def _create_pipeline():
"""Implements the chicago taxi pipeline with TFX and Kubeflow Pipelines."""
examples = csv_input(_data_root)
# Brings data into the pipeline or otherwise joins/converts training data.
example_gen = CsvExampleGen(input=examples)
# Computes statistics over data for visualization and example validation.
statistics_gen = StatisticsGen(examples=example_gen.outputs['examples'])
# Generates schema based on statistics files.
infer_schema = SchemaGen(statistics=statistics_gen.outputs['statistics'])
return pipeline.Pipeline(
pipeline_name='chicago_taxi_pipeline_kubeflow',
pipeline_root=_pipeline_root,
components=[example_gen, statistics_gen, infer_schema],
additional_pipeline_args={
'beam_pipeline_args': [
'--runner=DataflowRunner',
'--experiments=shuffle_mode=auto',
'--project=' + _project_id,
'--temp_location=' + os.path.join(_output_dir, 'tmp'),
'--region=' + _gcp_region,
],
},
log_root='/var/tmp/tfx/logs',
)
def create_pipeline():
# Read data in; can split data here
examples = csv_input(DATA_DIR)
example_gen = CsvExampleGen(input_base=examples, name='iris_example')
# Generate feature statistics
statistics_gen = StatisticsGen(input_data=example_gen.outputs.examples)
# Infer schema for data
infer_schema = SchemaGen(stats=statistics_gen.outputs.output)
# Identify anomomalies in training and serving data
validate_stats = ExampleValidator(stats=statistics_gen.outputs.output,
schema=infer_schema.outputs.output)
# Performs feature engineering; emits a SavedModel that does preprocessing
transform = Transform(input_data=example_gen.outputs.examples,
schema=infer_schema.outputs.output,
module_file=TRANSFORM_MODULE_FILE)
# Trains a model
trainer = Trainer(
module_file=MODEL_MODULE_FILE,
transformed_examples=transform.outputs.transformed_examples,
schema=infer_schema.outputs.output,
transform_output=transform.outputs.transform_output,
train_args=trainer_pb2.TrainArgs(num_steps=10000),
eval_args=trainer_pb2.EvalArgs(num_steps=5000))
# Evaluates the model on different slices of the data (bias detection?!)
model_analyzer = Evaluator(examples=example_gen.outputs.examples,
model_exports=trainer.outputs.output)
# Compares new model against a baseline; both models evaluated on a dataset
model_validator = ModelValidator(examples=example_gen.outputs.examples,
model=trainer.outputs.output)
# Pushes a blessed model to a deployment target (tfserving)
pusher = Pusher(model_export=trainer.outputs.output,
model_blessing=model_validator.outputs.blessing,
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=SERVING_DIR)))
return pipeline.Pipeline(pipeline_name=PIPELINE_NAME,
pipeline_root=DAGS_DIR,
components=[
example_gen, statistics_gen, infer_schema,
validate_stats, transform, trainer,
model_analyzer, model_validator, pusher
],
enable_cache=True,
metadata_db_root=METADATA_DIR,
additional_pipeline_args={
'logger_args': {
'log_root': LOGS_DIR,
'log_level': logging.INFO
}
})
def _create_pipeline():
"""Implements the chicago taxi pipeline with TFX."""
examples = csv_input(_data_root)
# Brings data into the pipeline or otherwise joins/converts training data.
example_gen = CsvExampleGen(input=examples)
# Computes statistics over data for visualization and example validation.
statistics_gen = StatisticsGen(examples=example_gen.outputs['examples'])
# Generates schema based on statistics files.
infer_schema = SchemaGen(statistics=statistics_gen.outputs['statistics'])
# Performs anomaly detection based on statistics and data schema.
validate_stats = ExampleValidator(
statistics=statistics_gen.outputs['statistics'],
schema=infer_schema.outputs['schema'])
return pipeline.Pipeline(
pipeline_name='chicago_taxi_simple',
pipeline_root=_pipeline_root,
components=[example_gen, statistics_gen, infer_schema, validate_stats],
enable_cache=True,
metadata_db_root=_metadata_db_root,
)
def _create_test_pipeline(pipeline_root: Text, csv_input_location: Text,
taxi_module_file: Text, output_bucket: Text,
enable_cache: bool):
"""Creates a simple Kubeflow-based Chicago Taxi TFX pipeline.
Args:
pipeline_name: The name of the pipeline.
pipeline_root: The root of the pipeline output.
csv_input_location: The location of the input data directory.
taxi_module_file: The location of the module file for Transform/Trainer.
enable_cache: Whether to enable cache or not.
