def compare_stats_for_examples(self,
examples_id,
other_examples_id,
name='',
other_name=''):
"""Compares stats for `examples_id` and `other_examples_id`.
Args:
examples_id: A `int` indicating the id of one `TFXArtifactTypes.EXAMPLES`
artifact.
other_examples_id: A `int` indicating the id of another
`TFXArtifactTypes.EXAMPLES` artifact.
name: (Optional) A `str` indicating the label to use for stats of
`examples_id`.
other_name: (Optional) A `str` indicating the label to use for stats of
`other_examples_id`.
"""
stats_artifact, other_stats_artifact = (
self.get_dest_artifact_of_type(examples_id,
TFXArtifactTypes.EXAMPLE_STATS),
self.get_dest_artifact_of_type(other_examples_id,
TFXArtifactTypes.EXAMPLE_STATS))
if stats_artifact and other_stats_artifact:
tfdv.visualize_statistics(tfdv.load_statistics(stats_artifact.uri),
rhs_statistics=tfdv.load_statistics(
other_stats_artifact.uri),
lhs_name=name,
rhs_name=other_name)
def Do(self, input_dict: Dict[Text, List[types.Artifact]],
output_dict: Dict[Text, List[types.Artifact]],
exec_properties: Dict[Text, Any]) -> None:
"""TensorFlow SchemaGen executor entrypoint.
This infers the schema using tensorflow_data_validation on the precomputed
stats of 'train' split.
Args:
input_dict: Input dict from input key to a list of artifacts, including:
- 'stats': A list of 'ExampleStatistics' type which must contain
split 'train'. Stats on other splits are ignored.
- 'statistics': Synonym for 'stats'.
output_dict: Output dict from key to a list of artifacts, including:
- output: A list of 'Schema' artifact of size one.
exec_properties: A dict of execution properties, includes:
- infer_feature_shape: Whether or not to infer the shape of the feature.
- exclude_splits: Names of splits that will not be taken into
consideration when auto-generating a schema.
Returns:
None
"""
# TODO(zhitaoli): Move constants between this file and component.py to a
# constants.py.
infer_feature_shape = exec_properties.get(INFER_FEATURE_SHAPE_KEY)
# Load and deserialize exclude splits from execution properties.
exclude_splits = json_utils.loads(
exec_properties.get(EXCLUDE_SPLITS_KEY, 'null')) or []
if not isinstance(exclude_splits, list):
raise ValueError('exclude_splits in execution properties needs to be a '
'list. Got %s instead.' % type(exclude_splits))
# Only one schema is generated for all splits.
schema = None
stats_artifact = artifact_utils.get_single_instance(
input_dict[STATISTICS_KEY])
for split in artifact_utils.decode_split_names(stats_artifact.split_names):
if split in exclude_splits:
continue
logging.info('Processing schema from statistics for split %s.', split)
stats_uri = io_utils.get_only_uri_in_dir(
os.path.join(stats_artifact.uri, split))
if not schema:
schema = tfdv.infer_schema(
tfdv.load_statistics(stats_uri), infer_feature_shape)
else:
schema = tfdv.update_schema(schema, tfdv.load_statistics(stats_uri),
infer_feature_shape)
output_uri = os.path.join(
artifact_utils.get_single_uri(output_dict[SCHEMA_KEY]),
_DEFAULT_FILE_NAME)
io_utils.write_pbtxt_file(output_uri, schema)
logging.info('Schema written to %s.', output_uri)
def Do(self, input_dict: Dict[Text, List[types.Artifact]],
output_dict: Dict[Text, List[types.Artifact]],
exec_properties: Dict[Text, Any]) -> None:
"""TensorFlow SchemaGen executor entrypoint.
This infers the schema using tensorflow_data_validation on the precomputed
stats of 'train' split.
Args:
input_dict: Input dict from input key to a list of artifacts, including:
- 'stats': A list of 'ExampleStatistics' type which must contain
split 'train'. Stats on other splits are ignored.
- 'statistics': Synonym for 'stats'.
output_dict: Output dict from key to a list of artifacts, including:
- output: A list of 'Schema' artifact of size one.
exec_properties: A dict of execution properties, includes:
- infer_feature_shape: Whether or not to infer the shape of the feature.
