def test_batch_train_component_with_an_output(self): input_example_meta = af.register_example( name='batch_train_example', support_type=ExampleSupportType.EXAMPLE_BATCH) model_meta = af.register_model(model_name='mnist_model', model_type=ModelType.SAVED_MODEL) example_meta = af.register_example( name='output_example', support_type=ExampleSupportType.EXAMPLE_BATCH, data_type='numpy', data_format='npz', batch_uri=os.path.abspath( os.path.dirname(__file__) + '/numpy_output.npz')) with af.config( af.BaseJobConfig(platform='local', engine='python', job_name='batch_train')): input_example = af.read_example( example_info=input_example_meta, executor=PythonObjectExecutor( python_object=ReadBatchExample())) train_channel = af.train( input_data_list=[input_example], executor=PythonObjectExecutor( python_object=TrainBatchMnistModelWithOutput()), model_info=model_meta, output_num=1) af.write_example(input_data=train_channel, example_info=example_meta) workflow_id = af.run(test_util.get_project_path()) res = af.wait_workflow_execution_finished(workflow_id) self.assertEqual(0, res)
def test_stream_train_component(self): batch_input_example_meta = af.register_example( name='stream_train_example', support_type=ExampleSupportType.EXAMPLE_BOTH) model_meta = af.register_model(model_name='mnist_model', model_type=ModelType.SAVED_MODEL) stream_input_example_meta = af.register_example( name='stream_train_example', support_type=ExampleSupportType.EXAMPLE_BOTH) with af.config( af.BaseJobConfig(platform='local', engine='python', job_name='stream_train')): batch_input_example = af.read_example( example_info=batch_input_example_meta, executor=PythonObjectExecutor( python_object=ReadBatchExample())) batch_train = af.train(input_data_list=[batch_input_example], executor=PythonObjectExecutor( python_object=TrainBatchMnistModel()), model_info=model_meta) stream_input_example = af.read_example( example_info=stream_input_example_meta, executor=PythonObjectExecutor( python_object=ReadStreamExample())) stream_train = af.train(input_data_list=[stream_input_example], executor=PythonObjectExecutor( python_object=TrainStreamMnistModel()), model_info=model_meta) af.stop_before_control_dependency(stream_train, batch_train) workflow_id = af.run(test_util.get_project_path()) res = af.wait_workflow_execution_finished(workflow_id) self.assertEqual(0, res)
def prepare_workflow(): data_set_dir, output_dir = DataSets().collect_data_file_dir() """ Prepare workflow: Example & Model Metadata registration. """ train_example_meta: ExampleMeta = af.register_example( name='train_data', support_type=ExampleSupportType.EXAMPLE_BATCH, data_type='pandas', data_format='csv', batch_uri=data_set_dir + '/train_data.csv') label_example_meta: ExampleMeta = af.register_example( name='label_data', support_type=ExampleSupportType.EXAMPLE_BATCH, data_type='pandas', data_format='csv', batch_uri=data_set_dir + '/label_data.csv') test_example_meta: ExampleMeta = af.register_example( name='test_data', support_type=ExampleSupportType.EXAMPLE_BATCH, data_type='pandas', data_format='csv', batch_uri=data_set_dir + '/test_data.csv') test_output_example_meta: ExampleMeta = af.register_example( name='test_output_data', support_type=ExampleSupportType.EXAMPLE_STREAM, data_type='kafka', data_format='csv', stream_uri='localhost:9092') train_model_meta: ModelMeta = af.register_model( model_name='label_model', model_type=ModelType.SAVED_MODEL) return train_example_meta, label_example_meta, test_example_meta, test_output_example_meta, train_model_meta
def test_read_example_with_numpy_npy(self): npy_name = 'test.npy' np.save(file=npy_name, arr=np.arange(10)) input_example_meta = af.register_example( name='input_numpy_example', data_type='numpy', data_format='npy', support_type=ExampleSupportType.EXAMPLE_BATCH, batch_uri=os.path.abspath( os.path.dirname(__file__) + "/" + npy_name)) output_example_meta = af.register_example( name='ouput_numpy_example', data_type='numpy', data_format='npy', support_type=ExampleSupportType.EXAMPLE_BATCH, batch_uri=os.path.abspath( os.path.dirname(__file__) + '/numpy_output.npy')) with af.config( af.BaseJobConfig(platform='local', engine='python', job_name='test_npy')): example_channel = af.read_example(example_info=input_example_meta) af.write_example(input_data=example_channel, example_info=output_example_meta) workflow_id = af.run(test_util.get_project_path()) res = af.wait_workflow_execution_finished(workflow_id) self.assertEqual(0, res)