Returns:
A logical TFX pipeline.Pipeline object.
"""
examples = csv_input(csv_input_location)
example_gen = CsvExampleGen(input_base=examples)
statistics_gen = StatisticsGen(input_data=example_gen.outputs.examples)
infer_schema = SchemaGen(stats=statistics_gen.outputs.output,
infer_feature_shape=False)
validate_stats = ExampleValidator(stats=statistics_gen.outputs.output,
schema=infer_schema.outputs.output)
transform = Transform(input_data=example_gen.outputs.examples,
schema=infer_schema.outputs.output,
module_file=taxi_module_file)
trainer = Trainer(
module_file=taxi_module_file,
transformed_examples=transform.outputs.transformed_examples,
schema=infer_schema.outputs.output,
transform_output=transform.outputs.transform_output,
train_args=trainer_pb2.TrainArgs(num_steps=10000),
eval_args=trainer_pb2.EvalArgs(num_steps=5000))
model_analyzer = Evaluator(
examples=example_gen.outputs.examples,
model_exports=trainer.outputs.output,
feature_slicing_spec=evaluator_pb2.FeatureSlicingSpec(specs=[
evaluator_pb2.SingleSlicingSpec(
column_for_slicing=['trip_start_hour'])
]))
model_validator = ModelValidator(examples=example_gen.outputs.examples,
model=trainer.outputs.output)
pusher = Pusher(
model_export=trainer.outputs.output,
model_blessing=model_validator.outputs.blessing,
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=os.path.join(output_bucket, 'model_serving'))))
return pipeline.Pipeline(
pipeline_name='chicago_taxi_pipeline_simple',
pipeline_root=pipeline_root,
components=[
example_gen, statistics_gen, infer_schema, validate_stats,
transform, trainer, model_analyzer, model_validator, pusher
],
enable_cache=enable_cache,
)
def create_e2e_components(
pipeline_root: Text,
csv_input_location: Text,
transform_module: Text,
trainer_module: Text,
) -> List[BaseComponent]:
"""Creates components for a simple Chicago Taxi TFX pipeline for testing.
Args:
pipeline_root: The root of the pipeline output.
csv_input_location: The location of the input data directory.
transform_module: The location of the transform module file.
trainer_module: The location of the trainer module file.
Returns:
A list of TFX components that constitutes an end-to-end test pipeline.
"""
examples = dsl_utils.csv_input(csv_input_location)
example_gen = CsvExampleGen(input=examples)
statistics_gen = StatisticsGen(examples=example_gen.outputs['examples'])
infer_schema = SchemaGen(
statistics=statistics_gen.outputs['statistics'],
infer_feature_shape=False)
validate_stats = ExampleValidator(
statistics=statistics_gen.outputs['statistics'],
schema=infer_schema.outputs['schema'])
transform = Transform(
examples=example_gen.outputs['examples'],
schema=infer_schema.outputs['schema'],
module_file=transform_module)
trainer = Trainer(
transformed_examples=transform.outputs['transformed_examples'],
schema=infer_schema.outputs['schema'],
transform_graph=transform.outputs['transform_graph'],
train_args=trainer_pb2.TrainArgs(num_steps=10),
eval_args=trainer_pb2.EvalArgs(num_steps=5),
module_file=trainer_module,
)
model_analyzer = Evaluator(
examples=example_gen.outputs['examples'],
model=trainer.outputs['model'],
feature_slicing_spec=evaluator_pb2.FeatureSlicingSpec(specs=[
evaluator_pb2.SingleSlicingSpec(
column_for_slicing=['trip_start_hour'])
]))
model_validator = ModelValidator(
examples=example_gen.outputs['examples'], model=trainer.outputs['model'])
pusher = Pusher(
model=trainer.outputs['model'],
model_blessing=model_validator.outputs['blessing'],
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=os.path.join(pipeline_root, 'model_serving'))))
return [
example_gen, statistics_gen, infer_schema, validate_stats, transform,
trainer, model_analyzer, model_validator, pusher
]
def testCsvExampleGenOnDataflowRunner(self):
"""CsvExampleGen-only test pipeline on DataflowRunner invocation."""
pipeline_name = 'kubeflow-csv-example-gen-dataflow-test-{}'.format(
self._random_id())
pipeline = self._create_dataflow_pipeline(pipeline_name, [
CsvExampleGen(input=dsl_utils.csv_input(self._data_root)),
])
self._compile_and_run_pipeline(pipeline)
def _create_pipeline():
"""Implements the chicago taxi pipeline with TFX."""