Returns:
None
"""
# TODO(zhitaoli): Move constants between this file and component.py to a
# constants.py.
train_stats_uri = io_utils.get_only_uri_in_dir(
artifact_utils.get_split_uri(input_dict['stats'], 'train'))
output_uri = os.path.join(
artifact_utils.get_single_uri(output_dict['output']),
_DEFAULT_FILE_NAME)
infer_feature_shape = exec_properties['infer_feature_shape']
absl.logging.info('Infering schema from statistics.')
schema = tfdv.infer_schema(tfdv.load_statistics(train_stats_uri),
infer_feature_shape)
io_utils.write_pbtxt_file(output_uri, schema)
absl.logging.info('Schema written to %s.' % output_uri)
def _validate_stats_output(self, stats_path):
self.assertTrue(tf.io.gfile.exists(stats_path))
stats = tfdv.load_statistics(stats_path)
self.assertLen(stats.datasets, 1)
data_set = stats.datasets[0]
self.assertGreater(data_set.num_examples, 0)
self.assertNotEmpty(data_set.features)
def test_e2e(self, stats_options, expected_stats_pbtxt,
expected_schema_pbtxt):
tfxio = tf_sequence_example_record.TFSequenceExampleRecord(
self._input_file, ['tfdv', 'test'])
stats_file = os.path.join(self._output_dir, 'stats')
with beam.Pipeline() as p:
_ = (p
| 'TFXIORead' >> tfxio.BeamSource()
| 'GenerateStats' >> tfdv.GenerateStatistics(stats_options)
| 'WriteStats' >> tfdv.WriteStatisticsToTFRecord(stats_file))
actual_stats = tfdv.load_statistics(stats_file)
test_util.make_dataset_feature_stats_list_proto_equal_fn(
self,
text_format.Parse(
expected_stats_pbtxt,
statistics_pb2.DatasetFeatureStatisticsList()))([actual_stats])
actual_schema = tfdv.infer_schema(actual_stats,
infer_feature_shape=True)
if hasattr(actual_schema, 'generate_legacy_feature_spec'):
actual_schema.ClearField('generate_legacy_feature_spec')
self._assert_schema_equal(
actual_schema,
text_format.Parse(expected_schema_pbtxt, schema_pb2.Schema()))
def _provide_schema(self, input_dict,
exec_properties) -> schema_pb2.Schema:
"""Generates schema from either schema or statistics."""
# TODO(zhitaoli): Move constants between this file and component.py to a
# constants.py.
stats = input_dict.get('stats') or input_dict.get('statistics')
schema = input_dict.get('schema')
if bool(stats) == bool(schema):
raise ValueError(
'Exactly only one of schema or stats must be provided')
if schema:
schema_uri = artifact_utils.get_single_uri(schema)
absl.logging.info('Schema is provided. Reading from %s.' %
schema_uri)
schema_reader = io_utils.SchemaReader()
try:
return schema_reader.read(
os.path.join(schema_uri, _DEFAULT_FILE_NAME))
except tf.errors.NotFoundError:
raise ValueError(
'Schema is provided, but failed to read from %s.' %
schema_uri)
train_stats_uri = io_utils.get_only_uri_in_dir(
artifact_utils.get_split_uri(stats, 'train'))
infer_feature_shape = exec_properties['infer_feature_shape']
return tfdv.infer_schema(tfdv.load_statistics(train_stats_uri),
infer_feature_shape)
def _validate_stats_output(self, stats_path):
self.assertTrue(tf.gfile.Exists(stats_path))
stats = tfdv.load_statistics(stats_path)
self.assertEqual(1, len(stats.datasets))
data_set = stats.datasets[0]
self.assertGreater(data_set.num_examples, 0)
self.assertNotEqual(0, len(data_set.features))
def _validate_stats_output(self, stats_path): self.assertTrue(tf.gfile.Exists(stats_path)) stats = tfdv.load_statistics(stats_path) self.assertEqual(1, len(stats.datasets)) data_set = stats.datasets[0] self.assertGreater(data_set.num_examples, 0) self.assertNotEqual(0, len(data_set.features))
def Do(self, input_dict: Dict[Text, List[types.Artifact]],
output_dict: Dict[Text, List[types.Artifact]],
exec_properties: Dict[Text, Any]) -> None:
self._log_startup(input_dict, output_dict, exec_properties)
logging.info('Validating schema against the computed statistics.')
