def test_construct(self):
examples = types.TfxArtifact(type_name='ExamplesPath')
model_exports = types.TfxArtifact(type_name='ModelExportPath')
evaluator = component.Evaluator(
examples=channel.as_channel([examples]),
model_exports=channel.as_channel([model_exports]))
self.assertEqual('ModelEvalPath', evaluator.outputs.output.type_name)
def setUp(self):
self._source_data_dir = os.path.join(
os.path.dirname(
os.path.dirname(os.path.dirname(os.path.dirname(__file__)))),
'components', 'testdata')
self._output_data_dir = os.path.join(
os.environ.get('TEST_UNDECLARED_OUTPUTS_DIR', self.get_temp_dir()),
self._testMethodName)
tf.gfile.MakeDirs(self._output_data_dir)
self._model_export = types.TfxArtifact(type_name='ModelExportPath')
self._model_export.uri = os.path.join(self._source_data_dir,
'trainer/current/')
self._model_blessing = types.TfxArtifact(type_name='ModelBlessingPath')
self._input_dict = {
'model_export': [self._model_export],
'model_blessing': [self._model_blessing],
}
self._model_push = types.TfxArtifact(type_name='ModelPushPath')
self._model_push.uri = os.path.join(self._output_data_dir,
'model_push')
tf.gfile.MakeDirs(self._model_push.uri)
self._output_dict = {
'model_push': [self._model_push],
}
self._exec_properties = {
'custom_config': {
'ai_platform_serving_args': {
'model_name': 'model_name',
'project_id': 'project_id'
},
},
}
self._executor = Executor()
def testCsvExampleGenWrapper(self):
input_base = types.TfxArtifact(type_name='ExternalPath', split='')
input_base.uri = '/path/to/dataset'
with patch.object(executor, 'Executor', autospec=True) as _:
wrapper = executor_wrappers.CsvExampleGenWrapper(
argparse.Namespace(
exec_properties=json.dumps(self.exec_properties),
outputs=types.jsonify_tfx_type_dict(
{'examples': self.examples}),
executor_class_path=
('tfx.components.example_gen.csv_example_gen.executor.Executor'
),
input_base=json.dumps([input_base.json_dict()])), )
wrapper.run(output_basedir=self.output_basedir)
# TODO(b/133011207): Validate arguments for executor and Do() method.
metadata_file = os.path.join(self.output_basedir,
'output/ml_metadata/examples')
expected_output_examples = types.TfxArtifact(
type_name='ExamplesPath', split='dummy')
# Expect that span and path are resolved.
expected_output_examples.span = 1
expected_output_examples.uri = (
'/path/to/output/csv_example_gen/examples/mock_workflow_id/dummy/'
)
with tf.gfile.GFile(metadata_file) as f:
self.assertEqual([expected_output_examples.json_dict()],
json.loads(f.read()))
def setUp(self):
self._source_data_dir = os.path.join(
os.path.dirname(os.path.dirname(__file__)), 'testdata')
output_data_dir = os.path.join(
os.environ.get('TEST_UNDECLARED_OUTPUTS_DIR', self.get_temp_dir()),
self._testMethodName)
self.component_name = 'test_component'
# Create input dict.
eval_examples = types.TfxArtifact(type_name='ExamplesPath',
split='eval')
eval_examples.uri = os.path.join(self._source_data_dir,
'csv_example_gen/eval/')
model = types.TfxArtifact(type_name='ModelExportPath')
model.uri = os.path.join(self._source_data_dir, 'trainer/current/')
self._input_dict = {
'examples': [eval_examples],
'model': [model],
}
# Create output dict.
self._blessing = types.TfxArtifact('ModelBlessingPath')
self._blessing.uri = os.path.join(output_data_dir, 'blessing')
self._output_dict = {'blessing': [self._blessing]}
# Create context
self._tmp_dir = os.path.join(output_data_dir, '.temp')
self._context = executor.Executor.Context(tmp_dir=self._tmp_dir,
unique_id='2')
def test_fetch_previous_result(self):
with metadata.Metadata(connection_config=self._connection_config) as m:
# Create an 'previous' execution.
exec_properties = {'log_root': 'path'}
eid = m.prepare_execution('Test', exec_properties)
input_artifact = types.TfxArtifact(type_name='ExamplesPath')
m.publish_artifacts([input_artifact])
output_artifact = types.TfxArtifact(type_name='ExamplesPath')
input_dict = {'input': [input_artifact]}
output_dict = {'output': [output_artifact]}
m.publish_execution(eid, input_dict, output_dict)
# Test previous_run.
self.assertEqual(None, m.previous_run('Test', input_dict, {}))
self.assertEqual(None, m.previous_run('Test', {}, exec_properties))
self.assertEqual(None, m.previous_run('Test2', input_dict,
exec_properties))
self.assertEqual(eid, m.previous_run('Test', input_dict, exec_properties))
# Test fetch_previous_result_artifacts.
new_output_artifact = types.TfxArtifact(type_name='ExamplesPath')
self.assertNotEqual(types.ARTIFACT_STATE_PUBLISHED,
new_output_artifact.state)
new_output_dict = {'output': [new_output_artifact]}
updated_output_dict = m.fetch_previous_result_artifacts(
new_output_dict, eid)
previous_artifact = output_dict['output'][-1].artifact
current_artifact = updated_output_dict['output'][-1].artifact
self.assertEqual(types.ARTIFACT_STATE_PUBLISHED,
current_artifact.properties['state'].string_value)
self.assertEqual(previous_artifact.id, current_artifact.id)
self.assertEqual(previous_artifact.type_id, current_artifact.type_id)
def setUp(self):
self._source_data_dir = os.path.join(
os.path.dirname(os.path.dirname(__file__)), 'testdata')
self._output_data_dir = os.path.join(
os.environ.get('TEST_UNDECLARED_OUTPUTS_DIR', self.get_temp_dir()),
self._testMethodName)
tf.gfile.MakeDirs(self._output_data_dir)
self._model_export = types.TfxArtifact(type_name='ModelExportPath')
self._model_export.uri = os.path.join(self._source_data_dir,
'trainer/current/')
self._model_blessing = types.TfxArtifact(type_name='ModelBlessingPath')
self._input_dict = {
'model_export': [self._model_export],
'model_blessing': [self._model_blessing],
}
self._model_push = types.TfxArtifact(type_name='ModelPushPath')
self._model_push.uri = os.path.join(self._output_data_dir, 'model_push')
tf.gfile.MakeDirs(self._model_push.uri)
self._output_dict = {
'model_push': [self._model_push],
}
self._serving_model_dir = os.path.join(self._output_data_dir,
'serving_model_dir')
tf.gfile.MakeDirs(self._serving_model_dir)
self._exec_properties = {
'push_destination':
json_format.MessageToJson(
pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=self._serving_model_dir))),
}
self._executor = executor.Executor()
def setUp(self):
self._mock_metadata = tf.test.mock.Mock()
self._input_dict = {
'input_data': [types.TfxArtifact(type_name='InputType')],
}
input_dir = os.path.join(
os.environ.get('TEST_TMP_DIR', self.get_temp_dir()),
self._testMethodName, 'input_dir')