examples = csv_input(_data_root)
# Brings data into the pipeline or otherwise joins/converts training data.
example_gen = CsvExampleGen(input_base=examples)
# Computes statistics over data for visualization and example validation.
statistics_gen = StatisticsGen(input_data=example_gen.outputs.examples)
# Generates schema based on statistics files.
infer_schema = SchemaGen(stats=statistics_gen.outputs.output)
# Performs anomaly detection based on statistics and data schema.
validate_stats = ExampleValidator(
stats=statistics_gen.outputs.output, schema=infer_schema.outputs.output)
# Performs transformations and feature engineering in training and serving.
transform = Transform(
input_data=example_gen.outputs.examples,
schema=infer_schema.outputs.output,
module_file=_taxi_module_file)
# Uses user-provided Python function that implements a model using TF-Learn.
trainer = Trainer(
module_file=_taxi_module_file,
transformed_examples=transform.outputs.transformed_examples,
schema=infer_schema.outputs.output,
transform_output=transform.outputs.transform_output,
train_args=trainer_pb2.TrainArgs(num_steps=10000),
eval_args=trainer_pb2.EvalArgs(num_steps=5000))
# Uses TFMA to compute a evaluation statistics over features of a model.
model_analyzer = Evaluator(
examples=example_gen.outputs.examples,
model_exports=trainer.outputs.output,
feature_slicing_spec=evaluator_pb2.FeatureSlicingSpec(specs=[
evaluator_pb2.SingleSlicingSpec(
column_for_slicing=['trip_start_hour'])
]))
# Performs quality validation of a candidate model (compared to a baseline).
model_validator = ModelValidator(
examples=example_gen.outputs.examples, model=trainer.outputs.output)
# Checks whether the model passed the validation steps and pushes the model
# to a file destination if check passed.
pusher = Pusher(
model_export=trainer.outputs.output,
model_blessing=model_validator.outputs.blessing,
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=_serving_model_dir)))
return [
example_gen, statistics_gen, infer_schema, validate_stats, transform,
trainer, model_analyzer, model_validator, pusher
]
def create_pipeline():
"""Implements the chicago taxi pipeline with TFX."""
examples = csv_input(data_root)
# Brings data into the pipeline or otherwise joins/converts training data.
example_gen = CsvExampleGen(input_base=examples)
# Computes statistics over data for visualization and example validation.
# statistics_gen = StatisticsGen(input_data=example_gen.outputs.examples) # Step 3
# Generates schema based on statistics files.
# schema_gen = SchemaGen(stats=statistics_gen.outputs.output) # Step 3
# Performs anomaly detection based on statistics and data schema.
# validate_stats = ExampleValidator( # Step 3
# stats=statistics_gen.outputs.output, # Step 3
# schema=schema_gen.outputs.output) # Step 3
# Performs transformations and feature engineering in training and serving.
# transform = Transform( # Step 4
# input_data=example_gen.outputs.examples, # Step 4
# schema=schema_gen.outputs.output, # Step 4
# module_file=taxi_module_file) # Step 4
# Uses user-provided Python function that implements a model using TF-Learn.
# trainer = Trainer( # Step 5
# module_file=taxi_module_file, # Step 5
# transformed_examples=transform.outputs.transformed_examples, # Step 5
# schema=schema_gen.outputs.output, # Step 5
# transform_output=transform.outputs.transform_output, # Step 5
# train_steps=10000, # Step 5
# eval_steps=5000, # Step 5
# warm_starting=True) # Step 5
# Uses TFMA to compute a evaluation statistics over features of a model.
# model_analyzer = Evaluator( # Step 6
# examples=example_gen.outputs.examples, # Step 6
# model_exports=trainer.outputs.output) # Step 6
# Performs quality validation of a candidate model (compared to a baseline).
# model_validator = ModelValidator( # Step 7
# examples=example_gen.outputs.examples, model=trainer.outputs.output) # Step 7
# Checks whether the model passed the validation steps and pushes the model
# to a file destination if check passed.
# pusher = Pusher( # Step 7
# model_export=trainer.outputs.output, # Step 7
# model_blessing=model_validator.outputs.blessing, # Step 7
# serving_model_dir=serving_model_dir) # Step 7
return [
example_gen,
# statistics_gen, schema_gen, validate_stats, # Step 3
# transform, # Step 4
# trainer, # Step 5
# model_analyzer, # Step 6
# model_validator, pusher # Step 7
]
def create_pipeline():
"""Implements the titanic taxi pipeline with TFX."""