def test_stream_transform_component(self): file = get_file_dir(__file__) + '/test1.csv' input_example_meta = af.register_example( name='test_example', support_type=ExampleSupportType.EXAMPLE_BOTH, stream_uri=file) output_file = get_file_dir( __file__) + "/output_transform_stream_test1.csv" output_example_meta = af.register_example( name='test_example_output', support_type=ExampleSupportType.EXAMPLE_BOTH, stream_uri=output_file) with af.config( af.BaseJobConfig(platform='local', engine='python', job_name='stream_transform')): input_example = af.read_example( example_info=input_example_meta, executor=PythonObjectExecutor( python_object=ReadStreamExample())) transform_example = af.transform( input_data_list=[input_example], executor=PythonObjectExecutor( python_object=TransformStreamData())) af.write_example(input_data=transform_example, example_info=output_example_meta.name, executor=PythonObjectExecutor( python_object=WriteStreamExample())) workflow_id = af.run(test_util.get_project_path()) res = af.wait_workflow_execution_finished(workflow_id) self.assertEqual(0, res)
def test_read_example_with_pandas(self): input_example_meta = af.register_example( name='input_pandas_example', data_type='pandas', data_format='csv', support_type=ExampleSupportType.EXAMPLE_BATCH, batch_uri=os.path.abspath( os.path.dirname(__file__) + '/test1.csv')) output_example_meta = af.register_example( name='ouput_pandas_example', data_type='pandas', data_format='csv', support_type=ExampleSupportType.EXAMPLE_BATCH, batch_uri=os.path.abspath( os.path.dirname(__file__) + '/pandas_output.csv')) with af.config( af.BaseJobConfig(platform='local', engine='python', job_name='test_csv')): example_channel = af.read_example(example_info=input_example_meta) af.write_example(input_data=example_channel, example_info=output_example_meta) workflow_id = af.run(test_util.get_project_path()) res = af.wait_workflow_execution_finished(workflow_id) self.assertEqual(0, res)
def test_project_register(self): print(sys._getframe().f_code.co_name) TestProject.build_ai_graph(1) af.register_example(name="a", support_type=af.ExampleSupportType.EXAMPLE_BOTH) w_id = af.submit_ai_flow() res = af.wait_workflow_execution_finished(w_id) self.assertEqual(0, res) e_meta = af.get_example_by_name("a") self.assertEqual("a", e_meta.name)
def run_project(project_root_path): af.set_project_config_file(project_root_path + '/project.yaml') # Config command line job, we set platform to local and engine to cmd_line here cmd_job_config = af.BaseJobConfig(platform=LocalPlatform.platform(), engine=CMDEngine().engine()) with af.config(cmd_job_config): # Command line job executor cmd_job = af.user_define_operation(executor=CmdExecutor(cmd_line="echo Start AI flow")) # Config python job, we set platform to local and engine to python here python_job_config = af.BaseJobConfig(platform=LocalPlatform.platform(), engine=PythonEngine.engine()) # Set execution mode of this python job to BATCH, # which indicates jobs with this config is running in the form of batch. python_job_config.exec_mode = af.ExecutionMode.BATCH with af.config(python_job_config): # Path of Source data(under '..../simple_transform_airflow' dir) source_path = os.path.dirname(os.path.abspath(__file__)) + '/source_data.csv' # Path of Sink data sink_path = os.path.dirname(os.path.abspath(__file__)) + '/sink_data.csv' # To make the project replaceable, we register the example in metadata service read_example_meta = af.register_example(name='read_example', support_type=ExampleSupportType.EXAMPLE_BATCH, data_format='csv', data_type='pandas', batch_uri=source_path) # Read