split_uris: List[Text] = []
for artifact in input_dict[executor.STATISTICS_KEY]:
for split in artifact_utils.decode_split_names(
artifact.split_names):
split_uris.append(split)
label_inputs = {
labels.STATS:
tfdv.load_statistics(
io_utils.get_only_uri_in_dir(
artifact_utils.get_split_uri(
input_dict[executor.STATISTICS_KEY], split_uris[0]))),
labels.SCHEMA:
io_utils.SchemaReader().read(
io_utils.get_only_uri_in_dir(
artifact_utils.get_single_uri(
input_dict[executor.SCHEMA_KEY])))
}
output_uri = artifact_utils.get_single_uri(
output_dict[executor.ANOMALIES_KEY])
label_outputs = {labels.SCHEMA_DIFF_PATH: output_uri}
self._Validate(label_inputs, label_outputs)
logging.info(
'Validation complete. Anomalies written to {}.'.format(output_uri))
def Do(self, input_dict,
output_dict,
exec_properties):
"""TensorFlow SchemaGen executor entrypoint.
This infers the schema using tensorflow_data_validation on the precomputed
stats of 'train' split.
Args:
input_dict: Input dict from input key to a list of artifacts, including:
- stats: A list of 'ExampleStatisticsPath' type which should contain
split 'train'. Stats on other splits are ignored.
output_dict: Output dict from key to a list of artifacts, including:
- output: A list of 'SchemaPath' artifact of size one.
exec_properties: A dict of execution properties. Not used yet.
Returns:
None
"""
# TODO(zhitaoli): Move constants between this file and component.py to a
# constants.py.
train_stats_uri = io_utils.get_only_uri_in_dir(
types.get_split_uri(input_dict['stats'], 'train'))
output_uri = os.path.join(
types.get_single_uri(output_dict['output']), _DEFAULT_FILE_NAME)
infer_feature_shape = False
tf.logging.info('Infering schema from statistics.')
schema = tfdv.infer_schema(
tfdv.load_statistics(train_stats_uri), infer_feature_shape)
io_utils.write_pbtxt_file(output_uri, schema)
tf.logging.info('Schema written to {}.'.format(output_uri))
def Do(self, input_dict, output_dict, exec_properties):
"""TensorFlow ExampleValidator executor entrypoint.
This validates the statistics on the 'eval' split against the schema.
Args:
input_dict: Input dict from input key to a list of artifacts, including:
- stats: A list of 'ExampleStatisticsPath' type which should contain
split 'eval'. Stats on other splits are ignored.
- schema: A list of 'SchemaPath' type which should contain a single
schema artifact.
output_dict: Output dict from key to a list of artifacts, including:
- output: A list of 'ExampleValidationPath' artifact of size one. It
will include a single pbtxt file which contains all anomalies found.
exec_properties: A dict of execution properties. Not used yet.
Returns:
None
"""
self._log_startup(input_dict, output_dict, exec_properties)
tf.logging.info('Validating schema against the computed statistics.')
schema = io_utils.SchemaReader().read(
io_utils.get_only_uri_in_dir(
types.get_single_uri(input_dict['schema'])))
stats = tfdv.load_statistics(
io_utils.get_only_uri_in_dir(
types.get_split_uri(input_dict['stats'], 'eval')))
output_uri = types.get_single_uri(output_dict['output'])
anomalies = tfdv.validate_statistics(stats, schema)
io_utils.write_pbtxt_file(os.path.join(output_uri, DEFAULT_FILE_NAME),
anomalies)
tf.logging.info(
'Validation complete. Anomalies written to {}.'.format(output_uri))
def parse_statistics(split_name: Text,
statistics: List[Artifact]) -> Dict[Text, int]:
stats_uri = io_utils.get_only_uri_in_dir(
artifact_utils.get_split_uri(statistics, split_name))
stats = tfdv.load_statistics(stats_uri)
return stats
def display_stats_for_examples(self, examples_id):
"""Displays stats for `examples_id`.
Args:
examples_id: A `int` indicating the id of a `TFXArtifactTypes.EXAMPLES`
artifact.