examples = csv_input(data_dir)
# Brings data into the pipeline
example_gen = CsvExampleGen(input_base=examples)
return [example_gen]
def create_pipeline():
"""Implements the chicago taxi pipeline with TFX."""
examples = csv_input(os.path.join(data_root, 'simple'))
# Brings data into the pipeline or otherwise joins/converts training data.
example_gen = CsvExampleGen(input_base=examples)
# Computes statistics over data for visualization and example validation.
statistics_gen = StatisticsGen(input_data=example_gen.outputs.examples)
# Generates schema based on statistics files.
infer_schema = SchemaGen(stats=statistics_gen.outputs.output)
# Performs anomaly detection based on statistics and data schema.
validate_stats = ExampleValidator(
stats=statistics_gen.outputs.output,
schema=infer_schema.outputs.output)
# Performs transformations and feature engineering in training and serving.
transform = Transform(
input_data=example_gen.outputs.examples,
schema=infer_schema.outputs.output,
module_file=taxi_module_file)
# Uses user-provided Python function that implements a model using TF-Learn.
trainer = Trainer(
module_file=taxi_module_file,
transformed_examples=transform.outputs.transformed_examples,
schema=infer_schema.outputs.output,
transform_output=transform.outputs.transform_output,
train_steps=10000,
eval_steps=5000,
warm_starting=True)
# Uses TFMA to compute a evaluation statistics over features of a model.
model_analyzer = Evaluator(
examples=example_gen.outputs.examples,
model_exports=trainer.outputs.output)
# Performs quality validation of a candidate model (compared to a baseline).
model_validator = ModelValidator(
examples=example_gen.outputs.examples, model=trainer.outputs.output)
# Checks whether the model passed the validation steps and pushes the model
# to a file destination if check passed.
pusher = Pusher(
model_export=trainer.outputs.output,
model_blessing=model_validator.outputs.blessing,
serving_model_dir=serving_model_dir)
return [
example_gen, statistics_gen, infer_schema, validate_stats, transform,
trainer, model_analyzer, model_validator, pusher
]
def __init__(self, base_dir, csvname):
self.base_dir = base_dir
self.csvname = csvname
self.components = []
examples = csv_input(os.path.join(self.base_dir, self.csvname))
self.example_gen = tfx.components.example_gen.csv_example_gen.component.CsvExampleGen(
input=examples)
self.statistics_gen = StatisticsGen(
self.example_gen.outputs['examples'],
instance_name=self.csvname + "_statistics_gen")
self.scheme_gen = SchemaGen(
statistics=self.statistics_gen.outputs['statistics'])
self.valid_stats = ExampleValidator(
statistics=self.statistics_gen.outputs["statistics"],
schema=self.scheme_gen.outputs["schema"])
def _create_pipeline():
"""Implements the chicago taxi pipeline with TFX."""
examples = csv_input(_data_root)
# Brings data into the pipeline or otherwise joins/converts training data.
example_gen = CsvExampleGen(input_base=examples)
# Computes statistics over data for visualization and example validation.
statistics_gen = StatisticsGen(input_data=example_gen.outputs.examples)
# Generates schema based on statistics files.
infer_schema = SchemaGen(stats=statistics_gen.outputs.output)
return pipeline.Pipeline(
pipeline_name='chicago_taxi_simple',
pipeline_root=_pipeline_root,
components=[example_gen, statistics_gen, infer_schema],
enable_cache=True,
metadata_db_root=_metadata_db_root,
)
def csv_input(self):
[csv] = dsl_utils.csv_input(uri='path')
self.assertEqual('ExternalPath', csv.type_name)
self.assertEqual('path', csv.uri)
def _create_pipeline():
"""Implements the chicago taxi pipeline with TFX."""
