
value_count {
min:1
max:1
}
presence {
min_count: 5
}
type: BYTES
domain: "MyAloneEnum"
}
feature {
name: "ignore_this"
lifecycle_stage: DEPRECATED
value_count {
min:1
}
presence {
min_count: 1
}
type: BYTES
}
""", schema_pb2.Schema())
expected_anomalies = {
'annotated_enum':
text_format.Parse(
"""
description: "Examples contain values missing from the schema: D "
"(~100%). "
severity: ERROR
short_description: "Unexpected string values"
reason {
type: ENUM_TYPE_UNEXPECTED_STRING_VALUES
short_description: "Unexpected string values"
description: "Examples contain values missing from the schema: D "
"(~100%). "
}
""", anomalies_pb2.AnomalyInfo())
}
options = stats_options.StatsOptions(schema=schema)
anomalies = validation_api.validate_instance(instance, options)
self._assert_equal_anomalies(anomalies, expected_anomalies)
def test_validate_instance(self):
instance = {'annotated_enum': np.array(['D'])}
schema = text_format.Parse(
"""
string_domain {
name: "MyAloneEnum"
value: "A"
value: "B"
value: "C"
}
feature {
name: "annotated_enum"
value_count {
min:1
max:1
}
presence {
min_count: 1
}
type: BYTES
domain: "MyAloneEnum"
}
feature {
name: "ignore_this"
lifecycle_stage: DEPRECATED
value_count {
min:1
}
presence {
min_count: 1
}
type: BYTES
}
""", schema_pb2.Schema())
expected_anomalies = {
'annotated_enum':
text_format.Parse(
"""
description: "Examples contain values missing from the schema: D "
"(~100%). "
severity: ERROR
short_description: "Unexpected string values"
reason {
type: ENUM_TYPE_UNEXPECTED_STRING_VALUES
short_description: "Unexpected string values"
description: "Examples contain values missing from the schema: D "
"(~100%). "
}
""", anomalies_pb2.AnomalyInfo())
}
options = stats_options.StatsOptions(schema=schema)
anomalies = validation_api.validate_instance(instance, options)
self._assert_equal_anomalies(anomalies, expected_anomalies)
def test_validate_instance_invalid_options(self):
instance = {'feature': np.array(['A'])}
with self.assertRaisesRegexp(ValueError,
'options must be a StatsOptions object.'):
_ = validation_api.validate_instance(instance, {})
def test_validate_instance_stats_options_without_schema(self):
instance = pa.Table.from_arrays([pa.array([['A']])], ['feature'])
# This instance of StatsOptions has no schema.
options = stats_options.StatsOptions()
with self.assertRaisesRegexp(ValueError, 'options must include a schema.'):
_ = validation_api.validate_instance(instance, options)
def test_validate_instance_invalid_options(self):
instance = pa.Table.from_arrays([pa.array([['A']])], ['feature'])
with self.assertRaisesRegexp(ValueError,
'options must be a StatsOptions object.'):
_ = validation_api.validate_instance(instance, {})