training example using af.read_example() # example_info is the meta information of the example read_example_channel = af.read_example(example_info=read_example_meta, exec_args=ExecuteArgs( batch_properties=Args(header=None, names=["a", "b", "c"]))) # Transform examples using af.transform() transform_channel = af.transform(input_data_list=[read_example_channel], executor=PythonObjectExecutor(python_object=SimpleTransform())) write_example_meta = af.register_example(name='write_example', support_type=ExampleSupportType.EXAMPLE_BATCH, data_format='csv', data_type='pandas', batch_uri=sink_path) # Write example to specific path write = af.write_example(input_data=transform_channel, example_info=write_example_meta, exec_args=ExecuteArgs(batch_properties=Args(sep=',', header=False, index=False))) # Add control dependency, which means read_example job will start right after command line job finishes. af.stop_before_control_dependency(read_example_channel, cmd_job) transform_dag = 'simple_transform' af.deploy_to_airflow(project_root_path, dag_id=transform_dag) context = af.run(project_path=project_root_path, dag_id=transform_dag, scheduler_type=SchedulerType.AIRFLOW)
def test_stream_evaluate_component(self): input_example_meta = af.register_example( name='batch_train_example', support_type=ExampleSupportType.EXAMPLE_BATCH) model_meta = af.register_model(model_name='mnist_model', model_type=ModelType.SAVED_MODEL) stream_evaluate_example_meta = af.register_example( name='stream_evaluate_example', support_type=ExampleSupportType.EXAMPLE_STREAM) stream_output_file = get_file_dir(__file__) + '/stream_evaluate' evaluate_output = af.register_artifact(name='stream_evaluate', stream_uri=stream_output_file) stream_evaluate_result_example_meta = af.register_example( name='stream_evaluate_result_example', support_type=ExampleSupportType.EXAMPLE_STREAM, stream_uri=stream_output_file) if os.path.exists(stream_output_file): os.remove(stream_output_file) with af.config( af.BaseJobConfig(platform='local', engine='python', job_name='stream_evaluate')): input_example = af.read_example( example_info=input_example_meta, executor=PythonObjectExecutor( python_object=ReadBatchExample())) batch_train = af.train(input_data_list=[input_example], executor=PythonObjectExecutor( python_object=TrainBatchMnistModel()), model_info=model_meta) stream_evaluate_example = af.read_example( example_info=stream_evaluate_example_meta, executor=PythonObjectExecutor( python_object=ReadStreamExample())) stream_evaluate = af.evaluate( input_data_list=[stream_evaluate_example], model_info=model_meta, executor=PythonObjectExecutor( python_object=EvaluateStreamMnistModel()), output_num=1) af.write_example(input_data=stream_evaluate, example_info=stream_evaluate_result_example_meta, executor=PythonObjectExecutor( python_object=WriteStreamExample())) af.stop_before_control_dependency(stream_evaluate, batch_train) workflow_id = af.run(test_util.get_project_path()) res = af.wait_workflow_execution_finished(workflow_id) self.assertEqual(0, res)
def test_read_example_with_numpy_npz(self): npy_name = 'test.npz' np.savez(npy_name, np.arange(10), np.sin(np.arange(10))) input_example_meta = af.register_example( name='input_numpy_example', data_type='numpy', data_format='npz', support_type=ExampleSupportType.EXAMPLE_BATCH, batch_uri=os.path.abspath( os.path.dirname(__file__) + "/" + npy_name)) output_example_meta_first = af.register_example( name='ouput_numpy_example_1', data_type='numpy', data_format='npz', support_type=ExampleSupportType.EXAMPLE_BATCH, batch_uri=os.path.abspath( os.path.dirname(__file__) + '/numpy_output_1.npz')) output_example_meta_second = af.register_example( name='ouput_numpy_example_2', data_type='numpy', data_format='npz', support_type=ExampleSupportType.EXAMPLE_BATCH, batch_uri=os.path.abspath( os.path.dirname(__file__) + '/numpy_output_2.npz')) with af.config( af.BaseJobConfig(platform='local', engine='python', job_name='test_npz')): example_channel = af.read_example(example_info=input_example_meta) transform_channel = af.transform( input_data_list=[example_channel], executor=PythonObjectExecutor( python_object=TransformTrainData()), output_num=2) af.write_example(input_data=transform_channel[0], example_info=output_example_meta_first) af.write_example(input_data=transform_channel[1], example_info=output_example_meta_second) workflow_id = af.run(test_util.get_project_path()) res = af.wait_workflow_execution_finished(workflow_id) self.assertEqual(0, res)