examples = csv_input(_data_root)
# Brings data into the pipeline or otherwise joins/converts training data.
example_gen = CsvExampleGen(input_base=examples)
# Computes statistics over data for visualization and example validation.
statistics_gen = StatisticsGen(input_data=example_gen.outputs.examples)
# Generates schema based on statistics files.
infer_schema = SchemaGen(stats=statistics_gen.outputs.output)
# Performs anomaly detection based on statistics and data schema.
validate_stats = ExampleValidator(stats=statistics_gen.outputs.output,
schema=infer_schema.outputs.output)
# Performs transformations and feature engineering in training and serving.
transform = Transform(input_data=example_gen.outputs.examples,
schema=infer_schema.outputs.output,
module_file=_taxi_module_file)
# Uses user-provided Python function that implements a model using TF-Learn.
trainer = Trainer(
module_file=_taxi_module_file,
transformed_examples=transform.outputs.transformed_examples,
schema=infer_schema.outputs.output,
transform_output=transform.outputs.transform_output,
train_args=trainer_pb2.TrainArgs(num_steps=10000),
eval_args=trainer_pb2.EvalArgs(num_steps=5000))
# Uses TFMA to compute a evaluation statistics over features of a model.
model_analyzer = Evaluator(
examples=example_gen.outputs.examples,
model_exports=trainer.outputs.output,
feature_slicing_spec=evaluator_pb2.FeatureSlicingSpec(specs=[
evaluator_pb2.SingleSlicingSpec(
column_for_slicing=['trip_start_hour'])
]))
# Performs quality validation of a candidate model (compared to a baseline).
model_validator = ModelValidator(examples=example_gen.outputs.examples,
model=trainer.outputs.output)
# Checks whether the model passed the validation steps and pushes the model
# to a file destination if check passed.
pusher = Pusher(model_export=trainer.outputs.output,
model_blessing=model_validator.outputs.blessing,
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=_serving_model_dir)))
return pipeline.Pipeline(
pipeline_name=_pipeline_name,
pipeline_root=_pipeline_root,
enable_cache=True,
metadata_connection_config=metadata.sqlite_metadata_connection_config(
_metadata_db_root),
components=[
example_gen, statistics_gen, infer_schema, validate_stats,
transform, trainer, model_analyzer, model_validator, pusher
],
additional_pipeline_args={
# LINT.IfChange
'beam_pipeline_args': [
# ----- Beam Args -----.
'--runner=PortableRunner',
# Points to the job server started in
# setup_beam_on_(flink|spark).sh
'--job_endpoint=localhost:8099',
'--environment_type=LOOPBACK',
# TODO(BEAM-6754): Utilize multicore in LOOPBACK environment. # pylint: disable=g-bad-todo
# TODO(BEAM-5167): Use concurrency information from SDK Harness. # pylint: disable=g-bad-todo
# Note; We use 100 worker threads to mitigate the issue with
# scheduling work between the Beam runner and SDK harness. Flink
# and Spark can process unlimited work items concurrently while
# SdkHarness can only process 1 work item per worker thread.
# Having 100 threads will let 100 tasks execute concurrently
# avoiding scheduling issue in most cases. In case the threads are
# exhausted, beam print the relevant message in the log.
'--experiments=worker_threads=100',
# TODO(BEAM-7199): Obviate the need for setting pre_optimize=all. # pylint: disable=g-bad-todo
'--experiments=pre_optimize=all',
# ----- Flink runner-specific Args -----.
# TODO(b/126725506): Set the task parallelism based on cpu cores.
# TODO(FLINK-10672): Obviate setting BATCH_FORCED.
'--execution_mode_for_batch=BATCH_FORCED',
],
# LINT.ThenChange(tfx/examples/chicago_taxi/setup_beam_on_portable_beam.sh)
},
)
def _create_pipeline():
"""Implements the chicago taxi pipeline with TFX."""
examples = csv_input(_data_root)
# Brings data into the pipeline or otherwise joins/converts training data.
example_gen = CsvExampleGen(input_base=examples)
# Computes statistics over data for visualization and example validation.
statistics_gen = StatisticsGen(input_data=example_gen.outputs.examples)
# Generates schema based on statistics files.
infer_schema = SchemaGen(stats=statistics_gen.outputs.output)
# Performs anomaly detection based on statistics and data schema.
validate_stats = ExampleValidator(
stats=statistics_gen.outputs.output, schema=infer_schema.outputs.output)
# Performs transformations and feature engineering in training and serving.
transform = Transform(
input_data=example_gen.outputs.examples,
schema=infer_schema.outputs.output,
module_file=_taxi_module_file)
# Uses user-provided Python function that implements a model using TF-Learn.
trainer = Trainer(
module_file=_taxi_module_file,
transformed_examples=transform.outputs.transformed_examples,
schema=infer_schema.outputs.output,
transform_output=transform.outputs.transform_output,
train_args=trainer_pb2.TrainArgs(num_steps=10000),
eval_args=trainer_pb2.EvalArgs(num_steps=5000))