"""
stats_artifact = self.get_dest_artifact_of_type(
examples_id, TFXArtifactTypes.EXAMPLE_STATS)
if stats_artifact:
tfdv.visualize_statistics(
tfdv.load_statistics(
os.path.join(stats_artifact.uri, 'stats_tfrecord')))
print("display shema")
tfdv.display_schema(
tfdv.infer_schema(statistics=tfdv.load_statistics(
os.path.join(stats_artifact.uri, 'stats_tfrecord'))))
def display(self, artifact: types.Artifact):
from IPython.core.display import display # pylint: disable=g-import-not-at-top
from IPython.core.display import HTML # pylint: disable=g-import-not-at-top
for split in artifact_utils.decode_split_names(artifact.split_names):
display(HTML('<div><b>%r split:</b></div><br/>' % split))
stats_path = os.path.join(artifact.uri, split, 'stats_tfrecord')
stats = tfdv.load_statistics(stats_path)
tfdv.visualize_statistics(stats)
def validate_stats_against_schema(self): # type: () -> bool
stats = tfdv.load_statistics(self.stats_path)
self.anomalies = tfdv.validate_statistics(stats, self.schema)
if len(self.anomalies.anomaly_info.items()) > 0:
logger.error("Anomalies found in training dataset...")
logger.error(str(self.anomalies.anomaly_info.items()))
self.upload_anomalies()
return False
else:
logger.info("No anomalies found")
return True
def parse_schema_from_stats(cls, stats_path):
# type: (str) -> Tuple[Dict[str, Union[tf.FixedLenFeature, tf.VarLenFeature, tf.SparseFeature]], Schema] # noqa: E501
"""
Returns TensorFlow Feature Spec and parsed tf.metadata Schema for given tf.metadata
DatasetFeatureStatisticsList.
:param stats_path: tf.metadata DatasetFeatureStatisticsList path
"""
import tensorflow_data_validation as tfdv
stats = tfdv.load_statistics(stats_path)
schema = tfdv.infer_schema(stats)
return schema_to_feature_spec(schema), schema
def infer_schema(stats_path, schema_path):
"""Infers a schema from stats in stats_path.
Args:
stats_path: Location of the stats used to infer the schema.
schema_path: Location where the inferred schema is materialized.
"""
print('Infering schema from statistics.')
schema = tfdv.infer_schema(tfdv.load_statistics(stats_path),
infer_feature_shape=False)
print(text_format.MessageToString(schema))
print('## Statistics ##')
stats = tfdv.load_statistics(stats_path)
# print(text_format.MessageToString(stats))
for d in stats.datasets:
for f in d.features:
print(f.name)
print('Writing schema to output path.')
file_io.write_string_to_file(schema_path,
text_format.MessageToString(schema))
def display(self, artifact: types.Artifact):
from IPython.core.display import display # pylint: disable=g-import-not-at-top
from IPython.core.display import HTML # pylint: disable=g-import-not-at-top
for split in artifact_utils.decode_split_names(artifact.split_names):
display(HTML('<div><b>%r split:</b></div><br/>' % split))
stats_path = io_utils.get_only_uri_in_dir(
artifact_utils.get_split_uri([artifact], split))
if artifact_utils.is_artifact_version_older_than(
artifact, artifact_utils._ARTIFACT_VERSION_FOR_STATS_UPDATE): # pylint: disable=protected-access
stats = tfdv.load_statistics(stats_path)
else:
stats = tfdv.load_stats_binary(stats_path)
tfdv.visualize_statistics(stats)
def infer_schema(stats_path, schema_path):
"""Infers a schema from stats in stats_path.
Args:
stats_path: Location of the stats used to infer the schema.
schema_path: Location where the inferred schema is materialized.
"""
print('Infering schema from statistics.')
schema = tfdv.infer_schema(tfdv.load_statistics(stats_path),
infer_feature_shape=False)
print(text_format.MessageToString(schema))
print('Writing schema to output path.')
tfdv.write_schema_text(schema, schema_path)
def infer_schema(stats_path, schema_path):
"""Infers a schema from stats in stats_path.
Args:
stats_path: Location of the stats used to infer the schema.
schema_path: Location where the inferred schema is materialized.