def test_batch_predict_component(self): input_example_meta = af.register_example( name='input_train_example', support_type=ExampleSupportType.EXAMPLE_BOTH) model_meta = af.register_model(model_name='mnist_model', model_type=ModelType.SAVED_MODEL) batch_output_file = get_file_dir(__file__) + '/batch_predict' evaluate_output = af.register_artifact(name='batch_evaluate', batch_uri=batch_output_file) output_example_meta = af.register_example( name='output_result_example', support_type=ExampleSupportType.EXAMPLE_BATCH, data_type='numpy', data_format='txt', batch_uri=batch_output_file) if os.path.exists(batch_output_file): os.remove(batch_output_file) with af.config( af.BaseJobConfig(platform='local', engine='python', job_name='batch_predict')): batch_example = af.read_example( example_info=input_example_meta, executor=PythonObjectExecutor( python_object=ReadBatchExample())) batch_train = af.train(input_data_list=[batch_example], executor=PythonObjectExecutor( python_object=TrainBatchMnistModel()), model_info=model_meta) batch_predict = af.predict( input_data_list=[batch_example], model_info=model_meta, executor=PythonObjectExecutor( python_object=PredictBatchMnistModel()), output_num=1) af.write_example(input_data=batch_predict, example_info=output_example_meta) af.stop_before_control_dependency(batch_predict, batch_train) workflow_id = af.run(test_util.get_project_path()) res = af.wait_workflow_execution_finished(workflow_id) self.assertEqual(0, res)
def prepare_workflow(train_data_file: str, first_test_data_file: str, first_result_data_file: str): """ Prepare workflow: Example & Model Metadata registration. """ train_example_meta: ExampleMeta = af.register_example( name='train_data', support_type=ExampleSupportType.EXAMPLE_BATCH, data_type='pandas', data_format='csv', batch_uri=train_data_file) first_test_example_meta: ExampleMeta = af.register_example( name='first_test_data', support_type=ExampleSupportType.EXAMPLE_BATCH, data_type='pandas', data_format='csv', batch_uri=first_test_data_file) second_test_example_data: ExampleMeta = af.register_example( name='second_test_data', support_type=ExampleSupportType.EXAMPLE_STREAM, data_type='kafka', data_format='csv', stream_uri='localhost:9092') first_result_example_meta: ExampleMeta = af.register_example( name='first_result_111', support_type=ExampleSupportType.EXAMPLE_BATCH, data_type='pandas', data_format='csv', batch_uri=first_result_data_file) second_result_example_meta: ExampleMeta = af.register_example( name='second_result_111', support_type=ExampleSupportType.EXAMPLE_STREAM, data_type='kafka', data_format='csv', stream_uri='localhost:9092') train_model_meta: ModelMeta = af.register_model( model_name='auto_encoder', model_type=ModelType.SAVED_MODEL) return train_example_meta, first_test_example_meta, second_test_example_data, \ first_result_example_meta, second_result_example_meta, train_model_meta
def test_batch_train_component(self): input_example_meta = af.register_example( name='batch_train_example', support_type=ExampleSupportType.EXAMPLE_BATCH) model_meta = af.register_model(model_name='mnist_model', model_type=ModelType.SAVED_MODEL) with af.config( af.BaseJobConfig(platform='local', engine='python', job_name='batch_train')): input_example = af.read_example( example_info=input_example_meta, executor=PythonObjectExecutor( python_object=ReadBatchExample())) af.train(input_data_list=[input_example], executor=PythonObjectExecutor( python_object=TrainBatchMnistModel()), model_info=model_meta) workflow_id = af.run(test_util.get_project_path()) res = af.wait_workflow_execution_finished(workflow_id) self.assertEqual(0, res)