# Uses TFMA to compute a evaluation statistics over features of a model.
model_analyzer = Evaluator(
examples=example_gen.outputs.examples,
model_exports=trainer.outputs.output,
feature_slicing_spec=evaluator_pb2.FeatureSlicingSpec(specs=[
evaluator_pb2.SingleSlicingSpec(
column_for_slicing=['trip_start_hour'])
]))
# Performs quality validation of a candidate model (compared to a baseline).
model_validator = ModelValidator(
examples=example_gen.outputs.examples, model=trainer.outputs.output)
# This custom component serves as a bridge between pipeline and human model
# reviewers to enable review-and-push workflow in model development cycle. It
# utilizes Slack API to send message to user-defined Slack channel with model
# URI info and wait for go / no-go decision from the same Slack channel:
# * To approve the model, users need to reply the thread sent out by the bot
# started by SlackComponent with 'lgtm' or 'approve'.
# * To reject the model, users need to reply the thread sent out by the bot
# started by SlackComponent with 'decline' or 'reject'.
slack_validator = SlackComponent(
model_export=trainer.outputs.output,
model_blessing=model_validator.outputs.blessing,
slack_token=_slack_token,
channel_id=_channel_id,
timeout_sec=3600,
)
# Checks whether the model passed the validation steps and pushes the model
# to a file destination if check passed.
pusher = Pusher(
model_export=trainer.outputs.output,
model_blessing=slack_validator.outputs.slack_blessing,
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=_serving_model_dir)))
return [
example_gen, statistics_gen, infer_schema, validate_stats, transform,
trainer, model_analyzer, model_validator, slack_validator, pusher
]
def _create_pipeline():
"""Implements the chicago taxi pipeline with TFX."""
examples = csv_input(_data_root)
# Brings data into the pipeline or otherwise joins/converts training data.
example_gen = CsvExampleGen(input_base=examples)
# Computes statistics over data for visualization and example validation.
# pylint: disable=line-too-long
# statistics_gen = StatisticsGen(input_data=example_gen.outputs.examples) # Step 3
# pylint: enable=line-too-long
# Generates schema based on statistics files.
# infer_schema = SchemaGen(stats=statistics_gen.outputs.output) # Step 3
# Performs anomaly detection based on statistics and data schema.
# validate_stats = ExampleValidator( # Step 3
# stats=statistics_gen.outputs.output, # Step 3
# schema=infer_schema.outputs.output) # Step 3
# Performs transformations and feature engineering in training and serving.
# transform = Transform( # Step 4
# input_data=example_gen.outputs.examples, # Step 4
# schema=infer_schema.outputs.output, # Step 4
# module_file=_taxi_module_file) # Step 4
# Uses user-provided Python function that implements a model using TF-Learn.
# trainer = Trainer( # Step 5
# module_file=_taxi_module_file, # Step 5
# transformed_examples=transform.outputs.transformed_examples, # Step 5
# schema=infer_schema.outputs.output, # Step 5
# transform_output=transform.outputs.transform_output, # Step 5
# train_args=trainer_pb2.TrainArgs(num_steps=10000), # Step 5
# eval_args=trainer_pb2.EvalArgs(num_steps=5000)) # Step 5
# Uses TFMA to compute a evaluation statistics over features of a model.
# model_analyzer = Evaluator( # Step 6
# examples=example_gen.outputs.examples, # Step 6
# model_exports=trainer.outputs.output, # Step 6
# feature_slicing_spec=evaluator_pb2.FeatureSlicingSpec(specs=[ # Step 6
# evaluator_pb2.SingleSlicingSpec( # Step 6
# column_for_slicing=['trip_start_hour']) # Step 6
# ])) # Step 6
# Performs quality validation of a candidate model (compared to a baseline).
# model_validator = ModelValidator( # Step 7
# examples=example_gen.outputs.examples, # Step 7
# model=trainer.outputs.output) # Step 7
# Checks whether the model passed the validation steps and pushes the model
# to a file destination if check passed.
# pusher = Pusher( # Step 7
# model_export=trainer.outputs.output, # Step 7
# model_blessing=model_validator.outputs.blessing, # Step 7
# push_destination=pusher_pb2.PushDestination( # Step 7
# filesystem=pusher_pb2.PushDestination.Filesystem( # Step 7
# base_directory=_serving_model_dir))) # Step 7
return pipeline.Pipeline(
pipeline_name='taxi',
pipeline_root=_pipeline_root,
components=[
example_gen,
# statistics_gen, infer_schema, validate_stats, # Step 3
# transform, # Step 4
# trainer, # Step 5
# model_analyzer, # Step 6
# model_validator, pusher # Step 7
],
enable_cache=True,
metadata_db_root=_metadata_db_root,
additional_pipeline_args={'logger_args': logger_overrides},
)
def create_e2e_components(
pipeline_root: Text,
csv_input_location: Text,
transform_module: Text,
trainer_module: Text,
) -> List[BaseComponent]:
"""Creates components for a simple Chicago Taxi TFX pipeline for testing.