# valid input artifacts must have a uri pointing to an existing directory.
for key, input_list in self._input_dict.items():
for index, artifact in enumerate(input_list):
artifact.id = index + 1
uri = os.path.join(input_dir, key, str(artifact.id), '')
artifact.uri = uri
tf.gfile.MakeDirs(uri)
self._output_dict = {
'output_data': [types.TfxArtifact(type_name='OutputType')],
}
self._exec_properties = {
'key': 'value',
}
self._base_output_dir = os.path.join(
os.environ.get('TEST_TMP_DIR', self.get_temp_dir()),
self._testMethodName, 'base_output_dir')
self._driver_args = data_types.DriverArgs(
worker_name='worker_name',
base_output_dir=self._base_output_dir,
enable_cache=True)
self._execution_id = 100
def test_do(self):
source_data_dir = os.path.join(
os.path.dirname(os.path.dirname(__file__)), 'testdata')
train_stats_artifact = types.TfxArtifact('ExampleStatsPath',
split='train')
train_stats_artifact.uri = os.path.join(source_data_dir,
'statistics_gen/train/')
output_data_dir = os.path.join(
os.environ.get('TEST_UNDECLARED_OUTPUTS_DIR', self.get_temp_dir()),
self._testMethodName)
schema_output = types.TfxArtifact('SchemaPath')
schema_output.uri = os.path.join(output_data_dir, 'schema_output')
input_dict = {
'stats': [train_stats_artifact],
}
output_dict = {
'output': [schema_output],
}
exec_properties = {}
schema_gen_executor = executor.Executor()
schema_gen_executor.Do(input_dict, output_dict, exec_properties)
self.assertNotEqual(0, len(tf.gfile.ListDirectory(schema_output.uri)))
def test_valid_channel(self):
instance_a = types.TfxArtifact('MyTypeName')
instance_b = types.TfxArtifact('MyTypeName')
chnl = channel.Channel('MyTypeName',
artifacts=[instance_a, instance_b])
self.assertEqual(chnl.type_name, 'MyTypeName')
self.assertItemsEqual(chnl.get(), [instance_a, instance_b])
def test_channel_as_channel_success(self):
instance_a = types.TfxArtifact('MyTypeName')
instance_b = types.TfxArtifact('MyTypeName')
chnl_original = channel.Channel('MyTypeName',
artifacts=[instance_a, instance_b])
chnl_result = channel.as_channel(chnl_original)
self.assertEqual(chnl_original, chnl_result)
def setUp(self):
self._mock_metadata = tf.test.mock.Mock()
self._input_dict = {
'input_data':
channel.Channel(
type_name='input_data',
artifacts=[types.TfxArtifact(type_name='input_data')])
}
input_dir = os.path.join(
os.environ.get('TEST_TMP_DIR', self.get_temp_dir()),
self._testMethodName, 'input_dir')
# valid input artifacts must have a uri pointing to an existing directory.
for key, input_channel in self._input_dict.items():
for index, artifact in enumerate(input_channel.get()):
artifact.id = index + 1
uri = os.path.join(input_dir, key, str(artifact.id), '')
artifact.uri = uri
tf.gfile.MakeDirs(uri)
self._output_dict = {
'output_data':
channel.Channel(type_name='output_data',
artifacts=[
types.TfxArtifact(type_name='output_data',
split='split')
])
}
self._input_artifacts = channel.unwrap_channel_dict(self._input_dict)
self._output_artifacts = {
'output_data': [types.TfxArtifact(type_name='OutputType')],
}
self._exec_properties = {
'key': 'value',
}
self._execution_id = 100
def test_invalid_channel_type(self):
instance_a = types.TfxArtifact('MyTypeName')
instance_b = types.TfxArtifact('MyTypeName')
with self.assertRaises(ValueError):
channel.Channel(
'AnotherTypeName',
static_artifact_collection=[instance_a, instance_b])
def test_pipeline_with_artifact_info(self):
artifacts_collection = [types.TfxArtifact('channel_one')]
channel_one = channel.Channel(type_name='channel_one',
artifacts=artifacts_collection)
component_a = _make_fake_component_instance(
name='component_a', inputs={}, outputs={'one': channel_one})
component_b = _make_fake_component_instance(
name='component_b',
inputs={
'a': component_a.outputs.one,
},
outputs={})
my_pipeline = pipeline.Pipeline(
pipeline_name='a',
pipeline_root='b',
components=[component_b, component_a],
metadata_connection_config=self._metadata_connection_config)
expected_artifact = types.TfxArtifact('channel_one')
expected_artifact.name = 'one'
expected_artifact.pipeline_name = 'a'
expected_artifact.pipeline_timestamp_ms = 0
expected_artifact.producer_component = 'component_a'
self.assertItemsEqual(my_pipeline.components,
[component_a, component_b])
self.assertEqual(component_a.outputs.one._artifacts[0].pipeline_name,
'a')
self.assertEqual(
component_a.outputs.one._artifacts[0].producer_component,
component_a.component_id)
self.assertEqual(component_a.outputs.one._artifacts[0].name, 'one')
self.assertEqual(component_b.inputs.a._artifacts[0].pipeline_name, 'a')
self.assertEqual(component_b.inputs.a._artifacts[0].producer_component,
component_a.component_id)
self.assertEqual(component_b.inputs.a._artifacts[0].name, 'one')
def test_do(self):
source_data_dir = os.path.join(
os.path.dirname(os.path.dirname(__file__)), 'testdata')
output_data_dir = os.path.join(
os.environ.get('TEST_UNDECLARED_OUTPUTS_DIR', self.get_temp_dir()),
self._testMethodName)