"""
# Infering schema from statistics
schema = tfdv.infer_schema(tfdv.load_statistics(stats_path),
infer_feature_shape=False)
# Writing schema to output path
file_io.write_string_to_file(schema_path,
text_format.MessageToString(schema))
def display_stats_for_examples(self, examples_id, split='train'):
"""Displays stats for `examples_id`.
Args:
examples_id: A `int` indicating the id of a `TFXArtifactTypes.EXAMPLES`
artifact.
split: A `string` specifying the split name, by default 'train' is used.
"""
stats_artifact = self.get_dest_artifact_of_type(
examples_id, TFXArtifactTypes.EXAMPLE_STATS)
if stats_artifact:
tfdv.visualize_statistics(
tfdv.load_statistics(
os.path.join(stats_artifact.uri, split, 'stats_tfrecord')))
def infer_schema(stats_path, schema_path):
"""Infers a schema from stats in stats_path.
Args:
stats_path: Location of the stats used to infer the schema.
schema_path: Location where the inferred schema is materialized.
"""
print('Infering schema from statistics.')
schema = tfdv.infer_schema(
tfdv.load_statistics(stats_path), infer_feature_shape=False)
print(text_format.MessageToString(schema))
print('Writing schema to output path.')
file_io.write_string_to_file(schema_path, text_format.MessageToString(schema))
def tfdv_detect_drift(
stats_older_path: str, stats_new_path: str
) -> NamedTuple('Outputs', [('drift', str)]):
import logging
import time
import tensorflow_data_validation as tfdv
import tensorflow_data_validation.statistics.stats_impl
logging.getLogger().setLevel(logging.INFO)
logging.info('stats_older_path: %s', stats_older_path)
logging.info('stats_new_path: %s', stats_new_path)
if stats_older_path == 'none':
return ('true', )
stats1 = tfdv.load_statistics(stats_older_path)
stats2 = tfdv.load_statistics(stats_new_path)
schema1 = tfdv.infer_schema(statistics=stats1)
tfdv.get_feature(schema1, 'duration').drift_comparator.jensen_shannon_divergence.threshold = 0.01
drift_anomalies = tfdv.validate_statistics(
statistics=stats2, schema=schema1, previous_statistics=stats1)
logging.info('drift analysis results: %s', drift_anomalies.drift_skew_info)
from google.protobuf.json_format import MessageToDict
d = MessageToDict(drift_anomalies)
val = d['driftSkewInfo'][0]['driftMeasurements'][0]['value']
thresh = d['driftSkewInfo'][0]['driftMeasurements'][0]['threshold']
logging.info('value %s and threshold %s', val, thresh)
res = 'true'
if val < thresh:
res = 'false'
logging.info('train decision: %s', res)
return (res, )
def validate_stats(stats_path, schema_path, anomalies_path):
"""Validates the statistics against the schema and materializes anomalies.
Args:
stats_path: Location of the stats used to infer the schema.
schema_path: Location of the schema to be used for validation.
anomalies_path: Location where the detected anomalies are materialized.
"""
# Validating schema against the computed statistics
schema = my_metadata.read_schema(schema_path)
stats = tfdv.load_statistics(stats_path)
anomalies = tfdv.validate_statistics(stats, schema)
# Writing anomalies to anomalies path to
file_io.write_string_to_file(anomalies_path,
text_format.MessageToString(anomalies))
def validate_stats(stats_path, schema_path, anomalies_path):
"""Validates the statistics against the schema and materializes anomalies.
Args:
stats_path: Location of the stats used to infer the schema.
schema_path: Location of the schema to be used for validation.
anomalies_path: Location where the detected anomalies are materialized.
"""
print('Validating schema against the computed statistics.')
schema = tfdv.load_schema_text(schema_path)
stats = tfdv.load_statistics(stats_path)
anomalies = tfdv.validate_statistics(stats, schema)
print('Detected following anomalies:')
print(text_format.MessageToString(anomalies))
print('Writing anomalies to anomalies path.')
file_io.write_string_to_file(anomalies_path,
text_format.MessageToString(anomalies))
def validate_stats(stats_path, schema_path, anomalies_path):
"""Validates the statistics against the schema and materializes anomalies.
Args:
stats_path: Location of the stats used to infer the schema.
schema_path: Location of the schema to be used for validation.
anomalies_path: Location where the detected anomalies are materialized.