Args:
pipeline_root: The root of the pipeline output.
csv_input_location: The location of the input data directory.
transform_module: The location of the transform module file.
trainer_module: The location of the trainer module file.
Returns:
A list of TFX components that constitutes an end-to-end test pipeline.
"""
examples = dsl_utils.csv_input(csv_input_location)
example_gen = CsvExampleGen(input=examples)
statistics_gen = StatisticsGen(examples=example_gen.outputs['examples'])
schema_gen = SchemaGen(statistics=statistics_gen.outputs['statistics'],
infer_feature_shape=False)
example_validator = ExampleValidator(
statistics=statistics_gen.outputs['statistics'],
schema=schema_gen.outputs['schema'])
transform = Transform(examples=example_gen.outputs['examples'],
schema=schema_gen.outputs['schema'],
module_file=transform_module)
latest_model_resolver = ResolverNode(
instance_name='latest_model_resolver',
resolver_class=latest_artifacts_resolver.LatestArtifactsResolver,
latest_model=Channel(type=Model))
trainer = Trainer(
transformed_examples=transform.outputs['transformed_examples'],
schema=schema_gen.outputs['schema'],
base_model=latest_model_resolver.outputs['latest_model'],
transform_graph=transform.outputs['transform_graph'],
train_args=trainer_pb2.TrainArgs(num_steps=10),
eval_args=trainer_pb2.EvalArgs(num_steps=5),
module_file=trainer_module,
)
# Set the TFMA config for Model Evaluation and Validation.
eval_config = tfma.EvalConfig(
model_specs=[tfma.ModelSpec(signature_name='eval')],
metrics_specs=[
tfma.MetricsSpec(
metrics=[tfma.MetricConfig(class_name='ExampleCount')],
thresholds={
'binary_accuracy':
tfma.MetricThreshold(
value_threshold=tfma.GenericValueThreshold(
lower_bound={'value': 0.5}),
change_threshold=tfma.GenericChangeThreshold(
direction=tfma.MetricDirection.HIGHER_IS_BETTER,
absolute={'value': -1e-10}))
})
],
slicing_specs=[
tfma.SlicingSpec(),
tfma.SlicingSpec(feature_keys=['trip_start_hour'])
])
evaluator = Evaluator(examples=example_gen.outputs['examples'],
model=trainer.outputs['model'],
eval_config=eval_config)
infra_validator = InfraValidator(
model=trainer.outputs['model'],
examples=example_gen.outputs['examples'],
serving_spec=infra_validator_pb2.ServingSpec(
tensorflow_serving=infra_validator_pb2.TensorFlowServing(
tags=['latest']),
kubernetes=infra_validator_pb2.KubernetesConfig()),
request_spec=infra_validator_pb2.RequestSpec(
tensorflow_serving=infra_validator_pb2.
TensorFlowServingRequestSpec()))
pusher = Pusher(
model=trainer.outputs['model'],
model_blessing=evaluator.outputs['blessing'],
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=os.path.join(pipeline_root, 'model_serving'))))
return [
example_gen,
statistics_gen,
schema_gen,
example_validator,
transform,
latest_model_resolver,
trainer,
evaluator,
infra_validator,
pusher,
]
def _create_test_pipeline(pipeline_name: Text, pipeline_root: Text,
csv_input_location: Text, taxi_module_file: Text,
container_image: Text):
"""Creates a simple Kubeflow-based Chicago Taxi TFX pipeline for testing.
Args:
pipeline_name: The name of the pipeline.
pipeline_root: The root of the pipeline output.
csv_input_location: The location of the input data directory.
taxi_module_file: The location of the module file for Transform/Trainer.
container_image: The container image to use.
Returns:
A logical TFX pipeline.Pipeline object.