# Create input dict.
train_examples = types.TfxArtifact(type_name='ExamplesPath',
split='train')
train_examples.uri = os.path.join(
source_data_dir, 'transform/transformed_examples/train/')
eval_examples = types.TfxArtifact(type_name='ExamplesPath',
split='eval')
eval_examples.uri = os.path.join(
source_data_dir, 'transform/transformed_examples/eval/')
transform_output = types.TfxArtifact(type_name='TransformPath')
transform_output.uri = os.path.join(source_data_dir,
'transform/transform_output/')
schema = types.TfxArtifact(type_name='ExamplesPath')
schema.uri = os.path.join(source_data_dir, 'schema_gen/')
input_dict = {
'transformed_examples': [train_examples, eval_examples],
'transform_output': [transform_output],
'schema': [schema],
}
# Create output dict.
model_exports = types.TfxArtifact(type_name='ModelExportPath')
model_exports.uri = os.path.join(output_data_dir, 'model_export_path')
output_dict = {'output': [model_exports]}
# Create exec properties.
module_file_path = os.path.join(source_data_dir, 'module_file',
'trainer_module.py')
exec_properties = {
'train_args':
json_format.MessageToJson(trainer_pb2.TrainArgs(num_steps=1000)),
'eval_args':
json_format.MessageToJson(trainer_pb2.EvalArgs(num_steps=500)),
'module_file':
module_file_path,
'warm_starting':
False,
}
trainer_executor = executor.Executor()
trainer_executor.Do(input_dict=input_dict,
output_dict=output_dict,
exec_properties=exec_properties)
# Check outputs.
self.assertTrue(
tf.gfile.Exists(os.path.join(model_exports.uri, 'eval_model_dir')))
self.assertTrue(
tf.gfile.Exists(
os.path.join(model_exports.uri, 'serving_model_dir')))
def test_construct(self):
examples = types.TfxArtifact(type_name='ExamplesPath')
model = types.TfxArtifact(type_name='ModelExportPath')
model_validator = component.ModelValidator(
examples=channel.as_channel([examples]),
model=channel.as_channel([model]))
self.assertEqual('ModelBlessingPath',
model_validator.outputs.blessing.type_name)
def test_execution(self):
with Metadata(connection_config=self._connection_config,
logger=self._logger) as m:
# Test prepare_execution.
exec_properties = {}
eid = m.prepare_execution('Test', exec_properties)
[execution] = m.store.get_executions()
self.assertProtoEquals(
"""
id: 1
type_id: 1
properties {
key: "state"
value {
string_value: "new"
}
}""", execution)
# Test publish_execution.
input_artifact = types.TfxArtifact(type_name='ExamplesPath')
m.publish_artifacts([input_artifact])
output_artifact = types.TfxArtifact(type_name='ExamplesPath')
input_dict = {'input': [input_artifact]}
output_dict = {'output': [output_artifact]}
m.publish_execution(eid, input_dict, output_dict)
# Make sure artifacts in output_dict are published.
self.assertEqual(types.ARTIFACT_STATE_PUBLISHED,
output_artifact.state)