"""
print('Validating schema against the computed statistics.')
schema = taxi.read_schema(schema_path)
stats = tfdv.load_statistics(stats_path)
anomalies = tfdv.validate_statistics(stats, schema)
print('Detected following anomalies:')
print(text_format.MessageToString(anomalies))
print('Writing anomalies to anomalies path.')
file_io.write_string_to_file(anomalies_path,
text_format.MessageToString(anomalies))
def group_stats_and_examples(
input_dict: Dict[Text, List[types.Artifact]]
) -> List[Tuple[types.Artifact, Dict[Text, DatasetFeatureStatistics]]]:
result = []
examples_list = input_dict[EXAMPLES_KEY]
if len(examples_list) > 1:
raise ValueError('only one examples artifact expected')
examples = examples_list[0]
group = {}
for split in artifact_utils.decode_split_names(examples.split_names):
statistics = tfdv.load_statistics(
io_utils.get_only_uri_in_dir(
types.artifact_utils.get_split_uri(input_dict[STATISTICS_KEY],
split)))
if len(statistics.datasets) != 1:
raise ValueError('one statistics set expected')
group[split] = statistics.datasets[0]
result.append((examples, group))
return result
def Do(self, input_dict: Dict[Text, List[types.Artifact]],
output_dict: Dict[Text, List[types.Artifact]],
exec_properties: Dict[Text, Any]) -> None:
"""TensorFlow ExampleValidator executor entrypoint.
This validates the statistics on the 'eval' split against the schema.
Args:
input_dict: Input dict from input key to a list of artifacts, including:
- stats: A list of type `standard_artifacts.ExampleStatistics` which
should contain the 'eval' split. Stats on other splits are ignored.
- schema: A list of type `standard_artifacts.Schema` which should
contain a single schema artifact.
output_dict: Output dict from key to a list of artifacts, including:
- output: A list of 'ExampleValidationPath' artifact of size one. It
will include a single pbtxt file which contains all anomalies found.
exec_properties: A dict of execution properties. Not used yet.
Returns:
None
"""
self._log_startup(input_dict, output_dict, exec_properties)
absl.logging.info('Validating schema against the computed statistics.')
label_inputs = {
labels.STATS:
tfdv.load_statistics(
io_utils.get_only_uri_in_dir(
artifact_utils.get_split_uri(input_dict[STATISTICS_KEY],
'eval'))),
labels.SCHEMA:
io_utils.SchemaReader().read(
io_utils.get_only_uri_in_dir(
artifact_utils.get_single_uri(input_dict[SCHEMA_KEY])))
}
output_uri = artifact_utils.get_single_uri(output_dict[ANOMALIES_KEY])
label_outputs = {labels.SCHEMA_DIFF_PATH: output_uri}
self._Validate(label_inputs, label_outputs)
absl.logging.info(
'Validation complete. Anomalies written to {}.'.format(output_uri))
def validate_stats_against_schema(self,
environment=None,
previous_statistics=None,
serving_statistics=None,
):
# type: (str, DatasetFeatureStatisticsList, DatasetFeatureStatisticsList) -> bool
stats = tfdv.load_statistics(self.stats_path)
self.anomalies = tfdv.validate_statistics(
stats,
self.schema,
environment=environment,
previous_statistics=previous_statistics,
serving_statistics=serving_statistics,
)
if len(self.anomalies.anomaly_info.items()) > 0:
logger.error("Anomalies found in training dataset...")
logger.error(str(self.anomalies.anomaly_info.items()))
self.upload_anomalies()
return False
else:
logger.info("No anomalies found")
return True
def Do(self, input_dict,
output_dict,
exec_properties):
"""TensorFlow ExampleValidator executor entrypoint.
This validates the statistics on the 'eval' split against the schema.
Args:
input_dict: Input dict from input key to a list of artifacts, including:
- stats: A list of 'ExampleStatisticsPath' type which should contain
split 'eval'. Stats on other splits are ignored.
- schema: A list of 'SchemaPath' type which should contain a single
schema artifact.
output_dict: Output dict from key to a list of artifacts, including:
- output: A list of 'ExampleValidationPath' artifact of size one. It
will include a single pbtxt file which contains all anomalies found.
exec_properties: A dict of execution properties. Not used yet.