def test_batch_model_validate(self): input_example_meta = af.register_example(name='batch_train_example', support_type=ExampleSupportType.EXAMPLE_BOTH) model_meta = af.register_model(model_name='mnist_model', model_type=ModelType.SAVED_MODEL) with af.config(af.BaseJobConfig(platform='local', engine='python', job_name='evaluate')): input_example = af.read_example(example_info=input_example_meta, executor=PythonObjectExecutor(python_object=ReadBatchExample())) batch_train = af.train(input_data_list=[input_example], executor=PythonObjectExecutor(python_object=TrainBatchMnistModel()), model_info=model_meta) model_validate = af.model_validate(input_data_list=[input_example], model_info=model_meta, executor=PythonObjectExecutor(python_object=BatchModelValidate()), output_num=0) af.stop_before_control_dependency(model_validate, batch_train) workflow_id = af.run(test_util.get_project_path()) res = af.wait_workflow_execution_finished(workflow_id) self.assertEqual(0, res)
def run_project(project_root_path): af.set_project_config_file(project_root_path + "/project.yaml") project_name = af.project_config().get_project_name() artifact_prefix = project_name + "." validate_trigger = af.external_trigger(name='validate') push_trigger = af.external_trigger(name='push') with af.global_config_file(project_root_path + '/resources/workflow_config.yaml'): # the config of train job is a periodic job which means it will # run every `interval`(defined in workflow_config.yaml) seconds with af.config('train_job'): # Register metadata raw training data(example) and read example(i.e. training dataset) train_example = af.register_example(name=artifact_prefix + 'train_example', support_type=ExampleSupportType.EXAMPLE_BATCH, batch_uri=EXAMPLE_URI.format('train')) train_read_example = af.read_example(example_info=train_example, executor=PythonObjectExecutor(python_object=ExampleReader())) # Transform(preprocessing) example train_transform = af.transform(input_data_list=[train_read_example], executor=PythonObjectExecutor(python_object=ExampleTransformer())) # Register model metadata and train model train_model = af.register_model(model_name=artifact_prefix + 'logistic-regression', model_type=ModelType.SAVED_MODEL, model_desc='logistic regression model') train_channel = af.train(input_data_list=[train_transform], executor=PythonObjectExecutor(python_object=ModelTrainer()), model_info=train_model) with af.config('validate_job'): # Validation of model # Read validation dataset and validate model before it is used to predict validate_example = af.register_example(name=artifact_prefix + 'validate_example', support_type=ExampleSupportType.EXAMPLE_STREAM, batch_uri=EXAMPLE_URI.format('evaluate')) validate_read_example = af.read_example(example_info=validate_example, executor=PythonObjectExecutor( python_object=ValidateExampleReader())) validate_transform = af.transform(input_data_list=[validate_read_example], executor=PythonObjectExecutor(python_object=ValidateTransformer())) validate_artifact_name = artifact_prefix + 'validate_artifact' validate_artifact = af.register_artifact(name=validate_artifact_name, batch_uri=get_file_dir(__file__) + '/validate_result') validate_channel = af.model_validate(input_data_list=[validate_transform], model_info=train_model, executor=PythonObjectExecutor( python_object=ModelValidator(validate_artifact_name))) with af.config('push_job'): # Push model to serving # Register metadata of pushed model push_model_artifact_name = artifact_prefix + 'push_model_artifact' push_model_artifact = af.register_artifact(name=push_model_artifact_name, batch_uri=get_file_dir(__file__) + '/pushed_model') push_channel = af.push_model(model_info=train_model, executor=PythonObjectExecutor( python_object=ModelPusher(push_model_artifact_name))) with af.config('predict_job'): # Prediction(Inference) predict_example = af.register_example(name=artifact_prefix + 'predict_example', support_type=ExampleSupportType.EXAMPLE_STREAM, stream_uri=EXAMPLE_URI.format('predict')) predict_read_example = af.read_example(example_info=predict_example, executor=PythonObjectExecutor(python_object=PredictExampleReader())) predict_transform = af.transform(input_data_list=[predict_read_example], executor=PythonObjectExecutor(python_object=PredictTransformer())) predict_channel = af.predict(input_data_list=[predict_transform], model_info=train_model, executor=PythonObjectExecutor(python_object=ModelPredictor())) # Save prediction result write_example = af.register_example(name=artifact_prefix + 'write_example', support_type=ExampleSupportType.EXAMPLE_STREAM, stream_uri=get_file_dir(__file__) + '/predict_result') af.write_example(input_data=predict_channel, example_info=write_example, executor=PythonObjectExecutor(python_object=ExampleWriter())) # Define relation graph connected by control edge: # Once a round of training is done, validator will be launched and # pusher will be launched if the new model is better. # Prediction will start once the first round of training is done and # when pusher pushes(deploys) a new model, the predictor will use the latest deployed model as well. af.model_version_control_dependency(src=validate_channel, model_version_event_type=ModelVersionEventType.MODEL_GENERATED, dependency=validate_trigger, model_name=train_model.name) af.model_version_control_dependency(src=push_channel, model_version_event_type=ModelVersionEventType.MODEL_VALIDATED, dependency=push_trigger, model_name=train_model.name) # Run workflow transform_dag = project_name af.deploy_to_airflow(project_root_path, dag_id=transform_dag) af.run(project_path=project_root_path, dag_id=transform_dag, scheduler_type=SchedulerType.AIRFLOW)
def run_project(project_root_path): af.set_project_config_file(project_root_path + "/project.yaml") project_name = af.project_config().get_project_name() artifact_prefix = project_name + "." validate_trigger = af.external_trigger(name='validate') push_trigger = af.external_trigger(name='push') with af.global_config_file(project_root_path + '/resources/workflow_config.yaml'): with af.config('train_job'): train_example = af.register_example(name=artifact_prefix + 'train_example', support_type=ExampleSupportType.EXAMPLE_STREAM, stream_uri=EXAMPLE_URI.format('train')) train_read_example = af.read_example(example_info=train_example, executor=PythonObjectExecutor(python_object=TrainExampleReader())) train_transform = af.transform(input_data_list=[train_read_example], executor=PythonObjectExecutor(python_object=TrainExampleTransformer())) train_model = af.register_model(model_name=artifact_prefix + 'logistic-regression', model_type=ModelType.SAVED_MODEL, model_desc='logistic regression model') train_channel = af.train(input_data_list=[train_transform], executor=PythonObjectExecutor(python_object=ModelTrainer()), model_info=train_model) with af.config('validate_job'): validate_example = af.register_example(name=artifact_prefix + 'validate_example', support_type=ExampleSupportType.EXAMPLE_STREAM, stream_uri=EXAMPLE_URI.format('evaluate'), data_format='npz') validate_read_example = af.read_example(example_info=validate_example, executor=PythonObjectExecutor( python_object=ValidateExampleReader())) validate_transform = af.transform(input_data_list=[validate_read_example], executor=PythonObjectExecutor(python_object=ValidateTransformer())) validate_artifact_name = artifact_prefix + 'validate_artifact' validate_artifact = af.register_artifact(name=validate_artifact_name, stream_uri=get_file_dir(__file__) + '/validate_result') validate_channel = af.model_validate(input_data_list=[validate_transform], model_info=train_model, executor=PythonObjectExecutor( python_object=ModelValidator(validate_artifact_name)), ) with af.config('push_job'): # Push model to serving # Register metadata of pushed model push_model_artifact_name = artifact_prefix + 'push_model_artifact' push_model_artifact = af.register_artifact(name=push_model_artifact_name, stream_uri=get_file_dir(__file__) + '/pushed_model') push_channel = af.push_model(model_info=train_model, executor=PythonObjectExecutor( python_object=ModelPusher(push_model_artifact_name))) with af.config('predict_job'): predict_example = af.register_example(name=artifact_prefix + 'predict_example', support_type=ExampleSupportType.EXAMPLE_STREAM, stream_uri=EXAMPLE_URI.format('predict')) predict_read_example = af.read_example(example_info=predict_example, executor=PythonObjectExecutor(python_object=PredictExampleReader())) predict_transform = af.transform(input_data_list=[predict_read_example], executor=PythonObjectExecutor(python_object=PredictTransformer())) predict_channel = af.predict(input_data_list=[predict_transform], model_info=train_model, executor=PythonObjectExecutor(python_object=ModelPredictor())) write_example = af.register_example(name=artifact_prefix + 'export_example', support_type=ExampleSupportType.EXAMPLE_STREAM, stream_uri=get_file_dir(__file__) + '/predict_result') af.write_example(input_data=predict_channel, example_info=write_example, executor=PythonObjectExecutor(python_object=ExampleWriter())) af.model_version_control_dependency(src=validate_channel, model_version_event_type=ModelVersionEventType.MODEL_GENERATED, dependency=validate_trigger, model_name=train_model.name) af.model_version_control_dependency(src=push_channel, model_version_event_type=ModelVersionEventType.MODEL_VALIDATED, dependency=push_trigger, model_name=train_model.name) # Run workflow transform_dag = project_name af.deploy_to_airflow(project_root_path, dag_id=transform_dag) af.run(project_path=project_root_path, dag_id=transform_dag, scheduler_type=SchedulerType.AIRFLOW)
def run_workflow(): """ Run the user-defined workflow definition. """ train_example_meta, label_example_meta, test_example_meta, test_output_example_meta, train_model_meta = prepare_workflow( ) python_job_config_0 = BaseJobConfig(job_name='read_train', platform='local', engine='python') python_job_config_1 = BaseJobConfig(job_name='train', platform='local', engine='python') flink_job_config_2 = LocalFlinkJobConfig() flink_job_config_2.job_name = 'test' flink_job_config_2.local_mode = 'python' flink_job_config_2.flink_home = os.environ['FLINK_HOME'] flink_job_config_2.set_table_env_create_func(MyStreamTableEnvCreator()) with af.config(python_job_config_0): python_job_0_read_train_data = af.read_example( example_info=train_example_meta, executor=PythonObjectExecutor(python_object=ReadTrainCsvExample())) python_job_0_read_label_data = af.read_example( example_info=label_example_meta, executor=PythonObjectExecutor(python_object=ReadLabelCsvExample())) write_train_data_example = af.register_example( name='write_train_data', support_type=ExampleSupportType.EXAMPLE_BATCH, data_type='pandas', data_format='csv', batch_uri='/tmp/write_train_data.csv') python_job_0_write_train_result = af.write_example( input_data=python_job_0_read_train_data, example_info=write_train_data_example, executor=PythonObjectExecutor( python_object=WriteTrainCsvExample())) with af.config(python_job_config_1): python_job_1_train_model = af.train( name='trainer_0', input_data_list=[ python_job_0_read_train_data, python_job_0_read_label_data ], executor=PythonObjectExecutor(python_object=TrainModel()), model_info=train_model_meta) with af.config(flink_job_config_2): flink_job_2_read_test_data = af.read_example( example_info=test_example_meta, executor=FlinkPythonExecutor(python_object=ReadTestCsvExample())) flink_job_2_predict_test_data = af.transform( input_data_list=[flink_job_2_read_test_data], executor=FlinkPythonExecutor( python_object=PredictTestLabelExecutor())) write_result = af.write_example( input_data=flink_job_2_predict_test_data, example_info=test_output_example_meta, executor=FlinkPythonExecutor( python_object=WritePredictTestExample())) af.stop_before_control_dependency(python_job_1_train_model, python_job_0_write_train_result) af.stop_before_control_dependency(write_result, python_job_1_train_model) workflow_id = af.run(get_project_path() + '/') res = af.wait_workflow_execution_finished(workflow_id) sys.exit(res)