# Make sure execution state are changed.
[execution] = m.store.get_executions_by_id([eid])
self.assertEqual('complete',
execution.properties['state'].string_value)
# Make sure events are published.
events = m.store.get_events_by_execution_ids([eid])
self.assertEqual(2, len(events))
self.assertEqual(input_artifact.id, events[0].artifact_id)
self.assertEqual(metadata_store_pb2.Event.DECLARED_INPUT,
events[0].type)
self.assertProtoEquals(
"""
steps {
key: "input"
}
steps {
index: 0
}""", events[0].path)
self.assertEqual(output_artifact.id, events[1].artifact_id)
self.assertEqual(metadata_store_pb2.Event.DECLARED_OUTPUT,
events[1].type)
self.assertProtoEquals(
"""
steps {
key: "output"
}
steps {
index: 0
}""", events[1].path)
def test_run(self, mock_publisher):
mock_publisher.return_value.publish_execution.return_value = {}
example_gen = FileBasedExampleGen(
executor_class=avro_executor.Executor,
input_base=external_input(self.avro_dir_path),
input_config=self.input_config,
output_config=self.output_config,
name='AvroExampleGenComponent')
output_data_dir = os.path.join(
os.environ.get('TEST_UNDECLARED_OUTPUTS_DIR', self.get_temp_dir()),
self._testMethodName)
pipeline_root = os.path.join(output_data_dir, 'Test')
tf.gfile.MakeDirs(pipeline_root)
pipeline_info = data_types.PipelineInfo(pipeline_name='Test',
pipeline_root=pipeline_root,
run_id='123')
driver_args = data_types.DriverArgs(enable_cache=True)
connection_config = metadata_store_pb2.ConnectionConfig()
connection_config.sqlite.SetInParent()
launcher = component_launcher.ComponentLauncher(
component=example_gen,
pipeline_info=pipeline_info,
driver_args=driver_args,
metadata_connection_config=connection_config,
additional_pipeline_args={})
self.assertEqual(
launcher._component_info.component_type, '.'.join(
[FileBasedExampleGen.__module__,
FileBasedExampleGen.__name__]))
launcher.launch()
mock_publisher.return_value.publish_execution.assert_called_once()
# Get output paths.
component_id = '.'.join([example_gen.component_name, example_gen.name])
output_path = os.path.join(pipeline_root, component_id, 'examples/1')
train_examples = types.TfxArtifact(type_name='ExamplesPath',
split='train')
train_examples.uri = os.path.join(output_path, 'train')
eval_examples = types.TfxArtifact(type_name='ExamplesPath',
split='eval')
eval_examples.uri = os.path.join(output_path, 'eval')
# Check Avro example gen outputs.
train_output_file = os.path.join(train_examples.uri,
'data_tfrecord-00000-of-00001.gz')
eval_output_file = os.path.join(eval_examples.uri,
'data_tfrecord-00000-of-00001.gz')
self.assertTrue(tf.gfile.Exists(train_output_file))
self.assertTrue(tf.gfile.Exists(eval_output_file))
self.assertGreater(
tf.gfile.GFile(train_output_file).size(),
tf.gfile.GFile(eval_output_file).size())
def test_unwrap_channel_dict(self):
instance_a = types.TfxArtifact('MyTypeName')
instance_b = types.TfxArtifact('MyTypeName')
channel_dict = {
'id': channel.Channel('MyTypeName',
artifacts=[instance_a, instance_b])
}
result = channel.unwrap_channel_dict(channel_dict)
self.assertDictEqual(result, {'id': [instance_a, instance_b]})
def test_fetch_previous_result(self):
with metadata.Metadata(connection_config=self._connection_config) as m:
# Create an 'previous' execution.
exec_properties = {'log_root': 'path'}
eid = m.register_execution(exec_properties=exec_properties,
pipeline_info=self._pipeline_info,
component_info=self._component_info)
input_artifact = types.TfxArtifact(type_name='ExamplesPath')
m.publish_artifacts([input_artifact])
output_artifact = types.TfxArtifact(type_name='ExamplesPath')
input_artifacts = {'input': [input_artifact]}
output_artifacts = {'output': [output_artifact]}
m.publish_execution(eid, input_artifacts, output_artifacts)
# Test previous_run.
self.assertEqual(
None,
m.previous_execution(input_artifacts=input_artifacts,
exec_properties={},
pipeline_info=self._pipeline_info,
component_info=self._component_info))
self.assertEqual(
None,
m.previous_execution(input_artifacts={},
exec_properties=exec_properties,
pipeline_info=self._pipeline_info,
component_info=self._component_info))
self.assertEqual(
None,
m.previous_execution(input_artifacts=input_artifacts,
exec_properties=exec_properties,
pipeline_info=self._pipeline_info,
component_info=data_types.ComponentInfo(
component_id='unique',
component_type='a.b.c')))
self.assertEqual(
eid,
m.previous_execution(input_artifacts=input_artifacts,
exec_properties=exec_properties,
pipeline_info=self._pipeline_info,
component_info=self._component_info))
# Test fetch_previous_result_artifacts.
new_output_artifact = types.TfxArtifact(type_name='ExamplesPath')
self.assertNotEqual(types.ARTIFACT_STATE_PUBLISHED,
new_output_artifact.state)
new_output_dict = {'output': [new_output_artifact]}
updated_output_dict = m.fetch_previous_result_artifacts(
new_output_dict, eid)
previous_artifact = output_artifacts['output'][-1].artifact
current_artifact = updated_output_dict['output'][-1].artifact
self.assertEqual(types.ARTIFACT_STATE_PUBLISHED,
current_artifact.properties['state'].string_value)
self.assertEqual(previous_artifact.id, current_artifact.id)
self.assertEqual(previous_artifact.type_id,
current_artifact.type_id)
def test_construct(self):
train_examples = types.TfxArtifact(type_name='ExamplesPath',
split='train')
eval_examples = types.TfxArtifact(type_name='ExamplesPath',
split='eval')
statistics_gen = component.StatisticsGen(
input_data=channel.as_channel([train_examples, eval_examples]))
self.assertEqual('ExampleStatisticsPath',
statistics_gen.outputs.output.type_name)
def setUp(self):
self.input_one = types.TfxArtifact('INPUT_ONE')
self.input_one.source = airflow_component._OrchestrationSource(
'input_one_key', 'input_one_component_id')
self.output_one = types.TfxArtifact('OUTPUT_ONE')
self.output_one.source = airflow_component._OrchestrationSource(
'output_one_key', 'output_one_component_id')
self.input_one_json = json.dumps([self.input_one.json_dict()])
self.output_one_json = json.dumps([self.output_one.json_dict()])
self._logger_config = logging_utils.LoggerConfig()
def setUp(self):
self._mock_metadata = tf.test.mock.Mock()
self._mock_metadata.publish_execution = tf.test.mock.Mock()
self._input_dict = {
'input_data': [types.TfxArtifact(type_name='InputType')],
}
self._output_dict = {
'output_data': [types.TfxArtifact(type_name='OutputType')],
}
self._execution_id = 100
def test_construct_without_transform_output(self):
transformed_examples = types.TfxArtifact(type_name='ExamplesPath')
schema = types.TfxArtifact(type_name='SchemaPath')
trainer = component.Trainer(
module_file='/path/to/module/file',
