def testTaxiPipelineConstructionAndDefinitionFileExists(self):
logical_pipeline = taxi_pipeline_kubeflow_simple._create_pipeline(
pipeline_name=taxi_pipeline_kubeflow_simple._pipeline_name,
pipeline_root=taxi_pipeline_kubeflow_simple._pipeline_root,
data_root=taxi_pipeline_kubeflow_simple._data_root,
module_file=taxi_pipeline_kubeflow_simple._module_file,
serving_model_dir=taxi_pipeline_kubeflow_simple._serving_model_dir,
direct_num_workers=1)
self.assertEqual(9, len(logical_pipeline.components))
KubeflowDagRunner().run(logical_pipeline)
file_path = os.path.join(
self._tmp_dir, 'chicago_taxi_pipeline_kubeflow_simple.tar.gz')
self.assertTrue(tf.io.gfile.exists(file_path))
def testTaxiPipelineConstructionAndDefinitionFileExists(self):
logical_pipeline = taxi_pipeline_kubeflow_local._create_pipeline(
pipeline_name=taxi_pipeline_kubeflow_local._pipeline_name,
pipeline_root=taxi_pipeline_kubeflow_local._pipeline_root,
data_root=taxi_pipeline_kubeflow_local._data_root,
module_file=taxi_pipeline_kubeflow_local._module_file,
serving_model_dir=taxi_pipeline_kubeflow_local._serving_model_dir,
beam_pipeline_args=[])
self.assertEqual(10, len(logical_pipeline.components))
KubeflowDagRunner().run(logical_pipeline)
file_path = os.path.join(
self.tmp_dir, 'chicago_taxi_pipeline_kubeflow_local.tar.gz')
self.assertTrue(fileio.exists(file_path))
def testTaxiPipelineConstructionAndDefinitionFileExists(self):
logical_pipeline = taxi_pipeline_kubeflow_gcp.create_pipeline(
pipeline_name=taxi_pipeline_kubeflow_gcp._pipeline_name,
pipeline_root=taxi_pipeline_kubeflow_gcp._pipeline_root,
module_file=taxi_pipeline_kubeflow_gcp._module_file,
ai_platform_training_args=taxi_pipeline_kubeflow_gcp.
_ai_platform_training_args,
ai_platform_serving_args=taxi_pipeline_kubeflow_gcp.
_ai_platform_serving_args)
self.assertEqual(9, len(logical_pipeline.components))
KubeflowDagRunner().run(logical_pipeline)
file_path = os.path.join(self._tmp_dir,
'chicago_taxi_pipeline_kubeflow_gcp.tar.gz')
self.assertTrue(tf.io.gfile.exists(file_path))
def testTaxiPipelineConstructionAndDefinitionFileExists(self):
logical_pipeline = taxi_pipeline_kubeflow_simple._create_pipeline(
pipeline_name=taxi_pipeline_kubeflow_simple._pipeline_name,
pipeline_root=taxi_pipeline_kubeflow_simple._pipeline_root,
query=taxi_pipeline_kubeflow_simple._query,
module_file=taxi_pipeline_kubeflow_simple._module_file,
beam_pipeline_args=taxi_pipeline_kubeflow_simple.
_beam_pipeline_args,
)
self.assertEqual(9, len(logical_pipeline.components))
KubeflowDagRunner().run(logical_pipeline)
file_path = os.path.join(
self._tmp_dir, 'chicago_taxi_pipeline_kubeflow_simple.tar.gz')
self.assertTrue(tf.io.gfile.exists(file_path))
def testPipelineConstruction(self):
logical_pipeline = penguin_pipeline_sklearn_gcp._create_pipeline(
pipeline_name=self._pipeline_name,
pipeline_root=self._pipeline_root,
data_root=self._data_root,
trainer_module_file=self._trainer_module_file,
evaluator_module_file=self._evaluator_module_file,
ai_platform_training_args=self._ai_platform_training_args,
ai_platform_serving_args=self._ai_platform_serving_args,
beam_pipeline_args=[])
self.assertEqual(8, len(logical_pipeline.components))
KubeflowDagRunner().run(logical_pipeline)
file_path = os.path.join(self.tmp_dir, 'sklearn_test.tar.gz')
self.assertTrue(fileio.exists(file_path))
def testPenguinPipelineConstructionAndDefinitionFileExists(self):
logical_pipeline = penguin_pipeline_kubeflow_gcp.create_pipeline(
pipeline_name=penguin_pipeline_kubeflow_gcp._pipeline_name,
pipeline_root=penguin_pipeline_kubeflow_gcp._pipeline_root,
data_root=penguin_pipeline_kubeflow_gcp._data_root,
module_file=penguin_pipeline_kubeflow_gcp._module_file,
enable_tuning=True,
ai_platform_training_args=penguin_pipeline_kubeflow_gcp.