"""
examples = dsl_utils.csv_input(csv_input_location)
example_gen = CsvExampleGen(input_base=examples)
statistics_gen = StatisticsGen(input_data=example_gen.outputs.examples)
infer_schema = SchemaGen(stats=statistics_gen.outputs.output)
validate_stats = ExampleValidator( # pylint: disable=unused-variable
stats=statistics_gen.outputs.output,
schema=infer_schema.outputs.output)
transform = Transform(input_data=example_gen.outputs.examples,
schema=infer_schema.outputs.output,
module_file=taxi_module_file)
trainer = Trainer(
module_file=taxi_module_file,
transformed_examples=transform.outputs.transformed_examples,
schema=infer_schema.outputs.output,
transform_output=transform.outputs.transform_output,
train_args=trainer_pb2.TrainArgs(num_steps=10000),
eval_args=trainer_pb2.EvalArgs(num_steps=5000))
model_analyzer = Evaluator( # pylint: disable=unused-variable
examples=example_gen.outputs.examples,
model_exports=trainer.outputs.output,
feature_slicing_spec=evaluator_pb2.FeatureSlicingSpec(specs=[
evaluator_pb2.SingleSlicingSpec(
column_for_slicing=['trip_start_hour'])
]))
model_validator = ModelValidator(examples=example_gen.outputs.examples,
model=trainer.outputs.output)
pusher = Pusher( # pylint: disable=unused-variable
model_export=trainer.outputs.output,
model_blessing=model_validator.outputs.blessing,
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=os.path.join(pipeline_root, 'model_serving'))))
return tfx_pipeline.Pipeline(
pipeline_name=pipeline_name,
pipeline_root=pipeline_root,
components=[
example_gen, statistics_gen, infer_schema, validate_stats,
transform, trainer, model_analyzer, model_validator, pusher
],
log_root='/var/tmp/tfx/logs',
additional_pipeline_args={
'tfx_image': container_image,
},
)
def _create_test_pipeline(pipeline_root: Text, csv_input_location: Text,
taxi_module_file: Text, enable_cache: bool):
"""Creates a simple Kubeflow-based Chicago Taxi TFX pipeline.
Args:
pipeline_name: The name of the pipeline.
pipeline_root: The root of the pipeline output.
csv_input_location: The location of the input data directory.
taxi_module_file: The location of the module file for Transform/Trainer.
enable_cache: Whether to enable cache or not.
Returns:
A logical TFX pipeline.Pipeline object.
"""
examples = csv_input(csv_input_location)
example_gen = CsvExampleGen(input_base=examples)
statistics_gen = StatisticsGen(input_data=example_gen.outputs.examples)
infer_schema = SchemaGen(
stats=statistics_gen.outputs.output, infer_feature_shape=False)
validate_stats = ExampleValidator(
stats=statistics_gen.outputs.output, schema=infer_schema.outputs.output)
transform = Transform(
input_data=example_gen.outputs.examples,
schema=infer_schema.outputs.output,
module_file=taxi_module_file)
trainer = Trainer(
module_file=taxi_module_file,
transformed_examples=transform.outputs.transformed_examples,
schema=infer_schema.outputs.output,
transform_output=transform.outputs.transform_output,
train_args=trainer_pb2.TrainArgs(num_steps=10),
eval_args=trainer_pb2.EvalArgs(num_steps=5))
model_analyzer = Evaluator(
examples=example_gen.outputs.examples,
model_exports=trainer.outputs.output,
feature_slicing_spec=evaluator_pb2.FeatureSlicingSpec(specs=[
evaluator_pb2.SingleSlicingSpec(
column_for_slicing=['trip_start_hour'])
]))
model_validator = ModelValidator(
examples=example_gen.outputs.examples, model=trainer.outputs.output)
# Hack: ensuring push_destination can be correctly parameterized and interpreted.
# pipeline root will be specified as a dsl.PipelineParam with the name
# pipeline-root, see:
# https://github.com/tensorflow/tfx/blob/1c670e92143c7856f67a866f721b8a9368ede385/tfx/orchestration/kubeflow/kubeflow_dag_runner.py#L226
_pipeline_root_param = dsl.PipelineParam(name='pipeline-root')
pusher = Pusher(
model_export=trainer.outputs.output,
model_blessing=model_validator.outputs.blessing,
push_destination=pusher_pb2.PushDestination(
filesystem=pusher_pb2.PushDestination.Filesystem(
base_directory=os.path.join(str(_pipeline_root_param), 'model_serving'))))
return pipeline.Pipeline(
pipeline_name='parameterized_tfx_oss',
pipeline_root=pipeline_root,
components=[
example_gen, statistics_gen, infer_schema, validate_stats, transform,
trainer, model_analyzer, model_validator, pusher
],
enable_cache=enable_cache,
)