examples=channel.as_channel([transformed_examples]),
schema=channel.as_channel([schema]),
train_args=trainer_pb2.TrainArgs(num_steps=100),
eval_args=trainer_pb2.EvalArgs(num_steps=50))
self.assertEqual('ModelExportPath', trainer.outputs.output.type_name)
def test_construct(self):
model_export = types.TfxArtifact(type_name='ModelExportPath')
model_blessing = types.TfxArtifact(type_name='ModelBlessingPath')
pusher = component.Pusher(
model_export=channel.as_channel([model_export]),
model_blessing=channel.as_channel([model_blessing]),
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory='push_destination')))
self.assertEqual('ModelPushPath', pusher.outputs.model_push.type_name)
def test_construct(self):
example_validator = component.ExampleValidator(
stats=channel.as_channel([
types.TfxArtifact(type_name='ExampleStatisticsPath',
split='eval')
]),
schema=channel.as_channel(
[types.TfxArtifact(type_name='SchemaPath')]),
)
self.assertEqual('ExampleValidationPath',
example_validator.outputs.output.type_name)
def test_construct_with_slice_spec(self):
examples = types.TfxArtifact(type_name='ExamplesPath')
model_exports = types.TfxArtifact(type_name='ModelExportPath')
evaluator = component.Evaluator(
examples=channel.as_channel([examples]),
model_exports=channel.as_channel([model_exports]),
feature_slicing_spec=evaluator_pb2.FeatureSlicingSpec(specs=[
evaluator_pb2.SingleSlicingSpec(
column_for_slicing=['trip_start_hour'])
]))
self.assertEqual('ModelEvalPath', evaluator.outputs.output.type_name)
def testDo(self, mock_client):
# Mock query result schema for _BigQueryConverter.
mock_client.return_value.query.return_value.result.return_value.schema = self._schema
output_data_dir = os.path.join(
os.environ.get('TEST_UNDECLARED_OUTPUTS_DIR', self.get_temp_dir()),
self._testMethodName)
# Create output dict.
train_examples = types.TfxArtifact(type_name='ExamplesPath',
split='train')
train_examples.uri = os.path.join(output_data_dir, 'train')
eval_examples = types.TfxArtifact(type_name='ExamplesPath',
split='eval')
eval_examples.uri = os.path.join(output_data_dir, 'eval')
output_dict = {'examples': [train_examples, eval_examples]}
# Create exe properties.
exec_properties = {
'input_config':
json_format.MessageToJson(
example_gen_pb2.Input(splits=[
example_gen_pb2.Input.Split(
name='bq', pattern='SELECT i, f, s FROM `fake`'),
])),
'output_config':
json_format.MessageToJson(
example_gen_pb2.Output(
split_config=example_gen_pb2.SplitConfig(splits=[
example_gen_pb2.SplitConfig.Split(name='train',
hash_buckets=2),
example_gen_pb2.SplitConfig.Split(name='eval',
hash_buckets=1)
])))
}
# Run executor.
big_query_example_gen = executor.Executor()
big_query_example_gen.Do({}, output_dict, exec_properties)
# Check BigQuery example gen outputs.
train_output_file = os.path.join(train_examples.uri,
'data_tfrecord-00000-of-00001.gz')
eval_output_file = os.path.join(eval_examples.uri,
'data_tfrecord-00000-of-00001.gz')
self.assertTrue(tf.gfile.Exists(train_output_file))
self.assertTrue(tf.gfile.Exists(eval_output_file))
self.assertGreater(
tf.gfile.GFile(train_output_file).size(),
tf.gfile.GFile(eval_output_file).size())
def test_do(self):
source_data_dir = os.path.join(
os.path.dirname(os.path.dirname(__file__)), 'testdata')
output_data_dir = os.path.join(
os.environ.get('TEST_UNDECLARED_OUTPUTS_DIR', self.get_temp_dir()),
self._testMethodName)