Returns:
None
"""
self._log_startup(input_dict, output_dict, exec_properties)
tf.logging.info('Validating schema against the computed statistics.')
schema = io_utils.SchemaReader().read(
io_utils.get_only_uri_in_dir(
types.get_single_uri(input_dict['schema'])))
stats = tfdv.load_statistics(
io_utils.get_only_uri_in_dir(
types.get_split_uri(input_dict['stats'], 'eval')))
output_uri = types.get_single_uri(output_dict['output'])
anomalies = tfdv.validate_statistics(stats, schema)
io_utils.write_pbtxt_file(
os.path.join(output_uri, DEFAULT_FILE_NAME), anomalies)
tf.logging.info(
'Validation complete. Anomalies written to {}.'.format(output_uri))
def Do(self, input_dict: Dict[str, List[types.Artifact]],
output_dict: Dict[str, List[types.Artifact]],
exec_properties: Dict[str, Any]) -> None:
"""TensorFlow SchemaGen executor entrypoint.
This infers the schema using tensorflow_data_validation on the precomputed
stats of 'train' split.
Args:
input_dict: Input dict from input key to a list of artifacts, including:
- 'statistics': A list of 'ExampleStatistics' type which must contain
split 'train'.
output_dict: Output dict from key to a list of artifacts, including:
- schema: A list of 'Schema' artifact of size one.
exec_properties: A dict of execution properties, includes:
- infer_feature_shape: Whether or not to infer the shape of the feature.
- exclude_splits: Names of splits that will not be taken into
consideration when auto-generating a schema.
Returns:
None
"""
infer_feature_shape = bool(
exec_properties.get(
standard_component_specs.INFER_FEATURE_SHAPE_KEY, True))
# Load and deserialize exclude splits from execution properties.
exclude_splits = json_utils.loads(
exec_properties.get(standard_component_specs.EXCLUDE_SPLITS_KEY,
'null')) or []
if not isinstance(exclude_splits, list):
raise ValueError(
'exclude_splits in execution properties needs to be a '
'list. Got %s instead.' % type(exclude_splits))
# Only one schema is generated for all splits.
schema = None
stats_artifact = artifact_utils.get_single_instance(
input_dict[standard_component_specs.STATISTICS_KEY])
for split in artifact_utils.decode_split_names(
stats_artifact.split_names):
if split in exclude_splits:
continue
logging.info('Processing schema from statistics for split %s.',
split)
stats_uri = io_utils.get_only_uri_in_dir(
artifact_utils.get_split_uri([stats_artifact], split))
if artifact_utils.is_artifact_version_older_than(
stats_artifact,
artifact_utils._ARTIFACT_VERSION_FOR_STATS_UPDATE): # pylint: disable=protected-access
stats = tfdv.load_statistics(stats_uri)
else:
stats = tfdv.load_stats_binary(stats_uri)
if not schema:
schema = tfdv.infer_schema(stats, infer_feature_shape)
else:
schema = tfdv.update_schema(schema, stats, infer_feature_shape)
output_uri = os.path.join(
artifact_utils.get_single_uri(
output_dict[standard_component_specs.SCHEMA_KEY]),
DEFAULT_FILE_NAME)
io_utils.write_pbtxt_file(output_uri, schema)
logging.info('Schema written to %s.', output_uri)
def Do(self, input_dict: Dict[Text, List[Artifact]],
output_dict: Dict[Text, List[Artifact]],
exec_properties: Dict[Text, Any]) -> None:
"""Generate MetaFeatures for meta training datasets.
Args:
input_dict: Input dict from input key to a list of artifacts, including:
- statistics: output from StatisticsGen component.
output_dict: Output dict from key to a list of artifacts.
exec_properties: A dict of execution properties
"""
train_stats_uri = io_utils.get_only_uri_in_dir(
artifact_utils.get_split_uri(input_dict[STATISTICS_KEY], 'train'))
stats = tfdv.load_statistics(train_stats_uri)
if len(stats.datasets) != 1:
raise ValueError(
'DatasetFeatureStatisticsList proto contains multiple datasets. Only '
'one dataset is currently supported.')