_ai_platform_training_args,
ai_platform_serving_args=penguin_pipeline_kubeflow_gcp.
_ai_platform_serving_args,
beam_pipeline_args=penguin_pipeline_kubeflow_gcp.
_beam_pipeline_args)
self.assertEqual(10, len(logical_pipeline.components))
KubeflowDagRunner().run(logical_pipeline)
file_path = os.path.join(self.tmp_dir, 'penguin_kubeflow_gcp.tar.gz')
self.assertTrue(fileio.exists(file_path))
def testPipelineConstruction(self, resolve_mock):
# Avoid actually performing user module packaging because relative path is
# not valid with respect to temporary directory.
resolve_mock.side_effect = lambda pipeline_root: None
logical_pipeline = penguin_pipeline_sklearn_gcp._create_pipeline(
pipeline_name=self._pipeline_name,
pipeline_root=self._pipeline_root,
data_root=self._data_root,
trainer_module_file=self._trainer_module_file,
evaluator_module_file=self._evaluator_module_file,
ai_platform_training_args=self._ai_platform_training_args,
ai_platform_serving_args=self._ai_platform_serving_args,
beam_pipeline_args=[])
self.assertEqual(8, len(logical_pipeline.components))
KubeflowDagRunner().run(logical_pipeline)
file_path = os.path.join(self.tmp_dir, 'sklearn_test.tar.gz')
self.assertTrue(fileio.exists(file_path))
def testTaxiPipelineConstructionAndDefinitionFileExists(
self, resolve_mock):
# Avoid actually performing user module packaging because a placeholder
# GCS bucket is used.
resolve_mock.side_effect = lambda pipeline_root: None
logical_pipeline = taxi_pipeline_kubeflow_local._create_pipeline(
pipeline_name=taxi_pipeline_kubeflow_local._pipeline_name,
pipeline_root=taxi_pipeline_kubeflow_local._pipeline_root,
data_root=taxi_pipeline_kubeflow_local._data_root,
module_file=taxi_pipeline_kubeflow_local._module_file,
serving_model_dir=taxi_pipeline_kubeflow_local._serving_model_dir,
beam_pipeline_args=[])
self.assertEqual(10, len(logical_pipeline.components))
KubeflowDagRunner().run(logical_pipeline)
file_path = os.path.join(
self.tmp_dir, 'chicago_taxi_pipeline_kubeflow_local.tar.gz')
self.assertTrue(fileio.exists(file_path))
def testPenguinPipelineConstructionAndDefinitionFileExists(
self, resolve_mock):
# Avoid actually performing user module packaging because a placeholder
# GCS bucket is used.
resolve_mock.side_effect = lambda pipeline_root: None
logical_pipeline = penguin_pipeline_kubeflow_gcp.create_pipeline(
pipeline_name=penguin_pipeline_kubeflow_gcp._pipeline_name,
pipeline_root=penguin_pipeline_kubeflow_gcp._pipeline_root,
data_root=penguin_pipeline_kubeflow_gcp._data_root,
module_file=penguin_pipeline_kubeflow_gcp._module_file,
enable_tuning=True,
ai_platform_training_args=penguin_pipeline_kubeflow_gcp
._ai_platform_training_args,
ai_platform_serving_args=penguin_pipeline_kubeflow_gcp
._ai_platform_serving_args,
beam_pipeline_args=penguin_pipeline_kubeflow_gcp._beam_pipeline_args)
self.assertEqual(10, len(logical_pipeline.components))
KubeflowDagRunner().run(logical_pipeline)
file_path = os.path.join(self.tmp_dir, 'penguin_kubeflow_gcp.tar.gz')
self.assertTrue(fileio.exists(file_path))
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',
)
_ = KubeflowDagRunner().run(_create_pipeline())