# Create input dict.
train_examples = types.TfxArtifact(type_name='ExamplesPath',
split='train')
eval_examples = types.TfxArtifact(type_name='ExamplesPath',
split='eval')
eval_examples.uri = os.path.join(source_data_dir,
'csv_example_gen/eval/')
model_exports = types.TfxArtifact(type_name='ModelExportPath')
model_exports.uri = os.path.join(source_data_dir, 'trainer/current/')
input_dict = {
'examples': [train_examples, eval_examples],
'model_exports': [model_exports],
}
# Create output dict.
eval_output = types.TfxArtifact('ModelEvalPath')
eval_output.uri = os.path.join(output_data_dir, 'eval_output')
output_dict = {'output': [eval_output]}
# Create exec proterties.
exec_properties = {
'feature_slicing_spec':
json_format.MessageToJson(
evaluator_pb2.FeatureSlicingSpec(specs=[
evaluator_pb2.SingleSlicingSpec(
column_for_slicing=['trip_start_hour']),
evaluator_pb2.SingleSlicingSpec(
column_for_slicing=['trip_start_day', 'trip_miles']),
]))
}
# Run executor.
evaluator = executor.Executor()
evaluator.Do(input_dict, output_dict, exec_properties)
# Check evaluator outputs.
self.assertTrue(
tf.gfile.Exists(os.path.join(eval_output.uri, 'eval_config')))
self.assertTrue(
tf.gfile.Exists(os.path.join(eval_output.uri, 'metrics')))
self.assertTrue(tf.gfile.Exists(os.path.join(eval_output.uri,
'plots')))
def __init__(self,
input_config: example_gen_pb2.Input,
output_config: Optional[example_gen_pb2.Output] = None,
component_name: Optional[Text] = 'ExampleGen',
example_artifacts: Optional[channel.Channel] = None,
name: Optional[Text] = None):
"""Construct an QueryBasedExampleGen component.
Args:
input_config: An example_gen_pb2.Input instance, providing input
configuration.
output_config: An example_gen_pb2.Output instance, providing output
configuration. If unset, default splits will be 'train' and 'eval' with
size 2:1.
component_name: Name of the component, should be unique per component
class. Default to 'ExampleGen', can be overwritten by sub-classes.
example_artifacts: Optional channel of 'ExamplesPath' for output train and
eval examples.
name: Unique name for every component class instance.
"""
# Configure outputs.
output_config = output_config or utils.make_default_output_config(
input_config)
example_artifacts = example_artifacts or channel.as_channel([
types.TfxArtifact('ExamplesPath', split=split_name)
for split_name in utils.generate_output_split_names(
input_config, output_config)
])
spec = QueryBasedExampleGenSpec(component_name=component_name,
input_config=input_config,
output_config=output_config,
examples=example_artifacts)
super(_QueryBasedExampleGen, self).__init__(spec=spec, name=name)
def __init__(self,
model_export: channel.Channel,
model_blessing: channel.Channel,
slack_token: Text,
channel_id: Text,
timeout_sec: int,
slack_blessing: Optional[channel.Channel] = None,
name: Optional[Text] = None):
"""Construct a SlackComponent.
Args:
model_export: A Channel of 'ModelExportPath' type, usually produced by
Trainer component.
model_blessing: A Channel of 'ModelBlessingPath' type, usually produced by
ModelValidator component.
slack_token: A token used for setting up connection with Slack server.
channel_id: Slack channel id to communicate on.
timeout_sec: Seconds to wait for response before default to reject.
slack_blessing: Optional output channel of 'ModelBlessingPath' with result
of blessing; will be created for you if not specified.
name: Optional unique name. Necessary if multiple Pusher components are
declared in the same pipeline.
"""
slack_blessing = slack_blessing or channel.Channel(
type_name='ModelBlessingPath',
artifacts=[types.TfxArtifact('ModelBlessingPath')])
spec = SlackComponentSpec(slack_token=slack_token,
channel_id=channel_id,
timeout_sec=timeout_sec,
model_export=model_export,
model_blessing=model_blessing,
slack_blessing=slack_blessing)
super(SlackComponent, self).__init__(spec=spec, name=name)