stats = stats.datasets[0]
num_float_features = 0
num_int_features = 0
num_categorical_features = 0
for feature in stats.features:
name = feature.name
# For structured fields, name is set by path and is not in the name
# attribute.
if not name:
name = feature.path.step[0]
logging.info('Feature Name: %s', name)
if statistics_pb2.FeatureNameStatistics.FLOAT == feature.type:
num_float_features += 1
elif statistics_pb2.FeatureNameStatistics.INT == feature.type:
num_int_features += 1
else:
num_categorical_features += 1
metafeature_dict = {
'num_examples': stats.num_examples,
'num_int_features': num_int_features,
'num_float_features': num_float_features,
'num_categorical_features': num_categorical_features,
}
metafeature_dict['metafeature'] = [
stats.num_examples, num_int_features, num_float_features,
num_categorical_features
]
metafeature_path = os.path.join(
artifact_utils.get_single_uri(output_dict[METAFEATURES_KEY]),
artifacts.MetaFeatures.DEFAULT_FILE_NAME)
io_utils.write_string_file(metafeature_path,
json.dumps(metafeature_dict))
logging.info('MetaFeature saved at %s', metafeature_path)
def display(self, artifact: types.Artifact): stats_path = os.path.join(artifact.uri, 'stats_tfrecord') stats = tfdv.load_statistics(stats_path) tfdv.visualize_statistics(stats)
def Do(self, input_dict: Dict[str, List[types.Artifact]],
output_dict: Dict[str, List[types.Artifact]],
exec_properties: Dict[str, Any]) -> None:
"""TensorFlow ExampleValidator executor entrypoint.
This validates statistics against the schema.
Args:
input_dict: Input dict from input key to a list of artifacts, including:
- statistics: A list of type `standard_artifacts.ExampleStatistics`
generated by StatisticsGen.
- schema: A list of type `standard_artifacts.Schema` which should
contain a single schema artifact.
output_dict: Output dict from key to a list of artifacts, including:
- output: A list of 'standard_artifacts.ExampleAnomalies' of size one.
It will include a single binary proto file which contains all
anomalies found.
exec_properties: A dict of execution properties.
- exclude_splits: JSON-serialized list of names of splits that the
example validator should not validate.
Returns:
None
"""
self._log_startup(input_dict, output_dict, exec_properties)
# Load and deserialize exclude splits from execution properties.
exclude_splits = json_utils.loads(
exec_properties.get(standard_component_specs.EXCLUDE_SPLITS_KEY,
'null')) or []
if not isinstance(exclude_splits, list):
raise ValueError(
'exclude_splits in execution properties needs to be a '
'list. Got %s instead.' % type(exclude_splits))
# Setup output splits.
stats_artifact = artifact_utils.get_single_instance(
input_dict[standard_component_specs.STATISTICS_KEY])
stats_split_names = artifact_utils.decode_split_names(
stats_artifact.split_names)
split_names = [
split for split in stats_split_names if split not in exclude_splits
]
anomalies_artifact = artifact_utils.get_single_instance(
output_dict[standard_component_specs.ANOMALIES_KEY])
anomalies_artifact.split_names = artifact_utils.encode_split_names(
split_names)
schema = io_utils.SchemaReader().read(
io_utils.get_only_uri_in_dir(
artifact_utils.get_single_uri(
input_dict[standard_component_specs.SCHEMA_KEY])))
for split in artifact_utils.decode_split_names(
stats_artifact.split_names):
if split in exclude_splits:
continue
logging.info(
'Validating schema against the computed statistics for '
'split %s.', split)
stats_uri = io_utils.get_only_uri_in_dir(
artifact_utils.get_split_uri([stats_artifact], split))
if artifact_utils.is_artifact_version_older_than(
stats_artifact,
artifact_utils._ARTIFACT_VERSION_FOR_STATS_UPDATE): # pylint: disable=protected-access
stats = tfdv.load_statistics(stats_uri)
else:
stats = tfdv.load_stats_binary(stats_uri)
label_inputs = {
standard_component_specs.STATISTICS_KEY: stats,
standard_component_specs.SCHEMA_KEY: schema
}
output_uri = artifact_utils.get_split_uri(
output_dict[standard_component_specs.ANOMALIES_KEY], split)
label_outputs = {labels.SCHEMA_DIFF_PATH: output_uri}
self._Validate(label_inputs, label_outputs)
logging.info(
'Validation complete for split %s. Anomalies written to '
'%s.', split, output_uri)
